KR20190103927A - Interactive ai agent system and method for actively providing a security related service based on monitoring of a dialogue session among users via the dialogue session or a separate session, computer readable recording medium - Google Patents

Abstract

Provided is a method for monitoring a conversation session between a plurality of users and providing a service, which is provided by an interactive AI agent system. According to the present invention, the method comprises the steps of: separately receiving a user input from a plurality of users during a conversation session, wherein the user input is a conversation input which is transmitted and received between the users; determining a predetermined user intention corresponding to the user input on the basis of a predetermined knowledge base; determining whether to be a time point requiring provision of a service by an interactive AI agent system on the basis of the predetermined user intention, wherein the service is associated with performance of at least one task; determining whether the service is to be provided during the conversation session or through a separate session in response to determination of the time point requiring the provision of the service by the interactive AI agent system; and providing the service in response to determination on whether the service is to be provided during the conversation session or through the separate session.

Description

FIELD OF THE INTERACTIVE AI AGENT SYSTEM AND METHOD FOR Interactive AI Agent Systems, Methods, and Computer-readable Recording Media Providing Services Related to Security, Based on Monitoring of Interaction Sessions Between Users, and Proactively Through Conversation Sessions or Separate Sessions ACTIVELY PROVIDING A SECURITY RELATED SERVICE BASED ON MONITORING OF A DIALOGUE SESSION AMONG USERS VIA THE DIALOGUE SESSION OR A SEPARATE SESSION, COMPUTER READABLE RECORDING MEDIUM}

The present invention relates to monitoring an inter-user dialogue session by an interactive AI agent system and providing active services based on the same. More specifically, the interactive AI agent system monitors an inter-user dialogue session and provides a corresponding interactive AI agent. The present invention relates to a technology for actively determining whether a user needs a service from a system and actively providing a service required to a user in various ways without any explicit and specific request by the user.

In recent years, with advances in the field of artificial intelligence, in particular in the field of understanding natural language, the user has moved away from the operation of the traditional machine-oriented command input / output schemes, thereby allowing users to use natural language in a more human-friendly manner, such as speech and / or text. Increasingly, the development and use of interactive AI agent systems (e.g., chatbots), which enable the operator to operate the machine in a mediated manner and obtain the desired service from the machine. Accordingly, in a variety of fields, including but not limited to online counseling centers, online shopping malls, and the like, the user can provide the desired information or service to the interactive AI agent system through natural language conversations in the form of voice and / or text. You can request and get the results you want from it. In particular, recently, a growing number of interactive AI agent systems have been developed that are specialized in each specialized field such as finance, legal, medical, and public sectors to build a knowledge system that matches the specialty and provide more accurate services.

Meanwhile, as the spread of smart phones has increased, the use of various instant messenger services has exploded, and now a large part of people's conversations in their lives is being made through instant messages. Instant messages allow people to communicate on a variety of topics in real time with one or more remote parties. In particular, in recent years, an instant messenger service has been increasingly combined with an interactive AI agent system to allow people to obtain desired information or services from the interactive AI agent system as if they are talking to a friend through instant messages. .

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

Up to now, however, when using the interactive AI agent system via instant message, the user opens a conversation session with a specific interactive AI agent system (that is, a conversation session between the user and the interactive AI agent) and opens the interactive AI. You must make a direct request for the information or service you want for the agent system. Therefore, if a user wants to obtain certain information or services from the interactive AI agent system in relation to the contents of the conversation during the conversation with another user, the user actively starts the conversation and stops the interactive AI agent. You must open a separate chat session with the system and explicitly and specifically request the information or service you want. This process not only causes interruption of the existing conversation but also involves cumbersome procedures, which is inconvenient for the user.

According to one aspect of the present invention, there is provided a method for monitoring and providing a service between a plurality of user conversation sessions provided by an interactive AI agent system. The method of the present invention includes receiving user input from each of a plurality of users during a chat session, wherein the user input is a conversation input to and from a plurality of users, based on a predetermined knowledge base, the predetermined input corresponding to the user input. Determining a user intent, determining, based on the predetermined user intent, whether it is time to provide a service by the interactive AI agent system, wherein the service is associated with performing one or more tasks; In response to determining that the service is to be provided by the system, determining whether the service will be provided in a chat session or through a separate session, and whether the service will be provided during a chat session or a separate session. Providing a service according to the decision of whether to provide the It includes.

According to an embodiment of the present invention, the step of determining whether the service will be provided in a conversation session or through a separate session may be performed based on the type of service.

According to an embodiment of the present invention, the step of determining whether the service will be provided in a conversation session or through a separate session may be determined according to whether the service requires a security.

According to one embodiment of the invention, providing a service according to determining whether the service will be provided during a chat session or through a separate session, performing one or more tasks associated with the service, It may include providing the results of the above task performed in a chat session or a separate session.

According to one embodiment of the invention, depending on whether the service is to be provided during a chat session or through a separate session, providing the service comprises: performing one or more tasks associated with the service, Providing access to a given external server during a chat session or a separate session.

According to one embodiment of the invention, providing access to a given external server may include providing a link to the external server.

According to one embodiment of the invention, providing access to a given external server comprises providing a link for execution of a given application, where the given application provides access to the given external server. It may include.

According to one embodiment of the invention, providing access to a given external server may include invoking a given application, where the given application provides access to a given external service server. .

According to another feature of the invention, A computer readable recording medium comprising one or more instructions, wherein the one or more instructions, when executed for a computer, cause the computer to perform any one of the methods described above. do.

