KR20210065629A - Chatbot integration agent platform system and service method thereof - Google Patents

Abstract

The present invention is an integrated chatbot agent platform system for chatbot channel connection and integration, and a service method thereof, wherein a unified integrated chatbot service is provided through an integrated chatbot agent platform so that, when using a chatbot service, question and answer knowledge of individual client chatbots, propagated throughout and built for various respective public/private sector industries, may be connected, and thus a user may be provided with the respective chatbot services of various industries through one unified chatbot window, and the area of service of the chatbot service may be widely expanded, the accuracy and quality of chatbot questions and answers may be improved, and further, when building chatbots for each industry, it is possible to reduce development budget and shorten development time.

Description

CHATBOT INTEGRATION AGENT PLATFORM SYSTEM AND SERVICE METHOD THEREOF}

The present invention relates to a chatbot integration agent platform system and a service method for integrating chatbot channels, and more particularly, to a single unified chatbot integration agent for chatbot services spread and built for various public/private industrial fields when using a chatbot service. It relates to a chatbot integration agent platform system and a service method for the chatbot channel linkage integration that enables the platform to provide services.

Today, with the rise in the value of data utilization and the development of language processing technology, various convergence technologies and service markets using artificial intelligence-based technologies such as deep learning and natural language processing are being activated.

In the midst of the advent of the intelligent information society, as mobile-oriented interactive interfaces such as mobile messenger become popular, Chatbot, an artificial intelligence-based service that allows users to feel the artificial intelligence ecosystem the most, is a public/ It is spreading and growing across all sectors of private industry.

As the development of artificial intelligence-based technologies such as natural language processing, deep learning, and machine learning has accelerated due to the chatbot craze across all industries, the level of chatbot service has changed from pattern matching and keyword-oriented text processing-based chatbots It is developing into an intelligent chatbot using learning, natural language processing, and machine learning technologies, and is expected to develop into a personalized emotional chatbot that can exchange even human emotions/emotions as the technology matures.

Domestic chatbots are being built in the form of client chatbots according to the purpose of using chatbot services by using various chatbot engines for each chatbot company.

Looking at the types of chatbot services, it can be divided into five major application areas: interactive commerce and O2O (Online to Offline), business support (personal assistant), public administration support, entertainment, and corporate messenger. Conversation processing methods are NLU (Natural Language Understanding)/pattern (probability)-based dialog model, NLU/rule-based dialog model, machine learning-based dialog model, search and backbone link-based dialog model, and various dialog processing methods developed by each chatbot engine. is being built with

These conventional individual client chatbots have different chatbot structures and conversation processing methods depending on the purpose of the chatbot service, the host institution, and the construction company, making it difficult to mutually utilize the Q&A knowledge data between the chatbots.

In addition, since the conventional chatbot service technologies are not standardized, the same functions and knowledge are independently built for each chatbot service despite being a chatbot service for a similar purpose.

In addition, chatbot services, which have been spread to all existing industries, have individual service channels for each field, so users have the inconvenience of finding the desired channel among the numerous channels they want to use. When developing a chatbot, it is difficult to link between chatbot services, such as building the same function or knowledge base, and there is some overlap in the chatbot business.

Therefore, it is possible to provide a universal chatbot service that secures diversity and accuracy by unifying the chatbot channel and linking the knowledge base to solve the problem that it is difficult to mutually utilize functions or knowledge due to differences in technology implementation or conversation processing method of conventional chatbots. The system is in desperate need.

Domestic Registered Patent No. 10-1840420 (2018.05.04. Announcement)

The present invention has been devised to solve the above problems, and an object of the present invention is to link the Q&A knowledge of individual client chatbots scattered across public/private industry fields through a chatbot integration agent platform unified chatbot It is to provide a chatbot integration agent platform system and service method for the chatbot channel linkage integration that can expand the wide service area of the chatbot service and improve the quality of the chatbot question and answer by providing the service.

In order to achieve the above object, a first aspect of the present invention includes a plurality of client chatbots equipped with a common API (Application Programming Interface) and its own chatbot engine module; a plurality of user terminals for transmitting the contents of the chatbot query intended by the user; a chatbot query input channel module that receives the chatbot query content intended by the user transmitted from each user terminal and delivers it through at least one dialogue input channel; Receives the chatbot query content of the user delivered from the chatbot query input channel module, understands the user's intent for the chatbot query through natural language understanding/processing, and responds to the user's chatbot query based on the identified intent An integrated chatbot engine that judges answer processing or chatbot channel-linked answer processing, and selects at least one client chatbot channel that can answer the user's chatbot query when it is determined that the user's chatbot query is chatbot channel-linked answer processing module; an integrated interface module for transmitting the user's chatbot query content to the common API of the corresponding client chatbot through each client chatbot channel selected from the integrated chatbot engine module; and Q&A contents for the user's chatbot query transmitted from the common API of each client chatbot through the unified interface module are provided, and the Q&A contents for the corresponding user's chatbot query contents based on a preset answer recommendation standard After recommending the final Q&A in text format, an answer recommendation engine that provides a service so that the recommended final Q&A in the text format is transmitted to the user terminal through the corresponding conversation input channel of the chatbot query input channel module It is to provide a chatbot integration agent platform system for chatbot channel linkage integration including modules.

