KR20190094087A - User terminal including a user customized learning model associated with interactive ai agent system based on machine learning, and computer readable recording medium having the customized learning model thereon - Google Patents

Abstract

Provided is a user terminal. According to the present invention, the user terminal comprises: a user input module configured to receive a natural language input from a user; and an interactive AI agent module configured to provide an interactive AI agent service based on the natural language input, wherein the interactive AI agent service is provided using an adaptive learning model constructed according to a machine learning method. The adaptive learning model is configured to include a user customized learning model consistently learned and updated based on user-related characteristics data obtained from interaction with the interactive AI agent module by the user. The user customized learning model is stored in the user terminal. The learning and update of the user customized learning model are performed in the user terminal.

Description

USER TERMINAL INCLUDING A USER CUSTOMIZED LEARNING MODEL ASSOCIATED WITH INTERACTIVE AI AGENT SYSTEM BASED ON MACHINE LEARNING, AND COMPUTER READABLE RECORDING MEDIUM HAVING THE CUSTOMIZED LEARNING MODEL THEREON}

The present disclosure relates to a user terminal that includes a user-tailored learning model associated with a machine learning based interactive AI agent system, and more particularly based on user characteristic data generated by interaction with the interactive AI agent system. The present invention relates to a user terminal including a user-tailored learning model for learning and updating optimized for each user.

In recent years, with advances in the field of artificial intelligence, in particular in the field of understanding natural language, the user has moved away from the operation of the traditional machine-oriented command input / output schemes, thereby allowing users to use natural language in a more human-friendly manner, such as speech and / or text. Increasingly, the development and use of interactive AI agent systems, 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, the user can obtain desired services through an interactive AI agent system that provides natural language conversations in the form of voice and / or text. You can be provided.

Recently, beyond the conventional interactive AI agent system which provided only simple question-and-answer dialogue service based on fixed scenarios, the interactive AI agent system that provides more complex domain service based on free speech type voice input is provided. The demand is increasing. In order to provide complex domain services based on free speech input, the interactive AI agent system needs to build knowledge base models for conversation understanding and management and update them continuously.

Patent Document 1: Korean Patent Application Publication No. 10-2011-0072847

In order to improve the performance of the interactive AI agent system, it is necessary to continuously update the knowledge base models. In particular, given that individual conversational aspects and intents may vary, user adaptive update and management of knowledge base models (ie, customized update and management of knowledge base models that take into account the characteristics of each individual user), This may be necessary to improve the performance of the interactive AI agent system.

In recent years, attempts to build and update knowledge base models based on machine learning have been increasing. However, until now, since the construction, updating and management of the knowledge base models of the interactive AI agent system according to this learning were all performed on the server side for all users, such updating and management is sensitive and quick for each user. There is a problem that is not adaptive.

Therefore, by using the characteristic data of each individual user collected through interaction with the interactive AI agent system, it is possible to provide the update and management of adaptive learning models for the corresponding interactive AI agent system adaptively for each user. There is a need.

According to one feature of the present disclosure, a user terminal is provided. A user terminal of the present disclosure includes a user input module configured to receive natural language input from a user; And an interactive AI agent module configured to provide an interactive AI agent service based on natural language input, wherein the interactive AI agent service is provided using an adaptive learning model built according to a machine learning method. The model is configured to include a customized learning model that is continuously learned and updated based on characteristic data about the user obtained from the interaction with the interactive AI agent module by the user, wherein the customized learning model is on the user terminal. Saved, the training and updating of the customized learning model is performed on the user terminal.

According to an embodiment of the present disclosure, the adaptive learning model may further include a general learning model pre-trained by the data prepared in advance according to a machine learning method, and the user terminal may include at least a part of the general learning model. have.

According to an embodiment of the present disclosure, the user terminal may communicate with an external server according to a predetermined communication protocol, and at least part of the general-purpose learning model may be included on the server.

According to one embodiment of the present disclosure, training and updating of the customized learning model may be performed in real time according to an interaction with the interactive AI agent module by the user on the user terminal.

According to an embodiment of the present disclosure, the characteristic data about the user obtained from the interaction with the interactive AI agent module by the user may include recording of the user's utterance, whether or not a recognition / processing failure has occurred regarding the user's utterance, recognition / At least one of a cause and / or a solution when a processing failure occurs, a response by the interactive AI agent module according to a user's utterance record, and / or a task execution record.

