KR101932264B1 - 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 intent of a natural language input performed by an interactive AI agent system. The method comprises the steps of: receiving a natural language input from a user; determining whether a word or phrase defined as corresponding to arbitrary intent on a predetermined word dictionary model is included in the natural language input; mapping the natural language input to corresponding intent if it is determined that the word or phrase is included in the natural language input; extracting multiple pieces of entity information of the same type from the natural language input if it is determined that the word or phrase is not included in the natural language input; and mapping the natural language input to predetermined intent based on the extracted multiple pieces of the entity information of the same type.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method and an interactive AI agent system for providing an intent determination based on the analysis of a plurality of the same types of entity information and a computer readable recording medium having an interactive AI agent system and computer readable recording medium. OF A PLURALITY OF SAME TYPE ENTITY INFORMATION}

This disclosure relates to the interactive understanding of an interactive AI agent system and more particularly to an interactive AI agent system in which the intent of the user input can be determined based on the relationship between the entities included in the user input Understanding of the conversation being performed, and so on.

Description of the Related Art [0002] In recent years, with the development of artificial intelligence fields, especially natural language understanding fields, it has become possible to move away from the machine operation according to the conventional machine-centered command input / output method and to allow users to use natural language in a more human-friendly manner such as voice and / Interactive AI agent systems are increasingly being developed and utilized to interactively manipulate machines and obtain desired services from machines. Accordingly, in various fields, including but not limited to, an online consultation center or an online shopping mall, a user may request a desired service from the interactive AI agent system through natural language conversation in voice and / or text form More and more people want to get the results they want from them.

In such an interactive AI agent system, when an input of a natural language is made by a user, what is the intent of inputting the natural language, that is, determining the intent is an important process. The determination of the intent by the interactive AI agent system is based mainly on the presence of certain words having a predetermined meaning from the natural language input of the user. The entity information (for example, parameter information having a specific attribute and format such as date, name, time, telephone number, etc. as variables that can be included in inputting the user's natural language, etc.) The intent of the natural language input is determined and then used as a parameter value for obtaining the answer to the determined intent.

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

However, in conversations that occur between real people, expressions are explicitly intended using certain words having certain meanings, but instead of using words that include such specific explicit intention, (For example, in a case where the customer intends to display the intent directly and explicitly indicating " delivery is delayed " in the customer service center) Instead of displaying the tent, if we listed two date entities as "I ordered an item on January 3, but today is already on February 3" and indirectly indicate the intent of the delivery complaint from that relationship, etc. ).

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

According to one aspect of the present disclosure, a method for determining an 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 an arbitrary intent on a predetermined vocabulary dictionary model is included in natural language input; Mapping a natural language input to a corresponding intent if it is determined that the word or phrase is included in the natural language input; Extracting a plurality of identical types of entity information from the natural language input if it is 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 the same type of entity information.

According to one embodiment of the present disclosure, the step of mapping a natural language input to a predetermined intent comprises: a step of, based on the extracted plurality of the same type of entity information and a combination of words having a predetermined meaning existing during natural word input, And mapping the natural language input to a predetermined intent.

According to one embodiment of the present disclosure, the interactive AI agent system is configured to provide a service relating to shopping, and the step of mapping the natural language input to a predetermined intent comprises the steps of: Determining whether each of the plurality of entities has different values as entities of the same type related to quality, and whether there is a word indicating completion of the order or delivery during natural language input; And mapping the natural language input to an intent of a complaint or a return request based on the determination result.

According to one embodiment of the present disclosure, whether or not the extracted plurality of identical types of entity information are entities of the same type related to quality, respectively, indicates that the extracted plurality of identical types of entity information are different in size, color, performance, and price And may be determined depending on whether or not they are entities commonly associated with one.

According to one embodiment of the present disclosure, the interactive AI agent system is configured to provide a service relating to shopping, and the step of mapping the natural language input to the predetermined intent includes: Determining whether there is a word associated with the order or delivery during natural language input; And mapping the natural language input to an intent of the delivery inquiry or delivery complaint based on the determination result.

