JP7693372B2 - Information processing system, information processing method, and program - Google Patents

Description

The present invention relates to an information processing system, an information processing method, and a program that can analyze text data related to specific keywords and provide the analysis results.

Technology for analyzing texts on the Internet, such as SNS (Social Networking Service), has been known for some time.

For example, the following Patent Document 1 discloses a technology that divides a group of text data from a social networking site or the like, extracts characteristic words from each of the divided text data, calculates association values that indicate the association between the extracted characteristic words and each label that represents the nature of the text, and assigns labels to the divided text data based on certain criteria while referring to the calculated association values.

JP 2016-126748 A

Incidentally, for example, company planners will use the results of the above-mentioned SNS analysis to further conduct surveys and other research as appropriate to discover consumer needs and develop plans for new products and services.

However, traditionally, the service providers that perform the above-mentioned SNS analysis and other analyses are different from the companies that conduct the surveys, so after viewing the results of the analysis, the person in charge must access yet another service to request a survey.

In view of the above circumstances, the object of the present invention is to provide an information processing system, information processing method, and program that can provide text analysis and related research on the same platform.

In order to achieve the above object, an information processing system according to one embodiment of the present invention includes a communication unit and a control unit. The communication unit is capable of communicating with a user terminal of a user. The control unit extracts sentences related to a keyword input via the user terminal from a plurality of sentences collected from a network, analyzes the sentences, and classifies the sentences into different topics. Furthermore, the control unit generates an analysis result display screen having a sentence display field in which the sentences can be selectively displayed for each topic, and a research user interface for instructing a research on the topic via the Internet, and transmits the analysis result display screen to the user terminal.
Control unit and

This allows the information processing system to provide text analysis and related research on the same platform (screen displaying the analysis results). Here, the information processing system can be composed of one or more information processing devices.

When the control unit receives input to the survey user interface, it may generate a survey form creation screen for a survey on the topic and transmit it to the user terminal, and when the survey form is created on the creation screen and a request to start a survey is received, it may transmit a survey request to multiple consumer terminals.

This allows users to create a questionnaire and initiate a survey from the screen where they view the results of the text analysis.

When the control unit receives responses to the survey from the terminals of the multiple consumers, the control unit may generate a survey result display screen showing the results of tallying the responses and transmit the screen to the user terminal.

This allows the information processing system to allow users to view the survey results from the same platform where they viewed the analysis results.

The control unit may also place a chat user interface on the survey result display screen for initiating a chat with a terminal of any one of the multiple consumers who is the sender of the response.

When the control unit receives an input to the chat user interface, it may search for a terminal currently available for chat among the terminals of the multiple consumers who sent the response, and connect the searched terminal to the user terminal.

This allows the information processing system to allow users to start chatting with consumers who responded to the survey from the same screen where they viewed the survey results.

The information processing system may further include a storage unit that stores a consumer database related to multiple consumers with different attributes. In this case, the control unit may select multiple consumers to whom the survey request is to be sent from the consumer database, and may generate a screen that allows the user to select attributes of multiple consumers who will be in charge of the labeling process for the classified topics from the consumer database, and transmit the screen to the user terminal.

This allows the information processing system to have the user select consumers with specific attributes as labelers, allowing the system to deliberately bias the labeling method according to the user's intentions, differentiating the system from other labeling systems.

An information processing method according to another aspect of the present invention includes:
extracting sentences related to the keyword inputted by the user via the user terminal from among a plurality of sentences collected from the network;
Analyzing and classifying the text into different topics;
The method includes generating an analysis result display screen having a text display field in which the text can be selectively displayed for each topic, and a research user interface for instructing a research on the topic via the Internet, and transmitting the generated analysis result display screen to the user terminal.

A program according to another aspect of the present invention includes:
extracting sentences related to a keyword inputted by a user via a user terminal from a plurality of sentences collected from a network;
analyzing the text and classifying it into different topics;
and generating an analysis result display screen having a text display field in which the text can be selectively displayed for each topic, and a research user interface for instructing a research on the topic via the Internet, and transmitting the generated analysis result display screen to the user terminal.

As described above, the present invention makes it possible to provide text analysis and related research on the same platform. However, this effect does not limit the present invention.