According to an embodiment of the present disclosure, the interactive AI agent service may include determining an intent of a user corresponding to a natural language input and providing a conversation response corresponding to the determined intent.

According to another feature of the present disclosure, a computer readable recording medium having a user-customized learning model recorded thereon is provided. The computer readable recording medium of the present disclosure is included in a user terminal, and the customized learning model is used by the interactive AI agent module on the user terminal to provide an interactive AI agent service to the user. And based on characteristic data about the user obtained from the interaction with the interactive AI agent module by the user, configured to be continuously learned and updated on the user terminal.

According to the present disclosure, an adaptive learning model of an interactive AI agent system based on machine learning is generated by data (eg, user history data) or the like according to an interaction of a user with the corresponding interactive AI agent system at a user terminal. Learn and update in real time. Therefore, unlike the conventional case where only the update of the knowledge base model for the entire user is performed on the server side by the interactive AI agent system developer, almost real time regardless of whether the user terminal can be communicated or when the developer is involved, etc. As such, the history and characteristics of individual users may be reflected in a knowledge base model and the like.

1 is a functional block diagram schematically showing a configuration of a user terminal 100 according to an embodiment of the present disclosure.
2 is a functional block diagram schematically illustrating the functional configuration of the interactive AI agent module 110 of FIG. 1, in accordance with an embodiment of the present disclosure.
3 is a functional block diagram schematically illustrating a functional configuration of the conversation / task processing unit 204 of FIG. 2, according to 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 what is described below is only related to an embodiment of the present disclosure, but the present disclosure is not limited thereto.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the 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 an embodiment of the present disclosure, the interactive AI agent system may be a natural language input (eg, a natural language) input from a user through an interactive interaction with a user through a natural language in the form of voice and / or text. Receive and interpret commands, statements, requests, questions, etc.) from a user who has been determined to determine the user's intent and perform the necessary actions based on that user's intent, i.e. provide appropriate conversational response and / or Or any information processing system capable of providing performance of a task, without being limited to a particular form. In an embodiment of the present disclosure, the operation performed by the 'interactive AI agent system' may be, for example, a conversation response and / or a task execution respectively performed according to the intent of the user.

In an embodiment of the present disclosure, the dialogue response provided by the 'interactive AI agent system' may be in visual, auditory and / or tactile form (eg, voice, sound, text, video, image, symbol, emoticon, hyperlink, It may be included in various forms such as, but not limited to, animation, various knots, motion, haptic feedback, and the like. Tasks performed by the interactive AI agent system in embodiments of the present disclosure may, for example, retrieve information, proceed with payment, create a message, create an email, make a phone call, play music, take a picture, search for a user's location, map / Various types of tasks (including, but not limited to, navigation services) may be included.

In an embodiment of the present disclosure, an interactive AI agent system is a chatbot system based on a messenger platform, for example, a chatbot system that exchanges messages with a user on a messenger and provides various information desired by the user or performs a task. It is to be understood that the present disclosure is not limited thereto.

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 this disclosure. .

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

1 is a functional block diagram schematically showing a functional configuration of a user terminal 100 according to an embodiment of the present disclosure. As shown, the user terminal 100 includes a user input receiving module 102, a sensor module 104, a program memory module 106, a processing module 108, an interactive AI agent module 110, a communication module. 112, and a response output module 114.

According to an embodiment of the present disclosure, the user input receiving module 102 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 102 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 102 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 one embodiment of the present disclosure, the user input received at the user input receiving module 102 may be associated with performing a predetermined task, for example, executing a predetermined application or retrieving predetermined information, but the present disclosure is limited thereto. It is not. According to another embodiment of the present disclosure, the user input received by the user input receiving module 102 may require only a simple conversation response regardless of a predetermined application execution or information retrieval.