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

According to another aspect of the present disclosure, there is provided an interactive AI agent system for providing natural language understanding, comprising: a user input receiving module configured to receive natural language input from a user; Knowledge base model in vocabulary dictionary; 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 an arbitrary intent on the knowledge base 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, And if the word or phrase is judged not to be contained in the natural language input, extracts a plurality of pieces of entity information from the natural language input, and based on the extracted plurality of the same type of entity information, To a predetermined intent.

The interactive AI agent system according to the present disclosure is characterized in that even when it fails to determine the intent based on the presence of specific words having a predetermined meaning on the user input, Can be determined.

1 is a schematic diagram of a system environment in which an interactive AI agent system may be implemented, in accordance with one embodiment of the present disclosure;
Figure 2 is a functional block diagram that schematically illustrates the functional configuration of the user terminal 102 of Figure 1, in accordance with one embodiment of the present disclosure.
FIG. 3 is a functional block diagram that schematically illustrates the functional configuration of the interactive AI agent server 106 of FIG. 1, in accordance with one embodiment of the present disclosure.
4 is a flow diagram illustrating an exemplary operational flow for user intent determination performed by an interactive AI agent system for a shopping service, in accordance with one embodiment of the present disclosure;

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Hereinafter, when it is judged that there is a possibility that the gist of the present disclosure may be unnecessarily blurred, a detailed description of known functions and configurations will be omitted. It is also to be understood that the following description is merely illustrative of the embodiments of the present disclosure and the present disclosure is not limited thereto.

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

In the embodiments of the present disclosure, 'module' or 'sub-module' means a functional part that performs at least one function or operation, and may be implemented in hardware or software, or a combination of hardware and software. Also, a plurality of "modules" or "sub-modules" may be integrated into at least one software module and implemented by at least one processor, except for "module" or "sub-module" have.

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

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

1 is a schematic diagram of a system environment 100 in which an interactive AI agent system may be implemented, in accordance with one embodiment of the present disclosure. 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. As shown in FIG.

According to one embodiment of the present disclosure, each of the plurality of user terminals 102a-102n may be any user electronic device having wired or wireless communication capability. Each of the user terminals 102a-102n may be a variety of wired or wireless communication terminals, including, for example, a smart speaker, a music player, a game console, a digital TV, a set top box, a smart phone, a tablet PC, a desktop, a laptop, It is to be understood that the invention 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, i. E., Via the communication network 104, with the necessary information. According to one embodiment of the present disclosure, each of the user terminals 102a-102n may communicate with the external service server 108, i. E., Via the communication network 104, with the necessary information. In accordance with one 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 communicate with an interactive AI agent server (E.g., user authentication, provision of a specific conversation response) obtained via communication with the external service server 108 (e.g., the user terminal 102) and / or with the external service server 108 And / or performing certain tasks, etc.).

In an embodiment of the present disclosure, task execution as an operation corresponding to user input may be accomplished by, for example, searching for information, purchasing goods, composing a message, creating an email, dialing, playing music, photographing, And the like, as well as performing various various types of tasks (but not limited thereto). In accordance with one embodiment of the present disclosure, each of the user terminals 102a-102n may provide an interactive response as a result of an operation corresponding to a user input, in a visual, audible and / or tactile form (e.g., voice, Images, symbols, emoticons, hyperlinks, animations, various notices, motion, haptic feedback, and the like), and the like.

According to one embodiment of the present disclosure, the communication network 104 may comprise any wired or wireless communication network, e.g., 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, and the present disclosure is not limited thereto. In accordance with one embodiment of the present disclosure, the communication network 104 may be any of a variety of wired or wireless, including, but not limited to, Ethernet, GSM, EDGE, CDMA, TDMA, OFDM, Bluetooth, VoIP, Wi- May be implemented using a communication protocol.

