WO2020138608A1 - Question answering method and apparatus using plurality of chatbots - Google Patents

Abstract

A question answering method using a plurality of chatbots can comprise the steps of: receiving question data about a user's question through a communication interface; determining a morpheme included in the question data; determining at least one chatbot from among the plurality of chatbots on the basis of the determined morpheme and tagging information about each of the plurality of chatbots; transmitting the question data to the determined at least one chatbot; and transmitting the received answer to a user terminal of the user when an answer corresponding to the question data is received from the determined at least one chatbot.

Description

Method and device for question and answer using multiple chatbots

The following embodiments relate to a technique for answering a query using a plurality of chatbots.

With the development of artificial intelligence (AI) and social network service (SNS), a chatbot service capable of acquiring information like a conversation through an existing messenger is being actively introduced.

Chatbot is an interactive messenger that AI analyzes the contents of a question and gives an appropriate answer when a user enters a question like chatting through a messenger that was previously used. Leading companies at home and abroad have recently introduced chatbots to customer support services to reduce the number of personnel required to respond to customers, and to improve the quality of customer support services by rapidly responding 24 hours a day. The chatbot service can be used in various areas such as providing public information, ordering food, and providing map information.

On the other hand, chatbots are created separately according to each service provided, and each chatbot can provide only a response to a query related to the service. For more efficient use of the chatbot, it may be required to implement a chatbot that provides responses to multiple services in an integrated manner. Implementation of such a chatbot requires a large amount of storage space and network resources, and actual implementation may be difficult.

A query response method using a plurality of chat bots according to an embodiment includes receiving query data for a user's query through a communication interface; Determining a morpheme included in the query data; And determining at least one chatbot among the plurality of chatbots based on the determined morpheme and tagging information for each of the plurality of chatbots. Transmitting the query data to the determined at least one chatbot; And when receiving a response corresponding to the query data from the determined at least one chatbot, transmitting the received response to the user terminal of the user.

The determining of at least one chatbot according to an embodiment may include determining a part of speech of the morpheme; Determining a morpheme corresponding to a key part of speech among the morphemes based on a predetermined condition; And determining at least one chatbot among the plurality of chatbots based on the determined morpheme corresponding to the core part-of-speech and the tagging information.

The determining of at least one chatbot according to an embodiment may include generating vector data based on a combination of morphemes corresponding to the core parts of speech; And determining at least one chatbot among the plurality of chatbots based on the vector data and the tagging information.

Tagging information according to an embodiment may be determined based on information on words to which the plurality of chatbots can respond.

The determining of at least one chatbot according to an embodiment may include calculating a combination of each morpheme included in the vector data and similarity of the words; And determining at least one chatbot among the plurality of chatbots based on the similarity.

According to an embodiment, the determined at least one chatbot may remain active, and the remaining chatbots other than the determined at least one chatbot may remain inactive.

A query response method using a plurality of chat bots according to an embodiment includes receiving query data for a user's query through a communication interface; Determining whether the query data is text data; If the query data is text data, determining a morpheme included in the query data; Determining vector data based on the combination of morphemes; Determining at least one chatbot among the plurality of chatbots by comparing the combination of the morphemes included in the vector data and tagging information for each of the plurality of chatbots; Transmitting the query data to the determined at least one chatbot; And when receiving a response to the query data from the determined at least one chatbot, transmitting the response to the user terminal of the user.

The query response method according to an embodiment may further include detecting a character from the query data when the query data is image data, and determining the morpheme is based on the detected character. The morphemes to be included can be determined.

The detecting of the character according to an embodiment may include at least one of adjusting the resolution of the image data, changing the color of the image data to grayscale, and binarizing the image data; And detecting the character based on the result of the execution. How to answer questions using chatbot.

The detecting of the character according to an embodiment may include detecting a character included in the image data using optical character recognition.

The query response method according to an embodiment further includes converting the query data to text data when the query data is audio data, and determining the morpheme is based on the query data converted to the text data. Thus, a morpheme included in the query data can be determined.

Determining vector data according to an embodiment may include determining a part-of-speech speech; Determining a morpheme corresponding to a key part of speech among the morphemes; And determining the vector data based on a combination of morphemes corresponding to the key parts of speech.

