KR20190109706A - Method, interactive ai agent system and computer readable recoding medium for providing intent determination based on analysis of a plurality of same type entity information - Google Patents

Abstract

Provided is a method for determining an intent of natural language input performed by an interactive AI agent system. The method comprises the steps of: receiving natural language input from a user; determining whether a word or phrase defined as corresponding to any intent on a predetermined lexical dictionary model is included in the natural language input; mapping the natural language input to a corresponding intent when determined that the word or phrase is included in the natural language input; extracting a plurality of same types of entity information from the natural language input when determined that the word or phrase is not included in the natural language input; and mapping the natural language input to a predetermined intent based on the extracted plurality of same types of entity information.

Description

METHOD, INTERACTIVE AI AGENT SYSTEM AND COMPUTER READABLE RECODING MEDIUM FOR PROVIDING INTENT DETERMINATION BASED ON ANALYSIS OF A PLURALITY OF SAME TYPE ENTITY INFORMATION}

The present disclosure relates to understanding conversations in an interactive AI agent system, and more particularly by an interactive AI agent system, intent of which user input may be determined based on relationships between entities included in user input. Understanding of the conversations being performed.

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, which enable the operator to operate the machine in a mediated manner and obtain the desired services from the machine, are increasingly being used. Accordingly, in a variety of fields, including but not limited to online counseling centers, online shopping malls, and the like, users may request a desired service from an interactive AI agent system through natural language conversations in the form of voice and / or text. Increasingly, people want to get the results they want.

In such an interactive AI agent system, when there is a natural language input from a user, determining the intent of the natural language input, that is, the intent, is an important process. The determination of the intent by the interactive AI agent system is based primarily on the presence or absence of certain words having a certain meaning, from the user's natural language input. Entity information that may be included in the user's natural language input (e.g., parameter information having a specific attribute and format such as date, name, time, phone number, etc. as a variable that may be included in the user's natural language input) is typically the intent itself. Rather than being primarily used to identify, the intent for the natural language input is determined and then used as a parameter value to obtain an answer for the determined intent.

Patent Document 1: Korean Patent Application No. 10-2015-7035936

By the way, in conversations that occur between real people, they may express their intentions explicitly by using certain words with certain meanings, but instead of using words containing such specific explicit intentions, such words are sometimes used. It is sometimes possible to list separate entity information that is different from the group, and indirectly indicate the desired intent by the relationship between the entity information (eg, direct and explicit delivery complaints in the Customer Care Center. Instead of marking a tent, you list two date entities, such as "I ordered the goods on January 3, today is already February 3," and indirectly indicate the intent of the delivery complaint from that relationship. ).

Thus, in determining the intent by analyzing the user's natural language input, the conventional method based only on the presence or absence of certain words having a predetermined meaning, the user's indirectly revealed by the relationship between such entity information There is a problem that is difficult to identify the tent. Therefore, there is a need to provide an interactive AI agent system that can support intent determination of a user indirectly represented by the relationship between entity information.

According to one aspect of the present disclosure, a method for determining intent of a natural language input performed by an interactive AI agent system is provided. The method of the present disclosure includes receiving a natural language input from a user; Determining whether a word or phrase defined as corresponding to any intent on a given lexical dictionary model is included in the natural language input; If it is determined that the word or phrase is included in the natural language input, mapping the natural language input to a corresponding intent; If it is determined that the word or phrase is not included in the natural language input, extracting a plurality of same types of entity information from the natural language input; And mapping the natural language input to a predetermined intent based on the extracted plurality of same types of entity information.

According to an embodiment of the present disclosure, the mapping of the natural language input to a predetermined intent may be performed based on a combination of extracted plurality of same types of entity information and words having a predetermined meaning present in the natural language input. Mapping the natural language input to a predetermined intent.

According to an embodiment of the present disclosure, the interactive AI agent system is configured to provide a service related to shopping, and mapping the natural language input to a predetermined intent may include extracting a plurality of identical types of entity information, respectively. Determining whether there are different values as entities of the same type related to quality, and whether there is a word indicating completion of an order or delivery during natural language entry; And based on the determination result, mapping the natural language input to an intent of a complaint or return request.

According to one embodiment of the present disclosure, whether the extracted plurality of same types of entity information are entities of the same type which are each related to quality may include extracting the plurality of same types of entity information among sizes, colors, performances, and prices. It may be determined depending on whether the entity is related to one in common.