According to another feature of the invention, there is provided an interactive AI agent system configured to provide monitoring and intervention for a conversation session between multiple users. The interactive AI agent system of the present invention includes a communication module, an NLU module, and a conversation session monitoring module. The communication module of the present invention is configured to receive user input from each of a plurality of users during a chat session, wherein the user input is a conversation input to and from a plurality of users, and the NLU module is based on a predetermined knowledge base. It is configured to determine a predetermined user intention corresponding to the, the chat session monitoring module determines whether it is a point in time to provide a service by the interactive AI agent system, and is said to be a point in time to provide a service by the interactive AI agent system In response to the determination, the service is configured to determine whether the service will be provided during the chat session or through a separate session. The communication module of the present invention is further configured to provide a service, in accordance with determining whether the service will be provided during a chat session or through a separate session.

According to the present invention, a user immediately obtains desired information or service from an interactive AI agent system without having to actively open a separate conversation session or make a specific request during a conversation with another user through an instant message. can do. According to the present invention, since the interactive AI agent system operates as if it is another human user participating in a conversation between users, the user can conveniently obtain appropriate services in a timely manner.

1 is a diagram schematically illustrating a system environment in which an interactive AI agent system may be implemented, according to an embodiment of the present invention.
2 is a functional block diagram schematically showing the functional configuration of the user terminal 102 of FIG. 1, according to an embodiment of the invention.
3 is a functional block diagram schematically illustrating the functional configuration of the interactive AI agent server 108 of FIG. 1, in accordance with an embodiment of the present invention.
4 illustrates an exemplary operation for monitoring conversation sessions between users and providing services accordingly via messenger service server 106, performed by interactive AI agent server 108, in accordance with an embodiment of the present invention. A flow chart showing the flow.
FIG. 5 illustrates that, according to an embodiment of the present invention, the interactive AI agent server 108 monitors conversations between users through the messenger service server 106 and provides a predetermined service through a separate session with a specific user. This is a screen showing an example dialog in the case of providing.

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

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. For example, a component expressed in the singular should be understood as a concept including a plurality of components unless the context clearly indicates the singular. It is to be understood that the term "and / or" as used in this disclosure encompasses all possible combinations by one or more of the listed items. The terms 'comprise' or 'having' as used in the present disclosure are merely intended to designate that there exists a feature, number, step, operation, component, part, or combination thereof described on the present disclosure. It is not intended to exclude the possibility of the presence or the addition of one or more other features or numbers, steps, actions, components, parts or combinations thereof by use.

In the embodiment of the present invention, the module or the unit means a functional part that performs at least one function or operation, and may be implemented by hardware or software or by a combination of hardware and software. Also, a plurality of 'modules' or 'units' may be integrated by at least one software module and implemented by at least one processor, except for 'modules' or 'units', which need to be implemented by specific hardware. have.

In the exemplary embodiment of the present invention, the 'interactive AI agent system' is a natural language input (eg, natural language) input from the user through an interactive interaction via natural language in the form of voice and / or text with the user. Receive and interpret commands, statements, requests, questions, etc.) from the identified user to determine the user's intent and perform the necessary actions based on the user's intent, i.e. provide appropriate conversational responses and / or tasks It may refer to any information processing system capable of providing performance of, but is not limited to any particular form.

In an embodiment of the present invention, the dialogue response provided by the 'interactive AI agent system' may be in visual, auditory and / or tactile form (eg, voice, sound, text, video, image, symbol, emoticon, hyperlink, It may be included in various forms such as, but not limited to, animation, various knots, motion, haptic feedback, 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, making a payment, writing a message, writing an email, making a phone call, playing a music, taking a picture, searching a user's location, and mapping / Various types of tasks (including, but not limited to, navigation services) may be included.

According to the embodiment of the present invention, the 'interactive AI agent system' is specialized for general purpose interactive AI agent system designed for providing general information based on general knowledge, and for each specialty field such as finance, legal, medical, and public fields. It is important to note that you can include all the specialized, interactive AI agent systems for each sector that build a knowledge system that matches that specialization and provide more accurate services.

In addition, all terms used in this 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 is to be understood that the terms used in the dictionary, which are generally used, should be interpreted as having a meaning consistent with the contextual meaning of the related art, and shall not be construed as being excessively limited or extended unless clearly defined otherwise in the present disclosure. .

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

1 is a diagram schematically illustrating a system environment 100 in which an interactive AI agent system may be implemented, in accordance with an embodiment of the present invention. As shown, the system environment 100 includes a plurality of user terminals 102a-102n, a communication network 104, a messenger service server 106, an interactive AI agent server 108, and an external service server 110. It includes.

According to one embodiment of the invention, each of the plurality of user terminals 102a-102n may be any user electronic device having a wired or wireless communication function. Each of the user terminals 102a-102n may be various wired or wireless communication terminals including, for example, a smartphone, a tablet PC, a music player, a smart speaker, a desktop, a laptop, a PDA, a game console, a digital TV, a set-top box, and the like. It should be understood that it is not limited to any particular form.

According to an embodiment of the present invention, each of the user terminals 102a-102n can communicate with the messenger service server 106, that is, send and receive necessary information, through the communication network 104. According to one embodiment of the present invention, each of the user terminals 102a-102n establishes a chat session with one or a plurality of other user terminals 102a-102n through the communication network 104 and the messenger service server 106. In addition, the established conversation session may exchange a real-time conversation with one or more other user terminals 102a-102n in a voice and / or text manner. According to an embodiment of the present invention, each of the user terminals 102a-102n receives a user input in the form of voice and / or text from the outside, and is established through the communication network 104 and the messenger 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 an embodiment of the present invention, each of the user terminals 102a-102n can communicate with the interactive AI agent server 108, that is, send and receive necessary information, through the communication network 104. According to an embodiment of the present invention, each of the user terminals 102a to 102n may communicate with the external service server 110, that is, transmit and receive necessary information through the communication network 104. According to an embodiment of the present 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 be configured as an interactive AI agent server through the communication network 104 ( 108 and / or operation results corresponding to the above user input (eg, providing a specific conversation response and / or obtained through communication with an external service server 110 (and / or processing within user terminals 102a-102n)). To perform specific tasks, etc.) to the user.