Here, each client chatbot receives the user's chatbot query content transmitted from the unified interface module through the common API, and uses its own chatbot engine module and chatbot answer knowledge DB to respond to the user's chatbot query content It is preferable to generate text-type question-and-answer content and transmit the generated text-type question-and-answer content to the integrated interface module through a corresponding common API.

Preferably, the conversation input channel of the chatbot query input channel module may be formed of at least one of a mobile app, a social network service (SNS), a chatbot messenger, or a personal computer (PC).

Preferably, a database (DB) of pre-set text-type question-and-answer contents corresponding to at least one chatbot query content among simple greetings, introductions, daily conversations, or immediate-answer-type questions for each chatbot-linked service is stored and managed. A basic knowledge management DB may be further included.

Preferably, when the integrated chatbot engine module determines that the user's chatbot query is self-answering, it refers to the basic knowledge management DB and answers questions in a preset text format corresponding to the chatbot query contents of the user. After searching and generating , a service may be provided to transmit the search and generated text-type question-and-answer content to the corresponding user terminal through the corresponding conversation input channel of the chatbot query input channel module.

Preferably, a chatbot channel knowledge management DB for classifying and storing and managing at least one client chatbot channel for each client chatbot service field category in order to link the client chatbot may be further included.

Preferably, when the integrated chatbot engine module determines that the chatbot channel-linked answer processing for the user's chatbot query is processed, at least one client chatbot capable of answering the user's chatbot query with reference to the chatbot channel knowledge management DB You can select a channel.

Preferably, the answer recommendation criteria set in the answer recommendation engine module include cumulative user preference-based weight through client chatbot answer preference analysis, multiple answer keyword similarity rate through multiple answer similarity analysis, or machine learning based on word embedding. At least one reference result value among the similar query analysis result values through the

A second aspect of the present invention is a service method for integrating chatbot channels using a system including a plurality of client chatbots, a plurality of user terminals, and a chatbot integration agent platform equipped with a common API (Application Programming Interface), ( a) transmitting the chatbot query content intended by the user through each user terminal; (b) delivering the content of the chatbot query intended by the user, transmitted in step (a), to the chatbot integrated agent platform through at least one dialogue input channel of the chatbot query input channel module connected to the chatbot integrated agent platform ; (c) understand/process the user's chatbot query content delivered in step (b) through the integrated chatbot engine module provided in the chatbot integrated agent platform to understand/process the user's intent for the chatbot query, then identify judging a self-answer process or a chatbot channel-linked answer process for the user's chatbot query based on the intended intention; (d) As a result of the determination in step (c), when it is determined that the chatbot channel-linked answer processing for the user's chatbot query is processed, the chatbot query of the corresponding user is answered through the integrated chatbot engine module provided in the chatbot integrated agent platform. selecting at least one answerable client chatbot channel; (e) transmitting the chatbot query contents of the user to the common API of the corresponding client chatbot using each client chatbot channel selected in step (d) through the unified interface module provided in the chatbot unified agent platform; (f) ) Through each client chatbot, on the basis of the user's chatbot query content transmitted in step (e), a text-type Q&A corresponding to the corresponding user's chatbot query is generated, and then the generated text-type query is generated. Transmitting the response contents to the chatbot integrated agent platform using the corresponding common API (g) the chatbot query contents of the corresponding user transmitted in the step (f) through the response recommendation engine module provided in the chatbot integrated agent platform Recommending the final Q&A contents in text form among the Q&A contents for the chatbot query contents of the corresponding user based on the preset answer recommendation criteria by receiving the contents of the Q&A for the chatbot; and (h) the chatbot integrated agent platform Transmitting the final question and answer content in the text format recommended in step (g) to the user terminal through the corresponding dialog input channel of the chatbot query input channel module connected to the chatbot channel linkage integration It is to provide a chatbot integration agent platform service method.

Here, in step (b), the conversation input channel of the chatbot query input channel module is at least one of a mobile app, a social network service (SNS), a chatbot messenger, or a personal computer (PC). It is preferable to do

Preferably, before or after step (d), when it is determined that the user's chatbot query is self-answered as a result of the determination in step (c), the integrated chatbot engine module provided in the chatbot integrated agent platform is installed After referring to a separate basic knowledge management DB through a separate basic knowledge management DB to search for and generate preset text-type question and answer contents corresponding to the chatbot query contents of the user, the search and processing are performed through the corresponding conversation input channel of the chatbot query input channel module. The method may further include providing a service so that the generated text-type Q&A content is transmitted to a corresponding user terminal.

Preferably, the basic knowledge management DB has a preset text format corresponding to each chatbot query content of at least one of simple greetings, introduction, daily conversation, or immediate answer type query for each chatbot connection target service through the chatbot integrated agent platform. You can store and manage the contents of the Q&A into a database (DB).

Preferably, in step (d), when the integrated chatbot engine module determines that the chatbot channel-linked answer processing for the user's chatbot query is processed, it refers to a separate chatbot channel knowledge management DB to respond to the user's chatbot query. It is possible to select at least one client chatbot channel that can answer the question.

Preferably, the chatbot channel knowledge management DB classifies and stores and manages at least one client chatbot channel for each client chatbot service field category in order to link the client chatbot through the chatbot integrated agent platform. .

