KR20240133305A - Method for providing chatbot service and device for performing the same - Google Patents

Abstract

A method for providing a chatbot service and a device for performing the same are disclosed. The method for providing a chatbot service according to one embodiment may include an operation of receiving a first user input; an operation of obtaining information necessary for providing a response to the first user input from context information between a chatbot and a user obtained prior to the first user input; and an operation of outputting the response based on the obtained information.

Description

METHOD FOR PROVIDING CHATBOT SERVICE AND DEVICE FOR PERFORMING THE SAME

The disclosure below relates to a method for providing a chatbot service and a device for performing the same.

A chatbot may refer to a technology that uses artificial intelligence and natural language processing to help users interact with web-based services and/or applications.

The background technology described above is technology that the inventor possessed or acquired in the process of deriving the disclosure content of the present application, and cannot necessarily be said to be a publicly known technology disclosed to the general public prior to the present application.

One embodiment can improve user convenience by obtaining mandatory parameters required to provide information about user input from previous context information.

One embodiment may provide a way to easily retrieve previous context between a user and a chatbot.

One embodiment may provide an intuitive way to terminate an active conversation scenario.

One embodiment may provide a way to easily identify a conversation partner.

However, technical challenges are not limited to the technical challenges described above, and other technical challenges may exist.

A device for providing a chatbot service according to one embodiment may include a memory including instructions; and a processor electrically connected to the memory and configured to execute the instructions. When the instructions are executed by the processor, the processor may control a plurality of operations. The plurality of operations may include an operation of receiving a first user input; an operation of acquiring information necessary for providing a response to the first user input from context information between a chatbot and a user acquired prior to the first user input; and an operation of outputting the response based on the acquired information.

The context information may include one or more of a context between the chatbot and the user generated based on a second user input received prior to the first user input, a keyword included in the context, and a domain corresponding to the keyword.

The above outputting operation may include an operation of outputting one or more contexts among information corresponding to the first user input or the context information.

The above obtaining operation may include an operation of searching for a keyword associated with a parameter from the context information to obtain a parameter necessary to provide information corresponding to the first user input; and an operation of performing slot-filling by obtaining the parameter based on user responses to the searched keyword.

The above outputting operation may include an operation of outputting information corresponding to the first user input based on the above parameter.

The action of receiving the first user input may include an action of receiving a user input for searching a second context between the chatbot and the user that was acquired prior to the first context while the first context between the chatbot and the user is activated.

The above-described acquiring operation may include an operation of outputting a keyword included in the second context; an operation of receiving a user response to the keyword; and an operation of outputting a context associated with the user response among the second contexts.

The action of outputting the above context may include an action of outputting a context associated with the first context among the contexts associated with the user response.

The above plurality of actions may further include an action of displaying an interface that includes information about an activated context between the chatbot and the user.

Information about the activated context may include information about a conversation partner of the activated context.

A method for providing a chatbot service according to one embodiment may include an operation of receiving a first user input; an operation of obtaining information necessary to provide a response to the first user input from context information between the chatbot and the user obtained prior to the first user input; and an operation of outputting the response based on the obtained information.

The context information may include one or more of a context between the chatbot and the user generated based on a second user input received prior to the first user input, a keyword included in the context, and a domain corresponding to the keyword.

The above outputting operation may include an operation of outputting one or more contexts among information corresponding to the first user input or the context information.

The above obtaining operation may include an operation of searching for a keyword associated with a parameter from the context information to obtain a parameter necessary to provide information corresponding to the first user input; and an operation of performing slot-filling by obtaining the parameter based on user responses to the searched keyword.

The above outputting operation may include an operation of outputting information corresponding to the first user input based on the above parameter.

The action of receiving the first user input may include an action of receiving a user input for searching a second context between the chatbot and the user that was acquired prior to the first context while the first context between the chatbot and the user is activated.

The above-described acquiring operation may include an operation of outputting a keyword included in the second context; an operation of receiving a user response to the keyword; and an operation of outputting a context associated with the user response among the second contexts.

The action of outputting the above context may include an action of outputting a context associated with the first context among the contexts associated with the user response.