In accordance with 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 one embodiment of the present disclosure, the interactive AI agent server 106 sends and receives necessary information to and from the user terminals 102a-102n via the communication network 104, An operation result corresponding to the user input, i.e., a user intent, may be provided to the user.

In accordance with one embodiment of the present disclosure, the interactive AI agent server 106 receives user natural language input of voice, text, and / or touch form, for example, from the user terminals 102a-102n via the communication network 104 , And process the received natural language input based on previously prepared models to determine the user's intent. According to one embodiment of the present disclosure, the interactive AI agent server 106 may cause a corresponding operation to be performed based on the determined determined user intent. In accordance with one embodiment of the present disclosure, the interactive AI agent server 106 generates a specific control signal, e.g., to cause the user terminal 102a-102n to perform a particular task that matches the user intent, -102n. ≪ / RTI > In accordance with one embodiment of the present disclosure, the interactive AI agent server 106 may be configured to communicate with an external service (e. G., Via a communication network 104), such as, for example, a user terminal 102a-102n to perform a particular task, The server 108 can be connected.

According to one embodiment of the present disclosure, the interactive AI agent server 106 may generate and send a specific interactive response, e.g., consistent with a user intent, to the user terminals 102a-102n. According to one embodiment of the present disclosure, the interactive AI agent server 106 generates a corresponding interactive response in the form of voice and / or text, based on the determined determined user intent, and transmits the generated response to the communication network 104 to the user terminals 102a-102n. In accordance with one embodiment of the present disclosure, the interactive response generated by the interactive AI agent server 106 may include other visual elements such as images, video, symbols, emoticons, etc., along with the natural language responses of the speech and / Or other auditory elements such as sound, or other tactile elements. In accordance with one embodiment of the present disclosure, a response of the same type on the interactive AI agent server 106, depending on the type of user input received on the user terminal 102a-102n (e.g., whether it is speech input or text input) (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 this disclosure is not so limited. It should be appreciated that, in accordance with another embodiment of the present disclosure, responses in the form of voice and / or text may be generated and provided regardless of the type 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 previously mentioned. The external service server 108 may be, for example, an online consultation center server, an online shopping mall server, an information search server, and the like, and the present disclosure is not limited thereto. In accordance with one embodiment of the present disclosure, an interactive response based on a user intent, which is communicated from the interactive AI agent server 106 to the user terminals 102a-102n, It should be noted that this may include data content.

Although the interactive AI agent server 106 is shown as being a separate physical server configured to communicate with the external service server 108 via the communication network 104, 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.

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

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

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

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

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 can 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 signals obtained from the user input receiving module 202 and the sensor module 204, if necessary, and perform appropriate processing on these signals have. According to one embodiment of the present disclosure, the processing module 208 may, if necessary, perform appropriate processing on signals received from the outside via the communication module 210.

According to one embodiment of the present disclosure, the communication module 210 is configured to allow the user terminal 102 to communicate with the interactive AI agent server 106 and / or the external service server 108 via the communication network 104 of FIG. 1 Communication. According to one embodiment of the present disclosure, the communication module 212 is configured to receive signals from, for example, the user input receiving module 202 and the sensor module 204 via the communication network 104 in accordance with a predetermined protocol, To server 106 and / or to external service server 108. [ In accordance with one embodiment of the present disclosure, the communication module 210 may provide various signals received from the interactive AI agent server 106 and / or the external service server 108 via the communication network 104, e.g., voice and / Or a response signal including a natural language response in the form of a text, or various control signals, and perform appropriate processing according to a predetermined protocol.

According to one embodiment of the present disclosure, the response output module 212 may output a response corresponding to a user input in various forms, such as time, audible and / or tactile. According to one embodiment of the present disclosure, the response output module 212 includes a speaker or a headset, for example, and provides an audible response, e.g., voice and / or acoustic response, 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 technology such as LCD, LED, OLED, QLED, etc., Such as text, symbols, video, images, hyperlinks, animations, various notices, etc., to the user. According to one embodiment of the present disclosure, the response output module 212 includes a motion / haptic feedback generator, through which a tactile response, e.g., motion / haptic feedback, can be provided to the user. It should be appreciated that, in accordance with one embodiment of the present disclosure, the response output module 212 may concurrently provide any combination of two or more of a text response, a voice response and a motion / haptic feedback corresponding to a user input.