The determining of the at least one chatbot according to an embodiment may include calculating a combination of each morpheme included in the vector data and the similarity between words included in the tagging information; And determining at least one chatbot among the plurality of chatbots based on the similarity.

A query response device using a plurality of chat bots according to an embodiment includes a memory and a processor, the memory stores instructions executable by the processor, and the processor via a communication interface Receive query data for a user's query, determine a morpheme included in the query data, and determine at least one chatbot among a plurality of chatbots based on the determined morpheme and tagging information for each of the plurality of chatbots And, when transmitting the query data to the determined at least one chatbot, and receiving a response to the query data from the determined at least one chatbot, the response may be transmitted to the user terminal of the user.

The processor according to an embodiment determines the part-of-speech of the morpheme, determines a morpheme corresponding to a core part-of-speech among the morphemes based on a predetermined condition, and based on the morpheme and the tagging information corresponding to the determined key part-of-speech At least one chatbot among a plurality of chatbots may be determined.

The processor according to an embodiment generates vector data based on a combination of morphemes corresponding to the core part-of-speech, calculates a similarity of words included in tagging information and a combination of each morpheme included in the vector data, and the Based on the similarity, at least one chatbot among the plurality of chatbots may be determined.

The processor according to an embodiment, when the query data is image data, detects a character from the query data, determines a morpheme included in the detected character, and based on the determined morpheme and the tagging information At least one of the chatbots can be selected.

The processor according to an embodiment converts the query data into text data when the query data is audio data, determines a morpheme included in the query data, and determines the morpheme included in the query data, based on the converted query data. At least one chatbot among the plurality of chatbots may be determined based on the tagging information.

1 is a view for explaining the operation of the personalized content providing system in an embodiment.

2 illustrates a network configuration diagram of a question and answer system according to an embodiment.

3 is a flowchart illustrating a method for answering a query according to an embodiment.

4 is a flowchart illustrating an operation of a method for answering a query according to an embodiment.

5 is a diagram showing the overall configuration of a query response device according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, various modifications may be made to the embodiments, and the scope of the patent application right is not limited or limited by these embodiments. It should be understood that all modifications, equivalents, or substitutes for the embodiments are included in the scope of rights.

The terms used in the examples are for illustrative purposes only and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, the terms "include" or "have" are intended to indicate the presence of features, numbers, steps, actions, components, parts or combinations thereof described in the specification, one or more other features. It should be understood that the existence or addition possibilities of fields or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person skilled in the art to which the embodiment belongs. Terms, such as those defined in a commonly used dictionary, should be interpreted as having meanings consistent with meanings in the context of related technologies, and should not be interpreted as ideal or excessively formal meanings unless explicitly defined in the present application. Does not.

In addition, in the description with reference to the accompanying drawings, the same reference numerals are assigned to the same components regardless of reference numerals, and redundant descriptions thereof will be omitted. In describing the embodiments, when it is determined that detailed descriptions of related well-known technologies may unnecessarily obscure the subject matter of the embodiments, detailed descriptions thereof will be omitted.

1 is a view for explaining the operation of the query response system in an embodiment.

The chatbot can analyze the query data for the user's query and provide a response suitable for the query. The chatbot stores a response corresponding to each query in a database, and when receiving a query from a user, the chatbot can search for a response corresponding to the query in the database and provide it to the user.

Since chatbots must store responses to all queries in advance in a database, chatbots can be created for each subject that can provide responses within limited resources. For example, the chatbot 1 121 may be a chatbot that provides a response to a query related to the weather, and the chatbot n 122 may be a chatbot capable of answering a query related to a map.

Since each chatbot 121 and 122 can provide a response only to a query on a corresponding subject, the type of query that a user can inquire to each chatbot 121 and 122 may be limited. That is, the chatbot 1 121 that provides a response to a query related to the weather cannot provide an appropriate response to a query that queries the address of the library.

Extending a responsive subject to allow each chatbot 121, 122 to respond to a variety of subject queries may require large storage space and may require excessive resources for analyzing the query.

