System

Abstract

An object of the system according to the embodiment is to enable anyone to easily obtain an accurate answer using a generated AI specialized in a specialized field.SOLUTION: A system includes a generation AI, a learning unit, a feedback unit, and an interface unit. The generation AI is specialized in a specialized field. The learning unit asks questions in various patterns to the generated AI in advance, and learns how a human side thinks about an actual desired answer. The feedback unit receives feedback from the user in response to an answer to the generated AI and performs self-improvement based on the feedback. The interface unit allows a user to input a question in a natural language and provides an answer to the question.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] Previous technology had the problem that the generating AI could give incorrect answers and required a certain level of knowledge on the part of the questioner.

[0005] The system of the embodiment aims to enable anyone to easily obtain accurate answers using generative AI specialized in specialized fields. [Means for solving the problem]

[0006] The system according to the embodiment comprises a generation AI, a learning unit, a feedback unit, and an interface unit. The generation AI is specialized in a specialized field. The learning unit asks the generation AI various patterns of questions in advance, learning the actual desired answers and how humans thought about them. The feedback unit receives feedback from the user regarding the generation AI's answers, and improves itself based on that feedback. The interface unit allows the user to input a question in natural language, and provides an answer to that question. [Effects of the Invention]

[0007] The system according to the embodiment uses generative AI specialized in specialized fields, allowing anyone to easily obtain accurate answers. [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 pseudo-expert system according to the embodiment of the present invention is a system in which a generating AI with specialized knowledge and enhanced insight can easily provide the answer that anyone wants. As a result, the pseudo-expert system allows users without specialized knowledge to obtain specialized information using the generating AI.

[0029] A pseudo-expert system according to an embodiment includes a generation AI, a learning unit, a feedback unit, and an interface unit. The generation AI is trained to specialize in a specialized field. For example, the generation AI creates AI with specialized knowledge in fields such as medicine, law, engineering, and economics. The generation AI learns using specialized literature and databases to acquire deep knowledge in that field. The generation AI receives input from prompts containing instructions on what the user wants the generation AI to do, and the generation AI generates answers based on those prompts. The learning unit asks the generation AI various questions in advance to learn the actual desired answers and how humans think about them. For example, in the medical field, it learns what information is important when making a diagnosis based on a patient's symptoms. This allows the generation AI to more accurately understand the intent of the question and provide appropriate answers. The feedback unit receives user feedback on the generation AI's answers and uses that feedback to improve itself. For example, when a user evaluates the generation AI's answers as "correct" or "incorrect," the generation AI learns the evaluation and improves the accuracy of future answers. The interface unit allows a user to input a question in natural language and provides an answer to the question. For example, a user can input a question in natural language and the generating AI can provide an answer to the question. This allows even users without specialized knowledge to obtain specialized information using the generating AI. As a result, the pseudo-expert system according to the embodiment allows users without specialized knowledge to obtain specialized information using the generating AI. For example, it is possible to propose diagnoses and treatments in the medical field, provide solutions to legal problems in the legal field, propose solutions to technical problems in the engineering field, and propose investment strategies in the economics field.

[0030] Generative AI can be trained using different datasets for each specialized field. For example, in the medical field, generative AI is trained using medical papers and clinical data to create AI that can diagnose and suggest treatments. For example, a dataset related to a specific disease can be used to improve the accuracy of disease diagnosis. In the legal field, generative AI is trained using case law databases and legal documents to create AI that can provide legal advice and assist in the preparation of contracts. For example, a dataset related to a specific legal issue can be used to improve the accuracy of legal advice. In the economics field, generative AI is trained using economic data and market analysis reports to create AI that can develop investment strategies and economic forecasts. For example, a dataset related to a specific market can be used to improve the accuracy of investment decisions. This creates generative AI specialized for each specialized field.

[0031] Generative AI can be improved based on expert feedback. For example, in the medical field, generative AI works with doctors and researchers to evaluate the diagnostic results and treatment suggestions generated by the generative AI, and the AI ​​is improved based on that feedback. For example, the accuracy of diagnostic results and the appropriateness of treatments are evaluated. In the legal field, generative AI works with lawyers and legal scholars to evaluate the content of legal advice and contracts generated by the generative AI, and the AI ​​is improved based on that feedback. For example, the accuracy of legal advice and the validity of contracts are evaluated. In the economic field, generative AI works with economists and analysts to evaluate the economic forecasts and investment strategies generated by the generative AI, and the AI ​​is improved based on that feedback. For example, the accuracy of economic forecasts and the effectiveness of investment strategies are evaluated. In this way, generative AI is improved based on expert feedback.