According to an embodiment of the present disclosure, the interactive AI agent system is configured to provide a service related to shopping, and the mapping of the natural language input to a predetermined intent may include extracting a plurality of entity information from different dates. Determining whether there is a word associated with the order or delivery during the indicating entity information and natural language input; And based on the determination result, mapping the natural language input to the intent of the delivery inquiry or delivery complaint.

According to another aspect of the present disclosure, a computer readable recording medium including 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. A computer readable recording medium is provided.

According to yet another aspect of the present disclosure, an interactive AI agent system for providing natural language understanding comprises: a user input receiving module configured to receive natural language input from a user; Knowledge base model in the form of lexical dictionaries; And an interactive AI agent system including a natural language understanding module. The natural language understanding module of the present disclosure determines whether a word or phrase defined as corresponding to any intent on the knowledgebase model is included in the natural language input, and when it is determined that the word or phrase is included in the natural language input, the natural language If it is determined that the input is mapped to a corresponding intent, and it is determined that a word or phrase is not included in the natural language input, the plurality of entity information is extracted from the natural language input, and the natural language input is based on the extracted plurality of the same type of entity information. Is mapped to a predetermined intent.

The interactive AI agent system according to the present disclosure is indirect from there on the basis of the entity information on the user input, even if the intent fails to determine the intent based on the presence or absence of certain words having a predetermined meaning on the user input. The intent of the user represented by.

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 disclosure.
2 is a functional block diagram schematically illustrating the functional configuration of the user terminal 102 of FIG. 1, according to an embodiment of the disclosure.
3 is a functional block diagram schematically illustrating the functional configuration of the interactive AI agent server 106 of FIG. 1, in accordance with an embodiment of the present disclosure.
4 is a flow diagram illustrating an example operational flow for user intent determination performed by an interactive AI agent system for a shopping service, in accordance with an embodiment of the present disclosure.

Hereinafter, exemplary embodiments of the present disclosure 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 subject matter of the present disclosure, a detailed description of already known functions and configurations will be omitted. In addition, it should be understood that the contents described below are only related to the embodiments of the present disclosure, and 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 present disclosure. 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 exemplary embodiment of the present disclosure, the module or the unit means a functional part that performs at least one function or operation, and may be implemented in hardware or software or in 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 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, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

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 disclosure. As shown, the system environment 100 includes a plurality of user terminals 102a-102n, a communication network 104, an interactive AI agent server 106, and an external service server 108.

According to one embodiment of the present disclosure, 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 a variety of wired or wireless communication terminals, including, for example, smart speakers, music players, game consoles, digital TVs, set-top boxes, smart phones, tablet PCs, desktops, laptops, PDAs, and the like. It should be understood that it is not limited to any particular form. According to one embodiment of the present disclosure, each of the user terminals 102a-102n may communicate with the interactive AI agent server 106, that is, send and receive necessary information, through the communication network 104. According to one embodiment of the present disclosure, each of the user terminals 102a-102n may communicate with the external service server 108, that is, transmit and receive necessary information through the communication network 104. According to an embodiment of the present disclosure, 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 ( 106) and / or operation results corresponding to the above user input (e.g., user authentication, provision of specific conversation responses) obtained through communication with external service server 108 (and / or processing within user terminals 102a-102n). And / or perform a specific task, etc.).

In an embodiment of the present disclosure, performing a task as an operation corresponding to a user input includes searching for information, purchasing an item, writing a message, writing an email, making a phone call, playing a music, taking a picture, searching for a user's location, and a map / navigation service. And various types of tasks, including, but not limited to, performing such tasks. According to one embodiment of the present disclosure, 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, audio, 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 present disclosure, communication network 104 may include any wired or wireless communication network, such as a TCP / IP communication network. According to one embodiment of the present disclosure, 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 disclosure is not limited thereto. According to one embodiment of the present disclosure, the communication network 104 may include, for example, Ethernet, GSM, Enhanced Data GSM Environment (EDGE), CDMA, TDMA, OFDM, Bluetooth, VoIP, Wi-MAX, Wibro, and any other various wired or wireless. It may be implemented using a communication protocol.