The method may further include an action of displaying an interface that includes information about an activated context between the chatbot and the user.

Information about the activated context may include information about a conversation partner of the activated context.

Figure 1 is a drawing for explaining a chatbot system according to one embodiment.
Figure 2 is a diagram for explaining a conversation scenario according to one embodiment.
FIG. 3 may be a diagram for explaining a method of generating and storing context information according to one embodiment.
Figure 4 is a flowchart explaining a method for providing a chatbot service using context information according to one embodiment.
FIG. 5 illustrates an example of a method for providing a chatbot service using context information according to one embodiment.
FIG. 6 is a flowchart illustrating a context search method according to one embodiment.
Figure 7 illustrates an example of a context search method according to one embodiment.
FIG. 8 is a diagram for explaining a method for ending a conversation scenario according to one embodiment.
FIG. 9 is a drawing for explaining a method for displaying a conversation partner according to one embodiment.
Fig. 10 is a drawing for explaining a method for expressing emotions of a chatbot according to one embodiment.
FIG. 11 is a schematic block diagram of an electronic device according to one embodiment.
Figure 12 is a schematic block diagram of a server according to one embodiment.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be implemented in various forms. Therefore, the actual implemented form is not limited to the specific embodiments disclosed, and the scope of the present disclosure includes modifications, equivalents, or alternatives included in the technical idea described in the embodiments.

Although the terms first or second may be used to describe various components, such terms should be construed only for the purpose of distinguishing one component from another. For example, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component.

When it is said that a component is "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but there may also be other components in between.

Singular expressions include plural expressions unless the context clearly dictates otherwise. In this document, the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B or C", "at least one of A, B and C", and "at least one of A, B, or C" can each include any one of the items listed together in that phrase, or any and all possible combinations thereof. It should be understood that, as used herein, the terms "comprises" or "have" are intended to specify the presence of a described feature, number, step, operation, component, part, or combination thereof, but do not exclude the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning they have in the context of the relevant art, and will not be interpreted in an idealized or overly formal sense unless explicitly defined herein.

The term "module" as used in this document may include a unit implemented in hardware, software or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A module may be an integrally configured component or a minimum unit of the component or a portion thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

The term '~part' used in this document means a software or hardware component such as an FPGA or ASIC, and the '~part' performs certain roles. However, the '~part' is not limited to software or hardware. The '~part' may be configured to be on an addressable storage medium and may be configured to regenerate one or more processors. For example, the '~part' may include components such as software components, object-oriented software components, class components, and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functionality provided in the components and '~parts' may be combined into a smaller number of components and '~parts' or further separated into additional components and '~parts'. In addition, the components and '~parts' may be implemented to regenerate one or more CPUs in a device or a secure multimedia card. Additionally, '~bu' may include one or more processors.

Hereinafter, embodiments will be described in detail with reference to the attached drawings. When describing with reference to the attached drawings, identical components are given the same reference numerals regardless of the drawing numbers, and redundant descriptions thereof will be omitted.

Figure 1 is a drawing for explaining a chatbot service system according to one embodiment.

Referring to FIG. 1, according to one embodiment, a chatbot service system (100) may include an electronic device (110) and a server (160). However, FIG. 1 is an example for explaining the present invention, and the scope of the rights of the present invention should not be construed as being limited thereto. For example, the electronic device (110) may provide a chatbot service to a user independently without the server (160). When the electronic device (110) provides a chatbot service to a user independently, the electronic device (110) may perform the operation of the server (160) described in this specification.

The electronic device (110) may receive user input using various input devices (e.g., a microphone, a physical keyboard, a virtual keyboard, a camera, and/or a detection sensor) and transmit the user input to the server (160). The electronic device (110) may receive a system response (e.g., information corresponding to the user input) generated based on the user input from the server (160). The electronic device (110) may output the received system response in various ways. For example, the electronic device (110) may output the system response through a display or a speaker.

The server (160) may receive user input from the electronic device (110), generate a system response corresponding to the user input, and transmit the system response to the electronic device (110). For example, the server (160) may receive an inquiry message associated with a particular service and generate corresponding information.