1 is a diagram showing a configuration of a planning support system according to an embodiment of the present invention. 2 is a diagram showing a hardware configuration of a planning support server according to an embodiment of the present invention. FIG. 2 is a diagram showing a configuration of a database included in a planning support server according to an embodiment of the present invention; FIG. 11 is a flowchart showing the flow of a process for displaying SNS analysis results and survey results performed by a planning support server according to an embodiment of the present invention. FIG. 2 is a diagram showing an example of a home screen of a planning support tool according to an embodiment of the present invention. FIG. 13 is a diagram showing an example of a screen displayed during SNS analysis by the planning support tool according to one embodiment of the present invention. FIG. 13 is a diagram showing an example of an SNS analysis result display screen displayed on a user terminal in one embodiment of the present invention. FIG. 13 is a diagram showing an example of a questionnaire creation screen displayed on a user terminal in one embodiment of the present invention. FIG. 13 is a diagram showing an example of a questionnaire creation screen displayed on a user terminal in one embodiment of the present invention. FIG. 13 is a diagram showing an example of a questionnaire creation screen displayed on a user terminal in one embodiment of the present invention. FIG. 13 is a diagram showing an example of a survey result display screen displayed on a user terminal in one embodiment of the present invention. 13 is a diagram showing an example of a screen when a chat is requested on a survey result display screen displayed on a user terminal in one embodiment of the present invention. FIG. FIG. 13 is a diagram showing an example of the screen of the planning support tool when a chat partner is found in one embodiment of the present invention. FIG. 13 shows an example of a chat screen displayed on the planning support tool in one embodiment of the present invention. FIG. 13 is a diagram showing an example of a labeling staff setting screen displayed on the planning support tool in the modified example of the present invention.

The following describes an embodiment of the present invention with reference to the drawings.

[System Configuration]
FIG. 1 is a diagram showing the configuration of a planning support system according to this embodiment.

As shown in the figure, the system includes a planning support server 100 on the Internet 50 and multiple user terminals 200.

The planning support server 100 is a server that provides planning support services (planning support tools that can be executed on the web) for corporate planners on the web. The planning support server 100 is connected to multiple user terminals 200 via the Internet 50.

Specifically, the planning support server 100 extracts and analyzes posted data on SNS and other online sites related to keywords specified by the user terminal 200, classifies the data by topic, generates an SNS analysis result display screen, and transmits the screen to the user terminal 200. As will be described later, the SNS analysis result display screen also makes it possible to conduct surveys and chat with monitors owned by the operator of the planning support server 100.

The user terminal 200 (200A, 200B, 200C...) is a terminal used by a user (e.g., a corporate planning staff member, etc.), and is, for example, a smartphone, a mobile phone, a tablet PC (Personal Computer), a notebook PC, a desktop PC, etc.

The user terminal 200 inputs keywords into the planning support tool based on the user's operation, transmits an SNS analysis request to the planning support server 100, receives a web page displaying the SNS analysis results, etc., and displays it on the screen using a browser, etc.

The planning support tool may be implemented as an application installed on the user terminal 200, rather than as a web application.

[Hardware configuration of the planning support server]
Fig. 2 is a diagram showing the hardware configuration of the planning support server 100. As shown in the diagram, the planning support server 100 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, an input/output interface 15, and a bus 14 connecting these components to each other.

The CPU 11 accesses the RAM 13 etc. as necessary and performs various calculation processes while controlling all the blocks of the planning support server 100. The ROM 12 is a non-volatile memory in which firmware such as the OS, programs and various parameters to be executed by the CPU 11 are permanently stored. The RAM 13 is used as a working area for the CPU 11 and temporarily stores the OS, various applications being executed, and various data being processed.

The input/output interface 15 is connected to a display unit 16, an operation reception unit 17, a memory unit 18, a communication unit 19, etc.

The display unit 16 is a display device that uses, for example, an LCD (Liquid Crystal Display), an OELD (Organic ElectroLuminescence Display), a CRT (Cathode Ray Tube), etc.

The operation reception unit 17 is, for example, a pointing device such as a mouse, a keyboard, a touch panel, or other input device. If the operation reception unit 17 is a touch panel, the touch panel may be integrated with the display unit 16.