According to one embodiment of the present disclosure, the interactive AI agent server 106 may communicate with the user terminals 102a-102n via the communication network 104. According to an embodiment of the present disclosure, the interactive AI agent server 106 transmits and receives necessary information with the user terminals 102a-102n through the communication network 104, and thereby receives them on the user terminals 102a-102n. The operation result corresponding to the input user input, that is, the user intent, may be provided to the user.

According to an embodiment of the present disclosure, the interactive AI agent server 106 receives user natural language input in the form of voice, text, and / or touch from the user terminals 102a-102n, for example, via the communication network 104. The received natural language input may be processed based on previously prepared models to determine the user's intent. According to an embodiment of the present disclosure, the interactive AI agent server 106 may allow a corresponding operation to be performed based on the user intent determined above. According to one embodiment of the present disclosure, the interactive AI agent server 106 generates a specific control signal such that the user terminals 102a-102n perform a specific task corresponding to the user intent, for example. -102n). According to one embodiment of the present disclosure, the interactive AI agent server 106 is configured to provide an external service via the communication network 104, for example, to allow the user terminals 102a-102n to perform specific tasks that conform to the user intent. The server 108 can be connected.

According to one embodiment of the present disclosure, the interactive AI agent server 106 may generate a specific conversation response that corresponds to, for example, a user intent, and send it to the user terminals 102a-102n. According to an embodiment of the present disclosure, the interactive AI agent server 106 generates, based on the user intent determined above, a corresponding conversation response in voice and / or text form, and generates the generated response in a communication network ( Via 104, it may be delivered to the user terminals 102a-102n. According to one embodiment of the present disclosure, the conversation response generated by the interactive AI agent server 106, along with the above-described natural language response 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 present disclosure, the same type of response on the interactive AI agent server 106, depending on the type of user input received on the user terminals 102a-102n (eg, voice or text input). May be generated (eg, 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 disclosure is not so limited. In accordance with another embodiment of the present disclosure, 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 one embodiment of the present disclosure, the interactive AI agent server 106 may communicate with the external service server 108 via the communication network 104, as mentioned above. The external service server 108 may be, for example, an online consultation center server, an online shopping mall server, an information retrieval server, or the like, and the present disclosure is not limited thereto. According to one embodiment of the present disclosure, a conversation response based on user intent, delivered from the interactive AI agent server 106 to the user terminals 102a-102n, is retrieved and obtained from, for example, the external service server 108. It should be understood that this may include data content.

In this figure, the interactive AI agent server 106 is shown as a separate physical server configured to communicate with the external service server 108 via the communication network 104, but the present disclosure is not limited thereto. According to another embodiment of the present disclosure, it should be understood that the interactive AI agent server 106 may be included as part of various service servers such as an online consultation center server or an online shopping mall server.

2 is a functional block diagram schematically showing the functional configuration of the user terminal 102 shown in FIG. 1, according to an embodiment of the present disclosure. 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 disclosure, the user input receiving module 202 may input various types of inputs from a 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 disclosure, 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 disclosure, 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 disclosure, 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 searching for predetermined information, but the present disclosure is limited thereto. It doesn't happen. According to another embodiment of the present disclosure, the user input received by the user input receiving module 202 may require only a simple conversation response regardless of executing a predetermined application or searching for information. According to another embodiment of the present disclosure, the user input received at the user input receiving module 202 may relate to a simple statement for unilateral communication.

According to one embodiment of the present disclosure, 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 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 disclosure, 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 disclosure, 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 disclosure, 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 disclosure, the program memory module 206 may be any storage medium in which various programs, for example, various application programs and related data, which may be executed on the user terminal 102, are stored. According to one embodiment of the present disclosure, the program memory module 206 includes, for example, a dialing application, an email application, an instant messaging application, a camera application, a music playback application, a video playback application, an image management application, a map application, a browser application, 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 disclosure, 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 present disclosure, 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 disclosure, the processing module 208 may drive and execute various application programs on the program memory module 206. According to one embodiment of the present disclosure, the processing module 208 may receive the signals obtained by the user input receiving module 202 and the sensor module 204 and perform appropriate processing on these signals, if necessary. have. According to one embodiment of the present disclosure, the processing module 208 may perform appropriate processing on a signal received from the outside through the communication module 210 if necessary.