The question and answer system according to an embodiment sets a range of queries that can be answered by each of the chatbots 121 and 122 through the question and answering device 110 that serves as an intermediary between the user and the plurality of chatbots 121 and 122. Without needing to expand, it can provide a means to provide responses to various queries from users.

The query response device 110 may select at least one chatbot among the chatbots 121 and 122 according to the content of the user query to provide query data, and provide a response to the query data to the user. For example, when a user inputs query data for today's weather into the query response device 110, the query response device 110 analyzes the query data and provides a chatbot that provides query data with a response to the weather. (121). In addition, when the user inputs a query data for the address of the library to the query response device 110, the query response device 110 is a chatbot n (122) that provides a response to a query related to a map based on the query data Query data.

The chatbot selected by the query response device 110 is activated to generate a response to the query data, while the unselected chatbot can remain inactive. Through this, resources (power, network resources, etc.) required in the process of generating a response to the query can be reduced.

In addition, since the range of queries that can be answered for each chatbot is not extended, the query response system does not require additional storage space for additionally storing responses to queries for each chatbot.

A specific method of providing a response to a query using a plurality of chatbots by the query response device will be described in more detail through the accompanying drawings.

2 illustrates a network configuration diagram of a question and answer system according to an embodiment.

As shown in FIG. 2, the question and answer system may be configured to be connected through the query answering device 210 and a plurality of user terminals 231, 232, 233, and 234 through a communication network 220 such as the Internet. The query response device 210 may be implemented through a web server or a corresponding device. The query response device 210 receives query data from the user terminals 231, 232, 233, and 234 through a communication network such as the Internet, analyzes the query data, and analyzes the query data to provide a plurality of chatbots 240-1, 240-2, ..., Among 240-n), a chatbot capable of providing a response corresponding to the query data is determined, and query data can be provided to the determined chatbot. In this process, the chatbot receiving query data can be activated, and the rest of the chatbots can be inactive. The query response device 210 may provide a response to the user terminals 231, 232, 233, and 234 when receiving a response to the query data from the chatbot that provided the query data.

The user terminals 231, 232, 233, and 234 are terminals capable of accessing a server through a communication network with a communication function, and any of various electronic devices widely used today by general users such as smartphones, PCs, tablets, and laptops. It may be any one, but may include any communication device not limited thereto. A client program is installed in the user terminals 231, 232, 233, and 234, and may be connected to the query response device 210 through the program.

3 is a flowchart illustrating a method for answering a query according to an embodiment.

According to an embodiment, the query response device may receive query data for the user's query from the user terminal through the communication interface built in step 310. The query data may be text data generated by a user input through a user terminal, and may include query contents of the user.

According to an embodiment, the query response device may determine a morpheme included in the query data in step 320. The query response device may determine a morpheme included in the query data through a morpheme analysis algorithm.

According to an embodiment, the query response device may determine at least one chatbot to provide query data based on the morpheme determined in step 330 and tagging information for each of the plurality of chatbots.

The query response device may determine the part of speech of the morphemes included in the query data, and may determine the morpheme corresponding to the core part of speech among the morphemes based on the predetermined condition. For example, a key part-of-speech may be determined as a verb or noun as a key part-of-speech in determining the meaning of a query corresponding to query data, but the method of determining the key part-of-speech is not limited to this and may differ depending on implementation. have.

The query response device may generate vector data corresponding to the query data based on combinations of morphemes corresponding to the key parts of speech. For example, when three key parts of speech are determined, vector data may be generated as data including six combinations of key parts of speech.

The query response device may determine at least one chatbot to transmit query data among the plurality of chatbots based on the generated vector data and tagging information for each of the plurality of chatbots.

Tagging information is information that identifies each chatbot, and may be generated corresponding to each chatbot. Tagging information may be generated based on information about words that a corresponding chatbot can provide a response to. For example, the chatbot's tagging information that provides a response to a query about the weather can include temperature, precipitation, and sunshine words, and the chatbot's tagging information that provides a response to a query on the map includes an address, time required And the like.