Figure 2 is a diagram for explaining a conversation scenario according to one embodiment.

Referring to FIG. 2, according to one embodiment, a server (e.g., server (160) of FIG. 1) may activate a conversation scenario based on a user input (21) and provide a system response (e.g., information) corresponding to the user input (21). For example, the server (160) may determine an intent (e.g., test drive a vehicle) of the user input (21) and activate a conversation scenario (e.g., test network scenario) associated with the intent. The conversation scenario may mean a pre-designed conversation flow.

The server (160) can obtain mandatory parameters from information included in the user input (e.g., information such as location information, time information, date information, and/or name information). The mandatory parameters may mean information necessary for determining the intent of the user input (21) and/or information necessary for providing a system response (e.g., information) corresponding to the user input. For example, the server (160) can determine the intent of the user input (21) and obtain mandatory parameters (e.g., location and model name) necessary for information corresponding to the user input (21) from the user input (21).

If one or more of the required parameters (e.g., model name) are not acquired from the user input (21), the server (160) can generate a message (23) (e.g., follow-up question) for acquiring the unacquired required parameters and transmit the message (23) to an electronic device (e.g., electronic device (110) of FIG. 1). The user can provide a response (not shown) to the message (23) through the electronic device (110), and the server (160) can acquire the required parameters (e.g., the required parameters not acquired from the user input (21)) from the user response (not shown). In this way, the process in which the server (160) acquires the required parameters through the follow-up question is called slot-filling. To improve user convenience, the server (160) may perform slot filling based on information about the context (previous context) between the chatbot and the user (e.g., context information).

FIG. 3 may be a diagram for explaining a method of generating and storing context information according to one embodiment.

Referring to FIG. 3, according to one embodiment, a server (e.g., server (160) of FIG. 1) may generate and store context information including a context (31), a keyword (33) included in the context (31), and/or a domain (35) corresponding to the keyword (33). For example, the server (160) may generate context information by extracting a keyword (33) from a context (31) generated based on a user input (e.g., user input (21) of FIG. 2) and tagging a domain (35) corresponding to the keyword (33). The context (31) may mean information (or data) regarding a conversation context between a user and a chatbot. The context (31) may include information such as a user input (21) and/or a system response to the user input (21).

FIG. 4 and FIG. 5 are diagrams for explaining a method for providing a context information-based chatbot service according to one embodiment. FIG. 4 is a flowchart for explaining a method for providing a context information-based chatbot service, and FIG. 5 illustrates an example of a method for providing a context information-based chatbot service.

Referring to FIGS. 4 and 5, according to one embodiment, at operation 410, a server (e.g., server (160) of FIG. 1) may receive user input (53) from an electronic device (e.g., electronic device (110) of FIG. 1).

In operation 420, the server (160) can obtain required parameters (e.g., location and model name) from the user input (53) and check whether there is a required parameter (e.g., model name) among the required parameters that is not obtained from the user input (53).

In operation 430, if there is a required parameter that is not obtained from the user input (53), the server (160) can check whether there is information about a previous context (51) generated prior to the user input (53) (e.g., previous context information). For example, the previous context information is stored in a storage device (e.g., memory) included in the server (160), and the server (160) can retrieve the previous context information from the storage device.

In operation 440, if previous context information exists, the server (160) can check the correlation between the previous context information and the required parameter (e.g., the required parameter not obtained from the user input (53)). For example, the server (160) can check whether the previous context information includes a keyword (e.g., Ionic 6, Ionic 5) having a domain (e.g., Model) corresponding to the required parameter (e.g., model name).

In operation 450, if previous context information does not exist or the previous context information is not related to the required parameter, the server (160) may output a message (e.g., a follow-up question such as message (23) of FIG. 2) for obtaining the required parameter and transmit the message to the electronic device (110).

At operation 460, the server (160) may receive user input for a message (e.g., user input such as 'Ionic 6') from the electronic device (110).

In operation 470, the server (160) may use user input (e.g., user input received in operation 460) to output information (e.g., location information (57) of a dealership) corresponding to the user input (53) and transmit the information (57) to an electronic device (110).