In an embodiment of the present invention, performing a task as an operation corresponding to a user input includes searching for information, sending or making a payment, writing an SMS message, writing an email, making a phone call, playing music, taking a picture, searching for a user's location, and providing a map. It may include performing various types of tasks, including but not limited to, navigation services and the like. According to one embodiment of the present invention, each of the user terminals 102a-102n may have a conversational response as a result of an operation corresponding to a user input in a visual, auditory and / or tactile form (eg, voice, sound, text, video, And images, symbols, emoticons, hyperlinks, animations, various notes, motions, haptic feedback, and the like, but are not limited thereto.

According to one embodiment of the invention, the communication network 104 may include any wired or wireless communication network, such as 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, but the present invention is not limited thereto. According to one embodiment of the invention, the communication network 104 may be, for example, Ethernet, GSM, Enhanced Data GSM Environment (EDGE), CDMA, TDMA, OFDM, Bluetooth, VoIP, Wi-MAX, Wibro, or any other various wired or wireless. It may be implemented using a communication protocol.

According to an embodiment of the present invention, the messenger service server 106 may communicate with the user terminals 102a-102n through the communication network 104. According to an embodiment of the present invention, the messenger service server 106 may be connected to one or more of the corresponding user terminals 102a-102n according to a request received from the user terminals 102a-102n through, for example, the communication network 104. A conversation session may be established between the other user terminals 102a-102n, and a real time conversation may proceed between the user terminals 102a-102n participating in the conversation session. According to an embodiment of the present invention, when the messenger service server 106 establishes a conversation session between the user terminals 102a-102n in response to a request from the user terminals 102a-102n, the messenger service server 106 according to the user's selection It is possible to determine whether to use one or a plurality of interactive AI agent (interactive AI agent specialized in general or specialized fields) for the conversation session (in this case, the conversation session by the interactive AI agent system described later). Monitoring and active service provision, etc. will be performed if selected to use the interactive AI agent system in the establishment of the corresponding conversation session). According to one embodiment of the present invention, user input in the form of voice and / or text received on each user terminal 102a-102n may be a conversation session established via the communication network 104 and the messenger service server 106. Through this, it may be delivered to other user terminals 102a-102n participating in the conversation session.

According to one embodiment of the invention, the interactive AI agent server 108 may communicate with the user terminals 102a-102n via the communication network 104. According to one embodiment of the invention, the interactive AI agent server 108 receives, in advance, user inputs in the form of voice, text and / or touch from the user terminals 102a-102n via the communication network 104, for example. Based on the prepared knowledge models, the received user input can be processed to determine the intent of the user. According to one embodiment of the invention, the interactive AI agent server 108 may, for example, generate a specific conversation response that matches the user's intent and send it to the user terminals 102a-102n.

According to one embodiment of the invention, the interactive AI agent server 108 monitors a conversation session between the user terminals 102a-102n via the messenger service server 106, for example via the communication network 104, Receive respective user natural language inputs transmitted and received between user terminals 102a-102n on the conversation session. According to one embodiment of the invention, the interactive AI agent server 108 may determine the intent of the user by processing the received natural language input based on previously prepared knowledge models. According to one embodiment of the invention, the interactive AI agent server 108 generates a conversation response that matches the user intent obtained from the conversation session between the user terminals 102a-102n via the messenger service server 106. By intervening in a chat session between the corresponding user terminals 102a-102n or by establishing a separate session (eg, a separate chat session between the specific user terminal and the interactive AI agent server 108, etc.) May provide the generated chat response.

According to an embodiment of the present invention, the interactive AI agent server 108 generates, in voice and / or text form, a conversation response corresponding to the determined user intention, and generates the generated response through the communication network 104. , The user terminal 102a-102n and / or the messenger service server 106. According to one embodiment of the invention, the dialogue response generated by the interactive AI agent server 108, along with the above-described natural language responses in the form of voice and / or text, other visual elements such as images, videos, symbols, emoticons, etc. Or other acoustic elements such as sound, sound, or other tactile elements. According to one embodiment of the invention, the same type of response on the interactive AI agent server 108, depending on the type of user input received on the user terminals 102a-102n (eg, voice or text input). Can be generated (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 invention is not so limited. According to another embodiment of the present invention, it should be appreciated that responses in the form of voice and / or text may be generated and provided regardless of the form of user input.

According to an embodiment of the present invention, the interactive AI agent server 108 may allow a task corresponding to the determined user intention to be performed. According to one embodiment of the present invention, the interactive AI agent server 108 generates a specific control signal such that, for example, a specific task conforming to the user's intention is performed on the user terminals 102a-102n, so that the user terminal 102a- 102n). According to one embodiment of the invention, the interactive AI agent server 108 intervenes in a chat session between the user terminals 102a-102n via, for example, the messenger service server 106 to meet the user's intention on the chat session. A specific task execution procedure can be performed. According to an embodiment of the present invention, the interactive AI agent server 108 may be a separate session with a particular user, for example, separate from the conversation session between the user terminals 102a-102n via the messenger service server 106. For example, a separate conversation session between a specific user terminal and the interactive AI agent server 108 may be established), and a specific task execution procedure may be performed according to the user intention through the separate session.

According to one embodiment of the invention, the interactive AI agent server 108 processes certain tasks in accordance with the user's intention, for example in a chat session between the user terminals 102a-102n via the messenger service server 106. Provide a result (eg, a predetermined information search result). According to one embodiment of the invention, the interactive AI agent server 108 may, for example, perform certain task processing (eg, predetermined task) on a conversation session between the user terminals 102a-102n via the messenger service server 106. Various paths accessible to external service server 110 (eg, information retrieval server or financial server) for information retrieval or transfer execution, such as links to external service server 110 or to external service server 110. Links for the execution of certain applications (eg, certain information retrieval apps or money transfer apps) that provide access may be provided.

