KR101891496B1 - Interactive ai agent system and method for actively monitoring and joining a dialogue session among users, computer readable recording medium - Google Patents

Abstract

A method of monitoring and intervening a multi-user chat session provided by an interactive AI agent system is provided. The method of the present invention comprises the steps of: receiving a user input from each of a plurality of users during a chat session, the user input being a chat input received between a plurality of users; Determining whether an interactive AI agent system is to intervene in a conversation session based on a predetermined user intention, and in response to the interactive AI agent system determining to engage in a conversation session, And providing, via the chat session, a chat response corresponding to a predetermined user intention.

Description

FIELD OF THE INVENTION [0001] The present invention relates to interactive AI agent systems, methods, and computer readable recording media for providing active monitoring and intervention of interactive sessions between users.

The present invention relates to active monitoring and intervention of an online chat session between users by an interactive AI agent system, and more particularly, to an interactive AI agent system that monitors an online chat session between users, To provide an appropriate service by self-determining whether to intervene or not, and to go out on its own without a separate explicit and specific request from the user.

Description of the Related Art [0002] In recent years, with the development of artificial intelligence fields, especially natural language understanding fields, it has become possible to move away from the machine operation according to the conventional machine-centered command input / output method and to allow users to use natural language in a more human-friendly manner such as voice and / The development and utilization of an interactive AI agent system (e.g., chatbot) that allows a machine to interact with an intermediary method and obtain a desired service from the machine is increasingly being developed. Accordingly, in various fields, including but not limited to, an online consultation center or an online shopping mall, a user may interact with the interactive AI agent system through natural language conversation in the form of voice and / or text, You can ask and get the results you want from it. In recent years, there has been an increase in the number of interactive AI agent systems that are specialized for each specialized field such as financial, legal, medical, and public sectors, and build a knowledge system that meets the relevant field and provide more accurate service accordingly.

Meanwhile, with the spread of smart phones, the use of various instant messenger services has also increased explosively, and a large part of the conversation in people's lives is now performed through instant messages. Instant messages allow people to communicate with one or more remote parties in real-time on a variety of topics. More recently, in recent years, there has been an increasing number of cases where an instant messenger service is combined with an interactive AI agent system so that people can obtain desired information or services from an interactive AI agent system as if they are talking to a friend through an instant message .

Patent Document 1: Korean Patent Application No. 10-2015-0175948

However, until now, when the user wants to use the interactive AI agent system, the user has to actively and explicitly request the interactive AI agent system for the desired information or service. In particular, if a user feels the need to provide a service from the interactive AI agent system while a user is in conversation with another user through a predetermined online chat session, the user may pause the existing chat session, A dialog session with the agent system (that is, a dialog session between the user and the interactive AI agent system) must be separately opened and the desired information or service should be explicitly requested for the interactive AI agent system. This process not only leads to interruption of existing conversations but also involves troublesome procedures, which is inconvenient for users.

According to one aspect of the present invention there is provided a method of monitoring and intervening a multi-user chat session provided by an interactive AI agent system. The method of the present invention comprises the steps of: receiving a user input from each of a plurality of users during a chat session, the user input being a chat input received between a plurality of users; Determining whether an interactive AI agent system is to intervene in a conversation session based on a predetermined user intention, and in response to the interactive AI agent system determining to engage in a conversation session, And providing, through the conversation session, a conversation response that corresponds to a predetermined user intention.

According to one embodiment of the present invention, the step of determining whether or not the interactive AI agent system will intervene in the conversation session, based on a predetermined user intention, . ≪ / RTI >

According to one embodiment of the present invention, the step of determining whether or not the interactive AI agent system will intervene in the conversation session, based on a predetermined user intention, comprises the steps of: And determining whether service provision is required.

According to one embodiment of the present invention, the step of determining whether an interactive AI agent system will intervene in a conversation session based on a predetermined user intention may comprise: determining, by an interactive AI agent system And determining whether to make a call.

According to one embodiment of the present invention, the step of determining, based on a predetermined user intention, whether the interactive AI agent system is to intervene in a conversation session comprises acquiring explicit consent from at least one user of the plurality of users The method comprising the steps of:

According to one embodiment of the present invention, the predetermined service may include at least one of a predetermined information search, a predetermined settlement or remittance service, and a predetermined application execution service.

According to an embodiment of the present invention, the step of providing the conversation response meeting the predetermined user's intention may include the step of performing the service provision corresponding to the predetermined user's intention through the conversation session.

According to an embodiment of the present invention, the multi-user chat session may be a chat session established through the instant messenger service server.

According to one embodiment of the present invention, the talk session may be configured to be monitored by the interactive AI agent system for the talk session.

According to another aspect of the present invention there is provided a computer-readable medium having stored thereon one or more instructions that, when executed for a computer, cause the computer to perform the method of any of the methods described above , A computer-readable recording medium is provided.

According to another aspect of the present invention, there is provided an interactive AI agent system configured to provide monitoring and intervention for a multi-user chat session. The interactive AI agent system of the present invention includes a communication module, an NLU module, and a conversation session monitoring / intervention module. The communication module of the present invention is configured to receive a user input from each of a plurality of users during a chat session, wherein the user input is a chat input received between a plurality of users, and the NLU module receives, Wherein the interactive session monitoring / intervention module is configured to determine, based on a predetermined user intent, whether the interactive AI agent system is to intervene in the conversation session, and wherein the communication module In response to the interactive AI agent system determining to engage in a chat session, through the chat session, to provide a chat response that is consistent with a predetermined user intent.

