System

Abstract

An object of a system according to an embodiment is to accurately and efficiently respond to various inquiries.SOLUTION: A system includes an inquiry analysis part, an answer generation part, and an information acquisition part. The query analyzer includes a generation AI. The answer generation unit generates an answer on the basis of the inquiry content analyzed by the inquiry analysis unit. The information acquisition unit acquires information necessary for the answer generated by the answer generation unit from the cloud.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 techniques have had the problem of making it difficult to respond to a wide variety of inquiries accurately and efficiently.

[0005] The system according to the embodiment aims to respond to a variety of inquiries accurately and efficiently. [Means for solving the problem]

[0006] The system according to the embodiment includes a query analysis unit, an answer generation unit, and an information acquisition unit. The query analysis unit is equipped with a generation AI. The answer generation unit generates an answer based on the query content analyzed by the query analysis unit. The information acquisition unit acquires information required for the answer generated by the answer generation unit from the cloud. [Effects of the Invention]

[0007] The system according to the embodiment can respond to a variety of inquiries accurately and efficiently. [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) The automatic learning system according to the embodiment of the present invention utilizes a generation AI to refer to the content of inquiries and past data, automatically generate appropriate answers, and acquire necessary information from the cloud. This enables the automatic learning system to flexibly respond to a variety of inquiries and provide accurate and efficient answers.

[0029] The automated learning system according to the embodiment includes a query analysis unit, an answer generation unit, and an information acquisition unit. The query analysis unit includes a generation AI and analyzes the content of a query from a user. For example, the generation AI analyzes the content of the query using natural language processing technology and extracts information for generating an appropriate answer. The query analysis unit also references past data to learn patterns for generating an appropriate answer based on the content of the query. For example, the optimal answer to a similar query is learned based on past query data. The query analysis unit also references a user's behavioral history to provide information for generating a personalized answer. For example, the answer generation unit provides related information based on the user's past purchase history and browsing history. The answer generation unit generates an answer based on the query content analyzed by the query analysis unit. For example, the generation AI uses a template-based generation model to generate an answer corresponding to the content of the query. The generation AI can also use the generation model to generate an optimal answer corresponding to the content of the query. The answer generation unit also includes an emotion estimation function for generating an answer corresponding to the user's emotions. For example, the answer generation unit analyzes the user's tone of voice and facial expressions to generate an answer corresponding to the emotion. The information acquisition unit acquires information necessary for the answer generated by the answer generation unit from the cloud. For example, it acquires product information and customer information stored on the cloud and generates an answer based on that information. The information acquisition unit also evaluates the reliability of the information acquired from the cloud and prioritizes the use of highly reliable information. For example, it prioritizes the use of data from official information sources. Furthermore, the information acquisition unit takes into account the update frequency of the information acquired from the cloud and prioritizes the acquisition of the latest information. For example, it prioritizes the use of information from a frequently updated database. This enables the automatic learning system according to the embodiment to flexibly respond to a variety of inquiries and provide accurate and efficient answers. For example, the generation AI learns from past data and acquires the latest information from the cloud, thereby always providing accurate answers. Furthermore, by flexibly responding to a variety of inquiries, it is possible to quickly meet user needs.

[0030] The query analysis unit can refer to the user's past behavioral history and generate more personalized answers. For example, the generation AI in the query analysis unit references the user's past purchase history and browsing history to generate personalized answers based on the query content. For example, if a user makes an inquiry related to a product they previously purchased, detailed information about that product is provided. The query analysis unit also references the user's past inquiry history to provide consistent answers to similar inquiries. For example, if a user who has previously returned an item makes another inquiry about a return, the unit responds quickly based on the details of the previous procedure. The query analysis unit also learns user behavior patterns and provides pre-prepared answers to predicted inquiries. For example, it quickly provides pre-prepared answers to inquiries made by many users during a particular season. This makes it possible to provide more personalized answers to users.

[0031] The query analysis unit can add a multilingual support function so that it can handle inquiries in different languages. For example, the query analysis unit adds a multilingual support function to the generation AI so that it can handle inquiries in different languages. For example, it generates appropriate answers to inquiries in multiple languages, such as English, French, and Chinese. The query analysis unit also uses the multilingual support function to generate answers based on the language selected by the user. For example, if a user makes an inquiry in Spanish, an answer in Spanish is provided. The query analysis unit also automatically translates inquiries in different languages, and the generation AI generates an answer based on the translation results. For example, an inquiry in Japanese is translated into English, an answer is generated in English, and the answer is then translated back into Japanese and provided. This makes it possible to handle inquiries in different languages.

[0032] The query analysis unit can analyze images or videos and generate answers based on visual information. For example, the query analysis unit uses a generation AI to analyze images sent by users and generate answers based on their contents. For example, it analyzes photos of products and provides the product's stock status and detailed information. The query analysis unit can also analyze videos sent by users and generate answers based on visual information. For example, it can analyze videos of broken equipment and provide repair methods and support information. The query analysis unit can also use image recognition technology to automatically analyze the contents of images sent by users and generate appropriate answers. For example, it can analyze product barcodes and provide detailed information about the product. This makes it possible to provide answers based on visual information.

[0033] When referring to past data, the answer generation unit can evaluate the reliability of the data and prioritize learning from highly reliable data. For example, when the generation AI refers to past data, the answer generation unit introduces an algorithm that evaluates the reliability of the data and prioritizes learning from highly reliable data. For example, it prioritizes using data from highly reliable sources. In addition, the answer generation unit takes into account the source of the data and how often it is updated to evaluate its reliability. For example, it prioritizes learning from official databases and data that is frequently updated. In addition, the answer generation unit builds a system that filters out low-reliability data and learns only highly reliable data. For example, it filters based on the reliability score of the data. This allows it to prioritize learning from highly reliable data.

[0034] When referring to past data, the answer generation unit can generate an answer based on the latest trends based on changes in the data over time. For example, when the generation AI refers to past data, the answer generation unit takes into account changes in the data over time and generates an answer based on the latest trends. For example, it analyzes past data in time series and reflects the latest trends. The answer generation unit also builds a system that analyzes changes in the data over time and generates answers according to changes in trends. For example, it provides answers that take seasonal trends into consideration. The answer generation unit also reevaluates past data based on the latest trend information and generates an optimal answer. For example, it provides an answer that reflects the latest market trends. This makes it possible to provide answers based on the latest trends.