[0032] Generative AI can integrate generative AI from different fields of expertise to respond to complex questions that span multiple fields. For example, generative AI can integrate the fields of medicine and law to create a generative AI that can respond to questions about medical litigation. For example, it can provide legal advice about medical malpractice and advice on patient rights. It can integrate the fields of economics and engineering to create a generative AI that can respond to questions about technology investment. For example, it can provide advice on the market value and investment risks of new technologies. It can integrate the fields of medicine and economics to create a generative AI that can respond to questions about medical economics. For example, it can provide advice on how to reduce medical costs and how to choose medical insurance. This makes it possible to respond to questions that span multiple fields.

[0033] Generative AI can be applied to education and training programs to assist in the acquisition of specialized knowledge. For example, generative AI in the medical field is used to provide training programs for medical students and interns. For example, it performs case-based learning and diagnostic simulations. Generative AI in the legal field is used to provide training programs for law students and new lawyers. For example, it performs mock trials and contract drafting exercises. Generative AI in the economics field is used to provide training programs for economics students and new analysts. For example, it performs economic data analysis and investment strategy simulations. This helps to acquire specialized knowledge.

[0034] Generative AI can analyze users' past question history and perform personalized learning to provide answers optimized for each individual user. For example, in the medical field, generative AI analyzes patients' past question history and provides diagnoses and treatments optimized for each individual patient. For example, it can suggest more appropriate treatments based on past symptoms and diagnostic results. In the legal field, it analyzes clients' past question history and provides legal advice optimized for each client. For example, it can suggest more appropriate solutions based on past consultation content and legal issues. In the economic field, it analyzes investors' past question history and provides investment strategies optimized for each investor. For example, it can suggest more appropriate investment destinations based on past investment history and market analysis. This makes it possible to provide answers optimized for each user.

[0035] Generative AI can perform scenario-based learning to gain a deeper understanding of the intent of a question. For example, in the medical field, generative AI can perform scenario-based learning based on a patient's symptoms and medical history to enable complex diagnoses and treatment suggestions. For example, it can learn diagnostic scenarios for cases where multiple symptoms overlap. In the legal field, it can perform scenario-based learning for complex legal issues to enable detailed legal advice. For example, it can learn solution scenarios for problems involving multiple laws. In the economics field, it can perform scenario-based learning for complex market situations to enable detailed economic forecasts and investment strategies. For example, it can learn market scenarios influenced by multiple economic indicators. This allows it to gain a deeper understanding of the intent of a question.

[0036] Generative AI can apply learning to enhance insight to multilingual generative AI to accommodate different languages ​​and cultural areas. For example, in the medical field, generative AI is created to provide multilingual diagnoses and treatment suggestions to accommodate different languages ​​and cultural areas. For example, it is compatible with multiple languages ​​such as English, Spanish, and Chinese. In the legal field, generative AI is created to provide multilingual legal advice to accommodate different languages ​​and cultural areas. For example, it is compatible with multiple languages ​​such as English, French, and German. In the economics field, generative AI is created to provide multilingual economic forecasts and investment strategies to accommodate different languages ​​and cultural areas. For example, it is compatible with multiple languages ​​such as English, Japanese, and Korean. This makes it possible to accommodate different languages ​​and cultural areas.

[0037] Generative AI can apply learning to enhance insights to fields such as business intelligence and market research, improving the accuracy of data analysis. In the business intelligence field, for example, generative AI uses corporate performance data and market data to perform detailed analyses and predictions. For example, it performs sales forecasts and market share analysis. In the market research field, generative AI uses consumer data and market trends to perform detailed analyses and predictions. For example, it analyzes consumer behavior and predicts market acceptance of new products. In the economic field, generative AI uses economic indicators and market data to perform detailed analyses and predictions. For example, it predicts GDP growth rates and analyzes stock market trends. This can improve the accuracy of data analysis.

[0038] The feedback unit reflects user feedback in real time, enabling the accuracy of the generating AI's answers to be improved instantly. For example, in the medical field, the feedback unit collects feedback from patients in real time and immediately improves the generating AI's diagnostic accuracy. For example, it improves the AI ​​based on the patient's evaluation of the diagnostic results. In the legal field, the feedback unit collects feedback from clients in real time and immediately improves the accuracy of the generating AI's legal advice. For example, it improves the AI ​​based on the client's evaluation of the legal advice. In the economic field, the feedback unit collects feedback from investors in real time and immediately improves the accuracy of the generating AI's investment strategy. For example, it improves the AI ​​based on the investor's evaluation of the investment strategy. This allows the accuracy of the generating AI's answers to be improved instantly.

