JP2025036610A - Information sharing support system, information sharing support device, information sharing support method and program - Google Patents

Abstract

To improve efficiency of information sharing in a conference.SOLUTION: An information sharing support system receives an input of sentences indicating the details of utterance uttered in a conference, the details of description described in electronic mail, electronic file, or chat data, or combinations of these, determines the types of the sentences input through the input, and outputs a list of specific sentences having a type to be set, of the types, on the basis of a result of determination through the determination.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information sharing support system, an information sharing support device, an information sharing support method, and a program.

Conventionally, a method is known in which a conference support system reduces the burden of cumbersome tasks such as time adjustment and manages progress so that the chairperson can concentrate on the agenda and proceed accurately. In this method, the conference support system displays the progress of the conference and controls this display according to the progress of the conference. Specifically, the conference support system first sets the planned proceeding time required for each of multiple conference agendas in advance and creates a timetable for the entire conference. Next, the conference support system displays an indicator showing the elapsed time of the conference agenda at any time. Furthermore, the conference support system detects the end of the conference agenda and shifts the indicator to the next conference agenda. Then, when the conference agenda is finished, the conference support system reallocates the remaining planned proceeding time to each remaining conference agenda. In this way, the conference support system automatically adjusts the time so that the conference ends within the planned proceeding time, reducing the burden of time adjustment work. Therefore, the chairperson can concentrate on the agenda and accurately manage the progress of the conference (for example, Patent Document 1, etc.).

However, conventional methods only allow for time management of each agenda item in a meeting. On the other hand, there has been a demand for more efficient information sharing during meetings, for example by visualizing the contents of the meeting.

One aspect of the present invention aims to provide an information sharing support system that can make information sharing in meetings and other events more efficient.

In one aspect, an information sharing support system for supporting information sharing, comprising one or more information processing devices,
an input unit for inputting one or more sentences indicating the contents of a statement made in a conference, the contents of a statement written in an e-mail, an electronic file, or chat data, or a combination thereof;
a determination unit for determining a type of the sentence input by the input unit;
and an output unit that outputs a list of specific sentences that are of a set type among the types based on a result of the determination by the determination unit.

This can make information sharing during meetings etc. more efficient.

1 is a conceptual diagram illustrating an example of an overall configuration of a conference support system according to a first embodiment of the present invention. 1 is a block diagram showing an example of a hardware configuration of an information processing device according to an embodiment of the present invention; 1 is a functional block diagram illustrating an example of a functional configuration of a conference support system according to a first embodiment of the present invention. FIG. 2 is a diagram showing an example of a screen displayed by the conference support system according to the first embodiment of the present invention. 1 is a diagram showing an example of a setting screen for setting an agenda, a goal, and the like in the conference support system according to an embodiment of the first embodiment of the present invention. FIG. FIG. 11 is a diagram showing an example in which an alert and a remaining time are displayed on a screen displayed by the conference support system according to the first embodiment of the present invention. 10 is a flowchart illustrating an example of a process for determining a type of a statement content by the conference support system according to the first embodiment of the present invention. FIG. 2 is a diagram showing an example of a screen for switching between a summary and a full text in the conference support system according to the first embodiment of the present invention. 11 is a flowchart illustrating an example of a process for switching between a summary and a full text by the conference support system according to the first embodiment of the present invention. FIG. 2 is a diagram showing an example of a screen showing a summary displayed by the conference support system according to the first embodiment of the present invention. FIG. 2 is a diagram showing an example of a display of a topic generated by the conference support system according to the first embodiment of the present invention. 1 is a flowchart showing an example of topic generation by the conference support system according to the first embodiment of the present invention. FIG. 2 is a diagram showing an example of a display of an alert or the like by the conference support system according to the first embodiment of the present invention. FIG. 11 is a diagram showing an example of a list of specific sentences output by the conference support system according to the first embodiment of the present invention. FIG. 2 is a diagram showing an example of a display of a history by the conference support system according to the first embodiment of the present invention. FIG. 2 is a diagram showing an example of a communication diagram displayed by the conference support system according to the first embodiment of the present invention. FIG. 2 is a diagram showing an example of a display of a log in a communication diagram displayed by the conference support system according to the first embodiment of the present invention. FIG. 11 is a functional block diagram illustrating an example of a functional configuration of a conference support system according to a second embodiment of the present invention. FIG. 11 is a diagram showing an example of a summary screen displayed by the conference support system according to the second embodiment of the present invention. FIG. 11 is a diagram showing an example of an evaluation screen displayed by the conference support system according to the second embodiment of the present invention. FIG. 11 is a diagram showing an example of a screen for inputting a subjective evaluation displayed by the conference support system according to the second embodiment of the present invention. 13 is a flowchart illustrating an example of a process of performing an evaluation based on a time during which a conference is held by the conference support system according to the second embodiment of the present invention. FIG. 13 is a conceptual diagram illustrating an example of natural language processing using machine learning by a conference support system according to a third embodiment of the present invention. FIG. 13 is a conceptual diagram illustrating an example of an overall configuration of an information sharing support system according to a fourth embodiment of the present invention. FIG. 13 is a diagram illustrating an example of an output by the information sharing support system according to the fourth embodiment of the present invention. 13 is a flowchart illustrating an example of processing by an information sharing support system according to the fourth embodiment of the present invention. FIG. 13 is a conceptual diagram illustrating an example of an overall configuration of an information sharing support system according to another embodiment of the fourth embodiment of the present invention.

The following describes an embodiment of the present invention. In the following description, information sharing is performed in a conference, and a conference support system, which is an example of an information sharing support system, is used in the conference. Therefore, in the following example, one or more sentences (hereinafter simply referred to as "sentences") input to the conference support system are only the contents of what was said in the conference. A sentence is the smallest unit that indicates complete content when expressing thoughts or feelings in words.

First Embodiment
(Overall configuration example)
1 is a conceptual diagram for explaining an example of the overall configuration of a conference support system according to a first embodiment of the present invention. For example, as shown in the figure, the conference support system 1 has a server 10, which is an example of an information sharing support device, and one or more terminals 11. The server 10 and each terminal 11 are connected via a network 12. The server 10 and the terminals 11 are information processing devices such as PCs (Personal Computers), and have, for example, the following hardware configuration.

(Hardware configuration example)
2 is a block diagram showing an example of a hardware configuration of an information processing device according to an embodiment of the present invention. For example, the server 10 and the terminal 11 have a CPU (Central Processing Unit) 10H1, an I/F (interface) 10H2, and an output device 10H3. The server 10 and the terminal 11 also have an input device 10H4, a HD (Hard Disk) 10H5, and a storage device 10H6. Furthermore, each piece of hardware is connected via a bus 10H7. The server 10 and the multiple terminals 11 may have the same hardware configuration or different hardware configurations. Below, the server 10 will be described as an example in which the server 10 and the multiple terminals 11 have the same hardware configuration.

The CPU 10H1 is a calculation device that performs calculations to realize various processes and processing of various data, and a control device that controls each piece of hardware. Note that the server 10 may have multiple calculation devices or control devices.

The I/F 10H2 is, for example, a connector and a processing IC (Integrated Circuit). For example, the I/F 10H2 transmits and receives data to and from an external device via a network, etc.

The output device 10H3 is a display or the like that displays a display screen and a GUI (Graphical User Interface), etc.

The input device 10H4 is a touch panel, keyboard, mouse, microphone, or a combination of these, for inputting user operations, etc. It is more preferable that the microphone is a so-called directional microphone that can determine the direction of the sound source.

HD10H5 is an example of an auxiliary storage device. In other words, HD10H5 stores data such as programs, files, and various settings used in processing.

The storage device 10H6 is a so-called memory. In other words, programs or data stored in the HD 10H5 are read out to the storage device 10H6.

(Example of functional configuration)
3 is a functional block diagram illustrating an example of a functional configuration of a conference support system according to an embodiment of the present invention. For example, the conference support system 1 includes an input unit 1F1, a control unit 1F2, a storage unit 1F3, and an output unit 1F4.

For example, in the conference support system 1, the input unit 1F1 and the output unit 1F4 are each included in the terminal 11 (FIG. 1). The control unit 1F2 and the memory unit 1F3 are included in the server 10 (FIG. 1). Note that each unit shown in the figure may be included in either the terminal 11 or the server 10.

The input unit 1F1 inputs the content of statements made during the conference. For example, the input unit 1F1 is realized by the input device 10H4 (Figure 2) or the like.

The control unit 1F2 performs control to realize each process. Specifically, the control unit 1F2 has a judgment unit 1F21. As shown in the figure, the control unit 1F2 may also have a decoration unit 1F22, a time management unit 1F23, and a speaker judgment unit 1F24. For example, the control unit 1F2 is realized by the CPU 10H1 (Figure 2) or the like.

The storage unit 1F3 stores data that is input in advance. The storage unit 1F3 also realizes a database and the like. The storage unit 1F3 also stores the contents of statements. For example, the storage unit 1F3 is realized by the HD 10H5 (FIG. 2) and the storage device 10H6 (FIG. 2), etc.