The storage unit 18 is, for example, a non-volatile memory such as a hard disk drive (HDD), a flash memory (SSD; solid state drive), or other solid-state memory. The storage unit 18 stores the OS, various applications, and various data.

In particular, in this embodiment, the memory unit 18 stores user information about the users of each user terminal 200, monitor information about the subjects of the survey, survey (questionnaire) information, etc., and also stores applications and other programs that allow the planning support server 100 to use this data to execute SNS analysis results and survey result display processing. As will be described later, the memory unit 18 has a user information database, a monitor information database, and a survey information database as databases that contain such data.

The communication unit 19 is, for example, a NIC (Network Interface Card) for Ethernet or various modules for wireless communication such as a wireless LAN, and is responsible for communication processing with the user terminal 200.

Although not shown, the hardware configuration of the user terminal 200 is similar to that of the planning support server 100. In addition, an application for connecting to the planning support server 100 and executing restaurant search processing is installed on the user terminal 200.

[Database configuration of the planning support server]
FIG. 3 is a diagram showing the configuration of a database contained in the project support server 100. As shown in FIG.

As shown in the figure, the planning support server 100 has a user information database 31, a monitor information database 32, and a survey information database 33 in the memory unit 18.

The user information database 31 stores information about users who own user terminals 200 and are users (members) of the planning support service provided by the planning support server 100. Specifically, the user information database 42 stores information such as user ID, password, name, email address, company name, telephone number, address, age (group), and gender for each user.

The monitor information database 32 stores information about monitor users of different attributes who are consumers who have entered into a monitor contract with the operator of the project support server 100. Specifically, the monitor information database 42 stores information for each monitor, such as user ID, password, name, email address, telephone number, address (place of residence), age (group), sex, family structure (married/unmarried, number of family members, whether or not they have children, etc.), occupation (job type, school), annual income (household annual income, individual annual income), SNS used, type of residence (detached house, condominium, owned home, rented, etc.), mobile phone (carrier information), car ownership status, whether or not they have a license, and hobbies and interests.

The survey information database 33 stores information about the surveys created for the monitors, i.e., questionnaire data and response data for the surveys, statistical data on the survey results, etc.

These databases are used by mutual reference as necessary in the process of displaying SNS analysis results and survey results by the planning support server 100, which will be described later.

[Operation of the planning support server]
Next, a description will be given of the operation of the planning support server 100 configured as above. The operation is executed by the cooperation of hardware such as the CPU 11 and communication unit 19 of the planning support server 100 and software stored in the storage unit 18. For convenience, in the following description, the CPU 11 is assumed to be the subject of operation.

Figure 4 is a flowchart showing the process of displaying SNS analysis results and survey results by the planning support server 100.

As shown in the figure, the CPU 11 of the planning support server 100 first determines whether or not it has received an SNS analysis request along with keywords from the user terminal 200 (step 41).

Figure 5 is a diagram showing an example of the home screen of the planning support service. The user of the user terminal 200 logs in to the business support service using an ID and password. After logging in, a keyword input box 51 and an analysis request button 52 are displayed on the home screen displayed on the user terminal 200. In addition, for example, on the left end of the home screen, a home button 53 for transitioning to the home screen, an analysis result button 54 for transitioning to an SNS analysis result display screen, and a setting button 75 for making various settings are arranged, and below the keyword input box 51, there are a popular keyword display section 55 for displaying currently popular keywords, for example, in a ranking format, and a watched keyword section 55 for showing in a graph the progress of the popularity of keywords currently being watched by the user.

As shown in the figure, when a user of the user terminal 200 inputs a desired keyword (e.g., "jeans") into the keyword input box 51 and presses the analysis request button 52, the SNS analysis request is sent from the user terminal 200 to the planning support server 100 along with the keyword.

When it is determined that the SNS analysis request has been received (Yes in step 41), the CPU 11 extracts (collects) post data related to the keyword (typically, post data including the keyword) from post data on a specific SNS (step 42). In this case, the period to be extracted may be limited to a specific period such as the most recent few months or the most recent year.