[0035] The answer generation unit can refer to data from different industries and generate answers that utilize knowledge from those industries. For example, the answer generation unit allows the generation AI to refer to data from different industries and generate answers that utilize knowledge from those industries. For example, the answer generation unit refers to data from the medical industry to provide an appropriate answer to a health-related inquiry. The answer generation unit also integrates data from different industries, and builds a system in which the generation AI generates answers based on that data. For example, the answer generation unit integrates data from the technology industry and the consumer market to provide an answer that utilizes knowledge from both. The answer generation unit also refers to data from different industries, allowing the generation AI to generate answers from a multifaceted perspective. For example, the answer generation unit refers to data from the financial industry to provide an appropriate answer to a question about the economy. This makes it possible to provide answers that utilize knowledge from different industries.

[0036] The answer generation unit can visually grasp data trends using a data visualization tool. For example, when the generation AI refers to past data, the answer generation unit uses a data visualization tool to visually grasp data trends. For example, it displays data fluctuations using graphs and charts. The answer generation unit also uses a data visualization tool to analyze trends in past data and builds a system that generates answers based on the results. For example, it visually displays data peaks and trends. The answer generation unit also uses a data visualization tool to visually analyze past data and generate optimal answers. For example, it displays data concentration using a heat map. This makes it possible to visually grasp data trends.

[0037] When acquiring information from the cloud, the information acquisition unit can prioritize acquiring the latest information based on the frequency of information updates. For example, when the generation AI acquires information from the cloud, the information acquisition unit takes into account the frequency of information updates and prioritizes acquiring the latest information. For example, it prioritizes the use of information from a frequently updated database. The information acquisition unit also analyzes the update history of information on the cloud and builds a system that generates answers based on the latest information. For example, it provides answers based on the latest inventory information and price information. The information acquisition unit also introduces an algorithm that evaluates the frequency of information updates and prioritizes acquiring the most reliable latest information. For example, it prioritizes the use of data from information sources that are updated frequently. This allows the latest information to be acquired preferentially.

[0038] When acquiring information from the cloud, the information acquisition unit evaluates the reliability of the information and can prioritize the use of highly reliable information. For example, when the generation AI acquires information from the cloud, the information acquisition unit introduces an algorithm that evaluates the reliability of the information and prioritizes the use of highly reliable information. For example, it prioritizes the use of data from official information sources. The information acquisition unit also evaluates the reliability of information on the cloud and builds a system that generates answers based on highly reliable information. For example, it filters information based on a reliability score. The information acquisition unit also takes into account the source and update history of the information to evaluate the reliability of the information. For example, it prioritizes the use of data from highly reliable information sources. This allows the highly reliable information to be used preferentially.

[0039] The information acquisition unit can integrate information between different cloud services and provide comprehensive information. For example, the generation AI can integrate information between different cloud services in the information acquisition unit to provide comprehensive information. For example, the information acquisition unit can integrate data from multiple cloud services and provide a comprehensive answer. The information acquisition unit can also integrate information from different cloud services to build a system in which the generation AI generates an answer based on that data. For example, the information acquisition unit can integrate and provide information from multiple data sources. The information acquisition unit can also integrate information between different cloud services, allowing the generation AI to generate an answer from a multifaceted perspective. For example, the information acquisition unit can integrate and provide data from different cloud services. This makes it possible to provide comprehensive information.

[0040] The information acquisition unit can utilize real-time data to generate answers based on the latest situation. In the information acquisition unit, for example, the generation AI acquires real-time data from the cloud and generates answers based on the latest situation. For example, answers are provided based on real-time inventory information and price information. The information acquisition unit also builds a system that analyzes real-time data on the cloud and generates answers based on the latest situation. For example, answers are provided based on real-time weather information and traffic information. The information acquisition unit also utilizes real-time data, and the generation AI generates optimal answers based on the latest situation. For example, answers are provided based on real-time market trends. This makes it possible to provide answers based on the latest situation.

[0041] The answer generation unit can introduce a sub-AI to generate specialized answers for each type of inquiry. For example, the answer generation unit introduces a sub-AI that generates specialized answers for each type of inquiry so that the generation AI can respond to a variety of inquiries. For example, a technically specialized sub-AI will respond to technical inquiries. The answer generation unit also builds a system in which sub-AIs with specialized knowledge generate answers depending on the type of inquiry. For example, a medical-related inquiry will be responded to by a medical-specialized sub-AI. The answer generation unit also introduces a sub-AI so that the generation AI can provide specialized answers to a variety of inquiries. For example, a legal-specialized sub-AI will respond to legal inquiries. This makes it possible to provide specialized answers.

[0042] The answer generation unit can evaluate the urgency of an inquiry and generate answers in a priority order according to the urgency. For example, the answer generation unit uses a generation AI to evaluate the urgency of an inquiry and generate answers in a priority order according to the urgency. For example, inquiries with high urgency are responded to quickly. The answer generation unit also introduces an algorithm to evaluate the urgency of an inquiry and builds a system that generates answers in a priority order according to the urgency. For example, inquiries with high urgency are processed first. The answer generation unit also generates answers in a priority order according to the urgency, allowing the generation AI to respond quickly to a variety of inquiries. For example, answers are provided immediately to inquiries with high urgency. This makes it possible to provide answers in a priority order according to the urgency.

[0043] The answer generation unit can be made versatile so that it can respond to inquiries from different industries. For example, the answer generation unit makes the generation AI versatile, allowing it to respond to inquiries from different industries. For example, it provides appropriate answers to inquiries from the technology industry, medical industry, finance industry, etc. The answer generation unit also learns data from different industries and builds a system that enables the generation AI to respond to inquiries from a variety of industries. For example, it generates answers by integrating knowledge from different industries. The answer generation unit also makes the generation AI versatile, allowing it to flexibly respond to inquiries from a variety of industries. For example, it integrates sub-AIs with specialized knowledge from different industries. This allows it to respond to inquiries from different industries.

