System

Abstract

An object of a system according to an embodiment is to evaluate the dignity of a generated AI and contribute to the development thereof.SOLUTION: A system includes an evaluation part, a scoring part, and a disclosure part. The evaluation unit evaluates the generation AI. The grading unit grades the grade of the generated AI evaluated by the evaluation unit. The disclosure part periodically discloses the evaluation result scored by the scoring part.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] With conventional technology, there were no clear criteria for evaluating the quality of generative AI, and there was a problem in that evaluations that would contribute to its development were not carried out.

[0005] The system according to the embodiment aims to evaluate the quality of generative AI and contribute to its development. [Means for solving the problem]

[0006] The system according to the embodiment includes an evaluation unit, a scoring unit, and a publication unit. The evaluation unit evaluates the generating AI. The scoring unit scores the quality of the generating AI evaluated by the evaluation unit. The publication unit periodically publishes the evaluation results scored by the scoring unit. [Effects of the Invention]

[0007] The system according to the embodiment can evaluate the quality of generative AI and contribute to its development. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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 generative AI evaluation system according to an embodiment of the present invention evaluates generative AI from the perspective of "character" and promotes its development. This system evaluates generative AI from five perspectives: "language usage," "compassion," "culture," "positive thinking," and "beliefs." The evaluation is performed by a scoring AI, and the results are published periodically. As a result, the generative AI evaluation system can contribute to the development of generative AI by evaluating the character of generative AI and publishing the results.

[0029] A generative AI evaluation system according to an embodiment includes an evaluation unit, a scoring unit, and a publishing unit. The evaluation unit evaluates the generative AI. For example, the evaluation unit evaluates the sentences and dialogues generated by the generative AI from five perspectives: language usage, consideration, culture, positive thinking, and beliefs. The evaluation unit can also analyze the content of the sentences and dialogues generated by the generative AI and assign scores based on each perspective. For example, the evaluation unit evaluates whether honorific language and polite expressions are used appropriately in the sentences generated by the generative AI. The evaluation unit can also evaluate whether the sentences generated by the generative AI convey consideration for others. The evaluation unit can also evaluate whether knowledge of history, culture, science, and the like is appropriately reflected in the sentences generated by the generative AI. The evaluation unit can also evaluate whether the sentences generated by the generative AI contain positive expressions and encouraging words. The evaluation unit can also evaluate whether the sentences generated by the generative AI convey consistent beliefs. The scoring unit scores the quality of the generative AI evaluated by the evaluation unit. For example, the scoring department comprehensively scores the generative AI's quality based on the scores assigned by the evaluation department. The scoring department can also aggregate the scores for each aspect and calculate an overall score. The scoring department can also set standards for quantitatively evaluating the quality of the generative AI. The disclosure department regularly publishes the evaluation results scored by the scoring department. For example, the disclosure department publishes the evaluation results on an online platform. The disclosure department can also categorize and publish the evaluation results by different industries or applications. The disclosure department can also translate and publish the evaluation results into different languages. The disclosure department can also publish the evaluation results in a format that clearly shows the generative AI's areas for improvement and strengths. The disclosure department can also use an emotion estimation function to analyze what emotions the publication of the evaluation results evokes in users and adjust the results to evoke positive emotions. In this way, the generative AI evaluation system can contribute to the development of generative AI by evaluating the quality of generative AI and publishing the results.

[0030] The evaluation unit can evaluate the language used in sentences or dialogues generated by the generation AI. For example, the evaluation unit evaluates regional language use, such as Kansai dialect or Tohoku dialect, in sentences generated by the generation AI. For example, it checks whether honorific expressions in the Kansai dialect are used appropriately. The evaluation unit also takes into account regional differences in language use and evaluates whether regional expressions are used appropriately in sentences generated by the generation AI. For example, it checks whether the Hokkaido dialect is accurately reflected. The evaluation unit also evaluates whether regional honorific language and expressions are used appropriately in sentences generated by the generation AI. For example, it checks whether honorific expressions in the Kyushu region are used accurately. In this way, by evaluating the language used by the generation AI, appropriate language use can be promoted.

[0031] The evaluation unit can evaluate the consideration shown in the text or dialogue generated by the generative AI. For example, the evaluation unit evaluates the appropriate use of language in specialized fields such as the medical or legal industry in the text generated by the generative AI. For example, it checks whether medical terminology is used accurately. In addition, to evaluate the appropriate use of language in a specific industry or specialized field, the evaluation unit checks whether industry-specific terms and expressions are used accurately in the text generated by the generative AI. For example, it evaluates whether IT industry terminology is used appropriately. In addition, the evaluation unit evaluates the appropriate use of language in a specific industry or specialized field in the text generated by the generative AI. For example, it checks whether financial industry terminology is used accurately. In this way, by evaluating the consideration shown in the generative AI, consideration for others can be promoted.