The query response device calculates the similarity between each combination of morphemes included in the vector data corresponding to the query data and each word included in the chatbot's tagging information, and based on the calculated similarity, query data among the plurality of chatbots. You can decide which chatbot to provide. For example, when the vector data for the query data includes six morpheme combinations, the query response device calculates the similarity of the six morpheme combinations with words included in the tagging information of each chatbot, and calculates the similarity. Based on this, at least one chatbot among the plurality of chatbots may be determined. The method of determining the chatbot based on the similarity is to calculate the score for each chatbot based on each similarity calculated between each morphological combination and tagging information included in the vector data, and the chatbot with the highest calculated score is queried. It may be determined by the chatbot to send the data. The method for calculating the chatbot based on the similarity is not limited to this, and may include any modified method for determining the chatbot through the similarity.

According to an embodiment, the query response device may transmit query data to at least one chatbot determined in step 340.

A chatbot receiving query data among a plurality of chatbots linked with the query response device may maintain an active state to provide a response to the query data, and the remaining chatbots may maintain an inactive state. The meaning of maintaining the active state may mean a state in which normal power supply is provided for the operation of the chatbot, and a normal level of network resources are provided, and the inactive state is limited in power supply, such as a low power mode, and network resources. May mean a state provided less than a normal operating state. The question and answer system can provide the user with a question and answer service through fewer resources through selective activation of the described chatbot.

According to one embodiment, when receiving a response to the query data from the chatbot in step 350, the query response device may transmit the received response to the user terminal.

4 is a flowchart illustrating an operation of a method for answering a query according to an embodiment.

According to an embodiment, the query response device may receive query data for the user's query through the communication interface in step 410.

The query response device may determine whether the query data received in step 420 is text data. When the query data corresponds to text data, the query response device may determine a morpheme included in the query data in step 440.

If it is determined in step 420 that the query data is not text data, the query response device may perform additional processing on the query data through step 430. The query response device may detect a character from the query data when the query data corresponds to image data. The query response device may perform pre-processing on the query data to detect characters from the query data in the form of image data, and may detect characters from the query data on which the pre-processing has been performed. The query response device may adjust the resolution of the query data and change the color of the query data to grayscale to perform pre-processing for the query data through binarization of the query data. The query response device may detect a character from the query data on which pre-processing has been performed. Specifically, the query response device may detect a character in the query data that has been preprocessed by utilizing an optical character recognition function that converts a character included in the query data into a machine-readable character.

The query response device may determine a morpheme included in the query data through step 440 based on the detected character.

When the query data corresponds to audio data, the query response device may convert the query data into text data, and determine a morpheme included in the query data through step 440 based on the query data converted into text data.

When the morpheme included in the query data is determined through step 440, the query response device may generate vector data in the query data through step 460. Specifically, the question and answer device may determine a part-of-speech of the determined morpheme, and may determine morphemes corresponding to a core part-of-speech among morphemes based on a predetermined condition. The question and answer device may generate vector data based on a combination of morphemes corresponding to the key parts of speech. The specific method of generating vector data based on the morpheme corresponding to the core part of speech is the same as the method described through step 330 of FIG. 3.

The query response device may determine a chatbot to transmit query data among a plurality of chatbots based on the vector data generated through step 470. Specifically, the query response device calculates the similarity of words included in tagging information for each combination of morphemes and each of the plurality of chatbots included in the vector data, and queries data among the plurality of chatbots based on the calculated similarity. You can decide at least one chatbot to send. The specific method of determining the chatbot based on the calculated similarity is the same as described in step 330 of FIG. 3.

A chatbot determined to receive query data may remain active, and other chatbots may remain inactive.

According to an embodiment, the query response device may transmit query data to the chatbot determined through step 480.

According to an embodiment, when receiving a response to the query data from the chatbot that provided the query data through step 490, the query response device may provide the received response to the user terminal.

5 is a diagram showing the overall configuration of a query response device according to an embodiment.

Referring to FIG. 5, the query response device 500 may include a processor 510, a memory 520, and a communication interface 530. According to an embodiment, the query response device 500 may further include a database 540. The query response device 500 may correspond to the query response device 210 of FIG. 2.