The output unit 1F4 displays or prints the meeting contents, and outputs the meeting contents such as minutes, evaluation results, summaries, remarks, judgment results, or a combination of these to the meeting participants. For example, the output unit 1F4 is realized by the output device 10H3 (FIG. 2) or the like.

First, in the conference support system 1, the content of a statement made during a conference by a person who made the statement (hereinafter referred to as the "speaker") or a minutes keeper, etc., is input by the input unit 1F1. Specifically, the content of a statement is input in text format, for example, by a keyboard or the like. Note that the content of a statement may be the content that a participant verbally states and then input by a keyboard or the like later. In addition, in an online conference between remote locations using chat or the like, when a participant inputs the content he or she wishes to say by keyboard, the content of a statement may be the content input in the chat or the like. In other words, the content of a statement is not limited to the content that is spoken verbally. In other words, the content of a statement may be the content that is not stated verbally but is input by a keyboard or the like.

Alternatively, the content of the remarks may be input by voice using a microphone or the like. In other words, when the content of the remarks is input by voice, the conference support system 1 may perform voice recognition on the input voice and generate text data or the like.

Furthermore, the content of the remarks may be input by handwriting, for example, on an electronic whiteboard or a tablet terminal. In other words, the meeting support system 1 may convert characters written by hand on an electronic whiteboard or the like into text data or the like using OCR (Optical Character Recognition) or the like, and input the converted data.

The utterance content is an example of a sentence, and in addition, for example, the content written in an e-mail when sharing information via e-mail or the like may be input to the input unit 1F1 into the conference support system. In this case, the content is input, for example, as text data describing the content of the e-mail. Note that the sentence is not limited to being input as text data, and may be input as other document data, etc.

In addition, data indicating, for example, a daily report or report may be input to input unit 1F1. For example, the data such as a daily report input to input unit 1F1 may be text data indicating the contents of the daily report, data created on a web application, or data generated by reading a handwritten document using OCR or the like.

When the speaker determination unit 1F24 identifies who the speaker is from among the participants, the speaker determination unit 1F24 may use multiple directional microphones or the like to link the speaker with the direction in which the source of the sound is determined to be located, and identify the speaker from among the participants. Alternatively, the speaker determination unit 1F24 may perform voice authentication on the input voice data and identify the speaker based on the authentication result. Alternatively, the speaker determination unit 1F24 may identify the speaker by photographing the speaker with a camera or the like connected to the network 12 (Figure 1) and performing face authentication using the captured image.

In addition, information that can identify who made the statement may be input by the input unit 1F1 or the like. Specifically, for example, speaker information is first assigned in advance to each of a number of function keys ("F1" to "F12") on the keyboard. Then, when the statement is to be input, the conference support system 1 may assign the speaker information to the statement when a function key is pressed. In this way, the statement may be linked to the speaker.

When sharing information via e-mail, sender information is added based on data such as the sender and recipient contained in the e-mail header, etc.

Next, the conference support system 1 determines the type of the inputted utterance by the determination unit 1F21. Specifically, the types of utterances are, for example, "proposal," "question," "answer," "positive opinion," "negative opinion," "neutral opinion," "information," "request," "issue," "action item" (hereinafter sometimes referred to as "A.I."), and "decision." Below, an example of classifying the contents of utterances into such utterance types will be described.

First, in the conference support system 1, expressions defined in advance for each type of utterance are stored in memory unit 1F3 in order to determine the type of utterance. Furthermore, an expression is a sentence, phrase, or turn of phrase, etc., and memory unit 1F3 stores the type of utterance in association with an expression specific to that type of utterance. Then, when the content of the utterance is input by input unit 1F1, judgment unit 1F21 judges whether the content of the utterance includes an expression stored in memory unit 1F3. Next, when the content of the utterance includes an expression stored in memory unit 1F3, judgment unit 1F21 identifies the corresponding type from among the types of utterance. In this way, the conference support system 1 can determine the type of utterance of the content of the utterance made in the conference.

The output unit 1F4 also lists the meeting contents and outputs them. The output unit 1F4 may also decorate and display the remarks based on the type of remarks determined by the determination unit 1F21. Details of the listing and other operations will be described later.

(Input and output examples)
In the conference support system, for example, each terminal displays a screen such as the one shown below and performs each process.

Figure 4 is a diagram showing an example of a screen displayed by a conference support system according to an embodiment of the first embodiment of the present invention. For example, the screen displayed on each screen of each terminal has a display and a GUI (Graphical User Interface) as shown in the figure. The following will explain the screen shown in the figure as an example.

In this example, the output unit displays on the screen the agenda 301 and the purpose of the meeting, i.e., goal 302. When the agenda 301 and goal 302 are displayed during the meeting, it is possible to align the participants' awareness and the vector of the discussion. Therefore, the meeting support system can reduce derailment of the meeting. The agenda 301 and goal 302 are set in advance, for example, before the meeting begins or at the beginning of the meeting, as follows:

Figure 5 is a diagram showing an example of a setting screen for setting an agenda, goals, etc. in a conference support system according to an embodiment of the first embodiment of the present invention. For example, a setting screen as shown in the figure is displayed by the conference support system at the beginning of a conference. After the settings shown below are made on the setting screen, the settings are completed when the start button 505 is pressed. In other words, after the start button 505 is pressed, the screen shown in Figure 4 and the like are displayed by the conference support system.

As shown in the figure, a participant inputs an agenda into the agenda setting text box 501. Furthermore, the participant sets a goal for each agenda input into the agenda setting text box 501. The goal is input, for example, into the goal setting text box 502. In this way, the agenda and goal input into the agenda setting text box 501 and goal setting text box 502 are displayed by the meeting support system as agenda 301 and goal 302, as shown in FIG. 4.

In addition, a meeting notice may be created before the meeting is held. In such cases, the agenda and goal written in the meeting notice may be displayed as agenda 301 and goal 302 by the meeting support system, as shown in FIG. 4. In this way, when meeting participants are notified of a meeting notice in advance, the participants can make preparations in advance, making the meeting more efficient. In addition, when meeting participants are notified of a meeting notice in advance, the participants can determine whether or not they need to participate, and can avoid participating in unnecessary meetings.

Returning to FIG. 4, the current time 306, time allocation 307, and progress status 308 are displayed on the screen by the conference support system. The current time 306 is displayed based on a preset time or data indicating time acquired via a network or the like. Furthermore, the time allocation 307 is displayed based on the scheduled time for each agenda item that is preset. For example, the scheduled time for each agenda item is entered in the scheduled time setting text box 503 shown in FIG. 5. Furthermore, the progress status 308 is displayed as a progress bar or the like that indicates the percentage of time that has passed based on the time that has passed from the conference start time to the current time 306, as shown in the figure.

The following displays may also be made by the time management unit 1F23 (Figure 3) and the output unit 1F4 (Figure 3). For example, when the scheduled end time of the entire meeting or each agenda item approaches, the meeting support system may display the remaining time or an alert encouraging participants to wrap up the meeting. For example, in an example using the screen shown in Figure 4, the following displays are made by the meeting support system.

FIG. 6 is a diagram showing an example of an alert and remaining time displayed on a screen displayed by a conference support system according to an embodiment of the first embodiment of the present invention. As shown in the figure, remaining time 401, alert 402, etc. may be displayed by the conference support system. In the example shown in the figure, remaining time 401 is an example of a display indicating that the time from the current time to the scheduled end time of the entire conference is "less than 10 minutes". Furthermore, alert 402 is an example of a display notifying participants that the remaining time of the conference is running out and that they should wrap up the conference, such as by drawing a conclusion. When such a display is displayed, participants can more easily secure time to wrap up the discussion. Therefore, the conference support system can reduce the occurrence of participants becoming too engrossed in the discussion, running out of time, and making the conclusion or action items of the conference unclear.

Note that the alert and remaining time are not limited to being output in the format shown in the figure. For example, the output may be audio, etc.

Returning to FIG. 4, the comment content 303 is displayed on the screen. The comment content 303 is decorated based on the judgment result by the judgment unit 1F21 (FIG. 3). For example, as shown in the figure, each comment content is displayed with a display indicating the type of comment, such as "Q:", "A:", "Proposal:", "Opinion (P):", "Opinion (N):", "Information:", "Agenda:" and "A.I. Candidate:", added to the beginning or end of the sentence. The decoration may be any decoration that can distinguish the type of each comment. For example, the decoration may be color coding, character decoration such as italics and bold, font type, addition of characters to the beginning or end of the sentence, or a combination of these. The way in which the comment content is decorated can be set in advance in the conference support system. Specifically, for example, a comment content determined to be a "positive opinion" is displayed in blue, and the display "Opinion (P)" is added to the beginning of the sentence. Additionally, comments that are judged to be "negative opinions" and "issues" are displayed in red, and the words "Opinion (N)" and "Issue" are added to the beginning of each sentence. In this way, when the type of comment is indicated by decoration, participants can intuitively grasp important points in the meeting, the contents of the discussion, and the trends of the meeting. Note that decoration may be processed by the server 10 (FIG. 1) or by a browser installed on the terminal 11 (FIG. 1).