According to the present invention, a user can instantly access desired information or services from an interactive AI agent system without actively opening a separate conversation session or making a specific request during a conversation with another user via an online chat session Can be obtained. According to the present invention, since the interactive AI agent system operates as if it is another human user participating in a dialog between users, the user can conveniently obtain an appropriate service in a timely manner.

1 is a schematic diagram of a system environment in which an interactive AI agent system may be implemented, according to one embodiment of the present invention.
FIG. 2 is a functional block diagram that schematically illustrates the functional configuration of the user terminal 102 of FIG. 1, in accordance with one embodiment of the present invention.
3 is a functional block diagram that schematically illustrates the functional configuration of the interactive AI agent server 108 of FIG. 1, in accordance with one embodiment of the present invention.
4 is a flow chart illustrating an exemplary method for monitoring a chat session between users via an online chat service server 106 and providing services thereon, performed by an interactive AI agent server 108, in accordance with an embodiment of the present invention Fig.
FIG. 5 is a flow chart illustrating an example of an interactive AI agent server 108 intervening in a chat session between users via an online chat service server 106 and providing a predetermined service on the chat session according to an embodiment of the present invention This is an example dialog window.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. Hereinafter, when it is determined that there is a possibility that the gist of the present invention may be unnecessarily blurred, a detailed description of known functions and configurations will be omitted. In addition, it should be understood that the following description is only an embodiment of the present invention, and the present disclosure is not limited thereto.

The terminology used in this disclosure is used only to describe a specific embodiment and is not used to limit the invention. For example, an element expressed in singular < Desc / Clms Page number 5 > terms should be understood as including a plurality of elements unless the context clearly dictates a singular value. It is to be understood that the term "and / or" as used in this disclosure encompasses any and all possible combinations of one or more of the listed items. It should be understood that the terms " comprises " or " having ", etc. used in the present disclosure are intended to specify that there exist features, numbers, steps, operations, elements, It is not intended to exclude the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof, by use.

As used herein, the term " module " or " module " means a functional part that performs at least one function or operation, and may be implemented by hardware or software or a combination of hardware and software. Also, a plurality of "modules" or "sub-modules" may be integrated into at least one software module and implemented by at least one processor, except for "module" or "sub-module" have.

In the embodiment of the present invention, the 'interactive AI agent system' is a system in which a user interacts with a user via a natural word input (for example, a natural language) input from a user through interactive interaction via a natural language of voice and / (E.g., commands, statements, requests, questions, etc. from the user) to determine the intent of the user and to perform the necessary actions based on the user's intent, i.e., , And is not limited to any particular form of information processing system.

In an embodiment of the present invention, the interactive response provided by the " interactive AI agent system " may be in the form of a visual, auditory and / or tactile (e.g., voice, sound, text, video, image, symbol, emoticon, hyperlink, Animation, various notices, motion, haptic feedback, and the like), and the like. In the embodiment of the present invention, the task performed by the 'interactive AI agent system' may include, for example, searching for information, proceeding with a payment, composing a message, composing an email, dialing, playing music, photographing, (E.g., but not limited to) various types of tasks, including, but not limited to, navigation services, and the like.

In the embodiment of the present invention, the 'interactive AI agent system' is specialized for a general purpose interactive AI agent system designed for providing general information based on general purpose knowledge and for each specialized field such as finance, law, It should be noted that the system may include all kinds of specialized interactive AI agent systems that provide a more accurate service in accordance with the establishment of a knowledge system that meets the relevant field of expertise.

In addition, all terms used in the present disclosure, including technical or scientific terms, unless otherwise defined, have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It should be understood that commonly used predefined terms are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are not to be interpreted excessively or extensively unless explicitly defined otherwise in this disclosure .

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a schematic diagram of a system environment 100 in which an interactive AI agent system may be implemented, in accordance with one embodiment of the present invention. The system environment 100 includes a plurality of user terminals 102a-102n, a communication network 104, an online conversation service server 106, an interactive AI agent server 108, and an external service server 110 ).

According to one embodiment of the present invention, each of the plurality of user terminals 102a-102n may be any user electronic device having wired or wireless communication capability. Each of the user terminals 102a-102n may be a variety of wired or wireless communication terminals including, for example, a smart phone, a tablet PC, a music player, a smart speaker, a desktop, a laptop, a PDA, a game console, a digital TV, It is to be understood that the invention is not limited to any particular form.

According to one embodiment of the present invention, each of the user terminals 102a-102n can communicate with the on-line conversation service server 106 via the communication network 104, i.e., send and receive necessary information. In accordance with one embodiment of the present invention, each of the user terminals 102a-102n may communicate with one or more other user terminals 102a-102n via a communication network 104 and an online chat service server 106, And interact with one or more other user terminals 102a-102n in a voice and / or text manner via established chat sessions. In accordance with one embodiment of the present invention, each of the user terminals 102a-102n receives user input in the form of voice and / or text from the outside and establishes it via the communication network 104 and online conversation service server 106 Through the chat session, the user input may be provided to other user terminals 102a-102n participating in the chat session.