The memory 520 may be connected to the processor 510 and store instructions executable by the processor 510, data to be processed by the processor 510, or data processed by the processor 510. Memory 520 includes non-transitory computer-readable media, such as high-speed random access memory and/or non-volatile computer-readable storage media (eg, one or more disk storage devices, flash memory devices, or other non-volatile solid state memory devices). It can contain.

The communication interface 530 provides an interface for communicating with an external device (eg, a user terminal). The communication interface 530 may communicate with an external device through a wired or wireless network.

The database 540 may store information and data necessary for the query response device 500 to operate. For example, the database 540 may store tagging information for each chatbot, information for determining a morpheme corresponding to a key part of speech among a plurality of morphemes, and the like.

The processor 510 executes functions and instructions for execution in the query response device 500 and controls the overall operation of the query response device 500. The processor 510 receives query data for a user's query through a communication interface, determines a morpheme included in the query data, and among the plurality of chatbots based on the determined morpheme and tagging information for each of the plurality of chatbots At least one chatbot may be determined as a chatbot to transmit query data, and query data may be transmitted to the determined at least one chatbot. In addition, when receiving a response to the query data from the determined at least one chatbot, the processor 510 may transmit the received response to the user's user terminal.

The processor 510 may perform one or more operations related to the query response device in the query response method described in FIGS. 1 to 4.

According to an embodiment, the processor 510 determines a part-of-speech of the determined morpheme, determines a morpheme corresponding to a core part-of-speech among morphemes based on a predetermined condition, and based on the morpheme and tagging information corresponding to the determined core part-of-speech It is possible to determine at least one chatbot to transmit query data among a plurality of chatbots.

In addition, the processor 510 generates vector data based on the combination of morphemes corresponding to the key parts of speech, calculates the similarity of words included in tagging information and the combination of each morpheme included in the vector data, and based on the similarity To determine at least one of the plurality of chatbots.

When the query data is image data, the processor 510 detects a character from the query data, determines a morpheme included in the detected text, and determines at least one chatbot among a plurality of chatbots based on the determined morpheme and tagging information. You can decide by the chatbot to send the query data.

When the query data is audio data, the processor 510 converts the query data into text data, determines a morpheme included in the query data based on the converted query data, and a plurality of chatbots based on the determined morpheme and tagging information At least one of the chatbots can be determined as a chatbot to transmit query data.

The device described above may be implemented with hardware components, software components, and/or combinations of hardware components and software components. For example, the devices and components described in the embodiments include, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors (micro signal processors), microcomputers, field programmable gate arrays (FPGAs). , A programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose computers or special purpose computers. The processing device may run an operating system (OS) and one or more software applications running on the operating system. Further, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For convenience of understanding, a processing device may be described as one being used, but a person having ordinary skill in the art, the processing device may include a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include. For example, the processing device may include a plurality of processors or a processor and a controller. In addition, other processing configurations, such as parallel processors, are possible.

The software may include a computer program, code, instruction, or a combination of one or more of these, and configure the processing device to operate as desired, or process independently or collectively You can command the device. Software and/or data may be interpreted by a processing device, or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodied in the signal wave being transmitted. The software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, or the like alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiments or may be known and usable by those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs, DVDs, and magnetic media such as floptical disks. Includes hardware devices specifically configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language code that can be executed by a computer using an interpreter, etc., as well as machine language codes produced by a compiler. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described by a limited embodiment and drawings, those skilled in the art can make various modifications and variations from the above description. For example, 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 from the described method, or other components Alternatively, proper results can be achieved even if replaced or substituted by equivalents.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (19)

