System

Abstract

An object of a system according to an embodiment is to provide an appropriate answer to a question from a user and provide personalized support.SOLUTION: A system includes a two way conversation part, a classifying part, a dedicated AI group inquiring part, and a personalizing part. The two way conversation unit clarifies a question through two way conversation in response to a question from the user, and generates a prompt. The classification part classifies the inquiry. The dedicated AI group query unit queries a dedicated AI group prepared for each use on the network for the question classified by the classifying unit to extract an effective answer. The personalization unit accumulates the habit and preference of the user through the interaction between the user and the application, and is personalized with time, thereby improving the usability.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have had the problem that the process for obtaining appropriate answers to user questions is complicated, making it difficult to provide personalized support.

[0005] The system according to the embodiment aims to provide appropriate answers to questions posed by users and to provide personalized support. [Means for solving the problem]

[0006] The system according to the embodiment includes a two-way conversation unit, a classification unit, a dedicated AI group query unit, and a personalization unit. The two-way conversation unit clarifies questions posed by the user through two-way conversation and generates prompts. The classification unit classifies the questions. The dedicated AI group query unit queries the questions classified by the classification unit to a dedicated AI group prepared for each application on the network to extract effective answers. The personalization unit accumulates the user's habits and preferences through interactions between the user and the app, and becomes personalized over time, improving usability. [Effects of the Invention]

[0007] The system according to the embodiment can provide appropriate answers to user questions and provide personalized support. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A personal support app according to an embodiment of the present invention is a system that clarifies questions posed by users through two-way conversations, generates prompts, classifies questions, queries dedicated AIs prepared for each application on the network to extract effective answers, accumulates user habits and preferences, and becomes personalized over time, improving usability. This allows the personal support app to provide appropriate answers to users' questions, and becomes personalized over time, improving usability.

[0029] A personal support app according to an embodiment includes a two-way conversation unit, a classification unit, a dedicated AI group query unit, and a personalization unit. The two-way conversation unit responds to user inquiries with a two-way conversation to clarify the user's question and generate a prompt. For example, if a user asks, "What's the weather like tomorrow?", the two-way conversation unit poses a follow-up question, such as, "Where would you like to know the weather in?" to accurately understand the user's intent. The classification unit classifies the inquiry. For example, if a user asks, "What restaurant do you recommend?", the classification unit categorizes the inquiry as "restaurant recommendation." The dedicated AI group query unit queries the question classified by the classification unit to dedicated AI groups prepared for each purpose on the network to extract an effective answer. For example, it queries an AI dedicated to restaurant recommendation and provides an optimal answer. The personalization unit accumulates the user's habits and preferences through interactions between the user and the app, and becomes personalized over time, improving usability. For example, if a user frequently searches for "Italian restaurants," the personalization unit records that information and prioritizes recommending Italian restaurants in future searches. As a result, the personal support app according to the embodiment can provide appropriate answers to questions from the user, and become more personalized over time, improving usability.

[0030] The two-way conversation unit can refer to the user's past dialogue history and generate prompts based on past answers to similar questions. The two-way conversation unit, for example, analyzes the user's past dialogue history and generates prompts based on past answers to similar questions. For example, if the user has asked "What restaurant do you recommend?" in the past, the answer to that question is used as a reference. The two-way conversation unit also refers to the past dialogue history and generates prompts based on questions the user has previously asked and their answers. For example, if the user has asked "weather forecast" in the past, the answer to that question is used as a reference. The two-way conversation unit also generates prompts for similar questions based on the user's past dialogue history. For example, if the user has asked "traffic information" in the past, the answer to that question is used as a reference. In this way, more appropriate prompts can be generated by utilizing the past dialogue history.

[0031] The two-way conversation unit can analyze the user's gestures and facial expressions using a camera and generate prompts based on non-verbal information. The two-way conversation unit, for example, uses a camera to analyze the user's gestures and facial expressions and generates prompts based on non-verbal information. For example, if the user is smiling, a positive prompt is generated. The two-way conversation unit also analyzes the user's gestures and facial expressions in real time and generates prompts based on non-verbal information. For example, if the user is confused, a prompt that provides additional explanation is generated. The two-way conversation unit also uses a camera to analyze the user's facial expressions and generates prompts based on non-verbal information. For example, if the user is surprised, a prompt that provides a detailed explanation is generated. This makes it possible to generate prompts based on non-verbal information, thereby enabling a more appropriate response.

[0032] The two-way conversation unit can analyze the writing style and wording of the text input by the user and generate prompts that match the user's preferences. The two-way conversation unit, for example, analyzes the writing style and wording of the text input by the user and generates prompts that match the user's preferences. For example, a casual prompt is generated for a user who prefers casual language. Also, prompts that match the user's preferences are generated based on the writing style and wording of the text. For example, a formal prompt is generated for a user who prefers formal language. Also, the writing style and wording of the text input by the user is analyzed and prompts that match the user's preferences are generated. For example, a humorous prompt is generated for a user who likes humor. In this way, by generating prompts that match the user's preferences, more appropriate responses are possible.