According to one embodiment of the present disclosure, the communication module 210 is configured such that the user terminal 102 communicates with the interactive AI agent server 106 and / or the external service server 108 via the communication network 104 of FIG. 1. Enable communication According to an embodiment of the present disclosure, the communication module 212 is configured such that, for example, signals acquired on the user input receiving module 202 and the sensor module 204 may be interactive AI agents through the communication network 104 according to a predetermined protocol. May be sent to server 106 and / or external service server 108. According to one embodiment of the present disclosure, the communication module 210 may, for example, receive various signals, such as voice and / or the like, from the interactive AI agent server 106 and / or the external service server 108 via the communication network 104. Alternatively, a response signal or various control signals including a natural language response in text form may be received, and appropriate processing may 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 disclosure, 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 one embodiment of the present disclosure, 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 an embodiment of the present disclosure, the response output module 212 may include a motion / haptic feedback generator, thereby providing a tactile response, eg, motion / haptic feedback, to a user. In accordance with one embodiment of the present disclosure, 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 106 of FIG. 1, in accordance with an embodiment of the present disclosure. As shown, the interactive agent server 106 includes 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 management module 312, conversation generation module 314, and text-to-speech (TTS) module 316.

According to one embodiment of the present disclosure, the communication module 302 is configured such that the interactive AI agent server 106 is connected to the user terminal 102 and / or via the communication network 104 according to a predetermined wired or wireless communication protocol. Enable communication with an external service server 108. According to one embodiment of the present disclosure, the communication module 302 includes user input (eg, touch input, voice input and / or text input, etc.) that has been transmitted from the user terminal 102 via the communication network 104. And not limited thereto). According to one embodiment of the present disclosure, the user input may be a request signal of a specific task execution or conversation response.

According to one embodiment of the present disclosure, the communication module 302, along with or separately from the above-described user input, of the user terminal 102, which has been transmitted from the user terminal 102, via the communication network 104. Status information can be received. According to one embodiment of the present disclosure, the state information may include, 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. According to one embodiment of the present disclosure, the communication module 302 may further include a conversation response (eg, voice and / or textual natural language) generated by the interactive AI agent server 106 in response to the received user input. And / or control signals, etc.) and / or control signals may be performed as necessary to communicate to the user terminal 102 via the communication network 104.

According to an embodiment of the present disclosure, 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 one embodiment of the present disclosure, 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 disclosure, 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 may be generated, such as a sequence of words. According to an embodiment of the present disclosure, the STT module 304 may refer to each user characteristic data of the user database 310 to be described later when converting the received voice input into text data based on pattern matching. .

According to one embodiment of the present disclosure, 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 present disclosure, the text input received at the NLU module 306 is, for example, a user text input or communication module 302 that was received from the user terminal 102 via the communication network 104 at the communication module 302. ) May be a text recognition result generated by the STT module 304 from a user voice input received in the reference numeral). According to one embodiment of the present disclosure, 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 one embodiment of the present disclosure, the NLU module 306 may map the received text input to 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 106 in accordance with the user intent. According to one embodiment of the present disclosure, the NLU module 306 may refer to the aforementioned state information in mapping the received text input to one or more user intents. According to one embodiment of the present disclosure, 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 intents.

According to one embodiment of the present disclosure, conversation understanding knowledge base 308 may include, for example, a predefined ontology model. According to one embodiment of the present disclosure, the ontology model may be represented, for example, in a hierarchical structure between nodes, each node being a "intent" node or a child linked to an "intent" node corresponding to the user's intent. It may be one of the "property" nodes (child "nodes" nodes that are linked directly to "intent" nodes or relinked to "property" nodes of "intent" nodes). According to one embodiment of the present disclosure, an "intent" node and "attribute" nodes that are directly or indirectly linked to the "intent" node may constitute one domain, and the ontology may consist of a collection of such domains. Can be. According to one embodiment of the present disclosure, the conversation 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. Can be. According to one embodiment of the present disclosure, it should be understood that the ontology model may be dynamically changed by adding or deleting nodes, or modifying relationships between nodes.