According to one embodiment of the invention, the interactive AI agent server 108 is separate from a particular user, for example separate from a conversation session between the user terminals 102a-102n via the messenger service server 106. A session (eg, a separate conversation session between the specific user terminal and the interactive AI agent server 108, etc.) is established, and through the separate session, predetermined task processing results (eg, predetermined information) corresponding to the user's intention. Search results). According to one embodiment of the invention, the interactive AI agent server 108, for example, through a separate session above, the external service server 110 for a predetermined task processing (e.g., searching for information or executing a transfer). A given application (eg, a given information retrieval) that provides various paths that can be accessed (e.g., an information retrieval server or financial server), such as a link to the external service server 110 or access to the external service server 110. App or money transfer app), and the like.

According to one embodiment of the invention, the interactive AI agent server 108 is separate from the conversation session between the user terminals 102a-102n, eg, an external service server 110 for processing certain tasks in accordance with user intent. Control signals for calling a predetermined application (eg, a predetermined information retrieval app or a remittance app) that provide access to the < RTI ID = 0.0 >

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. 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 retrieval server, a map service server, a navigation service server, and the like. It doesn't happen. According to one embodiment of the present invention, the response based on the user intention, which is transmitted from the interactive AI agent server 108 to the user terminals 102a-102n and / or the messenger service server 106, is for example an external service server ( It should be understood that the data content may include data content retrieved and obtained from 110.

In this figure, the interactive AI agent server 108 is shown as a separate physical server configured to communicate with the external service server 110 through the communication network 104, but the present disclosure is not limited thereto. According to another embodiment of the present invention, the interactive AI agent 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 retrieval server, a map service server, or navigation. It should be understood that the service server may be included as part of various service servers such as a service server.

FIG. 2 is a functional block diagram schematically showing a functional configuration of the user terminal 102 shown in FIG. 1 according to an embodiment of the present invention. As shown, 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, and a response output module ( 212).

According to an embodiment of the present invention, the user input receiving module 202 may input various types of inputs from the user, for example, natural language inputs such as voice inputs and / or text inputs (and additionally other types of inputs such as touch inputs). ) Can be received. According to an embodiment of the present invention, the user input receiving module 202 may include, for example, a microphone and an audio circuit, and may acquire a user voice input signal through the 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 pointing devices such as a mouse, a joystick, a trackball, a keyboard, a touch panel, a touch screen, a stylus, and the like. The user may acquire text input and / or touch input signals input from the user through these input devices. According to an embodiment of the present invention, the user input received by the user input receiving module 202 may be associated with performing a predetermined task, for example, executing a predetermined application or retrieving predetermined information, but the present invention is limited thereto. 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 only simple conversation progress regardless of executing a predetermined application or searching for information.

According to one embodiment of the invention, the sensor module 204 includes one or more different types of sensors, through which the status information of the user terminal 102, for example, the physical state of the corresponding user terminal 102, The software and / or hardware state or information about the environment state of the user terminal 102 may be obtained. According to an embodiment of the present disclosure, the sensor module 204 may include, for example, an optical sensor, and detect an ambient light state of the corresponding user terminal 102 through the optical sensor. According to an embodiment of the present invention, the sensor module 204 may include, for example, a movement sensor, and detect whether the corresponding user terminal 102 is moved through the movement sensor. According to an embodiment of the present invention, the sensor module 204 may include, for example, a speed sensor and a GPS sensor, and may detect a position and / or orientation state of the corresponding user terminal 102 through these sensors. According to 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, contact sensors, and the like.

According to an embodiment of the present invention, the program memory module 206 may be any storage medium that stores various programs that can be executed on the user terminal 102, for example, various application programs and related data. According to one embodiment of the invention, the program memory module 206 includes, for example, instant messaging applications, dialing applications, email applications, camera applications, music playback applications, video playback applications, image management applications, map applications, browser applications, and the like. Various application programs, including, and data associated with the execution of these programs can be stored. According to an embodiment of the present invention, the program memory module 206 may be configured to include various types of volatile or nonvolatile memory such as DRAM, SRAM, DDR RAM, ROM, magnetic disk, optical disk, flash memory, and the like. .

According to one embodiment of the 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 an embodiment of the present invention, the processing module 208 may drive and execute various application programs on the program memory module 206. According to one embodiment of the invention, the processing module 208 may receive the signals obtained by 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 invention, the processing module 208 may perform appropriate processing on the signal received from the outside through the communication module 210, if necessary.

According to one embodiment of the invention, the communication module 210, the user terminal 102 via the communication network 104 of Figure 1, the messenger service server 106, the interactive AI agent server 108 and / or Enable communication with an external service server 110. According to an embodiment of the present invention, the communication module 210, for example, the signal obtained on the user input receiving module 202 and the sensor module 204 is a messenger service server (through the communication network 104 according to a predetermined protocol) ( 106, the interactive AI agent server 108 and / or the external service server 110. According to one embodiment of the invention, the communication module 210 is received from the messenger service server 106, the interactive AI agent server 108 and / or the external service server 110, for example, via the communication network 104. Various signals, for example, response signals including natural language responses in the form of voice and / or text, various control signals, and the like can be received, and appropriate processing can be performed according to a predetermined protocol.

According to an embodiment of the present disclosure, the response output module 212 may output a response corresponding to a user input in various forms such as visual, auditory, and / or tactile. According to one embodiment of the present invention, the response output module 212 includes various display devices such as a touch screen based on technologies such as LCD, LED, OLED, QLED, etc., and responds to user input through these display devices. Visual responses such as text, symbols, videos, images, hyperlinks, animations, various notes, and the like, to the user. According to one embodiment of the invention, the response output module 212 includes, for example, a speaker or a headset, and provides an audible response, such as a voice and / or acoustic response, to the user via the speaker or the headset, corresponding to a user input. can do. According to an embodiment of the present invention, the response output module 212 may include a motion / haptic feedback generator, thereby providing a tactile response, for example, motion / haptic feedback to the user. According to one embodiment of the present invention, it should be appreciated that the response output module 212 can simultaneously provide any two or more combinations of text response, voice response, and motion / haptic feedback corresponding to user input.