According to one embodiment of the present disclosure, the sensor module 104 includes one or more different types of sensors, through which the status information of the user terminal 100, for example, the physical state of the corresponding user terminal 100, The software and / or hardware state or information about the environment state of the user terminal 100 may be obtained. According to an embodiment of the present disclosure, the sensor module 104 may include, for example, an optical sensor, and detect an ambient light state of the corresponding user terminal 100 through the optical sensor. According to an embodiment of the present disclosure, the sensor module 104 may include, for example, a movement sensor, and detect whether the corresponding user terminal 100 is moved through the movement sensor. According to an embodiment of the present disclosure, the sensor module 104 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 100 through these sensors. According to another embodiment of the present disclosure, it should be appreciated that the sensor module 104 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 106 may be any storage medium in which various programs that can be executed on the user terminal 100, for example, various application programs and related data, are stored. According to one embodiment of the present disclosure, the program memory module 106 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 106 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 108 may communicate with each component module of the user terminal 100 and perform various operations on the user terminal 100. According to one embodiment of the present disclosure, the processing module 108 may drive and execute various application programs on the program memory module 106. According to one embodiment of the present disclosure, the processing module 108 may receive signals obtained from the user input receiving module 102 and the sensor module 104 and perform appropriate processing on these signals, if necessary. have.

According to an embodiment of the present disclosure, the interactive AI agent module 110 receives a user input in the form of voice, text, and / or touch received through the user input receiving module 102 and according to a machine learning scheme. The received user input may be processed based on the established adaptive learning model to determine the user's intent. According to one embodiment of the present disclosure, the interactive AI agent module 110 also generates a specific conversation response corresponding to the user intent based on a predetermined adaptive learning model and generates a response output module 114 described below. Can be output via According to an embodiment of the present disclosure, the interactive AI agent module 110 may also allow a predetermined task corresponding to the determined user intent to be performed on the user terminal 100.

According to an embodiment of the present disclosure, the above-described predetermined adaptive learning model may include a part of a general learning model that is not specific to an individual user, that is, a part of a general learning model and a part of a user-specific learning model specific to each individual user. have. According to one embodiment of the present disclosure, the interactive AI agent module 110 determines a user intent for user input based on both the user-tailored learning model and the general-purpose learning model portion and performs a corresponding conversation response or task accordingly. Can be provided. According to one embodiment of the present disclosure, the customized learning model part may be built on the user terminal 100 and continuously updated and managed on the user terminal 100. According to an embodiment of the present disclosure, at least a part of the general-purpose learning model part may be included on the user terminal 100 in a pre-learned form. According to one embodiment of the present disclosure, at least a portion of the universal learning model portion may be built on an external server, accessible by the interactive AI agent module 110 via the communication module 112 described below. have. According to another embodiment of the present disclosure, the entire general learning model portion may be built on an external server that can be accessed by the interactive AI agent module 110 via the communication module 112 described below.

According to one embodiment of the present disclosure, the dialogue response generated by the interactive AI agent module 110, along with the above-described natural language responses in the form of voice and / or text, other visual elements such as images, videos, symbols, emoticons, etc. Or other acoustic elements such as sound, sound, or other tactile elements. According to one embodiment of the present disclosure, depending on the type of user input received through the user input receiving module 102 (eg, whether it is a voice input or a text input), the same type on the interactive AI agent module 110 is provided. A response can 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 invention 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 an embodiment of the present disclosure, the interactive AI agent module 110 may communicate with a predetermined external service server (not shown) through the communication module 112 described later. The external service server may be, for example, a server providing an interactive AI agent service, an online consultation center server, a financial service server, a legal service server, a medical service server, an online shopping mall server, an information retrieval server, a map service server, a navigation service server, and the like. However, the present disclosure is not limited thereto.

According to one embodiment of the present disclosure, the communication module 112 enables the user terminal 100 to communicate with a predetermined external service server (not shown). According to an embodiment of the present disclosure, the communication module 112 may allow, for example, signals obtained on the user input receiving module 102 and the sensor module 104 to be transmitted to an external service server according to a predetermined protocol, or to an external service. Various signals received from the server, for example, response signals including natural language responses in the form of voice and / or text, or various control signals, etc. may be received and appropriate processing may be performed on the received signals according to a predetermined protocol.