Preferably, in step (f), each client chatbot uses its own chatbot engine module and chatbot answer knowledge DB to respond to the user's chatbot query content transmitted in step (e) to the user's chatbot query content. After generating the corresponding text-type Q&A content, the generated text-type Q&A content may be transmitted to an integrated interface module provided in the chatbot unified agent platform through a corresponding common API.

A third aspect of the present invention provides a computer-readable recording medium recording a program capable of executing the chatbot integration agent platform service method for the chatbot channel linkage integration described above.

The chatbot integration agent platform service method for the chatbot channel linkage integration according to the present invention can be implemented as a computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all kinds of recording devices in which data readable by a computer system is stored.

For example, computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, hard disk, floppy disk, removable storage device, and non-volatile memory (Flash Memory). , and optical data storage devices.

According to the chatbot integration agent platform system and service method for the chatbot channel linkage integration of the present invention as described above, the chatbot integration agent can link the Q&A knowledge of individual client chatbots scattered across all public/private industrial fields. By providing a unified and integrated chatbot service through the platform, there is an advantage in expanding the wide service area of the chatbot service and improving the quality of the chatbot question and answer.

In addition, according to the present invention, in order to solve the conventional multi-channel and redundancy problem, an integrated interface that can link existing chatbots, an integrated chatbot engine module for providing an integrated chatbot service, and a standard knowledge base for supporting questions and answers in various fields, etc. By building this, users can receive chatbot services for various industries through a single, unified chatbot window, improve the accuracy of Q&A by utilizing the existing chatbot's answer linkage, and furthermore, when building a chatbot for each industry field, chatbot It has the advantage of reducing the development budget and shortening the development time by using the integrated agent platform.

1 is an overall block diagram for explaining a chatbot integration agent platform system for chatbot channel linkage integration according to an embodiment of the present invention.
2 is a detailed block diagram illustrating the chatbot integrated agent platform applied to an embodiment of the present invention.
3 and 4 are overall flowcharts for explaining a chatbot integration agent platform service method for chatbot channel-linked integration according to an embodiment of the present invention.

The above-described objects, features and advantages will be described below in detail with reference to the accompanying drawings, and accordingly, those skilled in the art to which the present invention pertains will be able to easily implement the technical idea of the present invention. In describing the present invention, if it is determined that a detailed description of a known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description will be omitted.

Terms including an ordinal number, such as first, second, etc., may be used to describe various elements, but the elements are not limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, 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. The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise.

The terms used in the present invention have been selected as currently widely used general terms as possible while considering the functions in the present invention, which may vary depending on the intention or precedent of a person skilled in the art, the emergence of new technology, and the like. In addition, in specific cases, there are also terms arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the corresponding invention. Therefore, the term used in the present invention should be defined based on the meaning of the term and the overall content of the present invention, rather than the name of a simple term.

When a part "includes" a certain component throughout the specification, this means that other components may be further included, rather than excluding other components, unless otherwise stated. In addition, terms such as "...unit" and "module" described in the specification mean a unit that processes at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software. .

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the embodiments of the present invention illustrated below may be modified in various other forms, and the scope of the present invention is not limited to the embodiments described below. The embodiments of the present invention are provided to more completely explain the present invention to those of ordinary skill in the art.

Each block in the accompanying block diagram and combinations of steps in the flowchart may be executed by computer program instructions (execution engine), which computer program instructions may be executed by a processor of a general-purpose computer, special-purpose computer, or other programmable data processing equipment. It may be mounted so that its instructions, which are executed by the processor of a computer or other programmable data processing equipment, create means for performing the functions described in each block of the block diagram or in each step of the flowchart. These computer program instructions may also be stored in a computer-usable or computer-readable memory, which may direct a computer or other programmable data processing equipment to implement a function in a particular manner, such that the computer-usable or computer-readable memory It is also possible for the instructions stored in the block diagram to produce an article of manufacture containing instruction means for performing the functions described in each block of the block diagram or each step of the flowchart.

And, since the computer program instructions may be mounted on a computer or other programmable data processing equipment, a series of operational steps are performed on the computer or other programmable data processing equipment to create a computer-executed process to create a computer or other program It is also possible that instructions for performing the possible data processing equipment provide steps for carrying out the functions described in each block of the block diagram and each step of the flowchart.

In addition, each block or step may represent a module, segment, or portion of code comprising one or more executable instructions for executing specified logical functions, and in some alternative embodiments the blocks or steps referred to in the block or steps. It should be noted that it is also possible for functions to occur out of sequence. For example, it is possible that two blocks or steps shown one after another may be performed substantially simultaneously, and also the blocks or steps may be performed in the reverse order of the corresponding functions, if necessary.

1 is an overall block diagram for explaining a chatbot unified agent platform system for chatbot channel-linked integration according to an embodiment of the present invention, and FIG. 2 is a chatbot unified agent platform applied to an embodiment of the present invention. It is a detailed block diagram for

1 and 2, the chatbot integration agent platform system for chatbot channel-linked integration according to an embodiment of the present invention is largely a plurality of client chatbots (100-1 to 100-N), a plurality of user terminals ( 200-1 to 200-N), a chatbot query input channel module 300, and a chatbot integrated agent platform 400 and the like. On the other hand, since the components shown in FIGS. 1 and 2 are not essential, the chatbot integration agent platform system for chatbot channel-linked integration according to an embodiment of the present invention has more components or fewer components. may have

Hereinafter, the components of the chatbot integration agent platform system for the chatbot channel linkage integration according to an embodiment of the present invention will be described in detail as follows.