[0033] The classification unit analyzes the user's question and, if the question spans multiple categories, queries each dedicated AI in parallel. For example, the classification unit analyzes the user's question and, if the question spans multiple categories, queries each dedicated AI in parallel. For example, in response to the question, "What restaurants do you recommend and where are the tourist attractions in the area?", it queries the restaurant recommendation AI and the tourist information AI simultaneously. The content of the question is also analyzed and, if the question spans multiple categories, it queries each dedicated AI in parallel. For example, in response to the question, "What are the weather forecast and traffic information?", it queries the weather forecast AI and the traffic information AI simultaneously. The classifier also analyzes the user's question and, if the question spans multiple categories, it queries each dedicated AI in parallel. For example, in response to the question, "What are the movie showtimes and nearby restaurants?", it queries the movie information AI and the restaurant recommendation AI simultaneously. This allows for parallel queries to be made to questions that span multiple categories, providing quick and appropriate answers.

[0034] The classification unit can obtain additional information from related external databases or APIs depending on the content of the query and provide it to the dedicated AI. The classification unit obtains additional information from related external databases or APIs depending on the content of the query and provides it to the dedicated AI. For example, in response to a query such as "What's the latest news?", information is obtained from a news API and provided to a news-dedicated AI. In addition, in response to a user's query, additional information is obtained from related external databases or APIs and provided to the dedicated AI. For example, in response to a query such as "What are stock prices?", information is obtained from a financial database and provided to a stock price-dedicated AI. In addition, in response to the content of the query, additional information is obtained from related external databases or APIs and provided to the dedicated AI. For example, in response to a query such as "What is the weather forecast?", information is obtained from a weather database and provided to a weather forecast-dedicated AI. In this way, by obtaining additional information from external databases or APIs, a more appropriate answer can be provided.

[0035] The classification unit can also analyze the user's question as voice data and image data, and make a query to the dedicated AI based on the multimodal information. For example, the classification unit analyzes the user's question as voice data and makes a query to the dedicated AI based on the multimodal information. For example, it uses voice recognition technology to convert the voice data into text and provides it to the dedicated AI. It can also analyze the user's question as image data and make a query to the dedicated AI based on the multimodal information. For example, it uses image recognition technology to analyze the image data and provides it to the dedicated AI. It can also analyze the user's question as voice and image data and make a query to the dedicated AI based on the multimodal information. For example, it analyzes both voice and image data and provides it to the dedicated AI. In this way, by analyzing voice and image data, it is possible to provide an appropriate answer based on a wider variety of information.

[0036] The classification unit can strengthen the collaboration between different dedicated AIs and integrate answers from multiple dedicated AIs to provide to the user. The classification unit, for example, strengthens the collaboration between different dedicated AIs and integrates answers from multiple AIs to provide to the user. For example, it integrates answers from a weather forecast AI and a traffic information AI to provide to the user. In addition, it strengthens the collaboration between dedicated AIs and integrates answers from multiple AIs to provide to the user. For example, it integrates answers from a restaurant recommendation AI and a tourist information AI to provide to the user. In addition, it strengthens the collaboration between different dedicated AIs and integrates answers from multiple AIs to provide to the user. For example, it integrates answers from a news AI and a stock price AI to provide to the user. In this way, more comprehensive information can be provided by integrating answers from multiple dedicated AIs.

[0037] The personalization unit can analyze the user's interaction history and grasp long-term trends to improve the accuracy of personalization. The personalization unit, for example, analyzes the user's interaction history over the long term to improve the accuracy of personalization. For example, it identifies keywords that the user frequently searches for and topics of interest to the user. It also grasps the user's long-term trends based on the interaction history to improve the accuracy of personalization. For example, it analyzes the tendency of users to seek specific information at specific time periods. It also analyzes the user's interaction history to grasp long-term trends to improve the accuracy of personalization. For example, it analyzes the tendency of users to seek specific information in specific seasons. In this way, it is possible to grasp long-term trends and improve the accuracy of personalization.

[0038] The personalization unit can learn the user's behavioral patterns and automatically generate suggestions according to the predicted needs. The personalization unit, for example, learns the user's behavioral patterns and automatically generates suggestions according to the predicted needs. For example, if the user searches for restaurants every weekend, restaurant suggestions for the weekend are automatically generated. Furthermore, the personalization unit automatically generates suggestions according to the user's predicted needs based on the behavioral patterns. For example, if the user tends to attend a particular event, information related to that event is suggested. Furthermore, the personalization unit learns the user's behavioral patterns and automatically generates suggestions according to the predicted needs. For example, if the user tends to seek specific information in a particular season, information related to that season is suggested. In this way, by learning the user's behavioral patterns, it is possible to automatically generate suggestions according to the predicted needs.