According to one embodiment of the present disclosure, intent nodes and attribute nodes of each domain in the ontology model may be associated with words and / or phrases related to corresponding user intents or attributes, respectively. According to one embodiment of the present disclosure, 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, for example in the form of a lexical dictionary (specific (Not shown), the NLU module 306 may determine the user intent based on the ontology model implemented in the form of a lexical dictionary. For example, according to one embodiment of the present disclosure, upon receiving text input or a sequence of words, the NLU module 306 may determine which words of which domain in the ontology model are associated with each word in the sequence, Based on such a determination, the corresponding domain, ie user intent, can be determined.

However, when the NLU module 306 analyzes the text input based on the ontology model of the lexical dictionary type on the dialogue understanding knowledge base 308 described above, a so-called failure case may occur, in which the proper intent cannot be determined. . For example, instead of including a given word or phrase defined as being received that is mapped to a particular intent, the received text input bypasses the desired intent by listing entity information that has nothing to do with the given word or phrase. If you can express it. As mentioned earlier, for example, user input entered on an interactive AI agent server for a customer service center may not indicate an intent of a direct and explicit delivery complaint that "delivery is delayed" ( That is, you don't use the words "delivery", "late", etc.), "I ordered something on January 3rd, but it's already February 3rd." There may be cases where the intent of a delivery complaint is indirectly derived from a relationship between them. This indirect representation of intent may occur frequently (but is not limited to this), primarily when there are complaints, and because the word for complaint is not explicitly used, a search of the ontology model in the form of a lexical dictionary can be used. It may be difficult to determine the appropriate intent.

According to one embodiment of the present disclosure, the NLU module 306 determines an appropriate intent from an ontology model in the form of a lexical dictionary on the conversation understanding knowledge base 308 and, if a failure case occurs therefrom, follows a predetermined rule. Thus, a plurality of entities present in the input can be analyzed and an appropriate intent can be determined based thereon. According to one embodiment of the present disclosure, assuming, for example, an interactive AI agent server 106 that provides a service related to shopping, the NLU module 306 may, if an entity of the same type appear repeatedly multiple times. Input can be processed by defining rules to map to intents for complaints or return requests.

According to an embodiment of the present disclosure, the NLU module 306 analyzes the relationship of a plurality of entities existing in the received input and combines the words having a predetermined meaning present in the input with the result of analyzing the relationship of the entities. You can decide the tent. According to an embodiment of the present disclosure, for example, in the case of shopping, entity information having the same type but different values appears as a word representing quality such as size, color, performance, price, etc. At the same time, if there is a word on the input indicating completion of the order or delivery, the input may set a rule to correspond to the intent of the complaint or return request. For example, "Usually I wear 260mm shoes, but this brand should have ordered 270mm", "Here I paid 12,000 won and the other place was 10,000 won." "" I bought it because the speed is 100Mbps, but I don't think it's 50Mbps "," I ordered red, but it's blue, "etc.," 260mm "and" 270mm "," 12,000 won "and" 10,000 won ", Multiple entities of the same type (such as words using the same units) that have the same units, such as "free" and "2,000 won", "100 Mbps" and "50 Mbps", "red" and "blue," If words such as "should have been ordered", "I have paid", "I have paid", "I bought", "I ordered" and "I have ordered" are present to indicate the completion of an order or delivery, these sentences may be You can see that the tent is implicit The.

According to an embodiment of the present disclosure, in the case of, for example, shopping, entity information having different dates appears several times during a received input, and at the same time a word indicating order or delivery is present on the input. In such a case, such an input may set a rule to correspond to an intent regarding a delivery inquiry or a complaint. For example, "I ordered on January 3rd, but today is February 3rd" or "I bought it on March 3rd when I bought it, but I got it on March 7th". Multiple dates appear, such as "3rd", "3rd February", "3rd March", and "7th March", while orders or shipments such as "Order", "When You Buy", and "Received." If the word indicating the completion of the present, it can be seen that these sentences implicitly indicate the intent of the delivery inquiry or complaints.