Each of the client chatbots 100-1 to 100-N is respectively connected to the chatbot integrated agent platform 400 through the communication network 10, and in this case, the communication network 10 is a large-scale communication network capable of high-capacity, long-distance voice and data services. It is a communication network that is a high-speed backbone network of the Internet or Wi-Fi, WiGig, Wibro, and Wimax (World Interoperability for Microwave Access, Wimax) to provide high-speed multimedia services. ) and the like may be a next-generation wireless communication network.

The Internet includes the TCP/IP protocol and various services existing in its upper layers, namely HTTP (Hyper Text Transfer Protocol), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), It means a worldwide open computer network structure that provides Simple Network Management Protocol (SNMP), Network File Service (NFS), Network Information Service (NIS), etc., and each client chatbot (100-1 to 100-N) and/or An environment is provided for each user terminal 200 - 1 to 200 -N to be connected to the chatbot integrated agent platform 400 . Meanwhile, the Internet may be a wired or wireless Internet, or may be a core network integrated with a wired public network, a wireless mobile communication network, or a portable Internet.

If the communication network 10 is a mobile communication network, it may be a synchronous mobile communication network or an asynchronous mobile communication network. As an embodiment of the asynchronous mobile communication network, a wideband code division multiple access (WCDMA) type communication network may be used. In this case, although not shown in the drawings, the mobile communication network may include, for example, a Radio Network Controller (RNC). Meanwhile, although the WCDMA network is taken as an example, it may be a next-generation communication network such as a cellular-based 3G network, an LTE network, a 4G network, or a 5G network, and other IP-based IP networks. The communication network 10 serves to mutually transmit signals and data of the chatbot integrated agent platform 400 with each client chatbot 100-1 to 100-N and/or each user terminal 200-1 to 200-N. carry out

Each of these client chatbots 100-1 to 100-N generates and transmits a common question and answer content for the chatbot query content intended by each user transmitted from each user terminal 200-1 to 200-N. In addition to API (Application Programming Interface) 110, a chatbot engine module 120 and a chatbot answer knowledge DB 130 are mounted.

Here, the chatbot answer knowledge DB 130 stores the preset Q&A knowledge content corresponding to the user's chatbot query content within the scope of its own chatbot service field under the control of the chatbot engine module 120 into a database (DB) and stores it. and manage.

That is, each client chatbot 100-1 to 100-N receives the user's chatbot query content transmitted from the unified interface module 410 of the chatbot integration agent platform 400 through the common API 110 and receives its own The in-chatbot engine module 120 and the chatbot answer knowledge DB 130 are used to generate text-type Q&A contents corresponding to the user's chatbot query contents, and the generated text-type Q&A contents are converted to the corresponding common API. It performs a function of transmitting to the integrated interface module 410 of the chatbot integrated agent platform 400 through 110 .

Each of the user terminals 200-1 to 200-N is respectively connected to the chatbot query input channel module 300 and the chatbot integrated agent platform 400 through the communication network 10, and the contents of the chatbot query intended by the user are transmitted to the chatbot. It performs a function of transmitting to the integrated interface module 410 of the chatbot integrated agent platform 400 through the query input channel module 300 .

In addition, each user terminal 200-1 to 200-N self-answers to each user's chatbot query transmitted from the chatbot query input channel module 300 and the chatbot integrated agent platform 400 through the communication network 10 And/or the chatbot channel-linked answer processing may be provided with information data (ie, question-and-answer content, etc.) as a result of performing the chatbot channel-linked answer processing, and a service may be provided so that each corresponding user can visually and/or audibly check it.

Meanwhile, each of the user terminals 200-1 to 200-N applied to an embodiment of the present invention is a smart phone, a smart pad, or a smart note that communicates through the wireless Internet or the portable Internet. Note) is preferably composed of at least one mobile terminal device, in addition to a personal PC, a notebook PC, a Palm PC, a mobile game machine (Mobile play-station), a DMB (Digital Multimedia Broadcasting) phone with a communication function, It may comprehensively mean all wired and wireless home appliances/communication devices having a user interface for accessing the chatbot query input channel module 300 and the chatbot integrated agent platform 400, such as a tablet PC, an iPad, and the like.

If each of the user terminals 200-1 to 200-N consists of a smart phone, the smart phone downloads various application programs desired by the user, unlike a general mobile phone (aka feature phone). It is a phone based on an open operating system that can be received, used, and deleted freely. It supports not only commonly used functions such as voice/video calls and Internet data communication, but also all mobile phones or voice calls with mobile office functions. However, it is desirable to understand it as a communication device including any Internet phone or tablet PC that can access the Internet.

Such a smart phone may be implemented as a smart phone equipped with various open operating systems, and the open operating systems include, for example, Symbian of Nokia, BlackBerry of RIMS, iPhone of Apple, iPhone of Microsoft Corporation. (MS) Windows Mobile, Google's Android, Samsung Electronics' sea, etc. can be made.