[0032] The evaluation unit can evaluate the sophistication of the sentences or dialogue generated by the generation AI. The evaluation unit, for example, uses an emotion estimation function to evaluate what emotions the sentences generated by the generation AI evoke in the other person. For example, it checks whether the sentences evoke positive emotions in the other person. The evaluation unit also performs emotion estimation on the sentences generated by the generation AI and recommends appropriate language usage for the other person. For example, it avoids expressions that evoke negative emotions. The evaluation unit also uses the emotion estimation function to evaluate what emotions the sentences generated by the generation AI evoke in the other person and recommends appropriate language usage. For example, it recommends expressions that give the other person a sense of security. In this way, by evaluating the sophistication of the generation AI, it is possible to promote the depth of knowledge.

[0033] The evaluation unit can evaluate positive thinking in sentences or dialogues generated by the generative AI. For example, the evaluation unit evaluates expressions in sentences generated by the generative AI that propose positive solutions to specific difficult situations. For example, it checks whether specific proposals for problem solving are made. In addition, to evaluate expressions that propose positive solutions to specific difficult situations, the evaluation unit checks whether a positive approach is taken in the sentences generated by the generative AI. For example, it evaluates whether a proactive response is made to a difficult situation. In addition, the evaluation unit evaluates whether a sentence generated by the generative AI contains expressions that propose positive solutions to specific difficult situations. For example, it checks whether constructive proposals for problem solving are made. In this way, positive expression can be promoted by evaluating the generative AI's positive thinking.

[0034] The evaluation unit can evaluate the beliefs in the sentences or dialogues generated by the generation AI. For example, the evaluation unit evaluates whether the sentences generated by the generation AI contain consistent expressions based on specific values ​​or principles. For example, it checks whether the expressions are consistent based on specific ethics or beliefs. In addition, to evaluate consistent expressions based on specific values ​​or principles, the evaluation unit checks whether the sentences generated by the generation AI contain consistent expressions. For example, it evaluates whether the expressions are consistent based on specific values. In addition, the evaluation unit evaluates whether the sentences generated by the generation AI contain consistent expressions based on specific values ​​or principles. For example, it checks whether the expressions are consistent based on specific beliefs. In this way, consistent values ​​can be promoted by evaluating the beliefs of the generation AI.

[0035] The publication unit can publish the evaluation results on an online platform. For example, the publication unit publishes the evaluation results on an online platform such as a website or social media. The publication unit can also categorize and publish the evaluation results by different industries or applications. For example, evaluation results for the medical industry and the education industry can be displayed separately. The publication unit can also translate and publish the evaluation results into different languages. For example, the publication unit can translate and publish the evaluation results into languages ​​such as English and French. The publication unit can also publish the evaluation results in a format that clearly shows the strengths and areas for improvement of the generative AI. For example, the publication unit can visually display the evaluation results in graphs or charts. The publication unit can also use emotion estimation functionality to analyze what emotions the publication of the evaluation results evokes in users and adjust the expressions to evoke positive emotions. For example, the publication unit can change the wording of the evaluation results to be more positive. By publishing the evaluation results on an online platform, the evaluation results of the generative AI can be widely shared.

[0036] The summary generation unit can refer to background information and topic models to understand the context. For example, when the generation AI creates a summary, the summary generation unit automatically collects related background information and refers to it to understand the context. For example, it collects related news articles and academic papers. The summary generation unit also uses topic models to understand the context when the generation AI creates a summary. For example, it extracts related keywords and phrases based on the topic model. The summary generation unit also references related background information and topic models when the generation AI creates a summary, building a system for understanding the context. For example, it automatically collects related information and reflects it in the summary. This enables more accurate summaries by referring to background information and topic models to understand the context.

[0037] The summary generation unit can analyze the logical structure of an answer and the development of the arguments to generate a logical summary. For example, the summary generation unit uses a generation AI to analyze the logical structure of an answer and generate a logical summary. For example, it analyzes the development of arguments and logical consistency and reflects this in the summary. The summary generation unit also analyzes the development of arguments in an answer and builds a system in which the generation AI generates a logical summary. For example, it generates a summary based on the importance and relevance of arguments. The summary generation unit also develops an algorithm for the generation AI to analyze the logical structure of an answer and the development of arguments to generate a logical summary. For example, it evaluates the logical consistency and the importance of arguments. This makes it possible to generate a logical summary by analyzing the logical structure of an answer and the development of arguments in a question.

[0038] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0039] The generative AI evaluation system can further include a user feedback collection unit. The user feedback collection unit collects user feedback on the evaluation results of the generative AI. For example, it provides an interface where users can leave comments on the evaluation results. The user feedback collection unit can also analyze the collected feedback and use it to improve the evaluation criteria of the generative AI. For example, it can review the evaluation criteria based on user opinions. The user feedback collection unit can also periodically publish the collected feedback to ensure transparency. This makes it possible to build an evaluation system that reflects user opinions.