Next, the CPU 11 analyzes the collected post data to classify it into different topics (step 43). Specifically, the CPU 11 performs natural language processing on the collected post data using a unique analysis algorithm, for example, by extracting frequently appearing characteristic words and recognizing the relationships between the characteristic words and other words, and classifies the post data into major topics that exist in the world. Deep learning using AI (Artificial Intelligence) may be used for the analysis and classification.

The CPU 11 also assigns (labels) each classification with a label that indicates (summarises) the classified topic. The labeling may be performed by AI, or may be input by an operator of the planning support server 100 after interpreting the posts for each topic.

Figure 6 shows an example of a screen displayed during SNS analysis in the planning support service. This screen displays a progress status display field 57 where the progress of processes such as (1) collection of posted data, (2) classification of topics, and (3) interpretation (labeling) of topics can be confirmed. This figure shows the state when all three stages of processing have been completed and the analysis results are about to be displayed.

When the analysis and classification process is complete, the CPU 11 generates an SNS analysis result display screen and transmits it to the user terminal 200 (step 44).

Figure 7 is a diagram showing an example of the SNS analysis result display screen displayed on the user terminal 200. As shown in the figure, the SNS analysis result display screen has a keyword display section 58 that displays the input keywords, and a post display section 60 that allows SNS posts related to the keywords to be selectively displayed for each of the categorized topics.

The post display area 60 can be switched to display label tabs 59 for each label assigned to the keyword topic. The label tabs 59 are arranged from top to bottom, for example, in order of the number of posts with the corresponding label. In the example shown in the figure, it can be seen that 2,456 SNS posts related to the keyword "jeans" are categorized into topics such as "how to wash," "damage," "want," "article," "vintage," and "quantity." When any of the posts in the post display area 60 is tapped, the entire text of that post is enlarged and displayed.

If the user has entered multiple keywords, the keyword display section 58 is also displayed as multiple tabs, and by selecting each of them, it is possible to switch between displaying the post display area 60 related to each keyword and each screen described below for each keyword.

The SNS analysis result display screen also has, for example, a survey button 61 at the top of the post display area 60, which is a user interface for instructing a survey via the Internet regarding the topic of each label.

Then, the CPU 11 determines whether the survey button 61 has been pressed by the user of the user terminal 200 (step 45).

If it is determined that the survey button 61 has been pressed (Yes), the CPU 11 generates a survey creation screen for creating a questionnaire for the survey and transmits it to the user terminal 200 (step 46).

Figure 8 is a diagram showing an example of the survey creation screen displayed on the user terminal 200. As shown in the figure, the survey creation screen has a questionnaire input field 62 that has an input field for the title of the survey, a selection field for the gender and age group of the survey target, an input field for questions and answers, etc., and an input content confirmation button 63 for confirming and displaying the input content when input into the questionnaire input field 62 is completed.

Figure 9 shows an example of an input content confirmation screen that is displayed when the user of the user terminal 200 completes input into the survey form input field 62 and presses the input content confirmation button 63.

As shown in the figure, the input content confirmation screen has an input content display field 64, a survey start button 65 for requesting the start of the survey, and a cancel button 66 for returning to the survey creation screen and re-entering information.

Next, the CPU 11 determines whether or not a request to start the survey has been accepted by the user of the user terminal 200 pressing the survey start button 65 (step 47).

If a request to start the survey is received (Yes), the CPU 11 extracts a predetermined number of monitor users from the monitor information database 32 who match the survey target selected in the survey form input field 62, and sends a survey request to the contact information (email address or messenger ID) of the monitor's terminal (step 48).

Figure 10 shows an example of a screen displayed on the planning support tool when a survey request is sent to the monitor based on the survey start request. As shown in the figure, the screen displays a message that the survey has been sent, and that a message will be sent to the user of the user terminal 200 when the survey is completed. The survey form data for the created survey is stored in the survey information database 33.

Next, the CPU 11 determines whether the survey has been completed, i.e., whether responses have been received from a predetermined number or a predetermined percentage of the multiple monitor terminals to which the survey was sent (step 49).

If it is determined that the survey is completed (Yes), the CPU 11 tallies the responses received from the multiple monitor terminals, generates a survey result display screen showing the tallied results, and transmits it to the user terminal (step 50).