[0044] The answer generation unit can automatically classify the inquiry content and generate an appropriate answer. In the answer generation unit, for example, a generation AI automatically classifies the inquiry content and generates an appropriate answer. For example, inquiries about product inventory status, order status, return procedures, etc. are automatically classified. The answer generation unit also introduces an algorithm that automatically classifies the inquiry content, and builds a system in which the generation AI generates answers based on the classification results. For example, a template according to the type of inquiry is used. The answer generation unit also uses an automatic classification function so that the generation AI provides appropriate answers to a variety of inquiries. For example, the answer generation unit analyzes the inquiry content and generates the optimal answer. This makes it possible to automatically classify the inquiry content and provide appropriate answers.

[0045] The answer generation unit can evaluate the accuracy of answers and provide highly accurate answers preferentially. For example, the answer generation unit uses a generation AI to evaluate the accuracy of answers and provide highly accurate answers preferentially. For example, the answer generation unit evaluates accuracy based on past answer data and provides the optimal answer. The answer generation unit also introduces an algorithm to evaluate the accuracy of answers, and builds a system in which the generation AI provides answers based on the evaluation results. For example, highly accurate answers are displayed preferentially. The answer generation unit also builds a system in which low accuracy answers are filtered out and only highly accurate answers are provided. For example, filtering is performed based on the accuracy score of the answer. This makes it possible to provide highly accurate answers preferentially.

[0046] The answer generation unit can optimize the speed at which answers are generated, thereby enabling a rapid response. For example, the answer generation unit optimizes the speed at which the generation AI generates answers, thereby enabling a rapid response. For example, it optimizes the answer generation process and shortens response time. The answer generation unit also introduces an algorithm that optimizes the speed at which answers are generated, thereby building a system in which the generation AI provides answers quickly. For example, it improves the efficiency of answer generation. The answer generation unit also optimizes the generation speed, thereby enabling the generation AI to provide answers accurately and quickly. For example, it identifies and improves bottlenecks in answer generation. This enables a rapid response.

[0047] The answer generation unit can also respond to inquiries from different devices. The answer generation unit, for example, enables the generation AI to respond to inquiries from different devices. For example, it provides appropriate answers to inquiries from devices such as smartphones, tablets, and PCs. In addition, the answer generation unit builds a system in which the generation AI generates optimal answers for each device to respond to inquiries from different devices. For example, it provides answers according to the characteristics of the device. In addition, the answer generation unit adds device-compatible functions to the generation AI to flexibly respond to inquiries from different devices. For example, it provides concise answers to inquiries from smartphones. This makes it possible to respond to inquiries from different devices.

[0048] The answer generation unit automatically generates answer templates, enabling efficient answers. For example, the answer generation unit allows a generation AI to automatically generate answer templates, enabling efficient answers. For example, a template is used to quickly provide answers to frequently asked questions. The answer generation unit also introduces an algorithm that automatically generates answer templates, and builds a system in which the generation AI provides answers based on the templates. For example, the answer is customized based on the template. The answer generation unit also automatically generates templates, enabling the generation AI to efficiently provide answers. For example, the template is used to maintain consistency in answers. This makes it possible to achieve efficient answers.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The query analysis unit can refer to the user's past behavioral history and make personalized suggestions based on the user's hobbies and interests. For example, if the user has previously purchased books in a specific genre, it can provide information on new releases related to that genre. It can also recommend related articles and content based on the user's past browsing history. It can also learn the user's behavioral patterns and make pre-prepared suggestions based on predicted needs. For example, it can provide information on events that many users are interested in during a particular season. This allows for more personalized suggestions to be made to the user.

[0051] The query analysis unit can add a multilingual support function so that it can handle inquiries in different languages. For example, a multilingual support function can be added to the generation AI so that it can handle inquiries in different languages. For example, appropriate answers can be generated for inquiries in multiple languages, such as English, French, and Chinese. The query analysis unit also uses the multilingual support function to generate answers based on the language selected by the user. For example, if a user makes an inquiry in Spanish, an answer can be provided in Spanish. The query analysis unit can also automatically translate inquiries in different languages, and the generation AI can generate answers based on the translation results. For example, an inquiry in Japanese can be translated into English, an answer can be generated in English, and the answer can be translated again into Japanese and provided. This makes it possible to handle inquiries in different languages.

[0052] The query analysis unit can analyze images or videos and generate answers based on visual information. For example, the generation AI analyzes images sent by users and generates answers based on their contents. For example, it analyzes photos of products and provides the product's stock status and detailed information. The query analysis unit also analyzes videos sent by users and generates answers based on visual information. For example, it analyzes videos of broken equipment and provides repair methods and support information. The query analysis unit also uses image recognition technology to automatically analyze the contents of images sent by users and generate appropriate answers. For example, it analyzes the barcode of a product and provides detailed information about the product. This makes it possible to provide answers based on visual information.

[0053] When referencing past data, the answer generation unit can evaluate the reliability of the data and prioritize learning from highly reliable data. For example, when the generation AI refers to past data, an algorithm can be introduced to evaluate the reliability of the data, and highly reliable data can be prioritized for learning. For example, data from highly reliable sources can be used preferentially. The answer generation unit also takes into account the source of the data and how frequently it is updated to evaluate its reliability. For example, official databases and frequently updated data can be prioritized for learning. The answer generation unit can also filter out low-reliability data and build a system that learns only highly reliable data. For example, filtering can be performed based on the reliability score of the data. This allows highly reliable data to be prioritized for learning.

[0054] When referencing past data, the answer generation unit can generate answers based on the latest trends based on changes in the data over time. For example, when the generation AI refers to past data, it takes into account changes in the data over time and generates answers based on the latest trends. For example, it analyzes past data in chronological order and reflects the latest trends. The answer generation unit also builds a system that analyzes changes in the data over time and generates answers according to changes in trends. For example, it provides answers that take seasonal trends into consideration. The answer generation unit also reevaluates past data based on the latest trend information and generates optimal answers. For example, it provides answers that reflect the latest market trends. This makes it possible to provide answers based on the latest trends.