In operation 480, if the previous context information is related to the required parameter, the server (160) may output keywords (e.g., model name-related keywords (55)) related to the required parameter (e.g., model name) from among the keywords included in the previous context information, and transmit the keywords (55) to the electronic device (110).

In operation 490, the server (160) may receive a user input for a keyword (55) from the electronic device (110). The electronic device (110) may obtain the user input for the keyword (55) by recognizing the user's touch, gesture, and/or voice.

In operation 470, the server (160) may output information (e.g., location information (57) of the dealership) corresponding to the user input (53) based on the user input (e.g., the user input obtained in operation 490) and transmit the information (57) to the electronic device (110).

As described above with reference to FIGS. 4 and 5, the server (160) (or electronic device (110)) can improve user convenience by performing slot filling based on previous context information.

FIGS. 6 and 7 are flowcharts for explaining a context search method according to one embodiment. FIG. 6 is a flowchart for explaining a context search method and illustrates an example of a context search method.

Referring to FIGS. 6 and 7, according to one embodiment, operations 610 to 640 may be performed sequentially, but are not limited thereto. For example, two or more operations may be performed in parallel.

In operation 610, a server (e.g., server (160) of FIG. 1) may receive a user input for searching for a second context (71) (e.g., test drive network related context) while a first context (73) (e.g., service network related context) is activated. The second context (71) may represent a context acquired prior to the first context (73). A user may provide a user input for searching for the second context (71) to an electronic device (e.g., electronic device (110) of FIG. 1) in various ways, such as touch, gesture, and/or voice. For example, a user may provide a user input for searching for the second context (71) to the electronic device (110) by touching a display region (710) that displays information about the first context (73).

In operation 620, the server (160) may output a keyword (e.g., a vehicle test drive related keyword (75)) included in the second context (71) and transmit the keyword (75) to the electronic device (110).

At operation 630, the server (160) may receive a user response to a keyword (75). The user may select one or more keywords (e.g., keyword (77)) from among the keywords (75) in various ways, such as by touch, gesture, and/or voice.

In operation 640, the server (160) may output a context (e.g., a context about the price of the Grandeur Hybird) associated with a user response (e.g., a keyword (77)) from among the second contexts (71) in various ways (e.g., a pop-up). When there are multiple second contexts, the server (160) may output one or more contexts from among the multiple second contexts (not shown) based on a preset policy. For example, the server (160) may output one or more contexts associated with the first context (73) from among the second contexts (not shown). The server (160) may calculate an association between the first context and the second contexts based on keywords included in the contexts (e.g., the first context and the second contexts) and domains corresponding to the keywords.

As described above with reference to FIGS. 6 and 7, the server (160) (or electronic device (110)) can enhance user convenience by providing a way for the user to retrieve previous context through simple manipulation (e.g., touch, gesture, and/or voice).

FIG. 8 is a diagram for explaining a method for ending a conversation scenario according to one embodiment.

Referring to FIG. 8, according to one embodiment, a server (e.g., server (160) of FIG. 1) may provide an intuitive interface for terminating an activated context together with information about the activated context (e.g., a context related to a Grandeur Hybrid). For example, a user may terminate an activated context by touching an end button (e.g., an X button) displayed together with the activated context.

When the server (160) receives a user input to terminate the activated context, it can terminate the activated context and output a conversation topic supported by the chatbot (e.g., conversation topic (81)) along with a guidance message.

FIG. 9 is a drawing for explaining a method for displaying a conversation partner according to one embodiment.

Referring to FIG. 9, according to one embodiment, the server (160) may provide an interface that includes information about a conversation partner (e.g., a chatbot or a counselor) of an activated context. For example, the server (160) may display information about a conversation partner of an activated context in a specific area of the interface (e.g., area (910)).

Fig. 10 is a drawing for explaining a method for expressing emotions of a chatbot according to one embodiment.