As described above, since a smartphone uses an open operating system, a user can arbitrarily install and manage various application programs, unlike a mobile phone having a closed operating system.

The chatbot query input channel module 300 is connected to each user terminal 200-1 to 200-N and/or the chatbot integrated agent platform 400 through the communication network 10, and each user terminal 200-1 to 200-N is connected to the chatbot integrated agent platform 400. 200-N) receives the intended chatbot query content transmitted by each user and transmits the received chatbot query content to the chatbot integrated agent platform 400 through at least one dialog input channel 310 .

In addition, the chatbot query input channel module 300 receives information data as a result of performing self-answer processing and/or chatbot channel-linked answer processing to each user's chatbot query transmitted from the chatbot integrated agent platform 400, and input the corresponding conversation Through the channel 310 and the communication network 10, it is possible to perform a function of transmitting to each corresponding user terminal (200-1 to 200-N).

Meanwhile, the conversation input channel 310 of the chatbot query input channel module 300 is, for example, at least one of a mobile app, a social network service (SNS), a chatbot messenger, and/or a personal computer (PC). It is preferable to consist of one.

In addition, the chatbot integrated agent platform 400 includes each client chatbot 100-1 to 100-N, the chatbot query input channel module 300, and/or each user terminal 200-1 to 200 through the communication network 10. -N) and performs a function of providing a single unified chatbot Q&A knowledge service by linking the Q&A knowledge service of various client chatbots 100-1 to 100-N.

That is, the chatbot integrated agent platform 400 is largely, as shown in FIG. 2, an integrated chatbot engine module 410, an integrated interface module 420, an answer recommendation engine module 430, a basic knowledge management DB 440, and/or the chatbot channel knowledge management DB 450 may be included.

Here, the integrated chatbot engine module 410 performs overall control of the chatbot integrated agent platform 400 applied to an embodiment of the present invention, in particular, each user's chatbot query delivered from the chatbot query input channel module 300 . Receive content and understand the intent of each user's chatbot query through natural language understanding and/or processing, and based on the identified intent, self-response and/or chatbot channel-linked response processing for each user's chatbot query It performs the function of judging

In addition, the integrated chatbot engine module 410 performs a function of selecting at least one client chatbot channel capable of answering each user's chatbot query when it is determined that the chatbot channel-linked answer processing for each user's chatbot query is performed. do.

In addition, the integrated chatbot engine module 410 refers to the basic knowledge management DB 440 when it is determined that each user's chatbot query is self-answered, and a preset text form corresponding to the chatbot query content of each user is referred to. After searching and generating the Q&A contents of the chatbot query input channel module 300, through the corresponding conversation input channel 310 of the chatbot query input channel module 300, the searched and generated text Q&A contents are displayed in the respective user terminals 200-1 to 200-N) to provide a service to be transmitted.

In addition, the integrated chatbot engine module 400 refers to the chatbot channel knowledge management DB 450 when it is determined that the chatbot channel-linked answer processing for each user's chatbot query is at least capable of answering each user's chatbot query. It can perform the function of selecting one client chatbot channel.

The unified interface module 420 transmits the chatbot query contents of the user to the common API 110 of the respective client chatbots 100-1 to 100-N through each client chatbot channel selected from the integrated chatbot engine module 400 perform the function

In addition, the unified interface module 420 receives the text-type question-and-answer content corresponding to the chatbot query content of each user transmitted through the common API 110 of each client chatbot 100-1 to 100-N. It may perform a function of transmitting this to the answer recommendation engine module 430 .

The answer recommendation engine module 430 provides Q&A contents for the chatbot query contents of the corresponding user transmitted from the common API 110 of each client chatbot 100-1 to 100-N through the integrated interface module 420 . After receiving and recommending the final Q&A content in text form among the Q&A contents for each user's chatbot query content based on the preset answer recommendation criteria, the corresponding conversation input channel 310 of the chatbot query input channel module 300 ) to provide a service so that the recommended final Q&A content in the form of text is transmitted to the corresponding user terminals 200-1 to 200-N.

In this case, the answer recommendation criteria preset in the answer recommendation engine module 430 are, for example, cumulative user preference-based weight through client chatbot answer preference analysis, multiple answer keyword similarity rate through multiple answer similarity analysis, and/or word embedding based It is preferable to use at least one reference result value among similar query analysis results through machine learning learning.

For example, when using the reference result value of the cumulative user preference-based weight through the client chatbot answer preference analysis, the accumulation of each client chatbot 100-1 to 100-N in the Q&A contents for the chatbot query contents of the corresponding user After extracting the user preference-based weights, the Q&A content having the largest weight value among the extracted weight values may be recommended as the final Q&A content.

Also, in the case of the multiple-answer keyword similarity rate and the similar query analysis result value, the Q&A content having the largest reference result value as the weight value may be recommended as the final Q&A content.

The basic knowledge management DB 440 is at least one of simple greetings, introductions, daily conversations, and/or instant-response queries for each chatbot connection target service through the control of the integrated chatbot engine module 400 of the chatbot integrated agent platform 400 . It is possible to perform a function of storing and managing questions and answers in the form of preset text corresponding to each chatbot query content into a database (DB).