[0055] The answer generation unit can refer to data from different industries and generate answers that utilize knowledge from those industries. For example, the generation AI refers to data from different industries and generates answers that utilize knowledge from those industries. For example, it refers to data from the medical industry and provides an appropriate answer to a health-related inquiry. The answer generation unit also integrates data from different industries, and builds a system in which the generation AI generates answers based on that data. For example, it integrates data from the technology industry and the consumer market and provides an answer that utilizes knowledge from both. The answer generation unit also refers to data from different industries, allowing the generation AI to generate answers from a multi-faceted perspective. For example, it refers to data from the financial industry and provides an appropriate answer to a question about the economy. This makes it possible to provide answers that utilize knowledge from different industries.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The query analysis unit is equipped with a generation AI and analyzes the content of the user's query. For example, the generation AI uses natural language processing technology to analyze the content of the query and extract information to generate an appropriate answer. The query analysis unit also references past data to learn patterns for generating an appropriate answer based on the content of the query. Furthermore, the query analysis unit references the user's behavioral history and provides information for generating a personalized answer. Step 2: The answer generation unit generates an answer based on the query content analyzed by the query analysis unit. For example, the generation AI uses a template-based generation model to generate an answer according to the query content. The generation AI can also use the generation model to generate an optimal answer according to the query content. Furthermore, the answer generation unit has an emotion estimation function to generate an answer according to the user's emotions. Step 3: The information acquisition unit acquires from the cloud the information necessary for the answer generated by the answer generation unit. For example, it acquires product information and customer information stored on the cloud and generates an answer based on that information. The information acquisition unit also evaluates the reliability of the information acquired from the cloud and gives priority to using the more reliable information. Furthermore, the information acquisition unit takes into account the update frequency of the information acquired from the cloud and gives priority to acquiring the latest information.

[0058] (Example 2) The automatic learning system according to the embodiment of the present invention utilizes a generation AI to refer to the content of inquiries and past data, automatically generate appropriate answers, and acquire necessary information from the cloud. This enables the automatic learning system to flexibly respond to a variety of inquiries and provide accurate and efficient answers.

[0059] The automated learning system according to the embodiment includes a query analysis unit, an answer generation unit, and an information acquisition unit. The query analysis unit includes a generation AI and analyzes the content of a query from a user. For example, the generation AI analyzes the content of the query using natural language processing technology and extracts information for generating an appropriate answer. The query analysis unit also references past data to learn patterns for generating an appropriate answer based on the content of the query. For example, the optimal answer to a similar query is learned based on past query data. The query analysis unit also references a user's behavioral history to provide information for generating a personalized answer. For example, the answer generation unit provides related information based on the user's past purchase history and browsing history. The answer generation unit generates an answer based on the query content analyzed by the query analysis unit. For example, the generation AI uses a template-based generation model to generate an answer corresponding to the content of the query. The generation AI can also use the generation model to generate an optimal answer corresponding to the content of the query. The answer generation unit also includes an emotion estimation function for generating an answer corresponding to the user's emotions. For example, the answer generation unit analyzes the user's tone of voice and facial expressions to generate an answer corresponding to the emotion. The information acquisition unit acquires information necessary for the answer generated by the answer generation unit from the cloud. For example, it acquires product information and customer information stored on the cloud and generates an answer based on that information. The information acquisition unit also evaluates the reliability of the information acquired from the cloud and prioritizes the use of highly reliable information. For example, it prioritizes the use of data from official information sources. Furthermore, the information acquisition unit takes into account the update frequency of the information acquired from the cloud and prioritizes the acquisition of the latest information. For example, it prioritizes the use of information from a frequently updated database. This enables the automatic learning system according to the embodiment to flexibly respond to a variety of inquiries and provide accurate and efficient answers. For example, the generation AI learns from past data and acquires the latest information from the cloud, thereby always providing accurate answers. Furthermore, by flexibly responding to a variety of inquiries, it is possible to quickly meet user needs.

[0060] The query analysis unit can refer to the user's past behavioral history and generate more personalized answers. For example, the generation AI in the query analysis unit references the user's past purchase history and browsing history to generate personalized answers based on the query content. For example, if a user makes an inquiry related to a product they previously purchased, detailed information about that product is provided. The query analysis unit also references the user's past inquiry history to provide consistent answers to similar inquiries. For example, if a user who has previously returned an item makes another inquiry about a return, the unit responds quickly based on the details of the previous procedure. The query analysis unit also learns user behavior patterns and provides pre-prepared answers to predicted inquiries. For example, it quickly provides pre-prepared answers to inquiries made by many users during a particular season. This makes it possible to provide more personalized answers to users.

[0061] The query analysis unit can analyze the user's voice tone and facial expression and generate a response that corresponds to their emotion. For example, the generation AI in the query analysis unit analyzes the user's voice tone and generates a response that corresponds to their emotion. For example, if the user makes a query in an angry tone, a calm and polite response is provided. The query analysis unit also analyzes the user's facial expression and generates a response that corresponds to their emotion. For example, if the user has a confused expression, a detailed explanation or additional support is provided. The query analysis unit also analyzes both the voice tone and facial expression and generates a response based on a comprehensive emotional evaluation. For example, if the user makes a query in a happy tone, a response that includes positive feedback is provided. This makes it possible to provide a response that corresponds to the user's emotion.

[0062] The query analysis unit can add a multilingual support function so that it can handle inquiries in different languages. For example, the query analysis unit adds a multilingual support function to the generation AI so that it can handle inquiries in different languages. For example, it generates appropriate answers to inquiries in multiple languages, such as English, French, and Chinese. The query analysis unit also uses the multilingual support function to generate answers based on the language selected by the user. For example, if a user makes an inquiry in Spanish, an answer in Spanish is provided. The query analysis unit also automatically translates inquiries in different languages, and the generation AI generates an answer based on the translation results. For example, an inquiry in Japanese is translated into English, an answer is generated in English, and the answer is then translated back into Japanese and provided. This makes it possible to handle inquiries in different languages.

[0063] The query analysis unit can analyze images or videos and generate answers based on visual information. For example, the query analysis unit uses a generation AI to analyze images sent by users and generate answers based on their contents. For example, it analyzes photos of products and provides the product's stock status and detailed information. The query analysis unit can also analyze videos sent by users and generate answers based on visual information. For example, it can analyze videos of broken equipment and provide repair methods and support information. The query analysis unit can also use image recognition technology to automatically analyze the contents of images sent by users and generate appropriate answers. For example, it can analyze product barcodes and provide detailed information about the product. This makes it possible to provide answers based on visual information.