According to an embodiment of the present disclosure, the response output module 114 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 114 includes various display devices such as a touch screen based on technologies such as LCD, LED, OLED, QLED, etc., and responds to user input through these display devices. Visual responses such as text, symbols, videos, images, hyperlinks, animations, various notes, and the like, to the user. According to one embodiment of the present disclosure, the response output module 114 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 the user input. can do. According to an embodiment of the present disclosure, the response output module 114 may include a motion / haptic feedback generator, thereby providing a tactile response, eg, motion / haptic feedback, to a user. According to one embodiment of the present disclosure, it should be appreciated that the response output module 114 may simultaneously provide any two or more combinations of text response, voice response, and motion / haptic feedback corresponding to user input.

According to an embodiment of the present disclosure, the user terminal 100 may be any user electronic device having a wired or wireless communication function. The user terminal 100 may be, for example, various wired or wireless communication terminals including a smart phone, a tablet PC, a music player, a smart speaker, a desktop, a laptop, a PDA, a game console, a digital TV, a set top box, and the like. It should be understood that it is not limited.

2 is a functional block diagram schematically illustrating the functional configuration of the interactive AI agent module 110 of FIG. 1, in accordance with an embodiment of the present disclosure. As shown, the interactive AI agent module 110 includes a customized learning model 202, a customized learning model updater 204, a general purpose learning model 206, and a conversation / task processor 208. do.

According to one embodiment of the present disclosure, the user-tailored learning model 202, as described above with reference to Figure 1, the interactive AI agent module 110 processes the input from the user to determine the user intent and As part of the learning model used to generate and provide a conversation response or the like corresponding to the intent, the learning model may be a learning model constructed and updated by characteristic data about an individual user (ie, the user terminal 100). According to one embodiment of the present disclosure, the customized learning model 202 may be continuously re-learned and updated by the customized learning model updating unit 204 which will be described later.

According to an embodiment of the present disclosure, the user-tailored learning model update unit 204 may be configured to generate data generated as a user interacts with the interactive AI agent module 110 through the user terminal 100, that is, the corresponding data. Characteristic data about the user can be collected continuously. According to an embodiment of the present disclosure, the user-tailored learning model updating unit 204 may, for example, record a speech of a user, whether a recognition / processing failure occurs with respect to the user speech, a cause and / or a solution when a recognition / processing failure occurs, a user The response by the interactive AI agent module 110 according to the utterance recording and / or the task performance recording, etc. may be collected as characteristic data about the user. According to one embodiment of the present disclosure, the user-tailored learning model updater 204 further learns the user-learning model 202 by using continuously collected user characteristic data, and accordingly, the user-customized learning model 202. ) Can be updated continuously. According to an embodiment of the present disclosure, the user-tailored learning model updating unit 204 may learn and update the user learning model 202 in near real time according to the collection of the user characteristic data. According to one embodiment of the present disclosure, the collection of user characteristic data of the customized learning model updating unit 204 and the training and updating of the customized learning model 202 based thereon are performed on the user terminal 100 (with the help of an external server). It should be understood that the process can be performed alone).

According to one embodiment of the present disclosure, the general-purpose learning model 206, as described above with reference to Figure 1, the interactive AI agent module 110 processes input from the user to determine the user intent and As part of the learning model used to generate and provide conversational responses and the like that conform to the intent, it may be a general purpose learning model that is not specific to an individual user. According to an embodiment of the present disclosure, the general-purpose learning model 206 may be provided on the user terminal 100 in a state of being pre-learned by a data set prepared in advance. In this figure, the interactive AI agent module 110 on the user terminal 100 is shown to include a general-purpose learning model 206, but the present disclosure is not so limited. According to another embodiment of the present disclosure, the general-purpose learning model 206 may be built on an external server for providing a service of the interactive AI agent module 110. According to an embodiment of the present disclosure, the general-purpose learning model 206 may be distributedly distributed on the interactive AI agent module 110 on the user terminal 100 and on an external server. According to one embodiment of the present disclosure, the general-purpose learning model 206 may be additionally learned and updated by the intervention of an external server for providing a service of the interactive AI agent module 110 described above.

According to an embodiment of the present disclosure, the conversation / task processing unit 208 receives a user natural language input, processes the received user natural language input based on the user-customized learning model 202, the general-purpose learning model 206, and the like. The user's intent corresponding to the user's natural language input can be determined. According to one embodiment of the present disclosure, the conversation / task processing unit 208 may also provide an operation corresponding to the determined user intent, such as appropriate conversation response and / or task performance.