3 is a functional block diagram schematically illustrating the functional configuration of the interactive AI agent server 108 of FIG. 1, in accordance with an embodiment of the present invention. As shown, the interactive agent server 108 may include a communication module 302, a speech-to-text (STT) module 304, a natural language understanding (NLU) module 306. ), Conversation understanding knowledge base 308, user database 310, conversation session monitoring unit 312, conversation management module 314, conversation generation module 316, and speech synthesis (Text-To-Speech; TTS) Module 318.

According to an embodiment of the present invention, the communication module 302 is a communication AI agent server 108 via the communication network 104, according to a predetermined wired or wireless communication protocol, the user terminal 102, the messenger service Enable communication with server 106 and / or external service server 110. According to one embodiment of the invention, the communication module 302 is a user input (eg touch input, voice, etc.) that has been transmitted from the user terminal 102 and / or the messenger service server 106 via the communication network 104. Input, and / or text input, and the like, without limitation thereto). According to one embodiment of the present invention, the communication module 302, together with or separately from the above-described user input, has been transmitted from the user terminal 102 or the like via the communication network 104, the user terminal 102. It can receive the state information of. According to an embodiment of the present invention, the state information may be, for example, various state information related to the corresponding user terminal 102 at the time of the user input (for example, the physical state of the user terminal 102 and the software of the user terminal 102). And / or hardware status, environmental status information around the user terminal 102, and the like. In accordance with one embodiment of the present invention, the communication module 302 further includes a conversation response (eg, voice and / or textual natural language) generated by the interactive AI agent server 108 in response to the received user input. And / or control signals), and / or control signals, may be performed via the communication network 104 to the user terminal 102 and / or the messenger service server 106.

According to an embodiment of the present invention, the STT module 304 may receive a voice input among user inputs received through the communication module 302 and convert the received voice input into text data based on pattern matching or the like. have. According to an embodiment of the present invention, the STT module 304 may generate a feature vector sequence by extracting features from a user's voice input. According to an embodiment of the present invention, the STT module 304 may include a dynamic time warping (DTW) method, a HMM model (Hidden Markov Model), a GMM model (Gaussian-Mixture Mode), a deep neural network model, an n-gram model, and the like. Based on a variety of statistical models of, a text recognition result, such as a sequence of words, can be generated. According to an embodiment of the present invention, when converting the received voice input into text data based on pattern matching, the STT module 304 may refer to each user characteristic data of the user database 310 described later. .

According to one embodiment of the invention, the NLU module 306 may receive a text input from the communication module 302 or the STT module 304. According to one embodiment of the invention, the text input received at the NLU module 306 is received from the user terminal 102 and / or the messenger service server 106 via the communication network 104 at the communication module 302, for example. The text recognition result generated by the STT module 304 from the user text input or the user voice input received at the communication module 302, for example, a sequence of words. According to one embodiment of the invention, the NLU module 306, along with or after receiving the text input, state information associated with the user input, such as state information of the user terminal 102 at the time of the user input. And the like. As described above, the status information may include, for example, various status information related to the corresponding user terminal 102 at the time of user voice input and / or text input (eg, physical state of the user terminal 102 and software). And / or hardware status, environmental status information around the user terminal 102, and the like.

According to an embodiment of the present invention, the NLU module 306 may correspond to the received text input with one or more user intents based on the conversation understanding knowledge base 308 described below. The user intent here may be associated with a series of action (s) that can be understood and performed by the interactive AI agent server 108 in accordance with the user intent. According to one embodiment of the invention, the NLU module 306 may refer to the aforementioned state information in mapping the received text input to one or more user intentions. According to one embodiment of the invention, the NLU module 306 may reference each user characteristic data of the user database 310 described below in mapping the received text input to one or more user intentions.

According to one embodiment of the invention, the conversation understanding knowledge base 308 may include, for example, a predefined ontology model. According to one embodiment of the invention, the ontology model can be represented, for example, as a hierarchical structure between nodes, each node being a "intent" node or a sub-attribute linked to a "intent" node corresponding to a user's intent. It may be one of the nodes (subordinate "attributes" nodes directly linked to the "intent" node or back linked to the "attributes" node of the "intent" node. According to an embodiment of the present invention, an "intention" node and "attribute" nodes directly or indirectly linked to the "intention" node may constitute one domain, and an ontology may be configured as a set of such domains. . According to one embodiment of the invention, the dialogue understanding knowledge base 308 may be configured to include domains corresponding to all intents, for example, that the interactive AI agent system can understand and perform operations corresponding thereto. have. According to one embodiment of the present invention, it should be noted that the ontology model may be dynamically changed by adding or deleting nodes, or modifying relationships between nodes.

According to one embodiment of the invention, the intent node and attribute nodes of each domain in the ontology model may be associated with words and / or phrases related to the corresponding user intent or attributes, respectively. According to one embodiment of the invention, the dialogue understanding knowledge base 308 comprises an ontology model consisting of nodes in a hierarchy and a set of words and / or phrases associated with each node, e.g. in the form of a lexical dictionary (specific (Not shown), the NLU module 306 may determine user intention based on the ontology model implemented in the form of a lexical dictionary. For example, according to one embodiment of the present invention, when the NLU module 306 receives a text input or a sequence of words, the NLU module 306 may determine which words in which domain in the ontology model are associated with each word in the sequence, Based on such a determination, it is possible to determine the corresponding domain, ie user intention.

According to an embodiment of the present invention, the user database 310 may be a database that stores and manages 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, a previous conversation / behavior record of the user, pronunciation characteristic information of the user, user vocabulary preferences, and the location of the user for each user. , Settings language, contact / friend list, and various other user specific information.