[0064] The query analysis unit can estimate the user's emotions in real time and make suggestions that elicit positive emotions. For example, the query analysis unit uses an emotion estimation function to estimate the emotions of the user when entering a query in real time and make suggestions that elicit positive emotions. For example, if the user is feeling anxious, the query analysis unit makes suggestions that give the user a sense of security. The query analysis unit also analyzes the user's emotions in real time and provides an interface for eliciting positive emotions. For example, it presents encouraging messages and success stories. The query analysis unit also makes suggestions in real time that will make the user feel positive emotions based on the emotion estimation data. For example, it displays appropriate encouragement or praise based on the user's input. This makes it possible to make suggestions that elicit positive emotions from the user.

[0065] When referring to past data, the answer generation unit can evaluate the reliability of the data and prioritize learning from highly reliable data. For example, when the generation AI refers to past data, the answer generation unit introduces an algorithm that evaluates the reliability of the data and prioritizes learning from highly reliable data. For example, it prioritizes using data from highly reliable sources. In addition, the answer generation unit takes into account the source of the data and how often it is updated to evaluate its reliability. For example, it prioritizes learning from official databases and data that is frequently updated. In addition, the answer generation unit builds a system that filters out low-reliability data and learns only highly reliable data. For example, it filters based on the reliability score of the data. This allows it to prioritize learning from highly reliable data.

[0066] When referring to past data, the answer generation unit can generate an answer based on the latest trends based on changes in the data over time. For example, when the generation AI refers to past data, the answer generation unit takes into account changes in the data over time and generates an answer based on the latest trends. For example, it analyzes past data in time series and reflects the latest trends. The answer generation unit also builds a system that analyzes changes in the data over time and generates answers according to changes in trends. For example, it provides answers that take seasonal trends into consideration. The answer generation unit also reevaluates past data based on the latest trend information and generates an optimal answer. For example, it provides an answer that reflects the latest market trends. This makes it possible to provide answers based on the latest trends.

[0067] The answer generation unit can learn emotional information contained in past data and generate answers corresponding to the emotions. The answer generation unit, for example, uses an emotion estimation function to learn emotional information contained in past data and generate answers corresponding to the emotions. For example, the answer generation unit analyzes the user's emotions from past inquiry data and provides answers corresponding to similar emotions. The answer generation unit also analyzes emotional information contained in past data and builds a system that generates answers corresponding to the emotions. For example, answers with positive emotions are preferentially learned from past data. The answer generation unit also reevaluates past data based on the emotion estimation data and generates optimal answers corresponding to the emotions. For example, answers with negative emotions are filtered from past data. This makes it possible to provide answers corresponding to the emotions.

[0068] The answer generation unit can refer to data from different industries and generate answers that utilize knowledge from those industries. For example, the answer generation unit allows the generation AI to refer to data from different industries and generate answers that utilize knowledge from those industries. For example, the answer generation unit refers to data from the medical industry to provide an appropriate answer to a health-related inquiry. The answer generation unit also integrates data from different industries, and builds a system in which the generation AI generates answers based on that data. For example, the answer generation unit integrates data from the technology industry and the consumer market to provide an answer that utilizes knowledge from both. The answer generation unit also refers to data from different industries, allowing the generation AI to generate answers from a multifaceted perspective. For example, the answer generation unit refers to data from the financial industry to provide an appropriate answer to a question about the economy. This makes it possible to provide answers that utilize knowledge from different industries.

[0069] The answer generation unit can visually grasp data trends using a data visualization tool. For example, when the generation AI refers to past data, the answer generation unit uses a data visualization tool to visually grasp data trends. For example, it displays data fluctuations using graphs and charts. The answer generation unit also uses a data visualization tool to analyze trends in past data and builds a system that generates answers based on the results. For example, it visually displays data peaks and trends. The answer generation unit also uses a data visualization tool to visually analyze past data and generate optimal answers. For example, it displays data concentration using a heat map. This makes it possible to visually grasp data trends.

[0070] The answer generation unit can analyze the user's emotional response to past data and generate an answer that is likely to resonate emotionally. The answer generation unit, for example, uses an emotion estimation function to analyze the user's emotional response to past data and generate an answer that is likely to resonate emotionally. For example, answers with a large number of positive emotional responses are preferentially learned. The answer generation unit also analyzes the user's emotional response to past data and builds a system that generates answers that are likely to resonate emotionally. For example, answers with a high emotional score are preferentially provided. The answer generation unit also reevaluates past data based on the emotion estimation data and generates an optimal answer that is likely to resonate emotionally. For example, answers with a small number of negative emotional responses are preferentially provided. This makes it possible to provide an answer that is likely to resonate emotionally.

[0071] When acquiring information from the cloud, the information acquisition unit can prioritize acquiring the latest information based on the frequency of information updates. For example, when the generation AI acquires information from the cloud, the information acquisition unit takes into account the frequency of information updates and prioritizes acquiring the latest information. For example, it prioritizes the use of information from a frequently updated database. The information acquisition unit also analyzes the update history of information on the cloud and builds a system that generates answers based on the latest information. For example, it provides answers based on the latest inventory information and price information. The information acquisition unit also introduces an algorithm that evaluates the frequency of information updates and prioritizes acquiring the most reliable latest information. For example, it prioritizes the use of data from information sources that are updated frequently. This allows the latest information to be acquired preferentially.

[0072] When acquiring information from the cloud, the information acquisition unit evaluates the reliability of the information and can prioritize the use of highly reliable information. For example, when the generation AI acquires information from the cloud, the information acquisition unit introduces an algorithm that evaluates the reliability of the information and prioritizes the use of highly reliable information. For example, it prioritizes the use of data from official information sources. The information acquisition unit also evaluates the reliability of information on the cloud and builds a system that generates answers based on highly reliable information. For example, it filters information based on a reliability score. The information acquisition unit also takes into account the source and update history of the information to evaluate the reliability of the information. For example, it prioritizes the use of data from highly reliable information sources. This allows the highly reliable information to be used preferentially.