According to one embodiment of the present invention, each of the user terminals 102a-102n can communicate with the interactive AI agent server 108 through the communication network 104, i.e., send and receive necessary information. According to an embodiment of the present invention, each of the user terminals 102a-102n can communicate with the external service server 110 through the communication network 104, that is, send and receive necessary information. In accordance with one embodiment of the invention, each of the user terminals 102a-102n may receive user input in the form of voice, text and / or touch from the outside, and may interact with an interactive AI agent server (E.g., providing a specific conversation response and / or providing a result) corresponding to the upper user input obtained through communication with the external service server 110 (e.g., the user terminal 102a-108) and / Execution of a specific task, etc.) to the user.

In the embodiment of the present invention, task execution as an operation corresponding to a user input may be performed by, for example, searching for information, transferring a payment or proceeding with payment, writing an SMS message, creating an email, dialing, playing music, / ≪ / RTI > navigation service, and the like. ≪ RTI ID = 0.0 > In accordance with one embodiment of the present invention, each of the user terminals 102a-102n may provide a dialog response as a result of an operation corresponding to a user input, in a visual, audible and / or tactile form (e.g., Images, symbols, emoticons, hyperlinks, animations, various notices, motion, haptic feedback, and the like), and the like.

According to one embodiment of the present invention, the communication network 104 may include any wired or wireless communication network, e.g., a TCP / IP communication network. According to an embodiment of the present invention, the communication network 104 may include, for example, a Wi-Fi network, a LAN network, a WAN network, an Internet network, and the like, and the present invention is not limited thereto. In accordance with one embodiment of the present invention, the communication network 104 may be any of a variety of wired or wireless, such as Ethernet, GSM, EDGE, CDMA, TDMA, OFDM, Bluetooth, VoIP, Wi- May be implemented using a communication protocol.

According to one embodiment of the present invention, the online conversation service server 106 may communicate with the user terminals 102a-102n via the communication network 104. [ In accordance with one embodiment of the present invention, the online conversation service server 106 may communicate with one or more of the user terminals 102a-102n in response to a request received from the user terminals 102a-102n via the communication network 104, Establish a chat session between a plurality of other user terminals 102a-102n and allow a real-time chat to proceed between the user terminals 102a-102n participating in the chat session. According to one embodiment of the present invention, the online conversation service server 106, when establishing a chat session between the user terminals 102a-102n in response to a request from the user terminals 102a-102n, It is possible to determine whether or not to use one or a plurality of interactive AI agents (interactive AI agent specific to each general purpose or specialty field) for the conversation session (in this case, a conversation session Monitoring, intervention, etc., will be performed if selected to use the interactive AI agent system at the time of establishing the chat session). In accordance with one embodiment of the present invention, the user input in voice and / or text form received on each user terminal 102a-102n is communicated via the communication network 104 and the conversation session established via the online conversation service server 106 To other user terminals 102a-102n participating in the talk session. According to an embodiment of the present invention, the online conversation service server 106 may be an instant messenger service server.

In accordance with one embodiment of the present invention, the interactive AI agent server 108 may communicate with the user terminals 102a-102n via the communication network 104. [ In accordance with one embodiment of the present invention, the interactive AI agent server 108 receives user input in the form of voice, text, and / or touch, for example, from the user terminals 102a-102n via the communication network 104, The received user input may be processed based on the prepared knowledge models to determine the user's intent. In accordance with one embodiment of the present invention, the interactive AI agent server 108 may generate and send a specific interactive response, e.g., consistent with the user's intent, to the user terminals 102a-102n.

According to one embodiment of the present invention, the interactive AI agent server 108 monitors a chat session between the user terminals 102a-102n via the online chat service server 106, e.g., via the communications network 104 , And may receive each user natural language input received and transmitted between user terminals 102a-102n on the chat session. According to one embodiment of the present invention, the interactive AI agent server 108 may process the received natural language input based on previously prepared knowledge models to determine the intent of each user.

In accordance with one embodiment of the present invention, the interactive AI agent server 108 may provide an interactive response that matches the user's intent obtained from the chat session between the user terminals 102a-102n via the online chat service server 106 And intervene in the conversation session to provide the generated conversation response.

According to one embodiment of the present invention, the interactive AI agent server 108 generates an interactive response corresponding to the determined user intention in the form of voice and / or text, and transmits the generated response via the communication network 104 , User terminals 102a-102n, and / or online conversation service server 106. [ According to one embodiment of the present invention, the interactive response generated by the interactive AI agent server 108 may include other visual elements such as images, video, symbols, emoticons, etc., Or other auditory elements such as sound, or other tactile elements. In accordance with one embodiment of the present invention, the same type of response (e. G., On the interactive AI agent server 108) is performed on the interactive AI agent server 108 according to the type of user input received on the user terminal 102a- (E.g., a voice response is generated if a voice input is given and a text response is generated if a text input is given), but the present invention is not limited thereto. It should be noted that according to another embodiment of the present invention, responses in the form of voice and / or text may be generated and provided irrespective of the type of user input.