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

According to an embodiment of the present disclosure, as described above, the STT module 304 refers to each user characteristic data of the user database 310, for example, a pronunciation characteristic for each user, when converting a voice input into text data. You can get more accurate text data. According to one embodiment of the present disclosure, the NLU module 306 determines more accurate user intent by referring to each user characteristic data of the user database 310, such as each user's characteristic or context, when determining the user intent. can do. According to one embodiment of the present disclosure, 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 this 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 106, but the present disclosure is not limited thereto. According to another embodiment of the present disclosure, a user database 310 for storing and managing characteristic data for each user may exist in the user terminal 102, for example, and the user terminal 102 and the interactive AI agent server 106. It should be noted that they may be distributed in

According to one embodiment of the present disclosure, the conversation management module 312 may generate a series of operation flows corresponding thereto according to the user intent determined by the NLU module 306. According to one embodiment of the present disclosure, the conversation management module 312 is based on a certain conversation flow management model, for example, in response to a user intent received from the NLU module 306, for example, any conversation response and And / or determine whether to perform a task execution and generate a detailed operational flow accordingly.

According to one embodiment of the present disclosure, the conversation generation module 314 may generate a conversation response to be provided to the user based on the conversation flow generated by the conversation management module 312. According to an embodiment of the present disclosure, the conversation generating module 314 may, in the generation of the conversation response, user characteristic data (eg, a previous conversation record of the user, pronunciation characteristic information of the user, and the like) of the user database 310 described above. User vocabulary preferences, user's location, setting language, contact / friend list, each user's previous conversation, etc.).

According to one embodiment of the present disclosure, the TTS module 316 may receive a conversation response generated to be sent to the user terminal 102 by the conversation generation module 314. The conversation response received at the TTS module 316 may be a natural language or a sequence of words in text form. According to an embodiment of the present disclosure, the TTS module 316 may convert the received text form input into a speech form according to various types of algorithms.

In the embodiments of the present disclosure described above with reference to FIGS. 1 to 3, the interactive AI agent system allows the client-server model between the user terminal 102 and the interactive AI agent server 106, in particular the client, to provide only user input / output functions. Although described as being implemented based on a so-called "thin client-server model," which provides and delegates all other functionality of the interactive AI agent system to the server, the present disclosure is not so limited. According to another embodiment of the present disclosure, the interactive AI agent system should be aware 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 the functions between the user terminal and the server according to an embodiment of the present disclosure, the distribution of each function of the interactive AI agent system between the client and the server may vary from embodiment to embodiment. It should be appreciated that other implementations may be made.

In addition, in the embodiment of the present disclosure described above with reference to FIGS. 1 to 3, for convenience, a specific module has been described as performing certain operations, but the present disclosure is not limited thereto. According to another embodiment of the present disclosure, 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 is a flow diagram illustrating an example operational flow for user intent determination performed by an interactive AI agent system for a shopping service, in accordance with an embodiment of the present disclosure.

In step 402, the interactive AI agent system may receive input from a user. Then, at step 404, the interactive AI agent system may determine whether words or phrases defined as corresponding to the predetermined intent are included in the received input. If at step 404 it is determined that such words are included in the input, the procedure proceeds to step 406 and the interactive AI agent system may map the received input to the corresponding intent.

In step 404, if it is determined that words defined as corresponding to a given intent are not included in the received input, the procedure proceeds to step 408 and the interactive AI agent system receives the received input. In the meantime, it is possible to determine whether there is a word indicating the completion of an order or delivery while the entity information having different values as the entity of the same type indicating the quality appears multiple times. At step 408, if determined to be such, the procedure proceeds to step 410 and the interactive AI agent system may map the received input to an intent of the complaint or return request.

In step 408, if it is determined during the received input that entity information with different values as an entity of the same type indicating quality does not appear multiple times or a word indicating completion of an order or delivery does not exist, the procedure Proceeds to step 412. In step 412, the interactive AI agent system determines whether, among the received inputs, entity information with different dates appears multiple times and at the same time a word indicating order or delivery exists on that input. If determined to proceed, the procedure may proceed to step 414 to map the received input to a delivery inquiry or insolvency intent. In step 412, if it is determined that the entity information having different dates during the received input does not appear multiple times or that the words indicating the order or delivery do not exist, the procedure proceeds to step 416, where the interactive The AI agent system may determine that the intent determination for the input fails.

As will be appreciated by those skilled in the art, the present disclosure is not limited to the examples described herein but may be variously modified, reconfigured and replaced without departing from the scope of the present disclosure. 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 disclosure may include a storage medium readable by a computer processor or the like, such as an EPROM, an EEPROM, a nonvolatile memory such as 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 this disclosure are intended to be covered by the following claims.

Claims (1)

Intent determination method of natural language input performed by interactive AI agent system.

Images