[0039] The feedback unit can analyze feedback data, identify weaknesses in the generative AI, and develop algorithms to focus on improving those areas. For example, in the medical field, the feedback unit analyzes feedback data on diagnosis results and identifies weaknesses in the generative AI's diagnostic accuracy. For example, if the diagnostic accuracy for a specific disease is low, that area can be focused on for improvement. In the legal field, the feedback unit analyzes feedback data on legal advice and identifies weaknesses in the generative AI's advice accuracy. For example, if the advice accuracy for a specific legal issue is low, that area can be focused on for improvement. In the economic field, the feedback data on investment strategies can be analyzed and weaknesses in the generative AI's strategic accuracy can be identified. For example, if the accuracy of an investment strategy for a specific market is low, that area can be focused on for improvement. This makes it possible to identify weaknesses in the generative AI and focus on for improvement.

[0040] The feedback unit can share feedback loops between generative AIs in different fields of expertise to improve the overall accuracy of answers. For example, the feedback unit can share feedback loops between generative AIs in the medical and legal fields to improve the accuracy of answers regarding medical litigation. For example, this can improve the accuracy of legal advice regarding medical malpractice. Feedback loops can be shared between generative AIs in the economics and engineering fields to improve the accuracy of answers regarding technology investment. For example, this can improve the accuracy of advice regarding the market value and investment risks of new technologies. Feedback loops can be shared between generative AIs in the medical and economics fields to improve the accuracy of answers regarding medical economics. For example, this can improve the accuracy of advice regarding how to reduce medical costs and how to choose medical insurance. In this way, feedback loops can be shared between generative AIs in different fields of expertise to improve the overall accuracy of answers.

[0041] The feedback unit can link the feedback loop with user communities and forums, and reflect feedback between users in the generative AI. For example, in the medical field, the feedback unit can link with patient communities and forums to reflect feedback between patients in the generative AI. For example, it can improve diagnostic accuracy based on the experiences and opinions of patients with the same disease. In the legal field, it can link with legal consultation forums to reflect feedback between clients in the generative AI. For example, it can improve advice accuracy based on the experiences and opinions of clients regarding the same legal issue. In the economic field, it can link with investor communities and forums to reflect feedback between investors in the generative AI. For example, it can improve investment strategy accuracy based on the experiences and opinions of investors investing in the same market. This allows it to link with user communities and forums and reflect feedback between users in the generative AI.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The pseudo-expert system can also analyze the user's past behavioral history and provide advice based on the user's behavioral patterns. For example, in the medical field, it can analyze a patient's past medical history and lifestyle habits to provide more appropriate health management advice. In the legal field, it can analyze past legal problem resolution methods and consultation details to provide more appropriate legal advice. In the economic field, it can analyze past investment history and market trends to provide more appropriate investment strategies. This makes it possible to provide personalized advice based on the user's behavioral patterns.

[0044] The pseudo-expert system can also obtain real-time environmental data from users and provide advice based on that data. For example, in the medical field, it can provide appropriate health care advice by taking into account the patient's current environment (temperature, humidity, air quality, etc.). In the legal field, it can provide appropriate legal advice by taking into account the client's current situation (geographical location, time zone, etc.). In the economic field, it can provide appropriate investment strategies by taking into account the investor's current market situation (stock prices, exchange rates, etc.). This allows it to provide advice based on real-time environmental data.

[0045] The pseudo-expert system can further analyze users' past feedback and optimize the learning of the generative AI based on the content of the feedback. For example, in the medical field, analyzing patients' past feedback can improve the accuracy of diagnoses and treatment suggestions. In the legal field, analyzing clients' past feedback can improve the accuracy of legal advice. In the economic field, analyzing investors' past feedback can improve the accuracy of investment strategies. This allows for optimization of learning based on past feedback.

[0046] The pseudo-expert system can further analyze the user's past behavioral history and make predictions based on behavioral patterns. For example, in the medical field, it analyzes a patient's past medical history and lifestyle habits to predict future health risks. In the legal field, it analyzes past legal problem resolution methods and consultation details to predict future legal risks. In the economic field, it analyzes past investment history and market trends to predict future market trends. This makes it possible to make predictions based on behavioral patterns.