Furthermore, when a speaker is identified, the speaker may be displayed by the conference support system as shown in the figure. In the example shown in the figure, the speaker's name is displayed in parentheses. Note that the speaker may be displayed in a format other than that shown in the figure. Furthermore, a person who is a candidate for a speaker, i.e., a participant, is set in advance in the participant setting text box 504 on the setting screen shown in FIG. 5, for example. Furthermore, as shown in FIG. 4, the participant set in the participant setting text box 504 is displayed by the conference support system as in participant display 305.

Note that the illustrated example is an example in which a function key is set to be linked to each participant displayed in participant display 305. For example, in the illustrated example, when one of the participants, "Sato", speaks, if function key "F2" is pressed when entering the content of the statement made by "Sato" into the statement content input text box 304, the entered content of the statement is linked to "Sato", which is the speaker information. That is, in the illustrated example, when function key "F2" is pressed when entering the content of the statement into the statement content input text box 304, the conference support system displays the entered content of the statement with "(Sato)" added.

The type of comment is determined, for example, by the process shown below. Below, we will explain an example in which the types of comments are "question," "answer," "suggestion," "issue," and "opinion."

Figure 7 is a flowchart showing an example of a process for determining the type of remarks by the conference support system according to the first embodiment of the present invention. Note that if written content is input in addition to the remarks, the written content is also processed in the same way.

In step S01, the conference support system initializes the question flag. Specifically, the conference support system sets the question flag to "FALSE." The question flag is an example of data indicating whether the type of the previously input utterance is a "question." Hereinafter, when the question flag is "FALSE," this indicates that the type of the previously input utterance is a type other than a "question." On the other hand, when the question flag is "TRUE," this indicates that the type of the previously input utterance is a "question."

In step S02, the conference support system inputs the content of the statement. Specifically, the conference support system inputs the content of the statement by the input unit 1F1 (FIG. 3). That is, in the example shown in FIG. 4, the content of the statement is input as text or the like into the statement content input text box 304.

In step S03, the conference support system determines whether the question flag is "TRUE". Next, if the question flag is "TRUE" (YES in step S03), the conference support system proceeds to step S04. On the other hand, if the question flag is not "TRUE", i.e., is "FALSE" (NO in step S03), the conference support system proceeds to step S05.

In step S04, the conference support system determines that the type of the utterance is an "answer." An "answer" is a utterance that is returned in response to a utterance that corresponds to the utterance type of a "question." For this reason, the "answer" is allowed to be expressed freely. In other words, there are cases where an expression that can be determined as an "answer" cannot be set in advance for an "answer." Therefore, as shown in step S03, the conference support system determines whether the immediately preceding utterance is a "question," that is, whether the type of the utterance is an "answer" based on the question flag. In other words, if the immediately preceding utterance is a "question," the conference support system determines that the type of the next utterance is an "answer." On the other hand, if the immediately preceding utterance is other than a "question," the conference support system determines that the type of the next utterance is other than an "answer." In this way, the conference support system classifies the utterance as an "answer." Also, in step S04, the conference support system sets the question flag to "FALSE."

In step S05, the conference support system judges whether the utterance content includes a "question" expression. For example, the conference support system judges the type of utterance content based on the auxiliary verb portion of the utterance content. Specifically, first, expressions such as "?", "Is it ~?", or "Is it not ~?" are stored in advance in storage unit 1F3 (Figure 3). Next, using judgment unit 1F21 (Figure 3), the conference support system judges whether all or part of the utterance content input by input unit 1F1 (Figure 3) matches the stored expression. In other words, the judgment is realized by so-called pattern matching, etc.

Next, if it is determined in step S05 that the utterance contains the expression "question" (YES in step S05), the conference support system proceeds to step S06. On the other hand, if it is determined in step S05 that the utterance does not contain the expression "question" (NO in step S05), the conference support system proceeds to step S08.

In step S06, the conference support system determines that the type of comment is a "question."

In step S07, the conference support system sets the question flag to "TRUE."

In step S08, it is determined whether the utterance contains the expression "suggestion." For example, the conference support system determines the type of utterance from the auxiliary verb portion of the utterance, as with "question." Specifically, first, expressions such as "should" or "it would be better to do" are stored in advance in storage unit 1F3 (Figure 3). Next, using determination unit 1F21 (Figure 3), the conference support system determines whether all or part of the utterance input by input unit 1F1 (Figure 3) matches the stored expression.

Next, if it is determined in step S08 that the content of the statement contains the expression "proposal" (YES in step S08), the meeting support system proceeds to step S09. On the other hand, if it is determined in step S08 that the content of the statement does not contain the expression "proposal" (NO in step S08), the meeting support system proceeds to step S10.

In step S09, the conference support system determines that the type of comment is a "proposal."

In step S10, it is determined whether the utterance content includes an expression of "issue." For example, the meeting support system determines the type of utterance content from the auxiliary verb portion of the utterance content, as with "question." Specifically, first, expressions such as "need to do ~" or "must do ~" are stored in advance in storage unit 1F3 (Figure 3). Next, using determination unit 1F21 (Figure 3), the meeting support system determines whether all or part of the utterance content input by input unit 1F1 (Figure 3) matches the stored expression.

Next, if it is determined in step S10 that the utterance content includes the expression "issue" (YES in step S10), the meeting support system proceeds to step S11. On the other hand, if it is determined in step S10 that the utterance content does not include the expression "issue" (NO in step S10), the meeting support system proceeds to step S12.

In step S11, the meeting support system determines that the type of comment is "issue."

In step S12, the meeting support system determines that the type of comment is an "opinion."

As described above, steps S02 to S12 are repeated for each comment. By performing this process, the conference support system can determine the type of comment.

The conference support system may also display a summary. For example, when the following operation is performed, the conference support system switches between the summary and the full text.

Figure 8 is a diagram showing an example of a screen for switching between a summary and the full text by the conference support system according to an embodiment of the first embodiment of the present invention. The screen shown is an example of a screen displayed during a conference. When the summary instruction button BN1, which is shown as "Display extracted important sentences," is pressed, the conference support system switches the screen to display the summary.

FIG. 9 is a flowchart showing an example of a process for switching between a summary and a full text by a conference support system according to an embodiment of the first embodiment of the present invention. The conference support system performs the process shown in the figure to generate a summary. The types of comments are as follows: "suggestion," "question," "answer," "positive opinion," "negative opinion," "neutral opinion," "information," "request," "issue," "action item," "decision," etc.

In step S21, the conference support system initializes the summary flag. Specifically, the conference support system sets the summary flag to "FALSE." The summary flag is a flag that switches between extracting important parts of the input remarks and displaying a summary, or displaying the full text showing all remarks. Hereinafter, when the summary flag is "FALSE," the conference support system is set to display the full text. On the other hand, when the summary flag is "TRUE," the conference support system is set to display a summary.

In step S22, the conference support system accepts pressing of the summary instruction button BN1 (Figure 8). Each time the summary instruction button BN1 is pressed, the display switches between the full text and the summary.

In step S23, the conference support system determines whether the summary flag is "TRUE". Next, if it is determined that the summary flag is "TRUE" (YES in step S23), the conference support system proceeds to step S24. On the other hand, if it is determined that the summary flag is not "TRUE", i.e., is "FALSE" (NO in step S23), the conference support system proceeds to step S26.

In step S24, the conference support system displays the entire text. Specifically, for example, the screen shown in FIG. 8 is displayed by the conference support system. In other words, in the entire text, the conference support system displays all types of utterance content among the utterance content that is input.

In step S25, the conference support system sets the summary flag to "FALSE."

In step S26, the conference support system displays the summary. Specifically, for example, the conference support system displays a screen such as that shown below.

Figure 10 is a diagram showing an example of a screen showing a summary displayed by a conference support system according to an embodiment of the first embodiment of the present invention. Compared to the screen shown in Figure 8, the screen shown in Figure 10 differs in that a summary display ABS is displayed.

The summary is the result of extracting important utterance contents from the utterance contents input. Whether the utterance contents are important or not is determined based on whether the utterance contents are of a type of utterance contents that is set in advance as important. For example, the summary is the result of extracting utterance contents of utterance types judged as "proposal", "issue" and "action item" from all types of utterance contents input. In other words, the summary is a meeting minutes generated by the conference support system extracting utterance contents of a predetermined utterance type from the utterance contents input. Note that the illustrated example is an example in which the utterance contents of the utterance types judged as "issue" and "action item" are extracted by the conference support system from the full text shown in FIG. 8, and a summary is generated. As illustrated, the conference support system displays the utterance contents of the target utterance type and hides the utterance contents of the other utterance types. In other words, when the summary shown in FIG. 10 is displayed, the participants can easily create action items. In this way, when the summary is displayed, the participants can review the key points of the conference. Therefore, the conference support system can organize the issues, action items, decisions, etc., without missing anything. In this way, the conference support system can make the conference more efficient.

Returning to FIG. 9, in step S27, the conference support system sets the summary flag to "TRUE."

As described above, steps S22 to S27 are repeatedly performed by the conference support system. By performing such processing, the conference support system can switch between displaying the full text and the summary.