According to an embodiment of the present invention, as described above, the STT module 304 refers to each user characteristic data of the user database 310, for example, a pronunciation characteristic of each user, when converting a voice input into text data. You can get more accurate text data. According to an embodiment of the present invention, the NLU module 306 may make more accurate user intention determination by referring to each user characteristic data of the user database 310, for example, each user characteristic or context, when determining the user intention. Can be. According to an embodiment of the present invention, as described below, the conversation generating module 316 may refer to user characteristic data of the user database 310 when generating a conversation response.

In the figure, a user database 310 for storing and managing characteristic data for each user is illustrated 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 for storing and managing the characteristic data for each user may exist in the user terminal 102, for example, the user terminal 102 and the interactive AI agent server 108 It should be noted that they may be distributed in

According to an embodiment of the present invention, the chat session monitoring unit 312 monitors each chat item on the chat session established between the plurality of user terminals 102, that is, each user input through the messenger service server 106. can do. According to one embodiment of the invention, the chat session monitoring 312 is a conversation item from each user terminal 102, i.e., on a chat session between the plurality of user terminals 102 via the messenger service server 106; Based on each user input, each corresponding user intent obtained from NLU module 306 may be determined.

According to an embodiment of the present disclosure, the conversation session monitoring unit 312 may determine whether the user needs to provide a predetermined service based on the user's intention. According to an embodiment of the present invention, the above-described determination by the conversation session monitoring unit 312 may be made according to whether a predetermined (preregistered) condition is met or based on a neural network method. According to one embodiment of the present invention, the interactive AI agent server 108 corresponds to a user corresponding to a predetermined user input obtained on a conversation session between a plurality of user terminals 102, for example, via a messenger service server 106. If the intention is to retrieve certain information, transfer a certain amount of money to a specific person, or to execute a particular application (but the invention is not so limited), the user may need to provide a certain service. It can be set in advance as a viewpoint.

According to one embodiment of the present invention, when the conversation session monitoring unit 312 determines that the provision of a predetermined service is required based on a user's intention according to a predetermined user input obtained on the conversation session, a conversation management module (described below) 314) and a conversation response generated by the conversation creation module 316 or the like may be used to establish a separate session separately established on the conversation session through the messenger service server 106 or with a specific user who needs to provide the service. May be determined to be provided.

According to one embodiment of the present invention, the conversation management module 314 may generate a series of operation flows corresponding thereto according to the user intention determined by the NLU module 306. According to one embodiment of the present invention, the conversation management module 314 is based on a certain conversation flow management model, for example, in response to user intentions received from the NLU module 306, for example, any conversation response and / or Alternatively, it may be determined whether to perform a task, and a detailed operation flow may be generated accordingly.

According to an embodiment of the present invention, for example, by the above conversation monitoring unit 312, a predetermined service needs to be provided according to a user's intention identified on a conversation session between user terminals 102a-102n, and such a service is provided. If it is determined that the conversation session should be provided, the conversation management module 314 may perform a predetermined task corresponding to the user's intention and provide the result of the execution (for example, a predetermined information search result) through the conversation session. Can be. According to an embodiment of the present invention, for example, by the above conversation monitoring unit 312, a predetermined service needs to be provided according to a user's intention identified on a conversation session between user terminals 102a-102n, and such a service is provided. If it is determined that it should be provided on the corresponding chat session, the chat management module 314 may request that the external service server 110 (eg, perform certain task processing (eg, retrieve or transfer information) consistent with the user's intent. Any application (eg, any information retrieval app or money transfer app) that provides various paths that can be accessed to an information retrieval server or financial server, such as a link to an external service server 110 or access to an external service server 110. ), Etc. link can be provided through the corresponding chat session.

According to an embodiment of the present invention, for example, by the above conversation monitoring unit 312, a predetermined service needs to be provided according to a user's intention identified on a conversation session between user terminals 102a-102n, and such a service is provided. If it is determined that the communication session should be provided via a separate session other than the above conversation session, the conversation management module 314 may, for example, separate a specific user from the conversation session between the user terminals 102a-102n through the messenger service server 106. Establish a separate session with the user (e.g., a separate chat session between the specific user terminal and the interactive AI agent server 108, etc.), perform a predetermined task in accordance with the user's intention, and perform the result (e.g., Information search result) can be provided through the separate session. According to an embodiment of the present invention, for example, by the above conversation monitoring unit 312, a predetermined service needs to be provided according to a user's intention identified on a conversation session between user terminals 102a-102n, and such a service is provided. If it is determined that the communication session should be provided via a separate session other than the above conversation session, the conversation management module 314 may, for example, separate a specific user from the conversation session between the user terminals 102a-102n through the messenger service server 106. Establish a separate session with the user (e.g., a separate conversation session between the specific user terminal and the interactive AI agent server 108, etc.), and perform predetermined task processing (e.g., retrieve or transfer information) in accordance with the user's intent. Various paths that can be accessed to an external service server 110 (eg, an information retrieval server or a financial server), such as a link to an external service server 110 or A link for executing a predetermined application (eg, a predetermined information retrieval app or a remittance app) that provides access to the external service server 110 may be provided through the separate session.

According to an embodiment of the present invention, the conversation generating module 316 may generate a conversation 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 conversation generating module 316, in the generation of the conversation response, the user characteristic data of the user database 310 described above (eg, the user's previous conversation records, the user's pronunciation characteristic information, User vocabulary preferences, user's location, setting language, contact / friend list, each user's previous conversation, etc.).

According to one embodiment of the invention, the TTS module 318 may receive a conversation response generated to be sent to the user terminal 102 by the conversation generation module 316. The conversation response received at the TTS module 318 may be a natural language or a sequence of words in text form. According to an embodiment of the present invention, the TTS module 318 may convert the received text form input into a speech form according to various types of algorithms.