According to one embodiment of the present invention, the interactive AI agent server 108 may cause a task corresponding to the determined user intention to be performed. In accordance with one embodiment of the present invention, the interactive AI agent server 108 generates a specific control signal such that, for example, a particular task corresponding to the user's intent is performed on the user terminal 102a-102n, 102n. In accordance with one embodiment of the present invention, the interactive AI agent server 108 intervenes in a chat session between, for example, the user terminals 102a-102n via the online chat service server 106, It is possible to allow a specific task execution procedure to proceed. According to the present invention, the interactive AI agent server 108 can access the external service server 110 through the communication network 104 to perform a specific task corresponding to the user's intention.

According to an embodiment of the present invention, the interactive AI agent server 108 may communicate with the external service server 110 via the communication network 104, as described above. The external service server 110 may be, for example, an online consultation center server, a financial service server, a legal service server, a medical service server, an online shopping mall server, an information search server, a map service server, a navigation service server, It is not. According to one embodiment of the present invention, the response based on the user's intention, which is transmitted from the interactive AI agent server 108 to the user terminals 102a-102n and / or the online conversation service server 106, And may include data content retrieved and obtained from content provider 110.

Although the interactive AI agent server 108 is shown as being a separate physical server configured to communicate with the external service server 110 via the communication network 104, the present disclosure is not limited thereto. According to another embodiment of the present invention, the interactive AI agent server 110 may include, for example, an online consultation center server, a financial service server, a legal service server, a medical service server, an online shopping mall server, A service server, and the like, as a part of various service servers.

2 is a functional block diagram that schematically illustrates the functional configuration of the user terminal 102 shown in FIG. 1, in accordance with one embodiment of the present invention. The user terminal 102 includes a user input receiving module 202, a sensor module 204, a program memory module 206, a processing module 208, a communication module 210, 212).

According to an embodiment of the present invention, the user input receiving module 202 may receive various types of input from a user, for example, a natural language input such as a voice input and / or a text input (and additionally, Can be received. According to one embodiment of the present invention, the user input receiving module 202 includes, for example, a microphone and an audio circuit, and can acquire a user audio input signal through a microphone and convert the obtained signal into audio data. According to an embodiment of the present invention, the user input receiving module 202 may include various types of input devices such as various pointing devices such as a mouse, a joystick, and a trackball, a keyboard, a touch panel, a touch screen, , And can acquire a text input and / or a touch input signal inputted from a user through these input devices. According to one embodiment of the present invention, the user input received at the user input receiving module 202 may be associated with performing a predetermined task, such as performing a predetermined application or searching for certain information, etc. However, It is not. According to another embodiment of the present invention, the user input received by the user input receiving module 202 may be for simple conversation progression regardless of execution of a predetermined application or retrieval of information.

In accordance with one embodiment of the present invention, the sensor module 204 includes one or more different types of sensors through which the status information of the user terminal 102, such as the physical state of the user terminal 102, Software and / or hardware status, or information regarding the environmental conditions of the user terminal 102, and the like. According to an embodiment of the present invention, the sensor module 204 may include an optical sensor, for example, and may sense the ambient light condition of the user terminal 102 through the optical sensor. According to an embodiment of the present invention, the sensor module 204 includes, for example, a movement sensor and can detect whether the corresponding user terminal 102 is moving through the movement sensor. According to one embodiment of the present invention, the sensor module 204 includes, for example, a velocity sensor and a GPS sensor, and through these sensors, the position and / or orientation of the corresponding user terminal 102 can be detected. In accordance with another embodiment of the present invention, it should be appreciated that the sensor module 204 may include other various types of sensors, including temperature sensors, image sensors, pressure sensors, touch sensors, and the like.

According to one embodiment of the present invention, the program memory module 206 may be any storage medium that stores various programs that may be executed on the user terminal 102, such as various application programs and related data. In accordance with one embodiment of the present invention, program memory module 206 may include, for example, an instant messaging application, a dialer application, an email application, a camera application, a music playback application, a video playback application, an image management application, , And data related to the execution of these programs. According to one embodiment of the present invention, the program memory module 206 may be configured to include various types of volatile or non-volatile memory such as DRAM, SRAM, DDR RAM, ROM, magnetic disk, optical disk, .

According to one embodiment of the present invention, the processing module 208 may communicate with each component module of the user terminal 102 and perform various operations on the user terminal 102. According to one embodiment of the present invention, the processing module 208 can drive and execute various application programs on the program memory module 206. [ According to one embodiment of the present invention, the processing module 208 may receive signals from the user input receiving module 202 and the sensor module 204, if necessary, and perform appropriate processing on these signals have. According to one embodiment of the present invention, the processing module 208 may, if necessary, perform appropriate processing on signals received from the outside via the communication module 210.

According to one embodiment of the present invention, the communication module 210 is configured to allow the user terminal 102 to communicate with the online conversation service server 106, the interactive AI agent server 108 and / Or to communicate with the external service server 110. In accordance with one embodiment of the present invention, the communication module 210 may be configured to receive signals from, for example, the user input receiving module 202 and the sensor module 204 via the communication network 104 in accordance with a predetermined protocol, The interactive AI agent server 108, and / or the external service server 110, as described above. According to one embodiment of the present invention, the communication module 210 may receive (or receive) information from, for example, the online conversation service server 106, the interactive AI agent server 108 and / or the external service server 110 via the communication network 104 A response signal including a natural language response in the form of voice and / or text, or various control signals, and perform appropriate processing according to a predetermined protocol.