[0073] The information acquisition unit can analyze the user's emotional response to the information acquired from the cloud and provide information according to the emotion. The information acquisition unit, for example, uses an emotion estimation function to analyze the user's emotional response to the information acquired from the cloud and provide information according to the emotion. For example, information with a large number of positive emotional responses is preferentially provided. The information acquisition unit also analyzes the user's emotional response to the information acquired from the cloud and builds a system that provides information according to the emotion. For example, information with a high emotional score is preferentially provided. The information acquisition unit also reevaluates the information acquired from the cloud based on the emotion estimation data and provides optimal information according to the emotion. For example, information with a small number of negative emotional responses is preferentially provided. This makes it possible to provide information according to the emotion.

[0074] The information acquisition unit can integrate information between different cloud services and provide comprehensive information. For example, the generation AI can integrate information between different cloud services in the information acquisition unit to provide comprehensive information. For example, the information acquisition unit can integrate data from multiple cloud services and provide a comprehensive answer. The information acquisition unit can also integrate information from different cloud services to build a system in which the generation AI generates an answer based on that data. For example, the information acquisition unit can integrate and provide information from multiple data sources. The information acquisition unit can also integrate information between different cloud services, allowing the generation AI to generate an answer from a multifaceted perspective. For example, the information acquisition unit can integrate and provide data from different cloud services. This makes it possible to provide comprehensive information.

[0075] The information acquisition unit can utilize real-time data to generate answers based on the latest situation. In the information acquisition unit, for example, the generation AI acquires real-time data from the cloud and generates answers based on the latest situation. For example, answers are provided based on real-time inventory information and price information. The information acquisition unit also builds a system that analyzes real-time data on the cloud and generates answers based on the latest situation. For example, answers are provided based on real-time weather information and traffic information. The information acquisition unit also utilizes real-time data, and the generation AI generates optimal answers based on the latest situation. For example, answers are provided based on real-time market trends. This makes it possible to provide answers based on the latest situation.

[0076] The information acquisition unit can monitor the user's emotional response to information acquired from the cloud in real time and provide optimal information. The information acquisition unit, for example, uses an emotion estimation function to monitor the user's emotional response to information acquired from the cloud in real time and provide optimal information. For example, information with a high number of positive emotional responses is preferentially provided. The information acquisition unit also analyzes the user's emotional response to information acquired from the cloud in real time and builds a system that provides information according to the emotion. For example, information with a high emotion score is preferentially provided. The information acquisition unit also reevaluates the information acquired from the cloud in real time based on the emotion estimation data and provides optimal information according to the emotion. For example, information with a low number of negative emotional responses is preferentially provided. This makes it possible to provide optimal information according to the emotion.

[0077] The answer generation unit can introduce a sub-AI to generate specialized answers for each type of inquiry. For example, the answer generation unit introduces a sub-AI that generates specialized answers for each type of inquiry so that the generation AI can respond to a variety of inquiries. For example, a technically specialized sub-AI will respond to technical inquiries. The answer generation unit also builds a system in which sub-AIs with specialized knowledge generate answers depending on the type of inquiry. For example, a medical-related inquiry will be responded to by a medical-specialized sub-AI. The answer generation unit also introduces a sub-AI so that the generation AI can provide specialized answers to a variety of inquiries. For example, a legal-specialized sub-AI will respond to legal inquiries. This makes it possible to provide specialized answers.

[0078] The answer generation unit can evaluate the urgency of an inquiry and generate answers in a priority order according to the urgency. For example, the answer generation unit uses a generation AI to evaluate the urgency of an inquiry and generate answers in a priority order according to the urgency. For example, inquiries with high urgency are responded to quickly. The answer generation unit also introduces an algorithm to evaluate the urgency of an inquiry and builds a system that generates answers in a priority order according to the urgency. For example, inquiries with high urgency are processed first. The answer generation unit also generates answers in a priority order according to the urgency, allowing the generation AI to respond quickly to a variety of inquiries. For example, answers are provided immediately to inquiries with high urgency. This makes it possible to provide answers in a priority order according to the urgency.

[0079] The answer generation unit can generate flexible answers according to the user's emotions. The answer generation unit generates flexible answers according to the user's emotions, for example, by using an emotion estimation function. For example, if the user is feeling anxious, an answer that gives a sense of security is provided. The answer generation unit also analyzes the user's emotions in real time and builds a system that generates flexible answers according to the emotions. For example, if the user is feeling angry, a calm and polite answer is provided. The answer generation unit also generates an optimal answer according to the user's emotions based on the emotion estimation data. For example, if the user is feeling happy, a positive answer that shares that joy is provided. This makes it possible to provide flexible answers according to the emotions.

[0080] The answer generation unit can generate flexible answers according to the user's emotions. The answer generation unit generates flexible answers according to the user's emotions, for example, by using an emotion estimation function. For example, if the user is feeling anxious, an answer that gives a sense of security is provided. The answer generation unit also analyzes the user's emotions in real time and builds a system that generates flexible answers according to the emotions. For example, if the user is feeling angry, a calm and polite answer is provided. The answer generation unit also generates an optimal answer according to the user's emotions based on the emotion estimation data. For example, if the user is feeling happy, a positive answer that shares that joy is provided. This makes it possible to provide flexible answers according to the emotions.

[0081] The answer generation unit can be made versatile so that it can respond to inquiries from different industries. For example, the answer generation unit makes the generation AI versatile, allowing it to respond to inquiries from different industries. For example, it provides appropriate answers to inquiries from the technology industry, medical industry, finance industry, etc. The answer generation unit also learns data from different industries and builds a system that enables the generation AI to respond to inquiries from a variety of industries. For example, it generates answers by integrating knowledge from different industries. The answer generation unit also makes the generation AI versatile, allowing it to flexibly respond to inquiries from a variety of industries. For example, it integrates sub-AIs with specialized knowledge from different industries. This allows it to respond to inquiries from different industries.

[0082] The answer generation unit can automatically classify the inquiry content and generate an appropriate answer. In the answer generation unit, for example, a generation AI automatically classifies the inquiry content and generates an appropriate answer. For example, inquiries about product inventory status, order status, return procedures, etc. are automatically classified. The answer generation unit also introduces an algorithm that automatically classifies the inquiry content, and builds a system in which the generation AI generates answers based on the classification results. For example, a template according to the type of inquiry is used. The answer generation unit also uses an automatic classification function so that the generation AI provides appropriate answers to a variety of inquiries. For example, the answer generation unit analyzes the inquiry content and generates the optimal answer. This makes it possible to automatically classify the inquiry content and provide appropriate answers.