3 is a functional block diagram schematically illustrating a functional configuration of the conversation / task processing unit 208 of FIG. 2, according to an embodiment of the present disclosure. As shown, the conversation / task processing unit 204 may include a speech-to-text (STT) module 302, a natural language understanding (NLU) module 304, and a conversation management module ( 306, conversation creation module 308, and text-to-speech (TTS) module 310.

According to an embodiment of the present disclosure, the STT module 302 receives a voice input among user inputs received through the user input receiving module 102 and converts the received voice input into text data based on pattern matching or the like. can do. According to an embodiment of the present disclosure, the STT module 302 may extract a feature from a user's voice input to generate a feature vector sequence. According to an embodiment of the present disclosure, the STT module 302 may include a dynamic time warping (DTW) method, a HMM model (Hidden Markov Model), a GMM model (Gaussian-Mixture Mode), a deep neural network model, an n-gram model, and the like. Based on a variety of statistical models of, a text recognition result, such as a sequence of words, can be generated.

According to an embodiment of the present disclosure, the NLU module 304 may receive a text input from the user input receiving module 102 or the STT module 302. According to one embodiment of the present disclosure, the text input received at the NLU module 304 may be text recognition generated at the STT module 302 from, for example, a user text input or a user voice input received from the user input receiving module 102. The result can be, for example, a sequence of words. According to one embodiment of the present disclosure, the NLU module 304, along with or after receiving the text input, state information associated with the user input, such as state information of the user terminal 100 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 user terminal 100 at the time of user voice input and / or text input (eg, physical state of the user terminal 100 and software). And / or hardware status, environmental status information around the user terminal 100, and the like.

According to one embodiment of the present disclosure, the NLU module 304 includes a predetermined adaptive learning model (eg, an adaptive learning model including the user-defined learning model 202 and the general-purpose learning model 206, etc. of FIG. 2). Based on the received text input may correspond to one or more user intents. The user intent here may be associated with a series of action (s) that can be understood and performed by the interactive AI agent module 110 in accordance with the user intent. According to one embodiment of the present disclosure, the NLU module 304 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 conversation management module 306 may generate a series of operation flows corresponding thereto according to the user intent determined by the NLU module 304. According to one embodiment of the present disclosure, the conversation management module 306 may be configured to a predetermined learning model (eg, an adaptive learning model including the user-defined learning model 202, the general learning model 206, and the like of FIG. 2). Based on the user intent received from the NLU module 304, it may determine which actions to perform, such as which conversation responses and / or tasks to perform, and generate detailed action flows accordingly.

According to one embodiment of the present disclosure, the conversation generation module 308 may generate the necessary conversation response based on the operation flow generated by the conversation management module 306. According to an embodiment of the present disclosure, the dialogue generation module 308 may include adapting a predetermined learning model (eg, the customized learning model 202 and the general-purpose learning model 206 of FIG. 2, etc.) when generating a dialogue response. Based on the model learning model).

According to one embodiment of the present disclosure, the TTS module 310 may receive a conversation response generated by the conversation generation module 3108. The conversation response received at the TTS module 310 may be a natural language or a sequence of words in text form. According to an embodiment of the present disclosure, the TTS module 310 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, all functional components of the interactive AI agent system have been described as being implemented on the user terminal 100, but the present disclosure is not limited thereto. According to another embodiment of the present disclosure, each functional component of the interactive AI agent system may be distributed and implemented between the user terminal 100 and an external interactive AI agent server (not shown) through a communication network. Should know. According to an embodiment of the present disclosure, when the interactive AI agent system distributes and implements the functions between the user terminal and the server, the distribution of each function of the interactive AI agent system between the user terminal and the server may vary from embodiment to embodiment. It should be understood that this may be implemented. 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. In addition, in the above-described embodiment of the present disclosure with reference to FIGS. 1 to 3, the case where the customized learning model on the user terminal is used for the interactive AI agent service has been described, but the present disclosure is not limited thereto. According to another embodiment of the present disclosure, it should be understood that a user-tailored learning model on a user terminal may be extended to other machine learning based AI services, such as image retrieval and / or synthesis, speech recognition and / or synthesis, and the like. do.

As will be appreciated by those skilled in the art, the present invention is not limited to the examples described in the present disclosure 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)

As a user terminal,
A user input module configured to receive natural language input from a user.

Images