In the embodiment of the present invention described above with reference to Figs. 1 to 3, the interactive AI agent system is configured such that the user terminal 102 and the interactive AI agent server 108 are client-server models, in particular, the client only has user input / output functions. All other functions of the interactive AI agent system are provided as described and implemented based on a so-called "thin client-server model," which is delegated to a server, but the invention is not so limited. According to another embodiment of the present invention, the interactive AI agent system should be understood that the functions may be implemented by being distributed between the user terminal and the server, or alternatively, may be implemented as a standalone application installed on the user terminal. . In addition, when the interactive AI agent system distributes and implements the functions 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 carried out in each embodiment. It should be appreciated that other implementations may be made. In addition, in the embodiment of the present invention described above with reference to FIGS. 1 to 3, for convenience, a specific module has been described as performing certain operations, but the present invention is not limited thereto. According to another embodiment of the present invention, it should be understood that the operations described as performed by any particular module in the above description may be performed by a separate module from each other.

4 illustrates an exemplary operation for monitoring conversation sessions between users and providing services accordingly via messenger service server 106, performed by interactive AI agent server 108, in accordance with an embodiment of the present invention. A flow chart showing the flow.

In 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 messenger service server 106. can do. According to one embodiment of the invention, the received user input may be a text and / or voice input received on each corresponding user terminal 102.

In step 404, the interactive AI agent server 108 may analyze the user input obtained in step 402 and determine the corresponding user intent. According to one embodiment of the invention, the interactive AI agent server 108 may map each user input to one or more user intents based on a predetermined knowledge base. According to one embodiment of the invention, the interactive AI agent server 108 may be specialized in a particular field of expertise. In such a case, the knowledge base of the interactive AI agent server 108 is specialized in that area of expertise and may allow user intentions related to that field to be more accurately determined.

In step 406, the interactive AI agent server 108 may determine whether it is a point in time at which a given service is needed, based on the obtained user intent. According to an embodiment of the present invention, for example, a user's intention corresponding to a user input obtained on a conversation session between a plurality of user terminals 102 through a messenger service server 106 is searched for specific information, a predetermined amount of money to a specific person. If it is desired to transfer money or to execute a specific application, it may be predetermined that a predetermined service should be provided, but it should be understood that the present invention is not limited thereto. According to one embodiment of the present invention, while users A, B, and C exchange everyday conversations, for example, in a chat session via messenger service server 106, A and C refer to a particular news article, but B does not say " If you do not know the article in response to the "what," etc., but the intention to know the interactive AI agent server 108 may determine that it is necessary to provide information of a predetermined service, that is, the news article. According to an embodiment of the present invention, for example, during a conversation session between users A and B, A and B are "How much did you get yesterday?", "100,000 won", "I'll transfer" When the conversation is exchanged, the interactive AI agent server 108 may determine that it is necessary to provide a remittance service.

In step 406, if the interactive AI agent server 108 determines that it is not the time to provide the given service, 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, providing no response.

Alternatively, in step 406, in light of the user's intention, if it is determined that a given service is required, then the procedure proceeds to step 408 and the interactive AI agent server 108 provides the desired service required. It may be determined whether the provision is to be provided on the above existing conversation session through the messenger service server 106 or alternatively through a separate session established separately with the specific user who needs the service. According to one embodiment of the invention, this determination may be made, for example, according to predetermined criteria or user selection. According to one embodiment of the present invention, this determination may be made, for example, according to the type of service provided (eg, whether the service requires security, etc.).

In step 408, if it is determined that the service is to be provided on an existing chat session, the procedure proceeds to step 410, where the interactive AI agent server 108 proceeds with a predetermined operational flow (conversation) that matches its user intent. And / or provide a response and / or perform a task), and provide a result of the operation through the corresponding conversation session. According to an embodiment of the present invention, the interactive AI agent server 108 performs a task (eg, a predetermined news article retrieval service) for providing a service corresponding to a user's intention, and the result of performing the same (eg, a predetermined Search results of the news article) can be provided through a dialogue session between the corresponding users. According to one embodiment of the present invention, the interactive AI agent server 108 may be configured to provide an external service server 110 (eg, to perform predetermined task processing (eg, to retrieve or transfer information) corresponding to a user's intention. A variety of paths that can be accessed to an information retrieval server or financial server, such as a link to an external service server 110 (e.g., an information retrieval server or a financial server) or any application that provides access to the external service server 110 ( For example, a link for executing a predetermined information retrieval app or a remittance app) may be provided through a conversation session between corresponding users.

According to an embodiment of the present invention, for example, when users A, B, and C want to provide information of a specific news article during a conversation session through a messenger service server 106, an interactive AI agent server ( 108 may retrieve the news article and present the retrieved news article on the conversation session. According to one embodiment of the present invention, for example, when users A and B wish to provide a predetermined remittance service from A to B during a conversation session, the interactive AI agent server 108 transmits money. A link to a bank site for or a link to launch a bank app can be presented on the conversation session.

In step 408, if it is determined that the service will be provided through a separate session, the procedure proceeds to step 412, where the interactive AI agent server 108 passes the user terminal 102a via the messenger service server 106. A separate session with a specific user (eg, a separate conversation session between the specific user terminal requiring the corresponding service and the interactive AI agent server 108 or another separate communication session) apart from the conversation session between -102n) ) Can be established. The interactive AI agent server 108 then generates, at step 414, a predetermined flow of actions that may correspond to the user's intent (which may include providing a conversation response and / or performing a task, and the like). And the result of the operation can be provided through the corresponding separate session. According to one embodiment of the invention, the interactive AI agent server 108 performs a predetermined task (e.g., searching for a news article) for providing a service in accordance with the user's intention, and the result (e.g., a predetermined news article search). Results from searching for news articles) can be provided in a separate session. According to one embodiment of the present invention, the interactive AI agent server 108 may be configured to provide an external service server 110 (eg, to perform predetermined task processing (eg, to retrieve or transfer information) corresponding to a user's intention. A variety of paths that can be accessed to an information retrieval server or financial server, such as a link to an external service server 110 (e.g., an information retrieval server or a financial server) or any application that provides access to the external service server 110 ( For example, a link for executing a predetermined information retrieval app or a remittance app) may be provided through the above separate session.