The conference support system may also generate topics for the content of comments, etc. A topic is a word that indicates the title, topic, or subject of multiple sentences. For example, the conference support system displays the generated topics as follows:

Figure 11 is a diagram showing an example of the display of topics generated by a conference support system according to an embodiment of the first embodiment of the present invention. In the example shown, the conference support system generates topics 1101, and arranges and displays the corresponding comment content 1102 for each topic 1101.

The content of statements made in a conference is often made up of multiple topics 1101. Note that the content of statements made in a conference may be made up of multiple topics 1101 or may be the same as topic 1101.

As shown in the figure, the remarks 1102 are grouped by topic 1101. The remarks 1102 grouped by topic are then decorated according to the type of each remark 1102. The example shown in the figure is one in which, of the remarks 1102, the remarks 1102 of "positive opinions" are arranged on the left side, while the remarks 1102 of "negative opinions" and "issues" are arranged on the right side. In this way, by arranging the sentences according to their type, the conference support system can display the contents of the discussion in a way that makes it easy for the user to intuitively grasp them.

In addition, if the utterance content 1102 is a long utterance content, the conference support system may shorten the sentences of the utterance content 1102. For example, the conference support system may perform so-called sentence compression or the like. In other words, the conference support system may convert each utterance content into a simple format by using sentence compression or the like.

Specifically, the conference support system first performs a syntactic analysis of the utterance using a syntactic analysis tool or the like. The syntactic analysis then divides the utterance into multiple elements. The conference support system then assigns an importance level to each element. The conference support system then deletes elements with low importance levels based on the importance level. In this way, the conference support system can reduce the number of elements in a sentence and shorten the utterance without destroying the sentence structure.

The importance level is determined, for example, as follows:

- Nouns, proper nouns, and the subject or object case have high importance.

- Elements, adverbs, or attributive clauses that include "etc." or the particle "ya" to show examples are of low importance.

Therefore, the meeting support system compresses sentences by deleting attributive clauses, embedded sentences, subordinate clauses, etc., and shortens the content of speech. Sentence compression is, for example, a method disclosed in "Basics of Natural Language Processing" by Manabu Okumura, published by Corona Publishing.

In this way, when the topics are displayed by the meeting support system, the user can easily review the meeting. In other words, the meeting support system displays the "issues," "action items," and "decisions" associated with each topic, allowing the user to efficiently summarize the information shared during the meeting, etc.

The conferencing system is not limited to being used at the end of a conference. For example, minutes and the like may be entered and used after the conference has ended. Also, it is desirable to generate the distance between topics so as to minimize gaps and overlaps, for example, by the methods disclosed in "http://ryotakatoh.hatenablog.com/entry/2015/10/29/015502" and "http://tech-sketch.jp/2015/09/topic-model.html".

Topic 1101 is generated, for example, as follows:

Figure 12 is a flowchart showing an example of topic generation by the conference support system according to an embodiment of the first embodiment of the present invention. For example, when the process shown in the figure is performed, the screen shown in Figure 11 can be displayed by the conference support system.

In step S31, the conference support system inputs a sentence. For example, if a conference has been held using the conference support system, the conference support system is in a state in which the content of the statement made in the conference has been input.

In step S32, the conference support system estimates topic boundaries. Specifically, because topics are generated for each group of comment content, the conference support system first divides the comment content into groups. Therefore, the conference support system estimates topic boundaries that will separate the comment content into groups. For example, the conference support system estimates topic boundaries so that comment content with common content or comment content that can be estimated to be highly related to comment content are grouped together.

Topic boundaries are estimated, for example, using the following four methods:

The first estimation method is a method of estimating a topic boundary when a keyword that can be inferred to cause a topic transition is detected. Specific examples of keywords that can be inferred to cause a topic transition include "By the way" and "By the way." Such keywords are, for example, sentences that are set in advance in the meeting support system by a user before the meeting.

The second estimation method is a method of estimating a topic boundary when a word indicating a change in dialogue initiative is detected. Specifically, the second estimation method is a method of estimating a topic boundary when words such as "just now," "the other day," or "long ago" appear. Such words are, for example, sentences that are set in advance in the meeting support system by a user before the meeting.

The first and second estimation methods are, for example, the methods disclosed in "Detecting topic transitions in information-seeking chats," http://www.cl.cs.titech.ac.jp/_media/publication/632.pdf.

The third estimation method is a method in which the appearance of a sentence of the type "question" is estimated as a topic boundary. In other words, when there is a sentence that is judged to be a "question," the meeting support system estimates it as a topic boundary.

Furthermore, the fourth estimation method is an estimation method that estimates topic boundaries using "lexical cohesion." In the fourth estimation method, for example, "lexical cohesion" is calculated using a thesaurus or the like. Specifically, a chain consisting of a set of sentences that have a "lexical cohesion" relationship, a so-called "lexical chain," is first detected. Then, in the fourth estimation method, "lexical cohesion" is considered to indicate a meaningful grouping of sentences, and the start and end points of the "lexical chain" are estimated to be topic boundaries. For example, the fourth estimation method is a method disclosed in "Text Segmentation Based on Lexical Cohesion", "https://ipsj.ixsq.nii.ac.jp/ej/index.php?action=pages_view_main&active_action=repository_action_common_download&item_id=49265&item_no=1&attribute_id=1&file_no=1&page_id=13&block_id=8" and "Fundamentals of Natural Language Processing", by Manabu Okumura, Corona Publishing.

In step S33, the conference support system generates topics. That is, in step S33, the conference support system generates each topic for each topic boundary estimated in step S32. Therefore, step S33 is repeated the number of times equal to the number of groups separated by topic boundaries.

Topics are estimated using, for example, the following three methods:

The first generation method is to extract proper nouns or sentences not registered in a dictionary, so-called unknown words, from among sentences grouped by topic boundaries and use them as topics.

In the second generation method, first, nouns, verbs, or adjectives are extracted from the sentences grouped by topic boundaries. Next, in the second generation method, the conjugations of the extracted sentences are returned to their original forms. Then, the sentences that appear frequently are set as topics. In this way, the conference support system can display topics, etc.

Alternatively, in the third generation method, the topics may be, for example, important words contained in a group separated by topic boundaries. For example, important words can be identified by the TF-IDF (Term Frequency-Inverse Document Frequency) method or the like.

Then, the conference support system outputs a list of pre-set types of sentences (hereinafter referred to as "specific sentences") from among the utterances. First, assume that a conference is held using the conference support system. Next, in the case where there are specific sentences that are pre-classified as "issues," "action items," or "decisions," the conference system is set to perform the following processing.

Figure 13 is a diagram showing an example of the display of an alert or the like by the conference support system according to an embodiment of the first embodiment of the present invention. First, assume that a conference is held using the conference support system, and that a comment or the like that falls into the category of "issue" is made during the conference. That is, an example in which a specific sentence classified as "issue" is input will be described below. Then, for example, when the conference ends, the conference system outputs a screen as shown in the figure. Note that when the contents of an e-mail are input to the conference support system, the conference system outputs a screen as shown in the figure when the e-mail is received, etc.

Specifically, as shown in the figure, the conference support system displays an alert 1201. In the example shown, alert 1201 is a message that displays the utterances that are "issues" among the utterances made in the conference. In other words, alert 1201 makes it possible to identify utterances tagged as "issues", i.e., specific sentences, from among the utterances.

Alert 1201 may be a link that, when pressed, displays minutes or the like corresponding to the displayed comment content. When the user presses alert 1201, which serves as a link, minutes or the like are displayed, allowing the user to learn the background of the comment content displayed in alert 1201 or the process leading to a decision. In this way, for example, if the user is a manager, the manager can quickly grasp any newly arising "issues" before regular reports or the like are sent. This allows the manager to detect problems early and quickly follow up on the problems.

Next, in the illustrated example, when the list button 1202 is pressed, the meeting support system outputs a list of sentences of the type "issues," "action items," or "decisions," for example, as follows:

Figure 14 is a diagram showing an example of specific sentences listed and output by the conference support system according to an embodiment of the first embodiment of the present invention. In the example shown, the conference support system extracts utterances of the type that are "issues" and "action items," i.e., specific sentences, from the utterances, etc., and displays them as a list 1301. For example, the screen shown in Figure 14 is a screen displayed by the conference support system when the list button 1202 is pressed on the screen in Figure 13.

As shown in the figure, in list 1301, among the comments made during the meeting, the comments that fall into the categories of "issues," "action items," and "decisions" are listed and displayed in order. In addition, the types of sentences to be listed, such as "issues," "action items," and "decisions" in this example, are set in advance in the meeting support system.

When each specific sentence is displayed in a list in this way, for example, if the user is a manager, the manager can view list 1301 and centrally manage issues related to his or her own department.

As shown in the figure, a link 1302 may be provided for list 1301. Specifically, when link 1302 is pressed, details of the situation in which the "issue," "action item," and "decision" indicated by list 1301 occurred, i.e., minutes of a meeting related to a specific sentence, are displayed. This allows the user to understand details such as the process and background for determining the "issue," "action item," and "decision."