[0047] The pseudo-expert system can further analyze users' past feedback and optimize the learning of the generative AI based on the content of the feedback. For example, in the medical field, analyzing patients' past feedback can improve the accuracy of diagnoses and treatment suggestions. In the legal field, analyzing clients' past feedback can improve the accuracy of legal advice. In the economic field, analyzing investors' past feedback can improve the accuracy of investment strategies. This allows for optimization of learning based on past feedback.

[0048] The pseudo-expert system can further analyze the user's past behavioral history and make predictions based on behavioral patterns. For example, in the medical field, it analyzes a patient's past medical history and lifestyle habits to predict future health risks. In the legal field, it analyzes past legal problem resolution methods and consultation details to predict future legal risks. In the economic field, it analyzes past investment history and market trends to predict future market trends. This makes it possible to make predictions based on behavioral patterns.

[0049] The processing flow of the first embodiment will be briefly explained below.

[0050] Step 1: Generative AI is trained to specialize in a specialized field. For example, an AI with specialized knowledge is created in fields such as medicine, law, engineering, and economics. The generative AI learns using specialized literature and databases and gains in-depth knowledge in that field. The input to the generative AI is a prompt containing instructions on what the user wants the generative AI to do, and the generative AI generates an answer based on that prompt. Step 2: The learning unit asks the generation AI a variety of questions in advance, learning the actual desired answers and how humans thought about them. For example, in the medical field, it learns what information is important when making a diagnosis based on a patient's symptoms. This allows the generation AI to more accurately understand the intent of the question and provide appropriate answers. Step 3: The feedback unit receives user feedback on the AI's answers and uses that feedback to improve itself. For example, when a user evaluates the AI's answers as "correct" or "incorrect," the AI ​​learns from that evaluation and improves the accuracy of its answers from the next time onward. Step 4: The interface unit allows the user to input a question in natural language and provides an answer to that question. For example, the user can input a question in natural language and the generation AI can provide an answer to that question. This allows even users without specialized knowledge to use the generation AI to obtain specialized information.

[0051] (Example 2) The pseudo-expert system according to the embodiment of the present invention is a system in which a generating AI with specialized knowledge and enhanced insight can easily provide the answer that anyone wants. As a result, the pseudo-expert system allows users without specialized knowledge to obtain specialized information using the generating AI.

[0052] A pseudo-expert system according to an embodiment includes a generation AI, a learning unit, a feedback unit, and an interface unit. The generation AI is trained to specialize in a specialized field. For example, the generation AI creates AI with specialized knowledge in fields such as medicine, law, engineering, and economics. The generation AI learns using specialized literature and databases to acquire deep knowledge in that field. The generation AI receives input from prompts containing instructions on what the user wants the generation AI to do, and the generation AI generates answers based on those prompts. The learning unit asks the generation AI various questions in advance to learn the actual desired answers and how humans think about them. For example, in the medical field, it learns what information is important when making a diagnosis based on a patient's symptoms. This allows the generation AI to more accurately understand the intent of the question and provide appropriate answers. The feedback unit receives user feedback on the generation AI's answers and uses that feedback to improve itself. For example, when a user evaluates the generation AI's answers as "correct" or "incorrect," the generation AI learns the evaluation and improves the accuracy of future answers. The interface unit allows a user to input a question in natural language and provides an answer to the question. For example, a user can input a question in natural language and the generating AI can provide an answer to the question. This allows even users without specialized knowledge to obtain specialized information using the generating AI. As a result, the pseudo-expert system according to the embodiment allows users without specialized knowledge to obtain specialized information using the generating AI. For example, it is possible to propose diagnoses and treatments in the medical field, provide solutions to legal problems in the legal field, propose solutions to technical problems in the engineering field, and propose investment strategies in the economics field.

[0053] Generative AI can be trained using different datasets for each specialized field. For example, in the medical field, generative AI is trained using medical papers and clinical data to create AI that can diagnose and suggest treatments. For example, a dataset related to a specific disease can be used to improve the accuracy of disease diagnosis. In the legal field, generative AI is trained using case law databases and legal documents to create AI that can provide legal advice and assist in the preparation of contracts. For example, a dataset related to a specific legal issue can be used to improve the accuracy of legal advice. In the economics field, generative AI is trained using economic data and market analysis reports to create AI that can develop investment strategies and economic forecasts. For example, a dataset related to a specific market can be used to improve the accuracy of investment decisions. This creates generative AI specialized for each specialized field.