Figure 11 is a diagram showing an example of a survey result display screen displayed on the user terminal 200. As shown in the figure, the survey result display screen includes a survey result display section 67 that shows the aggregated results of the responses to each question in the survey as a graph or the like, and a download button 68 that enables the user to download the survey results as necessary. Furthermore, the survey result display screen has a chat button 69, for example at the left end, for chatting with the terminal of one of the monitors that sent the survey responses.

By viewing the results displayed on the survey result display screen, users can make hypotheses about product or service plans related to the needs (topics) discovered from the SNS analysis results.

Next, the CPU 11 determines whether a request to start a chat has been accepted by the user of the user terminal 200 pressing the chat button 69 (step 51).

If it is determined that the chat button 69 has been pressed (Yes), the CPU 11 searches for a monitor terminal that is currently available for chat among the monitor terminals, and if approval for a chat connection is obtained from any of the monitors, it connects that monitor terminal to the user terminal 200 and starts chatting (step 52).

Figure 12 shows an example of the screen of the planning support service when the chat button 69 is pressed and a monitor with whom you can chat is found. As shown in the figure, when a monitor with whom you can chat is found, a dialog 71 is displayed containing information to that effect and a hyperlink 72 to the chat screen.

Figure 14 shows an example of a chat screen 73 after a chat has been started via the hyperlink 72. The user of the user terminal 200 can interview the monitor by chat via the chat screen 73 and verify the accuracy of the plan that has been made based on the survey results.

Then, the CPU 11 determines whether an instruction to end the chat has been given from the user terminal 200 or the monitor terminal (step 53), and if it determines that an instruction to end the chat has been given (Yes), it disconnects both terminals and ends the chat.

The planning support service screen may also have a button for internal video calls. This allows you to discuss with other members of the planning team and further materialize the plan.

[summary]
As described above, according to this embodiment, the planning support server 100 can provide an analysis of SNS posts related to keywords that interest users and a questionnaire survey related to the analysis on the same platform (screen displaying the analysis results). In other words, in the past, the analysis of SNS, etc. to discover consumer needs related to products and services, and surveys such as questionnaires and chats for consumers after the consumer needs have been discovered, were provided on different platforms by different businesses, but according to this embodiment, planners can carry out the work from discovering consumer needs to planning products and services on a single platform provided by the planning support server 100.

[Modification]
The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit and scope of the present invention.

In the above embodiment, an example has been shown in which labeling of topics categorized for keywords input by a user is performed based on input by AI or an operator of the planning support server 100. However, the labeling may also be performed based on input by monitors (consumers) stored in the monitor information database 32, and the user of the user terminal 200 may select the attributes of the monitor in charge of the labeling on the planning support tool prior to inputting the keywords.

Figure 15 shows an example of the labeling staff setting screen displayed on the planning support tool.

For example, when the user presses the setting button 75 on the home screen after inputting a keyword into the keyword input box 51 (after pressing the analysis request button 52) and before the SNS analysis results are displayed, the planning support server 100 generates a labeling staff setting screen as shown in the figure and transmits it to the user terminal 200.

On the labeling staff setting screen, a keyword selection screen 81 is displayed first, and when the user selects a keyword for which he or she wants to select a labeling staff on the keyword selection screen 81, a labeling staff determination screen 82 as shown in the figure pops up.

On the labeling staff determination screen 82, the user can select and change the persona of the labeling staff. The persona can include attribute information stored in the monitor information database 32, such as gender, age, place of residence (prefecture, postal code), occupation (job type, school), annual income (household annual income, individual annual income), family structure (marital status, presence of children, family living together), type of residence (detached house, condominium, owned home, rented, etc.), mobile phone (carrier information), SNS usage, car ownership, license status, other hobbies and interests, etc.

As shown in the figure, the user can select the monitor with the attributes they wish to have labeled, for example by using a radio button, and press a confirmation button to determine the person in charge of labeling. The CPU 11 of the planning support server 100 extracts the contact information of the monitor's terminal that matches the selected attributes from the monitor information database 32, sends a labeling process request to the contact information, and receives the results of the labeling process from the monitor's terminal.