According to an embodiment of the present invention, the response output module 212 may output a response corresponding to a user input in various forms such as time, auditory, and / or tactile sense. According to one embodiment of the present invention, the response output module 212 includes various display devices such as a touch screen based on technology such as LCD, LED, OLED, QLED, and the like, Such as text, symbols, video, images, hyperlinks, animations, various notices, etc., to the user. According to one embodiment of the present invention, the response output module 212 may include, for example, a speaker or a headset and may provide an audible response, e.g., voice and / or acoustic response corresponding to user input, can do. According to one embodiment of the present invention, the response output module 212 includes a motion / haptic feedback generator, through which a tactile response, e.g., motion / haptic feedback, can be provided to the user. In accordance with one embodiment of the present invention, it should be appreciated that the response output module 212 may simultaneously provide any combination of two or more of a text response, a voice response, and a motion / haptic feedback corresponding to a user input.

3 is a functional block diagram that schematically illustrates the functional configuration of the interactive AI agent server 108 of FIG. 1, in accordance with one embodiment of the present invention. The interactive agent server 108 includes a communication module 302, a Speech-To-Text (STT) module 304, a Natural Language Understanding (NLU) module 306 A dialogue understanding knowledge base 308, a user database 310, a conversation session monitoring / interposing unit 312, a dialogue management module 314, a dialogue generation module 316, and a text-to-speech TTS < / RTI >

According to one embodiment of the present invention, the communication module 302 is configured to communicate with the interactive AI agent server 108 via the communication network 104 in accordance with a predetermined wired or wireless communication protocol using the user terminal 102, To communicate with the service server 106 and / or the external service server 110. According to one embodiment of the present invention, the communication module 302 is configured to communicate with the user terminal 102 and / or the online conversation service server 106 via the communication network 104, Voice input and / or text input, and the like). In accordance with one embodiment of the present invention, the communication module 302 includes a user terminal 102 that has been transmitted from the user terminal 102 or the like, via the communication network 104, with or without the user input described above, Can be received. According to one embodiment of the present invention, the state information may include various state information (e.g., the physical state of the user terminal 102, the software of the user terminal 102) related to the user terminal 102 at the time of user input And / or hardware state, environmental state information around the user terminal 102, etc.). In accordance with one embodiment of the present invention, the communication module 302 may also include an interactive response (e. G., A native < / RTI & And / or control signals to the user terminal 102 and / or the online conversation service server 106 via the communication network 104. The user terminal 102 and /

According to one embodiment of the present invention, the STT module 304 may receive speech input from user input received via the communication module 302 and convert the received speech input into text data based on pattern matching and the like have. According to one embodiment of the present invention, the STT module 304 may extract a feature from a user's speech input to generate a feature vector sequence. According to an exemplary embodiment of the present invention, the STT module 304 may be implemented by a DTW (Dynamic Time Warping) method, an HMM model (Hidden Markov Model), a GMM model (Gaussian-Mixture Mode), a deep neural network model, For example, a sequence of words, based on various statistical models of the speech recognition results. According to one embodiment of the present invention, the STT module 304 can refer to each user characteristic data of the user database 310, which will be described later, when converting the received voice input into text data based on pattern matching .

According to one embodiment of the present invention, the NLU module 306 may receive text input from the communication module 302 or the STT module 304. In accordance with one embodiment of the present invention, the textual input received at the NLU module 306 may be received from the user terminal 102 and / or the online conversation service server 106 via the communication network 104, May be a text recognition result, e.g. a sequence of words, generated in the STT module 304 from a received user text input or a user speech input received from the communication module 302. [ In accordance with one embodiment of the present invention, the NLU module 306 may include status information associated with the user input, such as with or after receipt of the text input, e.g., status information of the user terminal 102 at the time of the user input And the like. As described above, the status information may include various status information (e.g., the physical state of the user terminal 102, the software status of the user terminal 102) associated with the user terminal 102 at the time of user input and / And / or hardware state, environmental state information around the user terminal 102, etc.).

According to one embodiment of the present invention, the NLU module 306 may map the received text input to one or more user intents based on a dialog understanding knowledge base 308, which will be described later. Where the user intent can be associated with a series of operations (s) that can be understood and performed by the interactive AI agent server 108 according to the user intention. According to one embodiment of the present invention, the NLU module 306 may refer to the status information described above in associating the received text input with one or more user intentions. According to one embodiment of the present invention, the NLU module 306 may refer to each user characteristic data of the user database 310, which will be described later, in mapping the received text input to one or more user intentions.

According to one embodiment of the present invention, the conversation understanding knowledge base 308 may include, for example, a predefined ontology model. According to one embodiment of the present invention, an ontology model can be represented, for example, in a hierarchical structure between nodes, where each node is associated with an "intention" node corresponding to the user & Node (a sub-attribute node directly linked to an "intent" node or linked back to an "attribute" node of an "intent" node). According to one embodiment of the present invention, " attribute "nodes directly or indirectly linked to an" intention "node and its" intent "node may constitute one domain, and an ontology may be composed of such a set of domains . According to one embodiment of the present invention, the conversation understanding knowledge base 308 may be configured to include domains corresponding to all intents, for example, an interactive AI agent system that can understand and perform corresponding actions have. According to one embodiment of the present invention, it should be noted that the ontology model can be dynamically changed by addition or deletion of nodes or modification of relations between nodes.