[0039] The personalization unit can link the user's preference data with other applications and services to achieve integrated personalization. The personalization unit, for example, links the user's preference data with other applications and services to achieve integrated personalization. For example, it links with a music streaming service to make suggestions based on the user's music preferences. It also shares the preference data with other applications and services to achieve integrated personalization. For example, it links with a fitness app to make suggestions based on the user's exercise habits. It also links the user's preference data with other applications and services to achieve integrated personalization. For example, it links with a shopping app to make suggestions based on the user's purchasing history. In this way, it is possible to achieve integrated personalization by linking the preference data with other applications and services.

[0040] The personalization unit can add a content recommendation function based on the user's preferences and be utilized in the fields of entertainment and learning. For example, the personalization unit can add a content recommendation function based on the user's preferences and be utilized in the entertainment field. For example, it can recommend movies based on the user's movie preferences. Also, it can add a content recommendation function based on the user's preferences and be utilized in the learning field. For example, it can recommend learning content based on the user's learning history. Also, it can add a content recommendation function based on the user's preferences and be utilized in the fields of entertainment and learning. For example, it can recommend music based on the user's music preferences. In this way, by adding a content recommendation function based on preferences, it can be utilized in the fields of entertainment and learning.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The two-way conversation unit can refer to the user's past dialogue history and generate prompts based on past answers to similar questions. For example, the two-way conversation unit can analyze the user's past dialogue history and generate prompts based on past answers to similar questions. If the user has asked "What restaurant do you recommend?" in the past, that answer can be used as a reference. The two-way conversation unit can also refer to the past dialogue history and generate prompts based on questions the user has previously asked and their answers. If the user has asked "weather forecast" in the past, that answer can be used as a reference. A prompt for a similar question can be generated based on the user's past dialogue history. If the user has asked "traffic information" in the past, that answer can be used as a reference. In this way, more appropriate prompts can be generated by utilizing past dialogue history.

[0043] The two-way conversation unit can analyze the user's gestures and facial expressions using a camera and generate prompts based on non-verbal information. For example, the camera can be used to analyze the user's gestures and facial expressions and generate prompts based on non-verbal information. If the user is smiling, a positive prompt can be generated. The user's gestures and facial expressions can be analyzed in real time and a prompt can be generated based on non-verbal information. If the user is confused, a prompt that provides additional explanation can be generated. The camera can be used to analyze the user's facial expressions and generate prompts based on non-verbal information. If the user is surprised, a prompt that provides a detailed explanation can be generated. This makes it possible to generate prompts based on non-verbal information, enabling a more appropriate response.

[0044] The two-way conversation unit can analyze the style and wording of the text entered by the user and generate prompts that match the user's preferences. For example, the two-way conversation unit analyzes the style and wording of the text entered by the user and generates prompts that match the user's preferences. For a user who prefers casual language, a casual prompt is generated. A prompt that matches the user's preferences is generated based on the style and wording of the text. For a user who prefers formal language, a formal prompt is generated. The two-way conversation unit analyzes the style and wording of the text entered by the user and generates prompts that match the user's preferences. For a user who likes humor, a humorous prompt is generated. In this way, by generating prompts that match the user's preferences, more appropriate responses can be provided.

[0045] The classification unit analyzes the user's question and, if it spans multiple categories, queries each dedicated AI in parallel. For example, the classification unit analyzes the user's question and, if it spans multiple categories, queries each dedicated AI in parallel. For example, for the question, "What restaurants do you recommend and nearby tourist spots?", queries are made to the restaurant recommendation AI and the tourist information AI simultaneously. The content of the question is analyzed and, if it spans multiple categories, queries are made to each dedicated AI in parallel. For the question, "What are the weather forecast and traffic information?", queries are made to the weather forecast AI and the traffic information AI simultaneously. The classification unit analyzes the user's question and, if it spans multiple categories, queries are made to each dedicated AI in parallel. For the question, "What are the movie showtimes and nearby restaurants?", queries are made to the movie information AI and the restaurant recommendation AI simultaneously. This allows for parallel queries to be made to questions that span multiple categories, providing quick and appropriate answers.

[0046] The classification unit can obtain additional information from related external databases or APIs depending on the content of the query, and provide it to the dedicated AI. For example, depending on the content of the query, additional information is obtained from related external databases or APIs and provided to the dedicated AI. For a query such as "What's the latest news?", information is obtained from a news API and provided to a news-only AI. Depending on the user's query, additional information is obtained from related external databases or APIs and provided to the dedicated AI. For a query such as "What are stock prices?", information is obtained from a financial database and provided to a stock price-only AI. Depending on the content of the query, additional information is obtained from related external databases or APIs and provided to the dedicated AI. For a query such as "What's the weather forecast?", information is obtained from a weather database and provided to a weather forecast-only AI. In this way, by obtaining additional information from external databases or APIs, more appropriate answers can be provided.