The sentences displayed in list 1301 may be limited to sentences related to one's own department, for example. For example, if the participants in the input minutes of a meeting, etc. include people from one's own department, the conference support system determines that the sentences spoken in the meeting relate to one's own department. Also, in the case of e-mail, if the sender or recipient of the e-mail includes people from one's own department, the conference support system determines that the sentences written in the e-mail relate to one's own department. Furthermore, when sending e-mail, the conference support system can be set as one of the destinations, and when the e-mail is the destination, the conference support system determines that the sentences written in the sent e-mail relate to one's own department.

The meeting support system may also display the history of meetings and emails as follows:

Figure 15 is a diagram showing an example of a display of the history by the conference support system according to an embodiment of the first embodiment of the present invention. The screen shown is an example of a screen that is displayed when button 1303 is pressed on the screen shown in Figure 14, for example. When the user wishes to refer to the history of a comment among the listed comments, the user presses the corresponding button 1303.

When button 1303 is pressed, the conference support system extracts the remarks related to the listed remarks and displays them in chronological order. The extraction may be by topic, for example. As shown in the figure, "action items" and "decisions" related to the extracted remarks may also be displayed. Items to be displayed, such as "action items" and "decisions" shown in the figure, are set in advance in the conference support system.

The chronological position of the statement 1501 is determined by the date and time entered in the minutes of the meeting, etc. The chronological position of the statement 1502 entered in an e-mail, etc. is determined by the sending date and time entered in the SMTP header, etc.

In this way, when statements such as statement content 1501 and written content 1502 are displayed in chronological order, the user can understand the history of past decision-making, etc. For example, it can facilitate handover when a new manager is assigned due to a transfer, etc., and can facilitate reviewing or analyzing the cause of a problem when it occurs, etc.

Furthermore, the meeting support system may display a screen that visualizes communication as shown below. Hereinafter, a diagram that visualizes communication will be referred to as a "communication diagram."

Figure 16 is a diagram showing an example of a communication diagram displayed by the conference support system according to an embodiment of the first embodiment of the present invention. In the illustrated communication diagram, the amount of communication between users is represented by the thickness of the lines connecting the users. Note that the communication diagram is displayed by the conference support system when, for example, the visualization button 1203 is pressed on the screen shown in Figure 13.

First, the meeting support system extracts the participants and meeting time from the input minutes, etc. Then, the meeting support system calculates the strength of communication between each user (hereinafter referred to as "communication strength") based on the participants and meeting time, etc.

For example, communication intensity is a value calculated by adding up the conference time of conferences in which each user participated together. The conference support system may also calculate communication intensity by weighting the conference time based on the number of participants, for example. Specifically, in conferences with a small number of participants, for example a one-on-one conference with two participants, there is a high possibility of close communication. For this reason, the conference support system calculates communication intensity by multiplying the conference time of conferences with a small number of participants by a weighting coefficient that is a large value. In this way, communication intensity is calculated to be strong between users who spend a lot of conference time in conferences with a small number of participants.

In the case of e-mail, the communication strength is calculated based on the number of times the e-mail is sent and received, and the weighting of whether the e-mail is a "Destination" or "CC (Carbon Copy, broadcast)" message.

Then, the conference support system changes the thickness of the lines connecting each user based on the calculated communication strength. For example, in the illustrated example, if the communication strength between "User B" and "User A" is strong, a thick line LN1 connects "User B" UB and "User A" UA, as shown in the figure.

On the other hand, if the communication strength between "User D" UD and "User E" UE is weaker than that between "User B" UB and "User A" UA, then as shown in the figure, "User D" UD and "User E" UE are connected by a line LN2 that is thinner than the thick line LN1. In other words, like the thick line LN1 and the thin line LN2, the conference support system changes the thickness of the line connecting each user based on the communication strength.

In this way, the conference support system can visualize the density of communication between users. Furthermore, such a communication diagram allows users to understand the strength of the connections between users in the workplace. This allows users to understand who the key users are in the organization, and who are the important users who connect departments.

In addition, in the communication diagram, as shown in the figure, the conference support system may treat multiple users as "teams," such as "Team A" TA and "Team B" TB. As in the example shown, the conference support system may display lines connecting users and teams, and teams and teams, based on communication strength, just like between users.

In addition, when a line is pressed on the communication diagram, the meeting support system may display a screen such as the one below.

Figure 17 is a diagram showing an example of a log display in a communication diagram displayed by a conference support system according to an embodiment of the first embodiment of the present invention. For example, when the thick line LN1 or the thin line LN2 in Figure 16 is pressed, the conference support system displays a record of communication such as minutes of meetings between each user, a so-called log (hereinafter simply referred to as "log 1601"), as shown in Figure 17. Log 1601 shows, for example, a list of minutes of meetings attended by each user connected by a line, as shown in the figure. In addition, when a link indicated by log 1601 is pressed, the conference support system displays details of the minutes, etc., in the same way as when link 1302 shown in Figure 14 is pressed.

In this way, when the details of each communication are displayed by log 1601, etc., the user can understand the content of each communication, etc. Specifically, by log 1601, etc., the user can understand what reports are being made, or what decisions are being made by users who are the liaison with other departments, etc.

Second Embodiment
The second embodiment is an embodiment that is realized, for example, by the same overall configuration and hardware configuration as the first embodiment. Therefore, the description of the overall configuration and hardware configuration will be omitted, and the following description will focus on the differences. The second embodiment has a different functional configuration from the first embodiment.

Figure 18 is a functional block diagram illustrating an example of the functional configuration of a conference support system according to a second embodiment of the present invention. Compared to Figure 3, the functional configuration shown in Figure 18 differs in that the control unit 1F2 includes a cost calculation unit 1F31 and an evaluation unit 1F32.

The cost calculation unit 1F31 calculates the costs incurred by holding the conference based on the personnel costs of the participants.

The evaluation unit 1F32 evaluates the meeting based on the time the meeting took place, the number of comments, the types of comments, and the ratio of types of comments, etc.

The cost calculation unit 1F31 calculates the cost and the evaluation unit 1F32 evaluates the cost, for example, when the summary button 309, which is the button for "Go to summary/save screen" shown in FIG. 4, is pressed or when an alert 402 is displayed as shown in FIG. 6. For example, the conference system displays a summary screen such as the one shown below.

Figure 19 is a diagram showing an example of a summary screen displayed by a conference support system according to an embodiment of the second embodiment of the present invention. In the example of the screen shown in the figure, the agenda display 801 displays the agenda set by the conference support system in the agenda setting text box 501 (Figure 5) or the like in the opening notice or at the beginning of the conference. Furthermore, in the example of the screen shown in the figure, the goal display 802 displays the goal set by the conference support system in the goal setting text box 502 (Figure 5) or the like in the opening notice or at the beginning of the conference.

Based on the contents displayed in the agenda display 801 and the goal display 802, a conclusion to the discussion is entered in the conclusion input text box 803. Also, based on the contents displayed in the agenda display 801 and the goal display 802, an action item decided in the meeting is entered in the action item input text box 804. Note that a date, i.e., a deadline, may be set for the action item. Additionally, a person in charge may be set for the action item. Also, in the action item input text box 804, the meeting support system may display remarks that it has determined to be "action items" as candidates for action items.

The conference support system also displays the cost calculation by the cost calculation unit 1F31 (Figure 18) and the evaluation by the evaluation unit 1F32 (Figure 18) on an evaluation screen, for example, as shown below.

Figure 20 is a diagram showing an example of an evaluation screen displayed by a conference support system according to an embodiment of the second embodiment of the present invention. For example, the conference support system displays the cost and evaluation results of the conference as a score, amount, etc., as shown in the figure.

The meeting score 901 is an overall score calculated by adding up the scores of the achievement evaluation score 902, the meeting time evaluation score 903, the activity evaluation score 904, and the positive evaluation score 905.

The achievement evaluation score 902 is an evaluation result of whether or not a conclusion has been entered for each of the previously set goals for each agenda item set in the agenda setting text box 501 (Figure 5) or the like. For example, if four agenda items are set in the agenda setting text box 501 (Figure 5) or the like and two conclusions have been entered for the four agenda items, the meeting support system will set the achievement evaluation score 902 to half of the full score.

The meeting time evaluation score 903 is an evaluation result obtained by comparing the scheduled time, which is set in the meeting notification or in the scheduled time setting text box 503 (Figure 5), with the time the meeting took place. For example, if the time the meeting took place is shorter than the scheduled time, the meeting time evaluation score 903 will be high. On the other hand, if the time the meeting took place is longer than the scheduled time, the meeting time evaluation score 903 will be low.

The activity evaluation score 904 is an evaluation result based on the number of comments or the number of comments per unit time. For example, if the number of comments or the number of comments per unit time is large, the activity evaluation score 904 will be high. On the other hand, if the number of comments or the number of comments per unit time is small, the activity evaluation score 904 will be low. For this reason, if the activity evaluation score 904 is low, the meeting may have become a place for unnecessary information sharing, or people unrelated to the agenda may have been gathered and so-called side work may be taking place. Thus, the meeting support system can encourage improvements in the management of the meeting by providing feedback on these possibilities.