According to one embodiment of the present invention, the intention nodes and attribute nodes of each domain in the ontology model may be associated with words and / or phrases associated with corresponding user intents or attributes, respectively. According to one embodiment of the present invention, the conversation understanding knowledge base 308 includes an ontology model 308, which includes an ontology model, for example, a dictionary form (consisting of a set of words and / or phrases associated with each node, , And the NLU module 306 can determine the user's intention based on the ontology model implemented in the lexical dictionary form. For example, according to one embodiment of the present invention, the NLU module 306, upon receipt of a text input or a sequence of words, can determine which of the domains in the ontology model each word in the sequence is associated with, Based on such a determination, the corresponding domain, i.e. the user intent, can be determined.

According to an embodiment of the present invention, the user database 310 may be a database for storing and managing characteristic data for each user. According to an embodiment of the present invention, the characteristic data for each user included in the user database 310 may include, for example, previous conversation / behavior record of the user for each user, pronunciation feature information of the user, user lexical preference, , A set language, a contact / buddy list, and various other user-specific information.

In accordance with one embodiment of the present invention, as described above, the STT module 304 may be configured to refer to each user characteristic data of the user database 310, e.g., pronunciation characteristics for each user, , More accurate text data can be obtained. According to one embodiment of the present invention, the NLU module 306 determines each user characteristic data of the user database 310, for example, characteristics or contexts of each user, . According to one embodiment of the present invention, as described below, the dialog generation module 316 may refer to user characteristic data of the user database 310 at the time of generating the conversation response.

In this figure, a user database 310 for storing and managing characteristic data for each user is shown as being arranged in the interactive AI agent server 108, but the present invention is not limited thereto. According to another embodiment of the present invention, the user database 310, which stores and manages characteristic data for each user, may reside, for example, at the user terminal 102, and may include a user terminal 102 and an interactive AI agent server 108 As shown in FIG.

In accordance with one embodiment of the present invention, the conversation session monitoring / interposing unit 312 is configured to monitor each conversation item on the conversation session established between the plurality of user terminals 102 via the online conversation service server 106, Input can be monitored. In accordance with one embodiment of the present invention, the conversation session monitoring / intervening unit 312 is configured to monitor, on a chat session between a plurality of user terminals 102 via the online chatting service server 106, May determine each corresponding user intent obtained from the NLU module 306 based on the talk item, i.e., each user input.

According to one embodiment of the present invention, the conversation session monitoring / intervening unit 312 may determine, based on the user's intention, whether the interactive AI agent server 108 is in a situation where it should intervene in the conversation session. According to one embodiment of the present invention, the above-described determination by the conversation session monitoring / intervening unit 312 can be made based on whether or not a predetermined (pre-registered) condition is met or based on a neural network scheme. According to one embodiment of the present invention, the situation in which the interactive AI agent server 108 intervenes in the conversation session may be determined, for example, whether the user intention needs to provide a predetermined service by the interactive AI agent server 108 It can be decided according to whether or not. In accordance with one embodiment of the present invention, the interactive AI agent server 108 is configured to interact with a user agent 102 that corresponds to a predetermined user input obtained on a chat session between a plurality of user terminals 102, If the user intends to search for specific information, send a certain amount of money to a particular person, or desire execution of a particular application (but the invention is not limited thereby) It can be determined in advance that it should be provided.

According to one embodiment of the present invention, the conversation session monitoring / interposing unit 312 is configured to allow the interactive AI agent server 108 to intervene in the conversation session based on the user intent according to the predetermined user input obtained on the conversation session The dialog response and the like generated by the dialog management module 314 and the dialog generation module 316 and the like to be described later may be provided on the corresponding conversation session through the online conversation service server 106. [

According to one embodiment of the present invention, the dialogue management module 314 may generate a series of operational flows corresponding to the user intent determined by the NLU module 306. [ In accordance with one embodiment of the present invention, the conversation management module 314 may perform certain actions based on a predetermined conversation flow management model, e.g., in response to the user's intent received from the NLU module 306, e.g., Or to perform a task execution, and to generate a corresponding detailed operation flow.

In accordance with one embodiment of the invention, the dialog generation module 316 may generate an interaction response to be provided to the user based on the conversation flow generated by the conversation management module 314. According to one embodiment of the present invention, the dialog generation module 316, in generating the conversation response, generates user characteristic data (e.g., the user's previous conversation history, user's pronunciation feature information, A user's lexical preference, a user's location, a set language, a contact / friend list, and a previous conversation record of the user for each user).

In accordance with one embodiment of the present invention, the TTS module 318 may receive an interactive response that is generated by the dialog generation module 316 to be transmitted to the user terminal 102. The conversation response received at the TTS module 318 may be a natural word or a sequence of words having a textual form. According to one embodiment of the present invention, the TTS module 318 may convert the input of the above received text form into speech form according to various types of algorithms.