[0047] The classification unit can also analyze the user's question as voice data and image data, and query the dedicated AI based on the multimodal information. For example, the user's question is analyzed as voice data, and a query is sent to the dedicated AI based on the multimodal information. Voice recognition technology is used to convert the voice data into text, and the text is provided to the dedicated AI. The user's question is analyzed as image data, and a query is sent to the dedicated AI based on the multimodal information. Image recognition technology is used to analyze the image data, and the text is provided to the dedicated AI. The user's question is analyzed as voice and image data, and a query is sent to the dedicated AI based on the multimodal information. Both voice and image data are analyzed, and the text is provided to the dedicated AI. In this way, by analyzing voice and image data, it is possible to provide appropriate answers based on a wider variety of information.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The interactive conversation unit responds to a user's question through interactive conversation to clarify the question and generate a prompt. For example, if a user asks, "What's the weather like tomorrow?", the interactive conversation unit will ask a follow-up question such as, "Where do you want to know the weather in?" to accurately understand the user's intention. Step 2: The classifier classifies the query. For example, if the user asks "What restaurant do you recommend?", the classifier classifies the query into the category of "restaurant recommendation." Step 3: The dedicated AI query unit queries the questions classified by the classification unit to a dedicated AI group prepared for each purpose on the network to elicit an effective answer. For example, it queries an AI dedicated to restaurant recommendation and provides the optimal answer. Step 4: The personalization unit accumulates the user's habits and preferences through interactions between the user and the app, and over time, the app becomes more personalized and easier to use. For example, if a user frequently searches for "Italian restaurants," the personalization unit records that information and prioritizes Italian restaurants in future searches.

[0050] (Example 2) A personal support app according to an embodiment of the present invention is a system that clarifies questions posed by users through two-way conversations, generates prompts, classifies questions, queries dedicated AIs prepared for each application on the network to extract effective answers, accumulates user habits and preferences, and becomes personalized over time, improving usability. This allows the personal support app to provide appropriate answers to users' questions, and becomes personalized over time, improving usability.

[0051] A personal support app according to an embodiment includes a two-way conversation unit, a classification unit, a dedicated AI group query unit, and a personalization unit. The two-way conversation unit responds to user inquiries with a two-way conversation to clarify the user's question and generate a prompt. For example, if a user asks, "What's the weather like tomorrow?", the two-way conversation unit poses a follow-up question, such as, "Where would you like to know the weather in?" to accurately understand the user's intent. The classification unit classifies the inquiry. For example, if a user asks, "What restaurant do you recommend?", the classification unit categorizes the inquiry as "restaurant recommendation." The dedicated AI group query unit queries the question classified by the classification unit to dedicated AI groups prepared for each purpose on the network to extract an effective answer. For example, it queries an AI dedicated to restaurant recommendation and provides an optimal answer. The personalization unit accumulates the user's habits and preferences through interactions between the user and the app, and becomes personalized over time, improving usability. For example, if a user frequently searches for "Italian restaurants," the personalization unit records that information and prioritizes recommending Italian restaurants in future searches. As a result, the personal support app according to the embodiment can provide appropriate answers to questions from the user, and become more personalized over time, improving usability.

[0052] The two-way conversation unit can analyze the tone and speed of the user's voice, infer their emotional state, and generate appropriate prompts. For example, the two-way conversation unit analyzes the tone and speed of the user's voice in real time when asking a question to infer their emotional state. For example, if the user is in a hurry, it generates a prompt to provide a quick answer. It also analyzes changes in the tone and speed of the voice to determine whether the user is stressed or relaxed. For example, if the user is stressed, it generates a prompt to help them relax. It also infers their emotional state based on the tone and speed of the user's voice and generates appropriate prompts. For example, if the user is excited, it generates a prompt to help them respond calmly. This allows for a more appropriate response by generating prompts that correspond to the user's emotional state.

[0053] The two-way conversation unit can refer to the user's past dialogue history and generate prompts based on past answers to similar questions. The two-way conversation unit, for example, analyzes the user's past dialogue history and generates prompts based on past answers to similar questions. For example, if the user has asked "What restaurant do you recommend?" in the past, the answer to that question is used as a reference. The two-way conversation unit also refers to the past dialogue history and generates prompts based on questions the user has previously asked and their answers. For example, if the user has asked "weather forecast" in the past, the answer to that question is used as a reference. The two-way conversation unit also generates prompts for similar questions based on the user's past dialogue history. For example, if the user has asked "traffic information" in the past, the answer to that question is used as a reference. In this way, more appropriate prompts can be generated by utilizing the past dialogue history.

[0054] The two-way conversation unit uses the emotion estimation function to generate prompts according to the user's emotions and can carry out a dialogue to reduce the user's stress. The two-way conversation unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and generate prompts to reduce stress. For example, if the user is feeling stressed, it generates a prompt to relax. It also estimates the user's emotional state and carries out a dialogue to reduce stress. For example, if the user is feeling anxious, it generates a prompt to reassure the user. It also uses the emotion estimation function to generate prompts according to the user's emotions and carry out a dialogue to reduce stress. For example, if the user is angry, it generates a prompt to respond calmly. In this way, by generating prompts according to the user's emotions, it is possible to carry out a dialogue to reduce stress.