[0054] Generative AI can be improved based on expert feedback. For example, in the medical field, generative AI works with doctors and researchers to evaluate the diagnostic results and treatment suggestions generated by the generative AI, and the AI ​​is improved based on that feedback. For example, the accuracy of diagnostic results and the appropriateness of treatments are evaluated. In the legal field, generative AI works with lawyers and legal scholars to evaluate the content of legal advice and contracts generated by the generative AI, and the AI ​​is improved based on that feedback. For example, the accuracy of legal advice and the validity of contracts are evaluated. In the economic field, generative AI works with economists and analysts to evaluate the economic forecasts and investment strategies generated by the generative AI, and the AI ​​is improved based on that feedback. For example, the accuracy of economic forecasts and the effectiveness of investment strategies are evaluated. In this way, generative AI is improved based on expert feedback.

[0055] Generative AI can analyze the emotions of users when they ask questions and provide answers that correspond to those emotions. For example, in the medical field, generative AI can analyze the emotions of patients when they ask questions, and if they are feeling anxious or scared, provide answers that give them a sense of security. For example, it can include kind language and encouraging messages. In the legal field, it can analyze the emotions of clients when they ask questions, and if they are feeling nervous or anxious, provide answers that give them a sense of security. For example, it can provide specific advice on how to reduce legal risks. In the economics field, it can analyze the emotions of investors when they ask questions, and if they are feeling anxious or doubtful, provide answers that give them a sense of security. For example, it can introduce risk management methods and past success stories. This makes it possible to provide answers that correspond to the user's emotions.

[0056] Generative AI can integrate generative AI from different fields of expertise to respond to complex questions that span multiple fields. For example, generative AI can integrate the fields of medicine and law to create a generative AI that can respond to questions about medical litigation. For example, it can provide legal advice about medical malpractice and advice on patient rights. It can integrate the fields of economics and engineering to create a generative AI that can respond to questions about technology investment. For example, it can provide advice on the market value and investment risks of new technologies. It can integrate the fields of medicine and economics to create a generative AI that can respond to questions about medical economics. For example, it can provide advice on how to reduce medical costs and how to choose medical insurance. This makes it possible to respond to questions that span multiple fields.

[0057] Generative AI can be applied to education and training programs to assist in the acquisition of specialized knowledge. For example, generative AI in the medical field is used to provide training programs for medical students and interns. For example, it performs case-based learning and diagnostic simulations. Generative AI in the legal field is used to provide training programs for law students and new lawyers. For example, it performs mock trials and contract drafting exercises. Generative AI in the economics field is used to provide training programs for economics students and new analysts. For example, it performs economic data analysis and investment strategy simulations. This helps to acquire specialized knowledge.

[0058] Generative AI can analyze the emotions of users when they ask questions in real time, and provide an interface that elicits positive emotions. For example, in the medical field, generative AI can analyze the emotions of patients when they ask questions in real time, and provide an interface that elicits positive emotions. For example, it can display kind language and encouraging messages. In the legal field, it can analyze the emotions of clients when they ask questions in real time, and provide an interface that elicits positive emotions. For example, it can display specific advice for reducing legal risks. In the economics field, it can analyze the emotions of investors when they ask questions in real time, and provide an interface that elicits positive emotions. For example, it can display risk management methods and past success stories. This makes it possible to provide an interface that elicits positive emotions.

[0059] Generative AI can analyze users' past question history and perform personalized learning to provide answers optimized for each individual user. For example, in the medical field, generative AI analyzes patients' past question history and provides diagnoses and treatments optimized for each individual patient. For example, it can suggest more appropriate treatments based on past symptoms and diagnostic results. In the legal field, it analyzes clients' past question history and provides legal advice optimized for each client. For example, it can suggest more appropriate solutions based on past consultation content and legal issues. In the economic field, it analyzes investors' past question history and provides investment strategies optimized for each investor. For example, it can suggest more appropriate investment destinations based on past investment history and market analysis. This makes it possible to provide answers optimized for each user.

[0060] Generative AI can perform scenario-based learning to gain a deeper understanding of the intent of a question. For example, in the medical field, generative AI can perform scenario-based learning based on a patient's symptoms and medical history to enable complex diagnoses and treatment suggestions. For example, it can learn diagnostic scenarios for cases where multiple symptoms overlap. In the legal field, it can perform scenario-based learning for complex legal issues to enable detailed legal advice. For example, it can learn solution scenarios for problems involving multiple laws. In the economics field, it can perform scenario-based learning for complex market situations to enable detailed economic forecasts and investment strategies. For example, it can learn market scenarios influenced by multiple economic indicators. This allows it to gain a deeper understanding of the intent of a question.