According to an embodiment of the present invention, for example, when users A, B, and C want to provide A with information of a specific news article while in a conversation session through the messenger service server 106, they want to provide information of a specific news article. The server 108 may open a separate chat session with A, retrieve the news article, and present the retrieved news article on the separate chat session. According to an embodiment of the present invention, for example, when users A and B wish to provide a transfer of money transfer from A to B while a conversation is in progress, the interactive AI agent server 108 may be A. A separate chat session can be opened between and and a link to a bank site for money transfer or a link to run a bank app can be presented on the separate chat session.

According to one embodiment of the present invention, a service that may be provided by the interactive AI agent server 108 may, for example, provide information retrieved from an external service server 110 or the like or execute other service applications (eg, finance). App, map app, navigation app, etc., but is not limited thereto, but it should be understood that the present invention is not so limited.

In the present specification, mainly, the interactive AI agent server 108 is based only on its own judgment (such as determining whether a user intention requires providing a predetermined service by the interactive AI agent server 108). It should be understood that the present invention is described as determining whether to provide a service, but the present invention is not limited thereto. According to another embodiment of the present invention, the interactive AI agent server 108 may determine whether a user calls a predetermined name (eg, a predetermined name to refer to the corresponding interactive AI agent) during a conversation session. Certain procedures may be taken to provide a response and / or a service. However, even in this case, since the interactive AI agent server 108 continuously monitors each user input of the conversation session, the interactive AI agent server 108 receives the final confirmation of the user regarding the provision of the service by simply calling the user. It is only meant to be understood that the user does not need to explicitly request the desired service from the interactive AI agent server 108 again. According to another embodiment of the present invention, if the interactive AI agent server 108 wants to provide a predetermined service according to its own decision, before providing the service, whether the interactive AI agent server 108 desires to provide the service or not. You can also go through the procedure of asking the user.

FIG. 5 illustrates that, according to an embodiment of the present invention, the interactive AI agent server 108 monitors conversations between users through the messenger service server 106 and provides a predetermined service through a separate session with a specific user. This is a screen showing an example dialog in the case of providing.

As shown in FIG. 5A, the interactive AI agent server 108 is silent for some time during the conversation between users while monitoring their conversation. Subsequently, reference is made to a certain amount of transfer between users. Then, the interactive AI agent server 108, as shown in Fig. 5 (b), the interactive AI agent server 108 establishes a separate conversation session with the user who wants to receive the transfer service. It provides services through established conversation sessions. As shown in (b) of FIG. 5, the interactive AI agent server 108 first inquires about whether to run an app for remittance, obtains consent from a user, and then proceeds to connect to the corresponding bank app. It can be seen that. In this way, the user can easily receive the necessary service without having to interrupt the current conversation or go through a separate inconvenience procedure.

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

A computer program according to an embodiment of the present invention includes a storage medium readable by a computer processor or the like, for example, a nonvolatile memory such as an EPROM, an EEPROM, a flash memory device, a magnetic disk such as an internal hard disk and a removable disk, a magneto-optical disk, and It may be implemented in a form stored in various types of storage media, including a CDROM disk. In addition, the program code (s) may be implemented in assembly or machine language. All modifications and changes that fall within the true spirit and scope of the present invention are intended to be covered by the following claims.

Claims (10)

A method for monitoring and providing a service between a plurality of user conversation sessions provided by an interactive AI agent system,
Receiving user input from each of the plurality of users during the chat session, wherein the user input is a chat input exchanged 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 it is a point in time to provide a service by the interactive AI agent system, wherein the service is associated with performing one or more tasks;
In response to determining that the service is to be provided by the interactive AI agent system, determining whether the service will be provided in the conversation session or through a separate session, and
Providing the service in accordance with determining whether the service will be provided during the conversation session or through a separate session.
The method comprising the steps of monitoring and service between the conversation session between the plurality of users. The method of claim 1,
And determining whether the service will be provided in the chat session or through a separate session, based on the type of service. The method of claim 1,
Determining whether the service is provided in the chat session or through a separate session is determined according to whether the service is a service requiring security. . The method of claim 1,
In accordance with determining whether the service will be provided during the conversation session or through a separate session, providing the service may include:
Performing the one or more tasks associated with the service and providing results of performing the one or more tasks during the conversation session or the separate session. The method of claim 1,
In accordance with determining whether the service will be provided during the conversation session or through a separate session, providing the service may include:
Providing access to a given external server during the chat session or the separate session for performing the one or more tasks associated with the service. The method of claim 5,
And providing access to the given external server comprises providing a link to the external server. The method of claim 5,
Providing access to the given external server includes providing a link for execution of a given application, wherein the given application provides access to the given external server. How to monitor and service a chat session. The method of claim 5,
Providing access to the given external server comprises: invoking a given application, wherein the given application provides access to the given external service server. And how we provide services. A computer readable recording medium comprising one or more instructions,
The computer readable recording medium of the one or more instructions, when executed for a computer, causes the computer to perform the method of any one of claims 1 to 8. An interactive AI agent system configured to provide monitoring and intervention for multiple user chat sessions.
Communication module,
NLU module, and
Dialog session monitoring module
Including,
The communication module is configured to receive user input from each of the plurality of users during the conversation session, the user input being a conversation input to and from the plurality of users;
The NLU module is configured to determine a predetermined user intention corresponding to the user input based on a predetermined knowledge base.
The conversation session monitoring module determines whether it is time to provide a service by the interactive AI agent system, and in response to determining that it is a time when service provision by the interactive AI agent system is needed, the service communicates with the conversation. Configured to determine whether to be served among the session or through a separate session,
The communication module is further configured to provide the service, in accordance with determining whether the service will be provided during the conversation session or through a separate session,
Interactive AI Agent System.

Images