This allows the labeling results to be intentionally biased to match the company's (person in charge's) desired attributes for the monitors, making it possible to differentiate the results from those of other competing services that offer similar labeling services, and avoiding the possibility of the labeling results becoming uniform across services and making it impossible to guarantee the originality of the project.

For example, in the case of the keyword "jeans" input in the above embodiment, even if jeans manufacturers A and B use the planning support tool according to this embodiment, Company A can provide labeling results suited to the target demographic of each company's products by having a woman in the metropolitan area label the search keyword "jeans," while Company B can have a man with a high annual income label the same search keyword.

The GUIs such as the survey button 61, survey start button 65, and chat start button 69 in the above-described embodiment are not limited to those described and illustrated, and any form of GUI may be used, including buttons of other shapes, icons, characters, symbols, etc.

In the above embodiment, the CPU 11 of the project support server 100 analyzes SNS, but the text to be analyzed is not limited to SNS, and other texts such as blogs and product reviews may also be analyzed.

The planning support server 100 shown in the above embodiment may be configured as a system whose functions are distributed across multiple servers or information processing devices.

Of the inventions described in the claims of this application, the invention described as an "information processing method" has each step performed automatically by at least one device such as a computer through software-based information processing, and is not performed by a human using a device such as a computer. In other words, the "information processing method" is an information processing method using computer software, and is not a method in which a human operates a computing tool such as a computer.

11...CPU
18: Storage unit 19: Communication unit 31: User information database 32: Monitor information database 33: Survey information database 59: Label tab 60: Post display field 61: Survey button 62: Survey form input field 65: Survey start button 67: Survey result display field 69: Chat button 82: Labeling person setting screen 100: Planning support server 200: User terminal

Claims (8)

A communication unit capable of communicating with a user terminal of a user;
extracting sentences related to the keyword input via the user terminal from a plurality of sentences collected from the network, analyzing the sentences and classifying them into different topics;
and a control unit that generates an analysis result display screen having a text display field in which the text can be selectively displayed for each topic, and a research user interface for instructing a research on the topic via the Internet, and transmits the generated analysis result display screen to the user terminal. 2. The information processing system according to claim 1,
An information processing system in which, when the control unit receives input to the survey user interface, it generates a survey form creation screen for a survey on the topic and sends it to the user terminal, and when the survey form is created on the creation screen and a request to start a survey is received, it sends a survey request to multiple consumer terminals. 3. The information processing system according to claim 2,
When the control unit receives responses to the survey from the terminals of the multiple consumers, the control unit generates a survey result display screen showing a result of tallying the responses and transmits the survey result display screen to the user terminal. 4. The information processing system according to claim 3,
The control unit places a chat user interface on the survey result display screen for initiating a chat with a terminal of any one of the multiple consumers who is a sender of the response. 5. The information processing system according to claim 4,
An information processing system in which, when the control unit receives input to the chat user interface, it searches for a terminal currently available for chat among the terminals of multiple consumers who sent the response, and connects the searched terminal to the user terminal. 5. An information processing system according to claim 2,
The method further includes a storage unit that stores a consumer database relating to a plurality of consumers having different attributes,
The control unit selects from the consumer database a number of consumers to whom the survey request is to be sent, and generates a screen that allows the user to select from the consumer database attributes of a number of consumers who will be responsible for the process of assigning labels to the classified topics, and transmits the screen to the user terminal. extracting sentences related to the keyword inputted by the user via the user terminal from among a plurality of sentences collected from the network;
Analyzing and classifying the text into different topics;
generating an analysis result display screen having a text display field in which the texts can be selectively displayed for each topic, and a survey user interface for instructing a survey via the Internet regarding the topic, and transmitting the generated analysis result display screen to the user terminal ;
A computer implemented information processing method. In the information processing device,
extracting sentences related to a keyword inputted by a user via a user terminal from a plurality of sentences collected from a network;
analyzing the text and classifying it into different topics;
and generating an analysis result display screen having a text display field in which the text can be selectively displayed for each topic, and a research user interface for instructing a research on the topic via the Internet, and transmitting the generated analysis result display screen to the user terminal.

Images