[0055] The two-way conversation unit can analyze the user's gestures and facial expressions using a camera and generate prompts based on non-verbal information. The two-way conversation unit, for example, uses a camera to analyze the user's gestures and facial expressions and generates prompts based on non-verbal information. For example, if the user is smiling, a positive prompt is generated. The two-way conversation unit also analyzes the user's gestures and facial expressions in real time and generates prompts based on non-verbal information. For example, if the user is confused, a prompt that provides additional explanation is generated. The two-way conversation unit also uses a camera to analyze the user's facial expressions and generates prompts based on non-verbal information. For example, if the user is surprised, a prompt that provides a detailed explanation is generated. This makes it possible to generate prompts based on non-verbal information, thereby enabling a more appropriate response.

[0056] The two-way conversation unit can analyze the writing style and wording of the text input by the user and generate prompts that match the user's preferences. The two-way conversation unit, for example, analyzes the writing style and wording of the text input by the user and generates prompts that match the user's preferences. For example, a casual prompt is generated for a user who prefers casual language. Also, prompts that match the user's preferences are generated based on the writing style and wording of the text. For example, a formal prompt is generated for a user who prefers formal language. Also, the writing style and wording of the text input by the user is analyzed and prompts that match the user's preferences are generated. For example, a humorous prompt is generated for a user who likes humor. In this way, by generating prompts that match the user's preferences, more appropriate responses are possible.

[0057] The two-way conversation unit uses the emotion estimation function to generate the most effective prompt when the user has a specific emotion, thereby improving the quality of the conversation. The two-way conversation unit, for example, uses the emotion estimation function to generate the most effective prompt when the user has a specific emotion. For example, if the user is happy, it generates a positive prompt. The two-way conversation unit also estimates the user's emotional state and generates the most effective prompt when the user has a specific emotion. For example, if the user is sad, it generates a comforting prompt. The emotion estimation function also uses the most effective prompt when the user has a specific emotion, thereby improving the quality of the conversation. For example, if the user is excited, it generates a prompt that responds calmly. In this way, the quality of the conversation can be improved by generating prompts that correspond to the user's emotions.

[0058] The classification unit analyzes the user's question and, if the question spans multiple categories, queries each dedicated AI in parallel. For example, the classification unit analyzes the user's question and, if the question spans multiple categories, queries each dedicated AI in parallel. For example, in response to the question, "What restaurants do you recommend and where are the tourist attractions in the area?", it queries the restaurant recommendation AI and the tourist information AI simultaneously. The content of the question is also analyzed and, if the question spans multiple categories, it queries each dedicated AI in parallel. For example, in response to the question, "What are the weather forecast and traffic information?", it queries the weather forecast AI and the traffic information AI simultaneously. The classifier also analyzes the user's question and, if the question spans multiple categories, it queries each dedicated AI in parallel. For example, in response to the question, "What are the movie showtimes and nearby restaurants?", it queries the movie information AI and the restaurant recommendation AI simultaneously. This allows for parallel queries to be made to questions that span multiple categories, providing quick and appropriate answers.

[0059] The classification unit can obtain additional information from related external databases or APIs depending on the content of the query and provide it to the dedicated AI. The classification unit obtains additional information from related external databases or APIs depending on the content of the query and provides it to the dedicated AI. For example, in response to a query such as "What's the latest news?", information is obtained from a news API and provided to a news-dedicated AI. In addition, in response to a user's query, additional information is obtained from related external databases or APIs and provided to the dedicated AI. For example, in response to a query such as "What are stock prices?", information is obtained from a financial database and provided to a stock price-dedicated AI. In addition, in response to the content of the query, additional information is obtained from related external databases or APIs and provided to the dedicated AI. For example, in response to a query such as "What is the weather forecast?", information is obtained from a weather database and provided to a weather forecast-dedicated AI. In this way, by obtaining additional information from external databases or APIs, a more appropriate answer can be provided.

[0060] The classification unit can use the emotion estimation function to select the optimal dedicated AI according to the user's emotional state, thereby improving the quality of answers. The classification unit, for example, uses the emotion estimation function to analyze the user's emotional state and select the optimal dedicated AI. For example, if the user is feeling stressed, a dedicated AI for relaxation is selected. The classification unit also estimates the user's emotional state and selects the optimal dedicated AI. For example, if the user is excited, a dedicated AI for responding calmly is selected. The emotion estimation function also selects the optimal dedicated AI according to the user's emotional state, thereby improving the quality of answers. For example, if the user is feeling anxious, a dedicated AI for reassurance is selected. In this way, the quality of answers can be improved by selecting the optimal dedicated AI according to the user's emotional state.

[0061] The classification unit can also analyze the user's question as voice data and image data, and make a query to the dedicated AI based on the multimodal information. For example, the classification unit analyzes the user's question as voice data and makes a query to the dedicated AI based on the multimodal information. For example, it uses voice recognition technology to convert the voice data into text and provides it to the dedicated AI. It can also analyze the user's question as image data and make a query to the dedicated AI based on the multimodal information. For example, it uses image recognition technology to analyze the image data and provides it to the dedicated AI. It can also analyze the user's question as voice and image data and make a query to the dedicated AI based on the multimodal information. For example, it analyzes both voice and image data and provides it to the dedicated AI. In this way, by analyzing voice and image data, it is possible to provide an appropriate answer based on a wider variety of information.