FIG. 3 is a functional block diagram that schematically illustrates the functional configuration of the interactive AI agent server 106 of FIG. 1, in accordance with one embodiment of the present disclosure. The interactive agent server 106 includes a communication module 302, a Speech-To-Text (STT) module 304, a Natural Language Understanding (NLU) module 306 A dialogue understanding knowledge base 308, a user database 310, a dialogue management module 312, a dialogue generation module 314 and a speech-to-speech (TTS) module 316.

According to one embodiment of the present disclosure, the communication module 302 is configured to allow the interactive AI agent server 106 to communicate with the user terminal 102 and / or via the communication network 104, in accordance with any wired or wireless communication protocol, Thereby enabling communication with the external service server 108. According to one embodiment of the present disclosure, the communication module 302 includes user input (e.g., including touch input, voice input and / or text input, etc.) transmitted from the user terminal 102 via the communication network 104 And is not limited thereby). According to one embodiment of the present disclosure, the user input may be a request signal of a particular task execution or conversation response.

According to one embodiment of the present disclosure, the communication module 302 is coupled to the user terminal 102, which has been transmitted from the user terminal 102, via the communication network 104, with or without the user input, Status information can be received. According to one embodiment of the present disclosure, the state information may include various state information (e.g., the physical state of the user terminal 102, the software of the user terminal 102) associated with the user terminal 102 at the time of user input, And / or hardware state, environmental state information around the user terminal 102, etc.). In accordance with one embodiment of the present disclosure, communication module 302 may also include an interactive response (e. G., Natural language in voice and / or text form) generated in interactive AI agent server 106 in response to the user input received above. And / or control signals to the user terminal 102 via the communication network 104. The user terminal 102 may be connected to the user terminal 102 via the network 104,

According to one embodiment of the present disclosure, the STT module 304 can receive voice input from user input received via 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 extract a feature from a user's speech input to generate a feature vector sequence. According to one embodiment of the present disclosure, the STT module 304 may be implemented using a DTW (Dynamic Time Warping) method, an HMM model (Hidden Markov Model), a GMM model (Gaussian-Mixture Mode), a deep neural network model, For example, a sequence of words, based on various statistical models of the speech recognition results. According to one embodiment of the present disclosure, the STT module 304 may refer to each user characteristic data of the user database 310, described below, 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 text input from the communication module 302 or the STT module 304. The textual input received at the NLU module 306 may be transmitted to the user terminal 102 via a user text input or communication module 302 that has been received from the user terminal 102 via the communication network 104, For example, a sequence of words, generated by the STT module 304 from the user speech input received at the STT module 304. [ In accordance with one embodiment of the present disclosure, the NLU module 306, upon receiving or subsequent to receiving a textual input, receives status information associated with the user input, e.g., status information of the user terminal 102 at the time of the user input And the like. As described above, the status information may include various status information (e.g., the physical state of the user terminal 102, the software status of the user terminal 102) associated with the user terminal 102 at the time of user input and / And / or hardware state, environmental state information around the user terminal 102, etc.).