Referring to FIG. 10, according to one embodiment, the server (160) may display an emoticon (105_1, 105_3) representing the emotion of the chatbot in a specific area of the interface. For example, the server (160) may display an emoticon (105_1, 105_3) corresponding to a chatbot response (103_1, 103_3) to a user input (101_1, 101_3) in a specific area of the interface.

The server (160) enables natural interaction between the chatbot and the user by displaying emoticons (105_1, 105_3) that express the emotions of the chatbot.

FIG. 11 is a schematic block diagram of an electronic device according to one embodiment.

Referring to FIG. 11, according to one embodiment, an electronic device (1100) (e.g., the electronic device (110) of FIG. 1) may include a memory (1140) and a processor (1120).

The memory (1140) can store instructions (or programs) executable by the processor (1120). For example, the instructions can include instructions for executing operations of the processor (1120) and/or operations of each component of the processor (1120).

The memory (1140) may include one or more computer-readable storage media. The memory (1140) may include non-volatile storage devices (e.g., a magnetic hard disc, an optical disc, a floppy disc, a flash memory, an electrically programmable memory (EPROM), an electrically erasable and programmable memory (EEPROM).

The memory (1140) may be a non-transitory medium. The term "non-transitory" may indicate that the storage medium is not implemented as a carrier wave or a propagated signal. However, the term "non-transitory" should not be construed to mean that the memory (1140) is immovable.

The processor (1120) can process data stored in the memory (1140). The processor (1120) can execute computer-readable code (e.g., software) stored in the memory (1140) and instructions generated by the processor (1120).

The processor (1120) may be a data processing device implemented as hardware having a circuit having a physical structure for executing desired operations. For example, the desired operations may include code or instructions included in a program.

For example, a data processing device implemented in hardware may include a microprocessor, a central processing unit, a processor core, a multi-core processor, a multiprocessor, an application-specific integrated circuit (ASIC), or a field programmable gate array (FPGA).

The operation performed by the processor (1120) may be substantially the same as the operation of the electronic device (110) described with reference to FIGS. 1 to 10. Accordingly, a detailed description will be omitted.

Figure 12 is a schematic block diagram of a server according to one embodiment.

Referring to FIG. 12, according to one embodiment, a server (1200) (e.g., server (160) of FIG. 1) may include a memory (1240) and a processor (1220).

The memory (1240) may store instructions (or programs) executable by the processor (1220). For example, the instructions may include instructions for executing operations of the processor (1220) and/or operations of each component of the processor (1220).

The memory (1240) may include one or more computer-readable storage media. The memory (1240) may include non-volatile storage devices (e.g., a magnetic hard disc, an optical disc, a floppy disc, a flash memory, an electrically programmable memory (EPROM), an electrically erasable and programmable memory (EEPROM).

The memory (1240) may be a non-transitory medium. The term "non-transitory" may indicate that the storage medium is not implemented as a carrier wave or a propagated signal. However, the term "non-transitory" should not be construed to mean that the memory (1240) is immovable.

The processor (1220) can process data stored in the memory (1240). The processor (1220) can execute computer-readable code (e.g., software) stored in the memory (1240) and instructions generated by the processor (1220).

The processor (1220) may be a data processing device implemented as hardware having a circuit having a physical structure for executing desired operations. For example, the desired operations may include code or instructions included in a program.

For example, a data processing device implemented in hardware may include a microprocessor, a central processing unit, a processor core, a multi-core processor, a multiprocessor, an application-specific integrated circuit (ASIC), or a field programmable gate array (FPGA).

The operation performed by the processor (1220) may be substantially the same as the operation of the server (160) described with reference to FIGS. 1 to 10. Therefore, a detailed description will be omitted.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may be implemented using a general-purpose computer or a special-purpose computer, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and software applications running on the OS. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone, but those skilled in the art will appreciate that the processing device may include multiple processing elements and/or multiple types of processing elements. For example, a processing device may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

The software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing device to perform a desired operation or may independently or collectively command the processing device. The software and/or data may be stored on any type of machine, component, physical device, virtual equipment, computer storage medium, or device for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed over network-connected computer systems and stored or executed in a distributed manner. The software and data may be stored on a computer-readable recording medium.