[0062] The classification unit can strengthen the collaboration between different dedicated AIs and integrate answers from multiple dedicated AIs to provide to the user. The classification unit, for example, strengthens the collaboration between different dedicated AIs and integrates answers from multiple AIs to provide to the user. For example, it integrates answers from a weather forecast AI and a traffic information AI to provide to the user. In addition, it strengthens the collaboration between dedicated AIs and integrates answers from multiple AIs to provide to the user. For example, it integrates answers from a restaurant recommendation AI and a tourist information AI to provide to the user. In addition, it strengthens the collaboration between different dedicated AIs and integrates answers from multiple AIs to provide to the user. For example, it integrates answers from a news AI and a stock price AI to provide to the user. In this way, more comprehensive information can be provided by integrating answers from multiple dedicated AIs.

[0063] The classification unit uses the emotion estimation function to perform category classification according to the user's emotions and can query the most appropriate dedicated AI. The classification unit, for example, uses the emotion estimation function to analyze the user's emotional state and classify it into the most appropriate category. For example, if the user is feeling stressed, it classifies it into a category for relaxation. The classification unit also estimates the user's emotional state and classifies it into the most appropriate category. For example, if the user is excited, it classifies it into a category for responding calmly. The emotion estimation function also performs category classification according to the user's emotions and queries the most appropriate dedicated AI. For example, if the user is feeling anxious, it classifies it into a category for reassurance. In this way, by performing category classification according to the user's emotions, it is possible to query the more appropriate dedicated AI.

[0064] The personalization unit can analyze the user's interaction history and grasp long-term trends to improve the accuracy of personalization. The personalization unit, for example, analyzes the user's interaction history over the long term to improve the accuracy of personalization. For example, it identifies keywords that the user frequently searches for and topics of interest to the user. It also grasps the user's long-term trends based on the interaction history to improve the accuracy of personalization. For example, it analyzes the tendency of users to seek specific information at specific time periods. It also analyzes the user's interaction history to grasp long-term trends to improve the accuracy of personalization. For example, it analyzes the tendency of users to seek specific information in specific seasons. In this way, it is possible to grasp long-term trends and improve the accuracy of personalization.

[0065] The personalization unit can learn the user's behavioral patterns and automatically generate suggestions according to the predicted needs. The personalization unit, for example, learns the user's behavioral patterns and automatically generates suggestions according to the predicted needs. For example, if the user searches for restaurants every weekend, restaurant suggestions for the weekend are automatically generated. Furthermore, the personalization unit automatically generates suggestions according to the user's predicted needs based on the behavioral patterns. For example, if the user tends to attend a particular event, information related to that event is suggested. Furthermore, the personalization unit learns the user's behavioral patterns and automatically generates suggestions according to the predicted needs. For example, if the user tends to seek specific information in a particular season, information related to that season is suggested. In this way, by learning the user's behavioral patterns, it is possible to automatically generate suggestions according to the predicted needs.

[0066] The personalization unit uses the emotion estimation function to perform personalization based on the user's emotions, thereby improving user satisfaction. The personalization unit, for example, uses the emotion estimation function to analyze the user's emotional state and perform personalization based on emotions. For example, if the user is feeling stressed, information to help the user relax is provided. The personalization unit also estimates the user's emotional state and performs personalization based on emotions. For example, if the user is excited, information to help the user respond calmly is provided. The emotion estimation function also performs personalization based on the user's emotions, thereby improving user satisfaction. For example, if the user is feeling anxious, information to reassure the user is provided. In this way, personalization based on the user's emotions can improve user satisfaction.

[0067] The personalization unit can link the user's preference data with other applications and services to achieve integrated personalization. The personalization unit, for example, links the user's preference data with other applications and services to achieve integrated personalization. For example, it links with a music streaming service to make suggestions based on the user's music preferences. It also shares the preference data with other applications and services to achieve integrated personalization. For example, it links with a fitness app to make suggestions based on the user's exercise habits. It also links the user's preference data with other applications and services to achieve integrated personalization. For example, it links with a shopping app to make suggestions based on the user's purchasing history. In this way, it is possible to achieve integrated personalization by linking the preference data with other applications and services.

[0068] The personalization unit can add a content recommendation function based on the user's preferences and be utilized in the fields of entertainment and learning. For example, the personalization unit can add a content recommendation function based on the user's preferences and be utilized in the entertainment field. For example, it can recommend movies based on the user's movie preferences. Also, it can add a content recommendation function based on the user's preferences and be utilized in the learning field. For example, it can recommend learning content based on the user's learning history. Also, it can add a content recommendation function based on the user's preferences and be utilized in the fields of entertainment and learning. For example, it can recommend music based on the user's music preferences. In this way, by adding a content recommendation function based on preferences, it can be utilized in the fields of entertainment and learning.