[0083] The answer generation unit can generate suggestions for flexible responses according to the user's emotions. The answer generation unit generates suggestions for flexible responses according to the user's emotions, for example, using an emotion estimation function. For example, if the user is feeling anxious, the answer generation unit makes suggestions that give the user a sense of security. The answer generation unit also analyzes the user's emotions in real time and builds a system that generates suggestions for flexible responses according to the emotions. For example, if the user is feeling angry, the answer generation unit suggests a calm and polite response. The answer generation unit also suggests an optimal response according to the user's emotions based on the emotion estimation data. For example, if the user is feeling happy, the answer generation unit suggests a positive response that shares that joy. In this way, suggestions for flexible responses according to the emotions can be provided.

[0084] The answer generation unit can evaluate the accuracy of answers and provide highly accurate answers preferentially. For example, the answer generation unit uses a generation AI to evaluate the accuracy of answers and provide highly accurate answers preferentially. For example, the answer generation unit evaluates accuracy based on past answer data and provides the optimal answer. The answer generation unit also introduces an algorithm to evaluate the accuracy of answers, and builds a system in which the generation AI provides answers based on the evaluation results. For example, highly accurate answers are displayed preferentially. The answer generation unit also builds a system in which low accuracy answers are filtered out and only highly accurate answers are provided. For example, filtering is performed based on the accuracy score of the answer. This makes it possible to provide highly accurate answers preferentially.

[0085] The answer generation unit can optimize the speed at which answers are generated, thereby enabling a rapid response. For example, the answer generation unit optimizes the speed at which the generation AI generates answers, thereby enabling a rapid response. For example, it optimizes the answer generation process and shortens response time. The answer generation unit also introduces an algorithm that optimizes the speed at which answers are generated, thereby building a system in which the generation AI provides answers quickly. For example, it improves the efficiency of answer generation. The answer generation unit also optimizes the generation speed, thereby enabling the generation AI to provide answers accurately and quickly. For example, it identifies and improves bottlenecks in answer generation. This enables a rapid response.

[0086] The answer generation unit can provide accurate and efficient answers according to the user's emotions. The answer generation unit, for example, uses an emotion estimation function to provide accurate and efficient answers according to the user's emotions. For example, if the user is feeling anxious, an accurate answer that gives a sense of security is provided. The answer generation unit also analyzes the user's emotions in real time and builds a system that provides accurate and efficient answers according to the emotions. For example, if the user is feeling angry, a calm and polite answer is provided. The answer generation unit also provides an optimal answer according to the user's emotions based on the emotion estimation data. For example, if the user is feeling happy, a positive answer that shares that joy is provided. This makes it possible to provide accurate and efficient answers according to the emotions.

[0087] The answer generation unit can also respond to inquiries from different devices. The answer generation unit, for example, enables the generation AI to respond to inquiries from different devices. For example, it provides appropriate answers to inquiries from devices such as smartphones, tablets, and PCs. In addition, the answer generation unit builds a system in which the generation AI generates optimal answers for each device to respond to inquiries from different devices. For example, it provides answers according to the characteristics of the device. In addition, the answer generation unit adds device-compatible functions to the generation AI to flexibly respond to inquiries from different devices. For example, it provides concise answers to inquiries from smartphones. This makes it possible to respond to inquiries from different devices.

[0088] The answer generation unit automatically generates answer templates, enabling efficient answers. For example, the answer generation unit allows a generation AI to automatically generate answer templates, enabling efficient answers. For example, a template is used to quickly provide answers to frequently asked questions. The answer generation unit also introduces an algorithm that automatically generates answer templates, and builds a system in which the generation AI provides answers based on the templates. For example, the answer is customized based on the template. The answer generation unit also automatically generates templates, enabling the generation AI to efficiently provide answers. For example, the template is used to maintain consistency in answers. This makes it possible to achieve efficient answers.

[0089] The answer generation unit can build a feedback loop for providing accurate and efficient answers according to the user's emotions. The answer generation unit, for example, uses an emotion estimation function to build a feedback loop for providing accurate and efficient answers according to the user's emotions. For example, the answer is improved based on the user's emotional reaction. The answer generation unit also develops a system that analyzes the user's emotions in real time and builds a feedback loop for providing accurate and efficient answers according to the emotions. For example, the answer is adjusted according to changes in the user's emotions. The answer generation unit also builds a feedback loop for providing optimal answers according to the user's emotions based on the emotion estimation data. For example, the answer is improved based on the user's emotion score. This makes it possible to build a feedback loop for providing accurate and efficient answers according to the emotions.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The query analysis unit can estimate the user's emotions and evaluate the user's stress level based on the estimated user emotions. For example, if the user indicates a high stress level, it can make suggestions to encourage relaxation. The query analysis unit can also monitor the user's emotions in real time and take appropriate measures when the stress level rises. For example, it can provide resources and support information for stress reduction. The query analysis unit can also accumulate user emotion data and analyze long-term stress patterns to propose individual stress management plans. This allows for flexible responses according to the user's stress level.

[0092] The query analysis unit can refer to the user's past behavioral history and make personalized suggestions based on the user's hobbies and interests. For example, if the user has previously purchased books in a specific genre, it can provide information on new releases related to that genre. It can also recommend related articles and content based on the user's past browsing history. It can also learn the user's behavioral patterns and make pre-prepared suggestions based on predicted needs. For example, it can provide information on events that many users are interested in during a particular season. This allows for more personalized suggestions to be made to the user.

[0093] The query analysis unit can analyze the user's voice tone and facial expression to generate a response that corresponds to the user's emotions. For example, if the user makes a query in an angry tone, a calm and polite response is provided. The query analysis unit can also analyze the user's facial expression to generate a response that corresponds to the user's emotions. For example, if the user has a confused expression, a detailed explanation or additional support is provided. The query analysis unit can also analyze both the voice tone and facial expression to generate a response based on a comprehensive emotional evaluation. For example, if the user makes a query in a happy tone, a response that includes positive feedback is provided. This makes it possible to provide a response that corresponds to the user's emotions.