The positivity evaluation score 905 is an evaluation result based on the types of statements and the proportion of the types of statements judged by the judgment unit 1F21 (Figure 18). For example, if the proportion of types of statements evaluated as "suggestions" is high, the positivity evaluation score 905 will be high. On the other hand, if the proportion of types of statements evaluated as "suggestions" is low, the positivity evaluation score 905 will be low. For this reason, if the positivity evaluation score 905 is low, there is a possibility that the meeting is one with a lot of critiques and comments, and does not move closer to a conclusion. Therefore, the meeting support system can suggest this possibility and encourage participants to offer constructive opinions toward the goal.

The conference support system performs the above evaluation using evaluation unit 1F32 (Figure 18). Next, the conference support system can provide participants with objective feedback of the evaluation results for the conference by outputting the evaluation results to a screen or the like using output unit 1F4 (Figure 18). When feedback is provided in this way, the conference support system can suggest to participants which areas of the conference are likely to be problematic, or make participants aware of the time the conference took place, etc. This allows the conference support system to have participants reconsider which members to include in the conference or how the conference will proceed.

The conference support system may display each evaluation result, the number of comments, and the type of comments during the conference. For example, in the example shown in FIG. 4, the evaluation results may be displayed as in evaluation display 310. That is, the evaluation results may be displayed in real time during the conference. In this way, the conference support system can, for example, encourage people who do not speak much to speak up.

The meeting support system may also weight comments that are determined to be "issues" and "suggestions" during the evaluation. In this way, the meeting support system can encourage participants to make more comments that are in the category of "issues" and "suggestions." Therefore, the meeting support system can encourage more useful discussions.

In addition, the conference support system may display the cost calculation results, etc., on the evaluation screen. For example, the cost is calculated by the cost calculation unit 1F31 (FIG. 18) based on the conference time 906 and the labor costs of each participant. The calculated cost is displayed, for example, as a cost display 907, etc.

To calculate the costs, first, the labor cost per unit time of each participant is input into the conference support system. The labor cost may be a fixed amount for all participants, or may be set for each position. The labor cost may also be set based on actual salary, etc.

Next, the conference support system measures the time that has elapsed from the start time of the conference to the end time of the conference, and displays the measurement result in conference time 906. The conference support system then multiplies the labor cost per unit time of each participant by the conference time 906 to calculate the cost of each participant. Next, the conference support system sums up the respective costs of each participant, and displays the calculation result in cost display 907.

In addition, the evaluation results for each participant may be displayed on the evaluation screen by the conference support system. For example, the evaluation results for each participant may be displayed as a contribution display 908, etc.

The contribution display 908 shows the evaluation result for each participant based on, for example, the type of comment and the number of comment contents determined by the determination unit 1F21 (FIG. 18). Note that the comment contents are linked to the participant who made each comment by the speaker determination unit 1F24 shown in FIG. 3, etc.

The contribution level display 908 is calculated by the conference support system, for example, as follows. First, participants set weights for the types of comments that are considered important in accordance with the purpose of the conference, such as "neutral opinions" being given "1 point" and "issues" and "suggestions" being given "5 points." It is preferable that the conference support system be set so that constructive opinions such as "issues" and "suggestions" are given a higher weight. When set in this way, the conference support system can encourage useful discussions toward solving the problem.

Next, the conference support system evaluates each participant by multiplying the result of the judgment by the judgment unit 1F21 (FIG. 18) and the number of comments. The values calculated by this evaluation are the "degree of contribution" and "earned points" shown in the contribution display 908. In this way, when the "degree of contribution" etc. is fed back to the participants by the conference support system, the participants can use the "degree of contribution" etc. to reconsider which members to include in the conference. Therefore, the conference support system can encourage more useful discussions. Furthermore, by reducing the number of unnecessary members participating, the conference support system can reduce the costs associated with the conference.

The above-mentioned screens may be shared in real time by each terminal 11 connected to the network 12 shown in FIG. 1. In this way, even if a conference is held in a location without a display, if participants bring their own terminal 11 such as a laptop PC, each participant can view the above-mentioned screens and hold the conference.

The comments and the like may also be edited collaboratively from each terminal 11. For example, the server 10 converts the content to be displayed on the screen into, for example, an HTML (Hyper Text Markup Language) file and transmits it to each terminal 11. Next, when the comments and the like are input and data indicating the comments and the like is transmitted to the server 10, the server 10 transmits an HTML file reflecting the new comments and the like to each terminal 11.

The words displayed on the screen may be subjected to a translation process. For example, when a statement is input and data indicating the statement is sent to the server 10, the server 10 translates the statement and generates an HTML file indicating the statement before translation and the statement after translation. The server 10 then transmits the HTML file indicating the statement before translation and the statement after translation to each terminal 11. In this way, the conference support system can reduce miscommunication even when participants speak different languages.

Each terminal 11 may also perform user authentication. For example, user authentication is performed by inputting a user name into a user name input text box displayed on the screen. Alternatively, user authentication may be performed using an IC card or RFID. In this way, similar to the function key assignment shown in FIG. 4, the speaker and the content of the speech may be linked based on the authentication result of the above user authentication and the terminal at which the content of the speech was input. Note that information related to the speaker may be added by coloring, displaying the beginning or end of the sentence, etc., similar to the first embodiment.

Furthermore, a subjective evaluation of the content of the remarks may be input, and the conference support system may perform an evaluation based on the input subjective evaluation. For example, the subjective evaluation may be input as follows:

Figure 21 is a diagram showing an example of a screen for inputting a subjective evaluation displayed by a conference support system according to an embodiment of the second embodiment of the present invention. Compared to Figure 6, the example screen shown in the figure differs in that a subjective evaluation button 1001 is added for each of the displayed remarks.

As shown in the figure, a subjective evaluation button 1001 is displayed for each statement. Then, when each participant judges that the statement is one that he or she supports, the participant presses the subjective evaluation button 1001 displayed for the statement that he or she supports. The subjective evaluation button 1001 may be pressed by the participant in charge of input, or each participant may press it based on their own judgment. The subjective evaluation button 1001 may also be a button that is pressed when a statement is not supported. In this way, when the subjective evaluation is input, the conference support system can evaluate whether or not each statement is a good statement based on the subjective opinion of each participant. Then, the conference support system can display the evaluation results based on the subjective evaluation, and encourage participants to make good statements that will help achieve the purpose of the conference.

The conference support system may also display the content of a statement decorated based on an input from the subjective evaluation button 1001. For example, in the screen shown in the figure, the conference support system displays the content of a statement for which the subjective evaluation button 1001 was pressed as a large display 1002. As shown in the figure, the large display 1002 is an example of a decoration in which the font size of the characters indicating the content of a statement is larger than that of other content of statements. When the content of a statement is thus decorated and output, participants can intuitively see which of the content of statements is supported. The conference support system may also use user information to display the status of approval or disapproval of the content of a statement, such as who is in favor and who is against a particular opinion.

Note that decorations are realized, for example, by modifying CSS (Cascading Style Sheets) descriptions using a language such as Javascript (registered trademark) using support and non-support information.

When displaying summaries, the meeting support system may display statements that are determined to be important based on the input subjective evaluation, in addition to displaying based on the type of statement. This allows participants to better understand the process of the discussion that led to the conclusion. In other words, this allows the meeting support system to generate minutes that are effective for reviewing the meeting and sharing information.

Furthermore, the evaluation unit 1F32 (FIG. 18) may evaluate a meeting based on the time the meeting took place. For example, the evaluation unit 1F32 (FIG. 18) performs the evaluation as follows:

Figure 22 is a flowchart showing an example of a process for evaluating a conference based on the time the conference was held by a conference support system according to a second embodiment of the present invention.

In step S31, the conference support system accepts pressing of an evaluation button. For example, when an evaluation button such as "Rate this conference" shown in FIG. 10 is pressed, the conference support system starts the evaluation. The duration of the conference is the time from when the conference started to when the conference ended (hereinafter referred to as "elapsed time"). Furthermore, the scheduled duration of the conference (hereinafter simply referred to as "scheduled duration") is input to the conference support system in advance, such as before the evaluation button is pressed.

In step S32, the conference support system determines whether the elapsed time exceeds the scheduled time by 10% or more. Next, if the conference support system determines that the elapsed time exceeds the scheduled time by 10% or more (YES in step S32), the conference support system proceeds to step S33. On the other hand, if the conference support system determines that the elapsed time does not exceed the scheduled time by 10% or more (NO in step S32), the conference support system proceeds to step S34.

In step S33, the meeting support system sets the evaluation score to "0" points.

In step S34, the conference support system determines whether the elapsed time exceeds the scheduled time by less than 10%. Next, if the conference support system determines that the elapsed time exceeds the scheduled time by less than 10% (YES in step S34), the conference support system proceeds to step S35. On the other hand, if the conference support system determines that the elapsed time does not exceed the scheduled time by less than 10% (NO in step S34), the conference support system proceeds to step S36.

In step S35, the meeting support system sets the evaluation score to "5" points.

In step S36, the conference support system determines whether the elapsed time exceeds the scheduled time by less than 5%. Next, if the conference support system determines that the elapsed time exceeds the scheduled time by less than 5% (YES in step S36), the conference support system proceeds to step S37. On the other hand, if the conference support system determines that the elapsed time does not exceed the scheduled time by less than 5% (NO in step S36), the conference support system proceeds to step S38.