[0061] Generative AI can use emotion estimation functions to generate answers that take the user's emotional state into account. For example, in the medical field, generative AI can suggest diagnoses and treatments that take the patient's emotional state into account. For example, it can suggest explanations and treatments that reassure an anxious patient. In the legal field, it can provide legal advice that takes the client's emotional state into account. For example, it can provide explanations and advice that relax a nervous client. In the economic field, it can suggest investment strategies that take the investor's emotional state into account. For example, it can suggest investments that reduce risk to an anxious investor. This makes it possible to generate answers that take the user's emotional state into account.

[0062] Generative AI can apply learning to enhance insight to multilingual generative AI to accommodate different languages ​​and cultural areas. For example, in the medical field, generative AI is created to provide multilingual diagnoses and treatment suggestions to accommodate different languages ​​and cultural areas. For example, it is compatible with multiple languages ​​such as English, Spanish, and Chinese. In the legal field, generative AI is created to provide multilingual legal advice to accommodate different languages ​​and cultural areas. For example, it is compatible with multiple languages ​​such as English, French, and German. In the economics field, generative AI is created to provide multilingual economic forecasts and investment strategies to accommodate different languages ​​and cultural areas. For example, it is compatible with multiple languages ​​such as English, Japanese, and Korean. This makes it possible to accommodate different languages ​​and cultural areas.

[0063] Generative AI can apply learning to enhance insights to fields such as business intelligence and market research, improving the accuracy of data analysis. In the business intelligence field, for example, generative AI uses corporate performance data and market data to perform detailed analyses and predictions. For example, it performs sales forecasts and market share analysis. In the market research field, generative AI uses consumer data and market trends to perform detailed analyses and predictions. For example, it analyzes consumer behavior and predicts market acceptance of new products. In the economic field, generative AI uses economic indicators and market data to perform detailed analyses and predictions. For example, it predicts GDP growth rates and analyzes stock market trends. This can improve the accuracy of data analysis.

[0064] Using its emotion estimation function, generative AI can provide personalized learning content based on the user's emotions. In the field of education, for example, generative AI can provide learning content that takes into account the emotional state of students. For example, it can include interesting content and encouraging messages. In training programs, it can provide training content that takes into account the emotional state of participants. For example, it can include content and feedback that increases motivation. In online learning platforms, it can analyze the user's emotional state in real time and provide personalized learning content. For example, it can provide appropriate advice and supplementary materials according to the user's learning progress. This makes it possible to provide personalized learning content.

[0065] The feedback unit reflects user feedback in real time, enabling the accuracy of the generating AI's answers to be improved instantly. For example, in the medical field, the feedback unit collects feedback from patients in real time and immediately improves the generating AI's diagnostic accuracy. For example, it improves the AI ​​based on the patient's evaluation of the diagnostic results. In the legal field, the feedback unit collects feedback from clients in real time and immediately improves the accuracy of the generating AI's legal advice. For example, it improves the AI ​​based on the client's evaluation of the legal advice. In the economic field, the feedback unit collects feedback from investors in real time and immediately improves the accuracy of the generating AI's investment strategy. For example, it improves the AI ​​based on the investor's evaluation of the investment strategy. This allows the accuracy of the generating AI's answers to be improved instantly.

[0066] The feedback unit can analyze feedback data, identify weaknesses in the generative AI, and develop algorithms to focus on improving those areas. For example, in the medical field, the feedback unit analyzes feedback data on diagnosis results and identifies weaknesses in the generative AI's diagnostic accuracy. For example, if the diagnostic accuracy for a specific disease is low, that area can be focused on for improvement. In the legal field, the feedback unit analyzes feedback data on legal advice and identifies weaknesses in the generative AI's advice accuracy. For example, if the advice accuracy for a specific legal issue is low, that area can be focused on for improvement. In the economic field, the feedback data on investment strategies can be analyzed and weaknesses in the generative AI's strategic accuracy can be identified. For example, if the accuracy of an investment strategy for a specific market is low, that area can be focused on for improvement. This makes it possible to identify weaknesses in the generative AI and focus on for improvement.

[0067] The feedback unit can use the emotion estimation function to analyze the emotions of the user when providing feedback and reflect emotion-based feedback in the generation AI. For example, in the medical field, the feedback unit analyzes the emotions of patients when providing feedback and reflects emotion-based feedback in the generation AI. For example, by placing emphasis on feedback from patients who are feeling anxious, diagnostic accuracy can be improved. In the legal field, the feedback unit analyzes the emotions of clients when providing feedback and reflects emotion-based feedback in the generation AI. For example, by placing emphasis on feedback from clients who are feeling nervous, advice accuracy can be improved. In the economic field, the feedback unit analyzes the emotions of investors when providing feedback and reflects emotion-based feedback in the generation AI. For example, by placing emphasis on feedback from investors who are feeling anxious, investment strategy accuracy can be improved. In this way, emotion-based feedback can be reflected in the generation AI.