According to one embodiment of the present disclosure, the NLU module 306 may map the received text input to one or more user-defined intents based on a dialog understanding knowledge base 308, described below. Where the user intent can be associated with a series of operations (s) that can be understood and performed by the interactive AI agent server 106 according to the user's tent. According to one embodiment of the present disclosure, the NLU module 306 may refer to the state information described above 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 refer to 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, the conversation understanding knowledge base 308 may include, for example, a predefined ontology model. According to one embodiment of the present disclosure, an ontology model can be represented, for example, in a hierarchical structure between nodes, each node having an " intent " node corresponding to the user's intent or a &Quot; Attributes " node that is linked directly to an " Attributes " node or a " Attributes " node of an " Attributes " According to one embodiment of the present disclosure, the " intent " node and the " attribute " nodes directly or indirectly linked to the " intent " node can constitute one domain and the ontology comprises a set of such domains . According to one embodiment of the present disclosure, the dialogue understanding knowledge base 308 is configured to include domains corresponding to all intents, e.g., which the interactive AI agent system can understand and perform corresponding actions . It should be noted that, according to one embodiment of the present disclosure, the ontology model can be dynamically changed by addition or deletion of nodes, or modification of relations between nodes.

According to one embodiment of the present disclosure, the intent nodes and attribute nodes of each domain in the ontology model may be associated with words and / or phrases associated with the corresponding user's tent or attributes, respectively. According to one embodiment of the present disclosure, the conversation understanding knowledge base 308 includes an ontology model 308 that includes an ontology model including hierarchical nodes and a set of words and / or phrases associated with each node, , And the NLU module 306 may determine the user intent based on the ontology model implemented in the lexical dictionary form. For example, according to one embodiment of the present disclosure, the NLU module 306, upon receipt of a text input or a sequence of words, can determine which of the domains in the ontology model the respective words in the sequence are associated with, Based on such a determination, it is possible to determine the corresponding domain, i. E. The user tent.

However, when the NLU module 306 analyzes the text input based on the ontology model of the lexical dictionary form on the dialogue understanding knowledge base 308 described above, a so-called failure case may occur in which the appropriate intent is not determined . For example, instead of including a predetermined word or phrase defined as being mapped to a particular intent, the received textual entry may be arranged to bypass the desired intent by listing entity information that is entirely independent of the predetermined word or phrase And so on. As previously mentioned, for example, if the user input entered on the interactive AI agent server for the customer consultation center is replaced with an intent indication of direct and explicit delivery complaint " shipping is delayed " That is, I do not use the words "shipping", "late", etc.), "I ordered an item on January 3, but today is already February 3" There may be cases in which the intent of the delivery complaint is indirectly indicated from the relationship between the two. These indirect intent expressions can often occur (but are not limited to) when there is a major dissatisfaction, and since the word indicating dissatisfaction has not been explicitly used, the search of the ontology model of the vocabulary dictionary allows the user It may be difficult to determine an appropriate intent.

According to one embodiment of the present disclosure, the NLU module 306 determines an appropriate intent from the ontology model of the vocabulary dictionary form on the dialog understanding knowledge base 308 and, if a failure case occurs therefrom, Accordingly, a plurality of entities present at the input may be analyzed and an appropriate intent determined based thereon. In accordance with one embodiment of the present disclosure, for example, assuming an interactive AI agent server 106 that provides a service related to shopping, the NLU module 306, when an entity of the same type appears repeatedly a plurality of times, Inputs can be routed and mapped to intents for complaints or return requests.

According to one embodiment of the present disclosure, the NLU module 306 combines the results of analyzing the relationships of a plurality of entities present in the received input, together with words having a predetermined meaning present in the input, The tent can be determined. According to one embodiment of the present disclosure, for example, in the case of shopping, the entity information having the same type and different values as the words indicating the quality such as size, color, performance, price and the like appears a plurality of times during the received input And there is a word indicating the completion of the order or delivery on the corresponding input, such input may set the rule to correspond to the intent of the complaint or return request. For example, "Normally I wear shoes 260mm, I should have ordered 270mm.", "I paid 12,000 won here, and 10,000 other places.", "The other places are free of charge. 260mm "," 270mm "," 12,000won "and" 10,000won ", as shown in the sentences such as" Yes, I bought it at 100Mbps, I do not get 50Mbps, Entities of the same type such as "free" and "2,000 won", "100 Mbps" and "50 Mbps", "red" and "blue" If there are words indicating completion of an order or delivery such as "ordered", "paid", "paid", "bought", "ordered" and "come" It can be seen that the tent is implied. The.