In step S37, the meeting support system sets the evaluation score to "10" points.

In step S38, the conference support system determines whether the elapsed time is 10% or more shorter than the scheduled time. Next, if the conference support system determines that the elapsed time is 10% or more shorter than the scheduled time (YES in step S38), the conference support system proceeds to step S39. On the other hand, if the conference support system determines that the elapsed time is not 10% or more shorter than the scheduled time (NO in step S38), the conference support system proceeds to step S40.

In step S39, the meeting support system sets the evaluation score to "25" points.

In step S40, the conference support system determines whether the elapsed time is 5% or more shorter than the scheduled time. Next, if the conference support system determines that the elapsed time is 5% or more shorter than the scheduled time (YES in step S40), the conference support system proceeds to step S41. On the other hand, if the conference support system determines that the elapsed time is not 5% or more shorter than the scheduled time (NO in step S40), the conference support system proceeds to step S42.

In step S41, the meeting support system sets the evaluation score to "20" points.

In step S42, the meeting support system sets the evaluation score to "15" points.

For example, as shown in the figure, the conference support system will give a higher evaluation score when the elapsed time is shorter than the scheduled time. On the other hand, the conference support system will give a lower evaluation score when the elapsed time exceeds the scheduled time. Note that the numerical values of the evaluation score and the judgment criteria are not limited to the values and judgments shown in the figure, and may be changeable by settings, etc. As shown in the figure, the assessed evaluation score is displayed by the conference support system.

The conference support system may also display the evaluation results using stars or the like, as shown in FIG. 20. Furthermore, the conference support system may also display comments or the like encouraging behavioral change, as shown in FIG. 20. Furthermore, the conference support system may display the evaluation results related to time together with other evaluation results, as shown in FIG. 20. In this way, when the evaluation results evaluating the conference based on the time the conference was held are displayed, the conference support system can make the participants conscious of the time related to the conference and encourage them to achieve their goals within the time. In this way, the conference support system can make the conference more efficient.

Third Embodiment
The third embodiment is an embodiment realized by, for example, the same overall configuration, hardware configuration, and functional configuration as the first embodiment. The following mainly describes the differences. The third embodiment is different from the first embodiment in the determination method by the determination unit 1F21 (FIG. 3).

In the third embodiment, the conference support system uses a tagged corpus as so-called training data. The conference support system then learns a classifier that performs natural language processing by performing so-called supervised learning, which is a machine learning method. Below, an example will be described in which the tags, i.e., types of comments, are "suggestions," "questions," "answers," "positive opinions," "negative opinions," "neutral opinions," "information," "requests," "issues," "action items," and "decisions."

The machine learning technique may be, for example, a support vector machine (SVM), a naive Bayes classifier, decision tree learning, or a conditional random field (CRF). It is preferable that the machine learning technique is a support vector machine. A support vector machine can make decisions sequentially, improving real-time performance, etc.

The classifier determines the type of a statement based on the characteristics of the statement content (hereinafter referred to as "features"). Specifically, the features use the bag of words (BoW) of the statement, parts of speech such as auxiliary verbs, adverbs, adjectives, nouns, or auxiliary verbs contained in the statement content, and who the speaker is. For example, adjectives may indicate positive or negative expressions. In addition to positive or negative expressions, nouns may be expressions indicating "action items" and "issues" such as "needs consideration" and "needs a response". Furthermore, auxiliary verbs, etc., may be expressions indicating hope, obligation, necessity, request, proposal, assertion, conjecture, hearsay, evaluation, etc. at the end of a sentence. Therefore, when the classifier determines the type of a statement based on features, the meeting support system can accurately determine the type of a statement.

The conference support system performs natural language processing using machine learning, for example, according to the method described in "The Basics of Natural Language Processing," by Manabu Okumura, Corona Publishing.

FIG. 23 is a conceptual diagram showing an example of natural language processing using machine learning by a conference support system according to an embodiment of the third embodiment of the present invention. As shown in the figure, the conference support system trains a classifier CLF by supervised learning. First, data expressed as a set of feature-value pairs is input to the classifier CLF, and the classifier outputs a class to which the input test data TSD belongs. The class is indicated by a class label CLB. In other words, the class label CLB indicates the result of determining the type of utterance of the utterance content indicated by the test data TSD.

To train the classifier CLF using a machine learning algorithm, as shown in the figure, the conference support system inputs data and a set of pairs of classes to which the data belongs as training data TRD. Next, when the training data TRD is input, the conference support system trains the classifier CLF using a machine learning algorithm. After training the classifier CLF in this way, when test data TSD is input, the conference support system can output the class to which the test data TSD belongs using the classifier CLF.

The method of determining the type of speech using the classifier CLF allows the conference support system to determine the type of speech with greater accuracy than methods that use pattern matching, etc. Furthermore, the method of determining the type of speech using the classifier CLF requires less effort, such as updating the pattern matching rules, compared to methods that use pattern matching, etc. In other words, when the method of determining the type of speech using the classifier CLF is used, so-called maintainability can be improved.

The system may also be configured so that participants can change the class label. In this way, if the class label CLB resulting from the determination by the classifier CLF indicates a class different from the class intended by the participant, the participant can change the class. For example, even if the content of a statement is determined to be an "opinion" by the conference support system, if the participant thinks it is a "question," the participant can change the class label from "opinion" to "question."

In this way, when changes are made and feedback is provided, the conference support system can learn the classifier CLF, just as in the case where training data TRD is input in machine learning. This makes it possible to train the classifier CLF in the conference support system with less effort, such as updating data. Therefore, the conference support system can accurately determine the type of speech.

Alternatively, the classifier CLF may be trained using information about the person who made the identified utterance as the feature. In this way, the conference support system can determine the type of utterance taking into account the tendencies of the person who made the utterance. As a result, the conference support system can accurately determine the type of utterance.

Furthermore, the conference support system may determine the type of statement based on the role in the conference of the person who made the statement. For example, in a conference such as a report session, if the person who made the statement is a "decision maker," the information of the "decision maker" may be used as an attribute to determine the type of statement. In this way, the conference support system can determine the type of statement taking into account the tendencies of the person who made the statement. Therefore, the conference support system can accurately determine the type of statement. In particular, the conference support system can accurately determine types of statements such as "action items" and "decisions."

In addition, the accuracy often decreases as the number of types of utterances, i.e., labels, increases. Therefore, the meeting support system may divide the types of utterances into groups. For example, an example will be described in which the types of utterances are "suggestions," "questions," "answers," "positive opinions," "negative opinions," "neutral opinions," "information," "requests," "issues," "action items," and "decisions."

For example, let the groups be "Group 1" and "Group 2" as shown below.

First group: "Suggestions", "Questions", "Answers", "Positive opinions", "Negative opinions", "Neutral opinions", "Information" and "Requests".
Group 2: "Action items" and "Decisions"
Then, the conference support system determines which of the "first group" utterance types the utterance content belongs to. Next, the conference support system determines which of the "second group" utterance types the utterance content belongs to. In the configuration shown in Fig. 23, a classifier CLF is prepared for each group.

For example, suppose that someone says in a meeting, "I want something to be done between the people in charge." The meeting support system determines that this comment is a type of "answer" comment in the first group, and also a type of "action item" comment in the second group.

For example, suppose that the content of statements of the "action items" and "decisions" types is important in a meeting. In such a case, if important types of statements are selected and grouped, as in the second group described above, the meeting support system can accurately determine the content of important types of statements. Also, since the number of types of statements in each group is smaller than when they are not grouped, the meeting support system can accurately determine the types of statements.

(Fourth embodiment)
Furthermore, the information sharing support system 20 may have, for example, the following overall configuration.

Figure 24 is a conceptual diagram illustrating an example of the overall configuration of an information sharing support system according to an embodiment of the fourth embodiment of the present invention. For example, the information sharing support system 20 has an overall configuration including a conference support system 1 and an information sharing server 21. As shown in the figure, there may be multiple conference support systems 1. Also, in the information sharing support system 20, as shown in the figure, the conference support system 1, the information sharing server 21, and the terminal 11 do not have to be separate devices. For example, the conference support system 1 and the information sharing server 21 may be combined into a single information processing device. Below, the overall configuration shown in the figure will be described as an example.

Communication logs such as email data DEM, chat data DCH, and electronic file data DEF are input to the information sharing server 21 from external devices such as each terminal 11.

In this way, sentences may be input to the information sharing support system 20 in various data formats, not just the content of statements made in a meeting. Note that data such as email data DEM, chat data DCH, and electronic file data DEF may be input via the meeting support system 1, etc.

When a certain amount of data has been collected, a specific person such as a manager accesses the information sharing server 21, and a screen such as that shown in FIG. 14 is displayed. Next, when button 1303 is pressed, for example, the information sharing support system 20 outputs the sentences entered in each data format as follows:

Figure 25 is a diagram illustrating an example of an output by an information sharing support system according to an embodiment of the fourth embodiment of the present invention. The information sharing server 21 displays, for example, a screen as shown in the figure to a user via a display device or a terminal 11, etc.