[0069] The personalization unit uses the emotion estimation function to perform personalization according to the user's emotions, thereby promoting stress reduction and relaxation. The personalization unit, for example, uses the emotion estimation function to analyze the user's emotional state and perform personalization according to the emotions. For example, if the user is feeling stressed, information for relaxation is provided. The personalization unit also estimates the user's emotional state and performs personalization according to the emotions. For example, if the user is feeling anxious, information for reassurance is provided. The emotion estimation function also performs personalization according to the user's emotions, thereby promoting stress reduction and relaxation. For example, if the user is tired, information for relaxation is provided. In this way, personalization according to emotions can be performed to promote stress reduction and relaxation.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The two-way conversation unit can analyze the tone and speed of the user's voice to infer their emotional state and generate appropriate prompts. For example, the unit can analyze the tone and speed of the user's voice in real time when asking a question to infer their emotional state. If the user is in a hurry, it can generate a prompt to provide a quick answer. It can also analyze changes in the tone and speed of the voice to determine whether the user is stressed or relaxed. If the user is stressed, it can generate a prompt to help them relax. It can infer their emotional state based on the tone and speed of the user's voice and generate an appropriate prompt. If the user is excited, it can generate a prompt to help them respond calmly. This allows for more appropriate responses by generating prompts that correspond to the user's emotional state.

[0072] The two-way conversation unit can refer to the user's past dialogue history and generate prompts based on past answers to similar questions. For example, the two-way conversation unit can analyze the user's past dialogue history and generate prompts based on past answers to similar questions. If the user has asked "What restaurant do you recommend?" in the past, that answer can be used as a reference. The two-way conversation unit can also refer to the past dialogue history and generate prompts based on questions the user has previously asked and their answers. If the user has asked "weather forecast" in the past, that answer can be used as a reference. A prompt for a similar question can be generated based on the user's past dialogue history. If the user has asked "traffic information" in the past, that answer can be used as a reference. In this way, more appropriate prompts can be generated by utilizing past dialogue history.

[0073] The two-way conversation unit uses the emotion estimation function to generate prompts according to the user's emotions and can carry out a dialogue to reduce the user's stress. For example, the emotion estimation function is used to analyze the user's emotional state in real time and generate prompts to reduce stress. If the user is feeling stressed, a prompt to relax is generated. The user's emotional state is estimated and a dialogue to reduce stress is carried out. If the user is feeling anxious, a prompt to reassure is generated. The emotion estimation function is used to generate prompts according to the user's emotions and carry out a dialogue to reduce stress. If the user is angry, a prompt to respond calmly is generated. In this way, by generating prompts according to the user's emotions, a dialogue to reduce stress is possible.

[0074] The two-way conversation unit can analyze the user's gestures and facial expressions using a camera and generate prompts based on non-verbal information. For example, the camera can be used to analyze the user's gestures and facial expressions and generate prompts based on non-verbal information. If the user is smiling, a positive prompt can be generated. The user's gestures and facial expressions can be analyzed in real time and a prompt can be generated based on non-verbal information. If the user is confused, a prompt that provides additional explanation can be generated. The camera can be used to analyze the user's facial expressions and generate prompts based on non-verbal information. If the user is surprised, a prompt that provides a detailed explanation can be generated. This makes it possible to generate prompts based on non-verbal information, enabling a more appropriate response.

[0075] The two-way conversation unit can analyze the style and wording of the text entered by the user and generate prompts that match the user's preferences. For example, the two-way conversation unit analyzes the style and wording of the text entered by the user and generates prompts that match the user's preferences. For a user who prefers casual language, a casual prompt is generated. A prompt that matches the user's preferences is generated based on the style and wording of the text. For a user who prefers formal language, a formal prompt is generated. The two-way conversation unit analyzes the style and wording of the text entered by the user and generates prompts that match the user's preferences. For a user who likes humor, a humorous prompt is generated. In this way, by generating prompts that match the user's preferences, more appropriate responses can be provided.

[0076] The two-way conversation unit uses the emotion estimation function to generate the most effective prompt when the user has a specific emotion, thereby improving the quality of the conversation. For example, the emotion estimation function is used to generate the most effective prompt when the user has a specific emotion. If the user is happy, a positive prompt is generated. The user's emotional state is estimated and the most effective prompt when the user has a specific emotion is generated. If the user is sad, a comforting prompt is generated. The emotion estimation function is used to generate the most effective prompt when the user has a specific emotion, thereby improving the quality of the conversation. If the user is excited, a prompt that responds calmly is generated. In this way, the quality of the conversation can be improved by generating prompts that correspond to the user's emotions.