According to one embodiment of the present disclosure, for example, in the case of shopping, the entity information having different dates is displayed a plurality of times during the received input, and at the same time, there is a word indicating order or delivery on the corresponding input , Such input may set rules to correspond to intents regarding delivery inquiries or delivery complaints. For example, as you can see from sentences such as "I ordered on January 3, today is February 3" and "I said I needed it on March 3 when I was living, but I got it on March 7" Orders or deliveries such as "order", "buy", "received", etc., while different dates appear, such as "3 days", "February 3", "March 3", and "March 7" , The sentences implicitly indicate the intent of the delivery inquiry or delivery complaint.

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

According to one embodiment of the present disclosure, as described above, the STT module 304 may be configured to determine each user characteristic data of the user database 310, e.g., , More accurate text data can be obtained. According to one embodiment of the present disclosure, the NLU module 306 is configured to determine a more accurate user tent determination by referring to each user characteristic data of the user database 310, e.g., characteristics or contexts for each user, can do. According to one embodiment of the present disclosure, as described below, the dialog generation module 316 may refer to user characteristic data of the user database 310 at the time of generating the conversation response.

In this figure, a user database 310 for storing and managing characteristic data for each user is shown as being arranged in the interactive AI agent server 106, but the present disclosure is not limited thereto. According to another embodiment of the present disclosure, the user database 310, which stores and manages the characteristic data for each user, may reside, for example, at the user terminal 102, and may include a user terminal 102 and an interactive AI agent server 106 As shown in FIG.

In accordance with one embodiment of the present disclosure, the conversation management module 312 may generate a corresponding series of operational flows in accordance with the user ' s tent determined by the NLU module 306. [ In accordance with one embodiment of the present disclosure, the conversation management module 312 may determine, based on a predetermined conversational flow management model, any actions, e.g., any conversation responses and / or actions, corresponding to the user ' s tent received from the NLU module 306, / RTI > and / or task execution should be performed, and generate a corresponding detailed action flow.

In accordance with one embodiment of the present disclosure, the dialog generation module 314 may generate an interaction response to be provided to the user based on the conversation flow generated by the conversation management module 312. [ In accordance with one embodiment of the present disclosure, the dialog generation module 314, in the generation of the conversation response, generates user characteristic data (e.g., user's previous conversation history, user's pronunciation feature information, A user's lexical preference, a user's location, a set language, a contact / friend list, and a previous conversation record of the user for each user).

According to one embodiment of the present disclosure, the TTS module 316 may receive an interactive response that is generated by the dialog generation module 314 to be transmitted to the user terminal 102. [ The conversation response received at the TTS module 316 may be a natural word or a sequence of words having a textual form. According to one embodiment of the present disclosure, the TTS module 316 may convert the input of the received text form into a speech form, according to various types of algorithms.

In the embodiment of the present disclosure described above with reference to Figures 1-3, it is assumed that the interactive AI agent system is a client-server model between the user terminal 102 and the interactive AI agent server 106, And is based on a so-called " thin client-server model ", which delegates all other functions of the interactive AI agent system to the server, but this disclosure is not so limited. According to another embodiment of the present disclosure, it should be understood that the interactive AI agent system may be implemented in a distributed manner between a user terminal and a server, or alternatively may be implemented as a standalone application installed on a user terminal . In addition, when an interactive AI agent system implements the functions distributed between a user terminal and a 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 is It should be understood that the invention may be otherwise embodied.

Further, although the embodiments of the present disclosure described above with reference to Figs. 1 to 3 have been described as if a particular module performs certain operations for convenience, the present disclosure is not limited thereby. It should be noted that, in accordance with another embodiment of the present disclosure, the operations described above as performed by any particular module in the above description can be performed by separate and distinct modules, respectively.

4 is a flow diagram illustrating an exemplary operational flow for user intent determination performed by an interactive AI agent system for a shopping service, in accordance with one 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 a given intent are included in the received input. In step 404, if 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.