In the embodiment of the present invention described above with reference to FIGS. 1 to 3, when the interactive AI agent system is configured such that the user terminal 102 and the interactive AI agent server 108 are in a client-server model, And other all functions of the interactive AI agent system are described as being implemented based on the so-called "thin client-server model" delegated to the server, but the present invention is not limited thereto. According to another embodiment of the present invention, it should be understood that the interactive AI agent system may be implemented as a distributed application between the user terminal and the server, or as a stand-alone application installed on the user terminal . In addition, when the interactive AI agent system implements the functions of the interactive AI agent system distributed between the user terminal and the server according to an embodiment of the present invention, the distribution of each function of the interactive AI agent system between the client and the server is It should be understood that the invention may be otherwise embodied. In addition, although in the embodiments of the present invention described above with reference to FIGS. 1 to 3, the specific module has been described as performing certain operations for convenience, the present invention is not limited thereto. According to another embodiment of the present invention, it is to be understood that the operations described as being performed by any particular module in the above description may be performed by separate and distinct modules, respectively.

4 is a flow chart illustrating an exemplary method for monitoring a chat session between users via an online chat service server 106 and providing services thereon, performed by an interactive AI agent server 108, in accordance with an embodiment of the present invention Fig.

At step 402 the interactive AI agent server 108 receives user input from each user terminal 102 on a chat session established between two or more user terminals 102 via the online chat service server 106 . In accordance with one embodiment of the present invention, the received user input may be text and / or voice input received on each corresponding user terminal 102.

At step 404, the interactive AI agent server 108 may analyze the user input obtained at step 402 and determine a corresponding user intention. According to one embodiment of the present invention, the interactive AI agent server 108 may map each user input to one or more user intentions based on a predetermined knowledge base. According to one embodiment of the present invention, the interactive AI agent server 108 may be specialized for a particular field of specialization. In such a case, the knowledge base of the interactive AI agent server 108 is specialized for the particular field of interest and can be used to more accurately determine the user intent associated with the field.

At step 406, the interactive AI agent server 108 may determine, based on the acquired user intent, whether the interactive AI agent server 108 is in a situation where it should intervene in the chat session. As described above, according to an embodiment of the present invention, the situation in which the interactive AI agent server 108 intervenes in the conversation session may be determined, for example, And can be determined depending on whether or not it needs to be provided. According to one embodiment of the present invention, for example, the intention of the user corresponding to the user input obtained on the conversation session between the plurality of user terminals 102 via the online conversation service server 106 is determined by searching for specific information, It should be noted that the present invention is not limited to the above case in which the user desires to transfer money or to execute a specific application by intervening in the conversation session to provide necessary services.

For example, while a user A and B are exchanging daily conversations on a chat session through the online chat service server 106, when A refers to a particular news article to B, but B answers the article If it does not know, but intends to know, the conversation session monitoring / interceptor 312 may determine that the interactive AI agent server 108 is involved in the conversation session and needs to provide information for the news article. In such a case, according to one embodiment of the present invention, the interactive AI agent server 108 searches the article, intervenes in a chat session between the user terminals 102 via the online chat service server 106, It is possible to provide a corresponding news article link that is searched together with a response of " This article is an article. &Quot;

For example, when a user A and a user B talk on a predetermined conversation session while exchanging daily conversations, when a conversation between a user A and a user B receives a conversation such as "How far was yesterday?", "100,000 won" or " The intervention unit 312 may determine that the interactive AI agent server 108 is required to intervene in the conversation session and provide the remittance service. In such a case, according to one embodiment of the present invention, the interactive AI agent server 108 intervenes in a chat session between the user terminals 102 via the online chat service server 106 and sends a " And may proceed on the conversation session after obtaining a positive answer from the user and then transferring procedures (e.g., including but not limited to execution of a financial app).

If the interactive AI agent server 108 determines in step 406 that the interactive AI agent server 108 is not in a situation where it should intervene in the conversation session in light of the user's intent, the procedure returns to step 402 and the interactive AI agent server 108) can continue to monitor the conversation afterwards, maintaining silence without providing any response.

Alternatively, in step 406, in the light of the user's intent, if the interactive AI agent server 108 determines that it is in a situation that it should intervene in the conversation session, the procedure proceeds to step 408, Agent server 108 may generate a predetermined operational flow (which may include providing an interactive response and / or performing a task, etc.) that is consistent with the user's intent.

Interactive AI agent server 108 then determines at step 410 whether a chat session between user terminals 102 via online chat service server 106 is in accordance with the predetermined operational flow generated in step 408 above. To perform necessary conversation responses and / or service provisioning. In accordance with one embodiment of the present invention, the provision of services that can be performed on the conversation session by the interactive AI agent server 108 may include, for example, providing information retrieved from an external service server 110, (E.g., including, but not limited to, financial apps, map apps, navigation apps, etc.), but it should be understood that the invention is not so limited.