[0094] The query analysis unit can add a multilingual support function so that it can handle inquiries in different languages. For example, a multilingual support function can be added to the generation AI so that it can handle inquiries in different languages. For example, appropriate answers can be generated for inquiries in multiple languages, such as English, French, and Chinese. The query analysis unit also uses the multilingual support function to generate answers based on the language selected by the user. For example, if a user makes an inquiry in Spanish, an answer can be provided in Spanish. The query analysis unit can also automatically translate inquiries in different languages, and the generation AI can generate answers based on the translation results. For example, an inquiry in Japanese can be translated into English, an answer can be generated in English, and the answer can be translated again into Japanese and provided. This makes it possible to handle inquiries in different languages.

[0095] The query analysis unit can analyze images or videos and generate answers based on visual information. For example, the generation AI analyzes images sent by users and generates answers based on their contents. For example, it analyzes photos of products and provides the product's stock status and detailed information. The query analysis unit also analyzes videos sent by users and generates answers based on visual information. For example, it analyzes videos of broken equipment and provides repair methods and support information. The query analysis unit also uses image recognition technology to automatically analyze the contents of images sent by users and generate appropriate answers. For example, it analyzes the barcode of a product and provides detailed information about the product. This makes it possible to provide answers based on visual information.

[0096] The query analysis unit can estimate the user's emotions in real time and make suggestions that elicit positive emotions. For example, the emotion estimation function can be used to estimate the emotions of the user when they input a query in real time and make suggestions that elicit positive emotions. For example, if the user is feeling anxious, suggestions that give a sense of security can be made. The query analysis unit also analyzes the user's emotions in real time and provides an interface for eliciting positive emotions. For example, it presents encouraging messages and success stories. The query analysis unit also makes suggestions in real time that will make the user feel positive emotions based on the emotion estimation data. For example, it displays appropriate encouragement or praise based on the user's input. This makes it possible to make suggestions that elicit positive emotions from the user.

[0097] When referencing past data, the answer generation unit can evaluate the reliability of the data and prioritize learning from highly reliable data. For example, when the generation AI refers to past data, an algorithm can be introduced to evaluate the reliability of the data, and highly reliable data can be prioritized for learning. For example, data from highly reliable sources can be used preferentially. The answer generation unit also takes into account the source of the data and how frequently it is updated to evaluate its reliability. For example, official databases and frequently updated data can be prioritized for learning. The answer generation unit can also filter out low-reliability data and build a system that learns only highly reliable data. For example, filtering can be performed based on the reliability score of the data. This allows highly reliable data to be prioritized for learning.

[0098] When referencing past data, the answer generation unit can generate answers based on the latest trends based on changes in the data over time. For example, when the generation AI refers to past data, it takes into account changes in the data over time and generates answers based on the latest trends. For example, it analyzes past data in chronological order and reflects the latest trends. The answer generation unit also builds a system that analyzes changes in the data over time and generates answers according to changes in trends. For example, it provides answers that take seasonal trends into consideration. The answer generation unit also reevaluates past data based on the latest trend information and generates optimal answers. For example, it provides answers that reflect the latest market trends. This makes it possible to provide answers based on the latest trends.

[0099] The answer generation unit can learn emotional information contained in past data and generate answers corresponding to the emotions. For example, an emotion estimation function is used to learn emotional information contained in past data and generate answers corresponding to the emotions. For example, the emotion estimation function analyzes the user's emotions from past inquiry data and provides answers corresponding to similar emotions. The answer generation unit also analyzes emotional information contained in past data and builds a system that generates answers corresponding to the emotions. For example, answers with positive emotions are preferentially learned from past data. The answer generation unit also reevaluates past data based on the emotion estimation data and generates optimal answers corresponding to the emotions. For example, answers with negative emotions are filtered from past data. This makes it possible to provide answers corresponding to the emotions.

[0100] The answer generation unit can refer to data from different industries and generate answers that utilize knowledge from those industries. For example, the generation AI refers to data from different industries and generates answers that utilize knowledge from those industries. For example, it refers to data from the medical industry and provides an appropriate answer to a health-related inquiry. The answer generation unit also integrates data from different industries, and builds a system in which the generation AI generates answers based on that data. For example, it integrates data from the technology industry and the consumer market and provides an answer that utilizes knowledge from both. The answer generation unit also refers to data from different industries, allowing the generation AI to generate answers from a multi-faceted perspective. For example, it refers to data from the financial industry and provides an appropriate answer to a question about the economy. This makes it possible to provide answers that utilize knowledge from different industries.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The query analysis unit is equipped with a generation AI and analyzes the content of the user's query. For example, the generation AI uses natural language processing technology to analyze the content of the query and extract information to generate an appropriate answer. The query analysis unit also references past data to learn patterns for generating an appropriate answer based on the content of the query. Furthermore, the query analysis unit references the user's behavioral history and provides information for generating a personalized answer. Step 2: The answer generation unit generates an answer based on the query content analyzed by the query analysis unit. For example, the generation AI uses a template-based generation model to generate an answer according to the query content. The generation AI can also use the generation model to generate an optimal answer according to the query content. Furthermore, the answer generation unit has an emotion estimation function to generate an answer according to the user's emotions. Step 3: The information acquisition unit acquires from the cloud the information necessary for the answer generated by the answer generation unit. For example, it acquires product information and customer information stored on the cloud and generates an answer based on that information. The information acquisition unit also evaluates the reliability of the information acquired from the cloud and gives priority to using the more reliable information. Furthermore, the information acquisition unit takes into account the update frequency of the information acquired from the cloud and gives priority to acquiring the latest information.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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]

[0170] 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 query analysis unit equipped with generative AI, a response generation unit that generates a response based on the query content analyzed by the query analysis unit; an information acquisition unit that acquires information necessary for the answer generated by the answer generation unit from the cloud; A system characterized by:

2. The query analysis unit Referencing the user's past behavioral history to generate more personalized answers 2. The system of claim 1.

3. The query analysis unit Analyzes the user's tone of voice and facial expressions to generate responses that correspond to their emotions 2. The system of claim 1.

4. The query analysis unit Add a multilingual function to respond to inquiries in different languages.

2. The system of claim 1.

5. The query analysis unit Analyze images or videos to generate visually-based answers 2. The system of claim 1.

Images