Note that the screen as shown in the figure is not limited to being displayed based on the operation of button 1303 or the like. For example, when a certain type of comment such as "issue" is made in the input communication log, a push notification is first sent to a specific person such as a manager that an "issue" has occurred. Note that the type is set in advance. Then, when a link included in the push notification (such as a URL (Uniform Resource Locator) written in an email) is accessed, the screen as shown in the figure may be displayed.

For example, the information sharing server 21 generates a screen as shown in the figure by the following process.

Figure 26 is a flowchart showing an example of processing by an information sharing support system according to an embodiment of the fourth embodiment of the present invention. Note that in the figure, the same processes as those in Figure 12 are given the same reference numerals, and duplicated explanations will be omitted below.

In step S51, the information sharing support system 20 sorts the sentences. First, in the illustrated example, when the processing up to step S33 is performed, the information sharing support system 20 can extract sentences related to specific content. Next, the information sharing support system 20 sorts the extracted sentences, for example, in chronological order.

The example shown in FIG. 25 shows the result of sorting by the information sharing support system 20, with the oldest sentences arranged from the bottom to the top of the figure, from the newest sentences. When the sorted results are output in this way, the user can look at a screen like the one shown in the figure and understand how a certain topic was reached, etc.

The sentences to be output may be selected. For example, the information sharing support system 20 selects sentences as follows:

In step S52, the information sharing support system 20 selects a sentence. For example, the information sharing support system 20 selects a sentence to be output based on the format in which the sentence was input. Specifically, in the example shown in FIG. 24, a sentence is input from the conference support system 1 to the information sharing support system 20 in the minutes data format. Similarly, a sentence is input from the terminal 11 to the information sharing support system 20 in the email data DEM format, the chat data DCH format, and the electronic file data DEF format. Hereinafter, it is assumed that sentences are input to the information sharing support system 20 in four different formats in this way.

In the screen shown in FIG. 25, the conference icon ICM indicates that the sentence is based on the minutes data. Similarly, the chat icon ICC indicates that the sentence is based on the chat data DCH. Furthermore, the email icon ICE indicates that the sentence is based on the email data DEM. As shown in the figure, the information sharing support system 20 can indicate where each sentence was spoken, for example, by outputting the sentence along with each icon.

In addition, in the output, for example, as shown in FIG. 25, attached data FL may be linked to each sentence. The attached data FL may be, for example, meeting materials used in a meeting, or an attached file attached to an e-mail. In this way, when the attached data FL is linked to the sentence and output, it becomes easy to see the materials used when reviewing the history, and the user can understand the history in detail. In addition, for example, in a work style such as telework, the user can quickly identify and access the attached data FL even when there is no person in charge.

For example, if the user wishes to focus on sentences entered in a specific format, the user inputs an operation to select the sentence to be output using check boxes CB1, CB2, CB3, and CB4, etc., shown in FIG. 25. Specifically, in the example shown in FIG. 25, when check box CB1 is set, the information sharing support system 20 outputs sentences based on the minutes data. Similarly, when check box CB2 is set, the information sharing support system 20 outputs sentences based on chat data DCH. Furthermore, when check box CB3 is set, the information sharing support system 20 outputs sentences based on email data DEM. Furthermore, when check box CB4 is set, the information sharing support system 20 outputs sentences based on electronic file data DEF.

In the illustrated example, check boxes CB1, CB2, and CB3 are set, so the information sharing support system 20 selects and outputs from the input sentences, as shown in FIG. 25, sentences based on the minutes data, sentences based on the chat data DCH, and sentences based on the email data DEM.

The selection by the information sharing support system 20 is not limited to being based on the format in which the sentence is input. For example, when email data DEM is input, there is often affiliation data DAF indicating the affiliation of the person who sent the email data DEM. For example, the affiliation data DAF is an email address indicating the sender of the email.

The user then first sets a specific organization name, etc., in the information sharing support system 20. Next, the information sharing support system 20 selects email data DEM sent by people who belong to the set organization based on the affiliation data DAF. In this way, the information sharing support system 20 can output only statements made by people who belong to a specific organization. Therefore, the user can view a screen such as that shown in FIG. 25, for example, by narrowing down the output to statements made by people in his or her own department.

(Another embodiment)
Fig. 27 is a conceptual diagram for explaining an example of the overall configuration of an information sharing support system according to another embodiment of the fourth embodiment of the present invention. For example, the information sharing support system 20 may have the following overall configuration. Compared with Fig. 24, the illustrated overall configuration differs in that the conference support system 1 is not included.

In this way, the information sharing support system 20 may receive email data DEM, chat data DCH, electronic file data DEF, or a combination of these. In other words, holding a conference is not required, and the information sharing support system 20 may receive text in any format as long as it is data showing verbal exchanges, a so-called communication log.

All or part of the processes according to the present invention may be realized by a program written in a programming language such as assembler, C, C++, C#, Java (registered trademark), Javascript (registered trademark), Python (registered trademark), Ruby, and PHP, or an object-oriented programming language, for causing a computer to execute each procedure related to the conference support method. In other words, the program is a computer program for causing a computer, such as an information processing device or an information sharing support system having one or more information processing devices, to execute each procedure.

The program can be distributed by storing it on a computer-readable recording medium such as a ROM or an EEPROM (Electrically Erasable Programmable ROM). The recording medium can also be an EPROM (Erasable Programmable ROM), flash memory, a flexible disk, a CD-ROM, a CD-RW, a DVD-ROM, a DVD-RAM, a DVD-RW, a Blu-ray disk, an SD (registered trademark) card, or an MO. The program can also be distributed through a telecommunications line.

Furthermore, the information sharing support system may have two or more information processing devices connected to each other by a network or the like. In other words, the information sharing support system may distribute all or part of various processes, or perform processes in parallel such as a duplex system, or in a redundant manner such as a dual system.

Although the preferred embodiment of the present invention has been described in detail above, the present invention is not limited to the specific embodiment, and various modifications and variations are possible within the scope of the gist of the present invention described in the claims.

REFERENCE SIGNS LIST 1 Conference support system 10 Server 11 Terminal 1F1 Input unit 1F2 Control unit 1F21 Determination unit 1F22 Decoration unit 1F23 Time management unit 1F24 Speaker determination unit 1F31 Cost calculation unit 1F32 Evaluation unit 1F3 Storage unit 1F4 Output unit CLF Classifier

JP 2007-43493 A

Claims (12)

An information sharing support system for supporting information sharing, comprising one or more information processing devices,
an input unit for inputting a sentence indicating any one or a combination of the contents of a statement made in a conference, an e-mail, an electronic file, or a chat data;
a determination unit for determining a type of the sentence input by the input unit;
An information sharing support system comprising: an output unit that outputs a list of specific sentences that are of a set type among the types based on the judgment result by the judgment unit. The information sharing support system of claim 1, which displays an alert indicating the content of the specific sentence when the specific sentence is input. estimating topic boundaries that delimit groups of said sentences;
The information sharing support system according to claim 1 , further comprising: a topic generating unit configured to generate a topic for each of the groups separated by the topic boundary. The information sharing support system according to claim 3, wherein the topic indicates either the subject, topic, topic topic, or condensed sentence of a plurality of sentences belonging to the group. The information sharing support system according to any one of claims 1 to 4, wherein the output unit outputs the remarks or written contents in a chronological list. The information sharing support system according to any one of claims 1 to 5, which outputs a communication diagram showing a communication strength indicating the strength of communication by the conference or the e-mail. The communication diagram shows communication by lines,
The information sharing support system according to claim 6 , wherein when the line is pressed, a log of the communication is displayed. The information sharing support system according to any one of claims 1 to 7, which sorts and outputs the sentences input by the input unit. The information sharing support system according to claim 8, which selects the sentence to be output based on the affiliation of the person who sent the sentence, the format in which the sentence was entered, or a combination of these. An information sharing support method performed by an information sharing support system having one or more information processing devices and supporting information sharing, comprising:
an input step in which the information sharing support system inputs a sentence indicating any one of the contents of a statement made in a conference, an e-mail, an electronic file, or a chat data, or a combination thereof;
a determination step in which the information sharing support system determines a type of the sentence input by the input step;
The information sharing support method includes an output step in which the information sharing support system outputs a list of specific sentences that are the set type among the types based on the judgment result by the judgment step. A program for causing a computer to execute an information sharing support method for supporting information sharing, the information sharing support method comprising:
an input step in which the computer inputs a sentence indicating any one or a combination of the contents of a statement made in a conference, an e-mail, an electronic file, or a chat data;
a determination step in which the computer determines a type of the sentence input by the input step;
and an output step in which the computer outputs a list of specific sentences that are of a set type among the types based on a result of the judgment by the judgment step. An information sharing support device for supporting information sharing,
an input unit for inputting a sentence indicating any one or a combination of the contents of a statement made in a conference, an e-mail, an electronic file, or a chat data;
a determination unit for determining a type of the sentence input by the input unit;
and an output unit that outputs a list of specific sentences that are the set type among the types based on the result of the judgment by the judgment unit.

Images