The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may store program commands, data files, data structures, etc., alone or in combination, and the program commands recorded on the medium may be those specially designed and configured for the embodiment or may be those known to and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands such as ROMs, RAMs, and flash memories. Examples of program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc.

The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Although the embodiments have been described with limited drawings as described above, those skilled in the art can apply various technical modifications and variations based on the described embodiments. For example, even if the described techniques are performed in a different order than the described method, and/or the components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or are replaced or substituted by other components or equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents to the claims are also included in the scope of the claims described below.

Claims (20)

In a device for providing a chatbot service,
memory containing instructions; and
A processor electrically connected to the memory and configured to execute the instructions,
When the instructions are executed by the processor, the processor controls a plurality of operations,
The above multiple actions are:
An action to receive first user input;
An operation of obtaining information necessary to provide a response to the first user input from context information between the chatbot and the user obtained prior to the first user input; and
An action that outputs the response based on the acquired information.
A device comprising:
In the first paragraph,
The above context information is,
At least one of a context between the chatbot and the user generated based on a second user input received prior to the first user input, a keyword included in the context, and a domain corresponding to the keyword
A device comprising:
In the first paragraph,
The above output action is,
An operation of outputting one or more contexts among the information corresponding to the first user input or the context information.
A device comprising:
In the first paragraph,
The above acquisition action is,
An operation of searching for a keyword associated with a parameter from the context information to obtain a parameter necessary to provide information corresponding to the first user input; and
An operation for performing slot-filling by obtaining the above parameters based on user responses to searched keywords.
A device comprising:
In paragraph 4,
The above output action is,
An operation for outputting information corresponding to the first user input based on the above parameters.
A device comprising:
In the first paragraph,
The action of receiving the first user input is:
An operation of receiving a user input for searching a second context between the chatbot and the user obtained before the first context while the first context between the chatbot and the user is activated.
A device comprising:
In Article 6,
The above acquisition action is,
An action of outputting keywords included in the second context;
An action for receiving a user response to the above keyword; and
An action of outputting a context associated with the user response among the second contexts.
A device comprising:
In Article 7,
The action of outputting the above context is:
An action of outputting a context associated with the first context among the contexts associated with the user response.
A device comprising:
In the first paragraph,
An action that displays an interface containing information about the active context between the chatbot and the user.
A device further comprising:
In Article 9,
Information about the above activated context is:
Information about the conversation partner in the above activated context
A device comprising:
In terms of providing chatbot services,
An action to receive first user input;
An operation of obtaining information necessary to provide a response to the first user input from context information between the chatbot and the user obtained prior to the first user input; and
An action that outputs the response based on the acquired information.
A method comprising:
In Article 11,
The above context information is,
At least one of a context between the chatbot and the user generated based on a second user input received prior to the first user input, a keyword included in the context, and a domain corresponding to the keyword
A method comprising:
In Article 11,
The above output action is,
An operation of outputting one or more contexts among the information corresponding to the first user input or the context information.
A method comprising:
In Article 11,
The above acquisition action is,
An operation of searching for a keyword associated with a parameter from the context information to obtain a parameter necessary to provide information corresponding to the first user input; and
An operation for performing slot-filling by obtaining the above parameters based on user responses to searched keywords.
A method comprising:
In Article 14,
The above output action is,
An operation for outputting information corresponding to the first user input based on the above parameters.
A method comprising:
In Article 11,
The action of receiving the first user input is:
An operation of receiving a user input for searching a second context between the chatbot and the user obtained before the first context while the first context between the chatbot and the user is activated.
A method comprising:
In Article 16,
The above acquisition action is,
An action of outputting keywords included in the second context;
An action for receiving a user response to the above keyword; and
An action of outputting a context associated with the user response among the second contexts.
A method comprising:
In Article 17,
The action of outputting the above context is:
An action of outputting a context associated with the first context among the contexts associated with the user response.
A method comprising:
In Article 11,
An action that displays an interface containing information about the active context between the chatbot and the user.
A method further comprising:
In Article 19,
Information about the above activated context is:
Information about the conversation partner in the above activated context
A method comprising:

Images