In the question and answer method using a plurality of chat bots (chat bots), Receiving query data for a user's query through a communication interface; Determining a morpheme included in the query data; Determining at least one chatbot among the plurality of chatbots based on the determined morpheme and tagging information for each of the plurality of chatbots; Transmitting the query data to the determined at least one chatbot; And When receiving a response corresponding to the query data from the determined at least one chatbot, transmitting the received response to the user terminal of the user Including, question and answer method. According to claim 1, Determining the at least one chatbot, Determining a part of speech of the morpheme; Determining a morpheme corresponding to a core part of speech among the morphemes based on a predetermined condition; And Determining at least one chatbot among the plurality of chatbots based on the morpheme corresponding to the determined core part-of-speech and the tagging information. Including, question and answer method. According to claim 2, Determining the at least one chatbot, Generating vector data based on a combination of morphemes corresponding to the core parts of speech; And Determining at least one chatbot among the plurality of chatbots based on the vector data and the tagging information Including, question and answer method. According to claim 3, The tagging information, The plurality of chatbots is determined based on information about words that can respond, a question and answer method. According to claim 4, Determining the at least one chatbot, Calculating a combination of each morpheme included in the vector data and similarity of the words; And Determining at least one chatbot among the plurality of chatbots based on the similarity Including, question and answer method. According to claim 1, The determined at least one chatbot remains active, A method of answering a query, wherein the remaining chatbots other than the determined at least one chatbot remain inactive. In the question and answer method using a plurality of chat bot (chat bot), Receiving query data for a user's query through a communication interface; Determining whether the query data is text data; If the query data is text data, determining a morpheme included in the query data; Determining vector data based on the combination of morphemes; Determining at least one chatbot among the plurality of chatbots by comparing the combination of the morphemes included in the vector data and tagging information for each of the plurality of chatbots; Transmitting the query data to the determined at least one chatbot; And When receiving a response to the query data from the determined at least one chatbot, transmitting the response to the user terminal of the user Including, question and answer method. The method of claim 7, When the query data is image data, Detecting a character from the query data Further comprising, The step of determining the morpheme, A query response method for determining a morpheme included in the query data based on the detected character. The method of claim 8, The step of detecting the character, Adjusting the resolution of the image data, changing the color of the image data to grayscale, and performing at least one of binarization of the image data; And Detecting the character based on the performance result Including, question and answer method. The method of claim 8, The step of detecting the character, Detecting a character included in the image data using optical character recognition Including, question and answer method. The method of claim 7, When the query data is audio data, Converting the query data into text data Further comprising, The step of determining the morpheme, A query response method for determining a morpheme included in the query data based on the query data converted to the text data. The method of claim 7, Determining the vector data, Determining a part of speech of the morpheme; Determining a morpheme corresponding to a key part of speech among the morphemes; Determining the vector data based on a combination of morphemes corresponding to the core parts of speech Including, question and answer method. The method of claim 12, Determining the at least one chatbot, Calculating a similarity between a combination of each morpheme included in the vector data and a word included in the tagging information; And Determining at least one chatbot among the plurality of chatbots based on the similarity Including, question and answer method. A computer-readable recording medium recording a program for executing the method of any one of claims 1 to 13 in a computer. In the question and answer device using a plurality of chat bot (chat bot), Including memory and processors, The memory stores instructions executable by the processor, The processor, Receive query data for user queries through a communication interface, Determine the morpheme included in the query data, Determining at least one chatbot among the plurality of chatbots based on the determined morpheme and tagging information for each of the plurality of chatbots, Transmitting the query data to the determined at least one chatbot, When receiving a response to the query data from the determined at least one chatbot, the query response device transmits the response to the user terminal of the user. The method of claim 15, The processor, Determine the part of speech of the morpheme, A morpheme corresponding to a key part of speech among the morphemes is determined based on predetermined conditions, A query response device for determining at least one chatbot among the plurality of chatbots based on the morpheme corresponding to the determined core part-of-speech and the tagging information. The method of claim 15, The processor, Vector data is generated based on a combination of morphemes corresponding to the core parts of speech, The combination of each morpheme included in the vector data and the similarity of words included in tagging information are calculated, And determine at least one chatbot among the plurality of chatbots based on the similarity. The method of claim 15, The processor, When the query data is image data, Characters are detected from the query data, The morpheme included in the detected character is determined, And determine at least one chatbot among the plurality of chatbots based on the determined morpheme and the tagging information. The method of claim 15, The processor, When the query data is audio data, Convert the query data to text data, A morpheme included in the query data is determined based on the converted query data, And determine at least one chatbot among the plurality of chatbots based on the determined morpheme and the tagging information.

Images