[0068] The feedback unit can share feedback loops between generative AIs in different fields of expertise to improve the overall accuracy of answers. For example, the feedback unit can share feedback loops between generative AIs in the medical and legal fields to improve the accuracy of answers regarding medical litigation. For example, this can improve the accuracy of legal advice regarding medical malpractice. Feedback loops can be shared between generative AIs in the economics and engineering fields to improve the accuracy of answers regarding technology investment. For example, this can improve the accuracy of advice regarding the market value and investment risks of new technologies. Feedback loops can be shared between generative AIs in the medical and economics fields to improve the accuracy of answers regarding medical economics. For example, this can improve the accuracy of advice regarding how to reduce medical costs and how to choose medical insurance. In this way, feedback loops can be shared between generative AIs in different fields of expertise to improve the overall accuracy of answers.

[0069] The feedback unit can link the feedback loop with user communities and forums, and reflect feedback between users in the generative AI. For example, in the medical field, the feedback unit can link with patient communities and forums to reflect feedback between patients in the generative AI. For example, it can improve diagnostic accuracy based on the experiences and opinions of patients with the same disease. In the legal field, it can link with legal consultation forums to reflect feedback between clients in the generative AI. For example, it can improve advice accuracy based on the experiences and opinions of clients regarding the same legal issue. In the economic field, it can link with investor communities and forums to reflect feedback between investors in the generative AI. For example, it can improve investment strategy accuracy based on the experiences and opinions of investors investing in the same market. This allows it to link with user communities and forums and reflect feedback between users in the generative AI.

[0070] The feedback unit can use the emotion estimation function to analyze the user's emotions when providing feedback and provide an interface for encouraging positive feedback. For example, in the medical field, the feedback unit analyzes the emotions of patients when providing feedback and provides an interface for encouraging positive feedback. For example, it displays messages of gratitude and words of encouragement. In the legal field, it analyzes the emotions of clients when providing feedback and provides an interface for encouraging positive feedback. For example, it displays specific advice for mitigating legal risks. In the economic field, it analyzes the emotions of investors when providing feedback and provides an interface for encouraging positive feedback. For example, it displays risk management methods and past success stories. In this way, it is possible to provide an interface for encouraging positive feedback.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The pseudo-expert system can also analyze the user's past behavioral history and provide advice based on the user's behavioral patterns. For example, in the medical field, it can analyze a patient's past medical history and lifestyle habits to provide more appropriate health management advice. In the legal field, it can analyze past legal problem resolution methods and consultation details to provide more appropriate legal advice. In the economic field, it can analyze past investment history and market trends to provide more appropriate investment strategies. This makes it possible to provide personalized advice based on the user's behavioral patterns.

[0073] The pseudo-expert system can also obtain real-time environmental data from users and provide advice based on that data. For example, in the medical field, it can provide appropriate health care advice by taking into account the patient's current environment (temperature, humidity, air quality, etc.). In the legal field, it can provide appropriate legal advice by taking into account the client's current situation (geographical location, time zone, etc.). In the economic field, it can provide appropriate investment strategies by taking into account the investor's current market situation (stock prices, exchange rates, etc.). This allows it to provide advice based on real-time environmental data.

[0074] The pseudo-expert system can further estimate the user's emotions and adjust the content and method of feedback to the user based on the estimated emotions. For example, in the medical field, if a patient feels anxious, it can provide feedback that gives a sense of security. In the legal field, if a client feels nervous, it can provide feedback that relaxes them. In the economic field, if an investor feels anxious, it can provide feedback that reduces risk. In this way, it is possible to provide feedback that corresponds to the user's emotions.

[0075] The pseudo-expert system can further analyze users' past feedback and optimize the learning of the generative AI based on the content of the feedback. For example, in the medical field, analyzing patients' past feedback can improve the accuracy of diagnoses and treatment suggestions. In the legal field, analyzing clients' past feedback can improve the accuracy of legal advice. In the economic field, analyzing investors' past feedback can improve the accuracy of investment strategies. This allows for optimization of learning based on past feedback.