If it is determined at step 404 that words defined as corresponding to a given intent are not included in the received input, then the procedure proceeds to step 408 and the interactive AI agent system determines if the received input The entity information having different values as the entity of the same type indicating the quality appears a plurality of times and it can be determined whether there is a word indicating the completion of the order or the delivery. At step 408, if so, the procedure proceeds to step 410 and the interactive AI agent system may map the received input to an intent of a complaint or return request.

In step 408, if it is determined that, during the received input, the entity information having different values as an entity of the same type indicating the quality has not appeared a plurality of times, or that there is no word indicating completion of the order or delivery, The process proceeds to step 412. In step 412, the interactive AI agent system determines, during the received input, that the entity information having different dates appears a plurality of times, and that there is a word indicating order or delivery on the input, The procedure may proceed to step 414 to map the received input to an intent of the delivery inquiry or delivery complaint. If it is determined in step 412 that the entity information indicating different dates in the received input does not appear multiple times or that there is no word indicating order or delivery, then the procedure proceeds to step 416, The AI agent system may determine that the intent determination for that input has failed.

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, rearranged, and replaced within the scope of the present disclosure. It should be understood that the various techniques described herein may be implemented in hardware or software, or a combination of hardware and software.

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

Claims (7)

A method of determining intent of a natural language input performed by an interactive AI agent system, the interactive AI agent system being configured to provide a service related to shopping,
Receiving natural language input from a user;
Determining whether a word or phrase defined as corresponding to an arbitrary intent on a predetermined lexical dictionary model 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 included in the natural language input;
Extracting a plurality of parameter values from the natural language input when the word or phrase is not included in the natural language input, the plurality of parameter values being extracted having the same attribute and format, Quality related, with different values, or all representing different dates; And
Mapping the natural language input to a predetermined intent based on the extracted plurality of parameter values
≪ / RTI > The method according to claim 1,
Wherein mapping the natural language input to a predetermined intent comprises: inputting the natural language input to the predetermined intent based on a combination of the extracted plurality of parameter values and words having a predetermined meaning existing in the natural language input, The method comprising the steps of: 3. The method of claim 2,
Wherein the step of mapping the natural language input to a predetermined intent comprises:
Determining whether there is a word indicating completion of order or delivery during the natural language input when the extracted plurality of parameter values are related to the quality of the goods and have different values; And
And mapping the natural language input to an intent of a complaint or return request when it is determined that there is a word indicating completion of an order or delivery during the natural language input. The method of claim 3,
Wherein whether the extracted plurality of parameter values is related to the quality of the goods is determined based on whether the extracted plurality of parameter values are commonly related to one of size, color, performance, and price, respectively, Determination method. 3. The method of claim 2,
Wherein the step of mapping the natural language input to a predetermined intent comprises:
Determining whether a word associated with an order or delivery is present during the natural language input if the extracted plurality of parameter values represent different dates; And
And mapping the natural language input to an intent of a delivery inquiry or delivery complaint if it is determined that there is a word associated with the order or delivery during the natural language entry. A computer-readable medium having stored thereon one or more instructions,
Wherein the one or more instructions cause the computer to perform the method of any one of claims 1 to 5 when executed on a computer. An interactive AI agent system for providing natural language understanding, the interactive AI agent system being configured to provide a service related to shopping,
A user input receiving module configured to receive natural language input from a user;
Knowledge base model in vocabulary dictionary; And
Includes natural language understanding module,
The natural language understanding module comprises:
Determining whether a word or phrase defined as corresponding to an arbitrary intent on the knowledge base model 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 included in the natural language input,
Extracting a plurality of parameter values from the natural language input when the word or phrase is determined not to be included in the natural language input; and extracting a plurality of parameter values from the natural language input, And have different values, or all represent different dates -
And to map the natural language input to a predetermined intent based on the extracted plurality of parameter values.
Interactive AI agent system.

Images