In the present specification, mainly, when the interactive AI agent server 108 determines that it is necessary to determine whether or not the interactive AI agent server 108 determines that the interactive AI agent server 108 needs to provide a predetermined service by the interactive AI agent server 108, It should be understood that the present invention is not limited thereto, although it is described that the inter-user talk session is intervened. According to another embodiment of the present invention, the interactive AI agent server 108 may be configured so that when a user calls a predetermined name (e.g., a name pre-determined to refer to the interactive AI agent) during a chat session, And may proceed to provide a predetermined response and / or service by intervening in the session. In this case, however, since the interactive AI agent server 108 has continuously performed monitoring of each user input of the conversation session, it means that the interactive AI agent server 108 receives the final confirmation of the intervention in the conversation session simply by the user's call , It should be noted that the user need not explicitly request the interactive AI agent server 108 again for the desired service. According to another embodiment of the present invention, when the interactive AI agent server 108 intends to intervene in a conversation session according to its own judgment to provide a predetermined service, the interactive AI agent server 108, before providing the corresponding service, The user may be asked to confirm whether or not the user wants to provide the service.

FIG. 5 is a flow chart illustrating an example of an interactive AI agent server 108 intervening in a chat session between users via an online chat service server 106 and providing a predetermined service on the chat session according to an embodiment of the present invention This is an example dialog window.

5A, the interactive AI agent server 108 is silent while monitoring the conversation contents during the conversation between the users A and B for an initial period of time. 5B, when the user A and the user A refer to the remittance of a predetermined amount, the interactive AI agent server 108 intervenes in a conversation session between them and sends a remittance service Ask if you want to, and listen to the consent of the user. 5 (c), the interactive AI agent server 108 presents a window for transfer progress during the conversation session. This allows the user to easily proceed with the remittance process without having to go through the current interruption or other inconveniences.

As will be appreciated by those skilled in the art, the present invention is not limited to the examples described herein, but can be variously modified, rearranged, and replaced without departing from the scope of the present invention. It should be understood that the various techniques described herein may be implemented in hardware or software, or a combination of hardware and software.

A computer program according to an embodiment of the present invention may be stored in a storage medium readable by a computer processor or the like such as a nonvolatile memory such as EPROM, EEPROM, flash memory device, a magnetic disk such as an internal hard disk and a removable disk, CDROM disks, and the like. Also, the program code (s) may be implemented in assembly language or machine language. And all changes and modifications that fall within the true spirit and scope of the present invention are intended to be embraced by the following claims.

Claims (11)

A method for monitoring and intervening a multi-user talk session provided by an interactive AI agent system,
Receiving a user input from each of the plurality of users during the chat session, the user input being a chat input sent between the plurality of users;
Determining a predetermined user intention corresponding to the user input based on a predetermined knowledge base,
Determining, based on the predetermined user intent, whether the interactive AI agent system is to intervene in the chat session; and
In response to the interactive AI agent system determining to engage in the chat session, providing, via the chat session, an chat response that matches the predetermined user intention
Lt; / RTI >
Wherein the step of determining whether or not the interactive AI agent system is to intervene in the conversation session based on the predetermined user intention may include determining whether the predetermined user intention needs to provide a predetermined service by the interactive AI agent server The method comprising the steps of: determining whether a multi-user talk session is interrupted or not. The method according to claim 1,
Wherein the step of determining, based on the predetermined user intention, whether the interactive AI agent system is to intervene in the conversation session comprises: determining whether to intervene in the conversation session based on whether a predetermined condition is met or based on a neural network scheme; Monitoring and intervention of chat sessions. delete The method according to claim 1,
Wherein the step of determining whether or not the interactive AI agent system will intervene in the conversation session based on the predetermined user intention comprises determining whether to invoke the interactive AI agent system by at least one user of the plurality of users Further comprising the step of determining whether the inter-user talk session is interrupted. The method according to claim 1,
Wherein determining, based on the predetermined user intent, whether the interactive AI agent system is to intervene in the chat session further comprises acquiring explicit consent from at least one user of the plurality of users A method for monitoring and intervening a multi-user chat session. The method according to claim 1,
Wherein the predetermined service comprises at least one of a predetermined information retrieval, a predetermined remittance or payment service, and a predetermined application execution service. The method according to claim 1,
Wherein providing the conversation response that meets the predetermined user intent comprises performing a service provision that meets the predetermined user intent through the conversation session. The method according to claim 1,
Wherein the multi-user chat session is a chat session established through an instant messenger service server. The method according to claim 1,
Wherein the conversation session is set to be monitored by the interactive AI agent system for the conversation session. A computer-readable medium having stored thereon one or more instructions,
Wherein the one or more instructions cause the computer to perform the method of any one of claims 1, 2, and 4 to 9 when executed on a computer. An interactive AI agent system configured to provide monitoring and intervention for a multi-user chat session,
Communication module,
NLU modules, and
Conversation session monitoring / intervention module
/ RTI >
Wherein the communication module is configured to receive a user input from each of the plurality of users during the chat session, the user input being a chat input sent between the plurality of users,
Wherein the NLU module is configured to determine a predetermined user intention corresponding to the user input based on a predetermined knowledge base,
Wherein the interactive session monitoring / intervention module is configured to determine whether the predetermined user intent requires a predetermined service provision by the interactive AI agent server, and based on the predetermined user intent, The system being configured to determine whether to engage in the conversation session,
Wherein the communication module is further configured to provide, via the chat session, an interactive response meeting the predetermined user's intent in response to the interactive AI agent system determining to engage in the chat session,
Interactive AI agent system.

Images