[0077] The classification unit analyzes the user's question and, if it spans multiple categories, queries each dedicated AI in parallel. For example, the classification unit analyzes the user's question and, if it spans multiple categories, queries each dedicated AI in parallel. For example, for the question, "What restaurants do you recommend and nearby tourist spots?", queries are made to the restaurant recommendation AI and the tourist information AI simultaneously. The content of the question is analyzed and, if it spans multiple categories, queries are made to each dedicated AI in parallel. For the question, "What are the weather forecast and traffic information?", queries are made to the weather forecast AI and the traffic information AI simultaneously. The classification unit analyzes the user's question and, if it spans multiple categories, queries are made to each dedicated AI in parallel. For the question, "What are the movie showtimes and nearby restaurants?", queries are made to the movie information AI and the restaurant recommendation AI simultaneously. This allows for parallel queries to be made to questions that span multiple categories, providing quick and appropriate answers.

[0078] The classification unit can obtain additional information from related external databases or APIs depending on the content of the query, and provide it to the dedicated AI. For example, depending on the content of the query, additional information is obtained from related external databases or APIs and provided to the dedicated AI. For a query such as "What's the latest news?", information is obtained from a news API and provided to a news-only AI. Depending on the user's query, additional information is obtained from related external databases or APIs and provided to the dedicated AI. For a query such as "What are stock prices?", information is obtained from a financial database and provided to a stock price-only AI. Depending on the content of the query, additional information is obtained from related external databases or APIs and provided to the dedicated AI. For a query such as "What's the weather forecast?", information is obtained from a weather database and provided to a weather forecast-only AI. In this way, by obtaining additional information from external databases or APIs, more appropriate answers can be provided.

[0079] The classification unit can use the emotion estimation function to select the optimal dedicated AI according to the user's emotional state, thereby improving the quality of answers. For example, the emotion estimation function is used to analyze the user's emotional state and select the optimal dedicated AI. If the user is feeling stressed, a dedicated AI for relaxation is selected. The user's emotional state is estimated and the optimal dedicated AI is selected. If the user is excited, a dedicated AI for responding calmly is selected. The emotion estimation function is used to select the optimal dedicated AI according to the user's emotional state, thereby improving the quality of answers. If the user is feeling anxious, a dedicated AI for reassurance is selected. In this way, the quality of answers can be improved by selecting the optimal dedicated AI according to the user's emotional state.

[0080] The classification unit can also analyze the user's question as voice data and image data, and query the dedicated AI based on the multimodal information. For example, the user's question is analyzed as voice data, and a query is sent to the dedicated AI based on the multimodal information. Voice recognition technology is used to convert the voice data into text, and the text is provided to the dedicated AI. The user's question is analyzed as image data, and a query is sent to the dedicated AI based on the multimodal information. Image recognition technology is used to analyze the image data, and the text is provided to the dedicated AI. The user's question is analyzed as voice and image data, and a query is sent to the dedicated AI based on the multimodal information. Both voice and image data are analyzed, and the text is provided to the dedicated AI. In this way, by analyzing voice and image data, it is possible to provide appropriate answers based on a wider variety of information.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The interactive conversation unit responds to a user's question through interactive conversation to clarify the question and generate a prompt. For example, if a user asks, "What's the weather like tomorrow?", the interactive conversation unit will ask a follow-up question such as, "Where do you want to know the weather in?" to accurately understand the user's intention. Step 2: The classifier classifies the query. For example, if the user asks "What restaurant do you recommend?", the classifier classifies the query into the category of "restaurant recommendation." Step 3: The dedicated AI query unit queries the questions classified by the classification unit to a dedicated AI group prepared for each purpose on the network to elicit an effective answer. For example, it queries an AI dedicated to restaurant recommendation and provides the optimal answer. Step 4: The personalization unit accumulates the user's habits and preferences through interactions between the user and the app, and over time, the app becomes more personalized and easier to use. For example, if a user frequently searches for "Italian restaurants," the personalization unit records that information and prioritizes Italian restaurants in future searches.

[0083] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0084] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0085] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0088] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0089] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0090] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0091] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0092] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0093] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0094] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0096] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0097] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0100] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0108] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0111] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0124] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0133] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0134] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0135] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0136] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0137] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0138] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0139] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0140] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0141] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0142] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0143] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0144] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0145] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0146] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0147] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0148] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0149] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0150] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a two-way conversation unit that clarifies questions posed by a user through two-way conversation and generates prompts; a classification unit that classifies the questions; a dedicated AI group query unit that queries the questions classified by the classification unit to a dedicated AI group prepared for each purpose on the network to extract an effective answer; a personalization unit that accumulates the habits and preferences of the user through interactions between the user and the application, and personalizes the application over time to improve usability. A system characterized by:

2. The two-way conversation unit Analyzing the tone and rate of the user's voice to infer their emotional state and generate appropriate prompts 2. The system of claim 1.

3. The two-way conversation unit Refer to the user's past interaction history and generate prompts based on past answers to similar questions.

2. The system of claim 1.

4. The two-way conversation unit A prompt is generated according to the emotion of the user, and a dialogue is carried out to reduce stress of the user.

2. The system of claim 1.

5. The two-way conversation unit The camera analyzes the user's gestures and facial expressions and generates prompts based on non-verbal information.

2. The system of claim 1.

Images