The chatbot channel knowledge management DB 450 classifies at least one client chatbot channel by category of the client chatbot service field in order to link the client chatbot through the control of the integrated chatbot engine module 400 of the chatbot integrated agent platform 400, and a database ( DB) to store and manage functions.

On the other hand, the above-described chatbot integrated agent platform 400 is to be implemented by being mounted in the form of hardware and/or software in a terminal such as a server (Server) (not shown) and/or each user terminal (100-1 to 100-N). can

On the other hand, although the chatbot query input channel module 300 applied to an embodiment of the present invention is implemented in a form connected to the chatbot integration agent platform 400, it is not limited thereto, and the chatbot query input channel module 300 is integrated with the chatbot. It may be implemented by including it in the agent platform 400 .

Hereinafter, a chatbot integration agent platform service method for chatbot channel linkage integration according to an embodiment of the present invention will be described in detail.

3 and 4 are overall flowcharts for explaining a chatbot integration agent platform service method for chatbot channel-linked integration according to an embodiment of the present invention.

1 to 4 , in the chatbot integration agent platform service method for chatbot channel linkage integration according to an embodiment of the present invention, first, each user through each user terminal 100-1 to 100-N The intended chatbot query content is transmitted (S100).

Thereafter, the chatbot query contents intended by each user transmitted in step S100 through at least one dialogue input channel 310 of the chatbot query input channel module 300 connected to the chatbot integration agent platform 400 are integrated into the chatbot. It is transferred to the agent platform 400 (S200).

In this case, in step S200, the conversation input channel 310 of the chatbot query input channel module 300 is, for example, a mobile app, a social network service (SNS), a chatbot messenger, and/or a PC ( Personal Computer) is preferably made of at least one.

Then, through the integrated chatbot engine module 410 provided in the chatbot integrated agent platform 400, the chatbot query content of each user transmitted in step S200 is understood and/or processed in natural language to respond to the chatbot query of each user. After understanding the intention of the user (eg, understanding the range of knowledge of the client chatbok, etc.), based on the identified intention, it is determined that the user's own answer processing and/or the chatbot channel-linked answer processing are processed for each user's chatbot query (S300).

Next, as a result of the determination in step S300, when it is determined that the chatbot channel-linked answer processing for each user's chatbot query is processed, each user through the integrated chatbot engine module 410 provided in the chatbot integrated agent platform 400 At least one client chatbot channel capable of answering the chatbot query of the user is selected (S400).

At this time, in step S400, when the integrated chatbot engine module 410 provided in the chatbot integrated agent platform 400 determines that the chatbot channel-linked answer processing for each user's chatbot query is processed, a separate chatbot channel knowledge management DB With reference to 450 , it is preferable to select at least one client chatbot channel that can answer each user's chatbot query.

And, the chatbot channel knowledge management DB 450 classifies and stores and manages at least one client chatbot channel for each client chatbot service field category in order to link the client chatbot through the chatbot integrated agent platform 400. can

For example, the chatbot channel knowledge management DB 450 may classify channel recognition through similarity matching with a chatbot channel based on a client chatbot service field category and/or intent. That is, the chatbot channel knowledge management DB 450 may build a recognition category and/or intent for each client chatbot channel in order to recognize and link the client chatbot channel.

By using this chatbot channel knowledge management DB 450, the integrated chatbot engine module 410 processes the answer by matching the result of understanding the intent of each user's chatbot query and the recognition category and/or intent for each chatbot channel. It can determine possible client chatbot channels and process answers to queries.

Meanwhile, when there are a plurality of client chatbot channels selected through the integrated chatbot engine module 410 , at least one final client chatbot channel may be selected based on a normal pattern and/or probability.

Thereafter, the common API of each client chatbot 100-1 to 100-N using each client chatbot channel selected in step S400 through the unified interface module 420 provided in the chatbot integration agent platform 400 ( 110) to transmit the chatbot query contents of each user (S500).

Then, based on the chatbot query contents of each user transmitted in step S500 through each client chatbot 100-1 to 100-N, the text-type Q&A contents corresponding to the chatbot query contents of each user are displayed. After creation, the generated text-type Q&A content is transmitted to the chatbot integration agent platform 400 using the corresponding common API 110 (S600).

At this time, in step S600, each client chatbot 100-1 to 100-N transmits the chatbot query content of each user transmitted in step S500 to its own chatbot engine module 120 and chatbot answer knowledge DB 130. After generating text-type question-and-answer contents corresponding to each user's chatbot query contents using , the generated text-type question-and-answer contents are transmitted to the chatbot integrated agent platform 400 through the common API 110. It can be transmitted to the provided integrated interface module 420 .

Next, through the answer recommendation engine module 430 provided in the chatbot integrated agent platform 400, the Q&A contents for each user's chatbot query contents transmitted in step S600 are provided, and based on a preset answer recommendation standard As a result, the final Q&A in text format is recommended among the Q&A for each user's chatbot query (S700).

On the other hand, when there are multiple identical answers to each user's chatbot query content (when the meaning is the same but the vocabulary and/or sentences are different), the optimal answer and/or multiple answers may be simultaneously provided through the optimal answer recommendation.