[0076] The pseudo-expert system can further estimate the user's emotions and adjust the tone and content of the advice it gives to the user based on the estimated emotions. For example, in the medical field, if a patient feels anxious, it can provide reassuring advice in a gentle tone. In the legal field, if a client feels nervous, it can provide advice in a relaxing tone. In the economics field, if an investor feels anxious, it can provide advice in a tone that reduces risk. This makes it possible to provide advice that matches the user's emotions.

[0077] The pseudo-expert system can further analyze the user's past behavioral history and make predictions based on behavioral patterns. For example, in the medical field, it analyzes a patient's past medical history and lifestyle habits to predict future health risks. In the legal field, it analyzes past legal problem resolution methods and consultation details to predict future legal risks. In the economic field, it analyzes past investment history and market trends to predict future market trends. This makes it possible to make predictions based on behavioral patterns.

[0078] The pseudo-expert system can further estimate the user's emotions and adjust the frequency and timing of advice to the user based on the estimated emotions. For example, in the medical field, if a patient feels anxious, it can provide frequent reassuring advice. In the legal field, if a client feels nervous, it can provide relaxing advice at the appropriate time. In the economics field, if an investor feels anxious, it can provide risk mitigation advice at the appropriate time. This makes it possible to adjust the frequency and timing of advice according to the user's emotions.

[0079] The pseudo-expert system can further analyze users' past feedback and optimize the learning of the generative AI based on the content of the feedback. For example, in the medical field, analyzing patients' past feedback can improve the accuracy of diagnoses and treatment suggestions. In the legal field, analyzing clients' past feedback can improve the accuracy of legal advice. In the economic field, analyzing investors' past feedback can improve the accuracy of investment strategies. This allows for optimization of learning based on past feedback.

[0080] The pseudo-expert system can further estimate the user's emotions and adjust the tone and content of the advice it gives to the user based on the estimated emotions. For example, in the medical field, if a patient feels anxious, it can provide reassuring advice in a gentle tone. In the legal field, if a client feels nervous, it can provide advice in a relaxing tone. In the economics field, if an investor feels anxious, it can provide advice in a tone that reduces risk. This makes it possible to provide advice that matches the user's emotions.

[0081] The pseudo-expert system can further analyze the user's past behavioral history and make predictions based on behavioral patterns. For example, in the medical field, it analyzes a patient's past medical history and lifestyle habits to predict future health risks. In the legal field, it analyzes past legal problem resolution methods and consultation details to predict future legal risks. In the economic field, it analyzes past investment history and market trends to predict future market trends. This makes it possible to make predictions based on behavioral patterns.

[0082] The processing flow of the second embodiment will be briefly explained below.

[0083] Step 1: Generative AI is trained to specialize in a specialized field. For example, an AI with specialized knowledge is created in fields such as medicine, law, engineering, and economics. The generative AI learns using specialized literature and databases and gains in-depth knowledge in that field. The input to the generative AI is a prompt containing instructions on what the user wants the generative AI to do, and the generative AI generates an answer based on that prompt. Step 2: The learning unit asks the generation AI a variety of questions in advance, learning the actual desired answers and how humans thought about them. For example, in the medical field, it learns what information is important when making a diagnosis based on a patient's symptoms. This allows the generation AI to more accurately understand the intent of the question and provide appropriate answers. Step 3: The feedback unit receives user feedback on the AI's answers and uses that feedback to improve itself. For example, when a user evaluates the AI's answers as "correct" or "incorrect," the AI ​​learns from that evaluation and improves the accuracy of its answers from the next time onward. Step 4: The interface unit allows the user to input a question in natural language and provides an answer to that question. For example, the user can input a question in natural language and the generation AI can provide an answer to that question. This allows even users without specialized knowledge to use the generation AI to obtain specialized information.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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).

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0103] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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).

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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."

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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]

[0151] 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. Generative AI specialized in specialized fields, A learning unit asks the generating AI various questions in advance to learn the answers it actually wanted and how humans thought about them. a feedback unit that receives feedback from a user regarding the answer of the generating AI and performs self-improvement based on the feedback; an interface unit that allows a user to input a question in natural language and provides an answer to the question; A system characterized by:

2. The generated AI is Trained on different datasets for each specialization 2. The system of claim 1.

3. The generated AI is Improved based on expert feedback 2. The system of claim 1.

4. The generated AI is Analyzing the user's emotions when asking a question and providing the answer according to the emotions 2. The system of claim 1.

5. The generated AI is Integrates generative AI from different fields to respond to complex questions across multiple fields.

2. The system of claim 1.

Images