Thereafter, through the corresponding conversation input channel 310 of the chatbot query input channel module 300 connected to the chatbot integrated agent platform 400, the final question and answer contents in the text form recommended in step S700 are transmitted to the respective user terminals 200 . -1 to 200-N) (S800).

Additionally, although not shown in the drawing, before or after step S400, when it is determined as a self-answering process for each user's chatbot query as a result of the determination of step S300, the integration provided in the chatbot integration agent platform 400 After referring to the separate basic knowledge management DB 440 through the chatbot engine module 410 to search for and create preset text-type question and answer contents corresponding to the chatbot query contents of each user, the chatbot query input channel module The method may further include providing a service so that the content of the searched and generated text-type Q&A is transmitted to the respective user terminals 200-1 to 200-N through the corresponding conversation input channel 310 of (300). can

For example, a chatbot through the similarity rate matching based on the category and/or intent of the chatbot channel knowledge management DB 450 through the integrated chatbot engine module 410 provided in the chatbot integrated agent platform 400 . In the case of a query that does not require channel linkage, it is determined as self-answer processing, and the question and answer can be provided using the basic knowledge management DB 440 in the chatbot integrated agent platform 400 .

And, the basic knowledge management DB 440 corresponds to each chatbot query content of at least one of simple greetings, introductions, daily conversations, and/or instant-response queries for each chatbot connection target service through the chatbot integrated agent platform 400 . It is possible to store and manage the set text-type Q&A contents as a database (DB).

In addition, in the basic knowledge management DB 440 , the knowledge of the question and answer set for the non-judgment material may be stored and managed as a database DB.

On the other hand, the chatbot integration agent platform service method for the chatbot channel linkage integration according to an embodiment of the present invention can also be implemented as a computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all kinds of recording devices in which data readable by a computer system is stored.

For example, computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, hard disk, floppy disk, removable storage device, and non-volatile memory (Flash Memory). , and optical data storage devices.

In addition, the computer-readable recording medium may be distributed in a computer system connected through a computer communication network, and stored and executed as readable code in a distributed manner.

Although the preferred embodiment of the chatbot integration agent platform system and the service method for the chatbot channel-linked integration according to the present invention have been described above, the present invention is not limited thereto, and the claims and detailed description of the invention and the accompanying It is possible to carry out various modifications within the scope of the drawings, and this also belongs to the present invention.

100-1 to 100-N: client chatbot,
200-1 to 200-N: user terminal;
300: chatbot query input channel module,
400: chatbot integration agent platform;
410: integrated chatbot engine module,
420: integrated interface module;
430: answer recommendation engine module,
440: basic knowledge management DB,
450: chatbot channel knowledge management DB

Claims (14)

A plurality of client chatbots equipped with a common API (Application Programming Interface) and their own chatbot engine module;
a plurality of user terminals for transmitting the contents of the chatbot query intended by the user;
a chatbot query input channel module that receives the chatbot query content intended by the user transmitted from each user terminal and delivers it through at least one dialogue input channel;
Receives the chatbot query content of the user delivered from the chatbot query input channel module, understands the user's intent for the chatbot query through natural language understanding/processing, and responds to the user's chatbot query based on the identified intent An integrated chatbot engine that judges answer processing or chatbot channel-related answer processing, and selects at least one client chatbot channel that can answer the user's chatbot query when it is determined that the user's chatbot query is a chatbot channel-related answer processing module;
an integrated interface module for transmitting the user's chatbot query content to the common API of the corresponding client chatbot through each client chatbot channel selected from the integrated chatbot engine module; and
Among the Q&A contents for the chatbot query contents of the corresponding user, based on the preset answer recommendation criteria, by receiving the Q&A contents for the chatbot query contents of the corresponding user transmitted from the common API of each client chatbot through the integrated interface module After recommending the final Q&A content in text format, the answer recommendation engine module provides a service so that the recommended final Q&A content in the text format is transmitted to the user terminal through the corresponding conversation input channel of the chatbot query input channel module. Chatbot integration agent platform system for chatbot channel linkage integration, including.
The method of claim 1,
Each client chatbot receives the user's chatbot query content transmitted from the unified interface module through the common API, and uses its own chatbot engine module and chatbot answer knowledge DB in the form of a text corresponding to the user's chatbot query content A chatbot unified agent platform system for chatbot channel linkage integration, characterized in that generating a question and answer content of the text and transmitting the generated text format question answer content to the unified interface module through a corresponding common API.
The method of claim 1,
The conversation input channel of the chatbot query input channel module is integrated with a chatbot channel, characterized in that it is composed of at least one of a mobile app, a social network service (SNS), a chatbot messenger, or a personal computer (PC). Chatbot integrated agent platform system for
The method of claim 1,
Basic knowledge management that stores and manages a database (DB) of pre-set text-type Q&A contents corresponding to at least one chatbot query content among simple greetings, introductions, daily conversations, or instant-answer questions for each chatbot-linked service DB is more included,
The integrated chatbot engine module, when it is determined that the user's chatbot query is self-answering, refers to the basic knowledge management DB to search for and answer questions in a preset text form corresponding to the chatbot query contents of the user. After creation, the chatbot channel connection integration chatbot, characterized in that the service is provided to transmit the searched and generated text-type question-and-answer content to the user terminal through the corresponding conversation input channel of the chatbot query input channel module. Unified Agent Platform System.
The method of claim 1,
A chatbot channel knowledge management DB is further included to classify and database (DB) at least one client chatbot channel for each client chatbot service field in order to link the client chatbot, store and manage it,
The integrated chatbot engine module selects at least one client chatbot channel capable of answering the user's chatbot query by referring to the chatbot channel knowledge management DB when it is determined that the chatbot channel-linked answer processing for the user's chatbot query is processed. Chatbot integration agent platform system for chatbot channel linkage integration, characterized in that
The method of claim 1,
The answer recommendation criteria preset in the answer recommendation engine module are: cumulative user preference-based weight through client chatbot answer preference analysis, multiple answer keyword similarity rate through multiple answer similarity analysis, or similar query through word embedding-based machine learning learning A chatbot integration agent platform system for chatbot channel linkage integration, characterized in that using at least one reference result value among the analysis result values.
A service method for integrating chatbot channels using a system including a plurality of client chatbots, a plurality of user terminals, and a chatbot integration agent platform equipped with a common API (Application Programming Interface),
(a) transmitting the contents of the chatbot query intended by the user through each user terminal;
(b) delivering the content of the chatbot query intended by the user, transmitted in step (a), to the chatbot integrated agent platform through at least one dialogue input channel of the chatbot query input channel module connected to the chatbot integrated agent platform ;
(c) understand/process the user's chatbot query content delivered in step (b) through the integrated chatbot engine module provided in the chatbot integrated agent platform to understand/process the user's intent for the chatbot query, then identify judging a self-answer process or a chatbot channel-linked answer process for the user's chatbot query based on the intended intention;
(d) As a result of the determination in step (c), when it is determined that the chatbot channel-linked answer processing for the user's chatbot query is processed, the chatbot query of the corresponding user is answered through the integrated chatbot engine module provided in the chatbot integrated agent platform. selecting at least one answerable client chatbot channel;
(e) transmitting the chatbot query contents of the user to the common API of the corresponding client chatbot using each client chatbot channel selected in step (d) through the unified interface module provided in the chatbot unified agent platform;
(f) through each client chatbot, on the basis of the user's chatbot query transmitted in step (e), a text-type Q&A corresponding to the corresponding user's chatbot query is generated, and then the generated text format transmitting the question and answer contents of the chatbot integration agent platform using the corresponding common API;
(g) receiving the question and answer contents for the user's chatbot query transmitted in step (f) through the answer recommendation engine module provided in the chatbot integrated agent platform, and based on a preset answer recommendation standard, the user's recommending the final Q&A contents in text form among the Q&A contents for the chatbot query contents; and
(h) transmitting the final question and answer content in text form recommended in step (g) to the user terminal through the corresponding conversation input channel of the chatbot query input channel module connected to the chatbot integrated agent platform; Chatbot integration agent platform service method for chatbot channel linkage integration.
8. The method of claim 7,
In step (b), the conversation input channel of the chatbot query input channel module is made of at least one of a mobile app, a social network service (SNS), a chatbot messenger, or a personal computer (PC). Chatbot integration agent platform service method for chatbot channel-linked integration, characterized.
8. The method of claim 7,
before or after step (d),
As a result of the determination in step (c), if it is determined that the user's chatbot query is self-answered, the user's information is obtained by referring to a separate basic knowledge management DB through the integrated chatbot engine module provided in the chatbot integrated agent platform. After retrieving and generating preset text-type Q&A contents corresponding to the chatbot query contents, the searched and generated text-type Q&A contents are sent to the corresponding user terminal through the corresponding conversation input channel of the chatbot query input channel module. Chatbot integration agent platform service method for the chatbot channel linkage integration, characterized in that it further comprises the step of providing a service to be transmitted.
10. The method of claim 9,
The basic knowledge management DB is, through the chatbot integrated agent platform, a set text-type question-and-answer content corresponding to each chatbot query content of at least one of simple greetings, introductions, daily conversations, or immediate-answer questions for each chatbot-linked service Chatbot integration agent platform service method for chatbot channel linkage integration, characterized in that it stores and manages the database (DB).
8. The method of claim 7,
In step (d), the integrated chatbot engine module is capable of answering the user's chatbot query by referring to a separate chatbot channel knowledge management DB when it is determined that the chatbot channel-linked answer processing for the user's chatbot query is processed. A chatbot integration agent platform service method for chatbot channel linkage integration, characterized in that at least one client chatbot channel is selected.
12. The method of claim 11,
The chatbot channel knowledge management DB classifies and stores and manages at least one client chatbot channel for each client chatbot service field category in order to link the client chatbot through the chatbot integrated agent platform. Chatbot integration agent platform service method for channel-linked integration.
8. The method of claim 7,
In step (f), each client chatbot uses its own chatbot engine module and chatbot answer knowledge DB to convert the chatbot query content of the user sent in step (e) to the text corresponding to the chatbot query content of the user. After generating the Q&A content in the form of a chatbot, the chatbot for channel linkage integration, characterized in that the generated Q&A content in the text form is transmitted to the unified interface module provided in the chatbot unified agent platform through the corresponding common API. How to service the Unified Agent Platform.
A computer-readable recording medium in which a program capable of executing the method of any one of claims 7 to 13 by a computer is recorded.

Images