[0040] The evaluation unit can also evaluate the ethics of the text generated by the generative AI. For example, it can check whether the text generated by the generative AI contains any ethically questionable language. The evaluation unit can also evaluate whether the text generated by the generative AI contains socially acceptable language. For example, it can check whether it contains discriminatory language or prejudice. The evaluation unit can also evaluate whether the text generated by the generative AI complies with ethical guidelines. For example, it can check whether language regarding privacy and data protection is appropriate. In this way, evaluating the ethics of the generative AI can promote socially responsible dialogue.

[0041] The generative AI evaluation system can further include a user profile management unit. The user profile management unit manages user profile information and reflects it in the evaluation results of the generative AI. For example, it collects information such as the user's age, occupation, and interests and reflects it in the evaluation results. The user profile management unit can also provide individually customized evaluation results based on the user's profile information. For example, it can provide evaluation results specialized for a specific industry or occupation. The user profile management unit can also periodically update the user's profile information to reflect the latest information. This allows for more personalized evaluations by providing evaluation results based on the user's profile information.

[0042] The generative AI evaluation system can further include a data security management unit. The data security management unit manages the security of the data handled by the generative AI. For example, it encrypts the data and controls access. The data security management unit can also take measures to ensure privacy protection of the data handled by the generative AI. For example, it can set guidelines for handling personal information. The data security management unit can also evaluate the security risks of the data handled by the generative AI and take appropriate measures. For example, it can evaluate the risk of data leakage and implement measures. This ensures the security of the data handled by the generative AI, making it possible to build a highly reliable evaluation system.

[0043] The evaluation unit can also evaluate the environmental awareness of the text generated by the generation AI. For example, it can check whether the text generated by the generation AI shows awareness of environmental protection. The evaluation unit can also evaluate whether the text generated by the generation AI contains environmentally friendly expressions. For example, it can check whether the text contains expressions related to sustainable development and eco-friendly initiatives. The evaluation unit can also evaluate whether the text generated by the generation AI proposes specific solutions to environmental problems. For example, it can check whether the text includes suggestions for recycling and improving energy efficiency. In this way, evaluating the environmental awareness of the generation AI can promote a more sustainable society.

[0044] The processing flow of the first embodiment will be briefly explained below.

[0045] Step 1: The evaluation unit evaluates the generation AI. For example, the evaluation unit evaluates the sentences and dialogues generated by the generation AI from five perspectives: language use, compassion, culture, positive thinking, and beliefs. The evaluation unit can also analyze the content of the sentences and dialogues generated by the generation AI and assign a score based on each perspective. For example, the evaluation unit evaluates whether honorific language and polite expressions are used appropriately in the sentences generated by the generation AI. The evaluation unit can also evaluate whether the sentences generated by the generation AI convey consideration for the other person. The evaluation unit can also evaluate whether knowledge of history, culture, science, etc. is appropriately reflected in the sentences generated by the generation AI. The evaluation unit can also evaluate whether the sentences generated by the generation AI contain positive expressions and encouraging words. The evaluation unit can also evaluate whether the sentences generated by the generation AI convey consistent beliefs. Step 2: The scoring unit scores the quality of the generative AI evaluated by the evaluation unit. For example, the scoring unit comprehensively scores the quality of the generative AI based on the scores assigned by the evaluation unit. The scoring unit can also aggregate the scores for each aspect and calculate an overall score. The scoring unit can also set standards for quantitatively evaluating the quality of the generative AI. Step 3: The publishing department periodically publishes the evaluation results scored by the scoring department. For example, the publishing department may publish the evaluation results on an online platform. The publishing department may also categorize and publish the evaluation results by different industries or applications. The publishing department may also translate and publish the evaluation results into different languages. The publishing department may also publish the evaluation results in a format that clearly shows the strengths and areas for improvement of the generation AI. The publishing department may also use an emotion estimation function to analyze what emotions the publication of the evaluation results evokes in users and adjust the results to evoke positive emotions.

[0046] (Example 2) The generative AI evaluation system according to an embodiment of the present invention evaluates generative AI from the perspective of "character" and promotes its development. This system evaluates generative AI from five perspectives: "language usage," "compassion," "culture," "positive thinking," and "beliefs." The evaluation is performed by a scoring AI, and the results are published periodically. As a result, the generative AI evaluation system can contribute to the development of generative AI by evaluating the character of generative AI and publishing the results.

[0047] A generative AI evaluation system according to an embodiment includes an evaluation unit, a scoring unit, and a publishing unit. The evaluation unit evaluates the generative AI. For example, the evaluation unit evaluates the sentences and dialogues generated by the generative AI from five perspectives: language usage, consideration, culture, positive thinking, and beliefs. The evaluation unit can also analyze the content of the sentences and dialogues generated by the generative AI and assign scores based on each perspective. For example, the evaluation unit evaluates whether honorific language and polite expressions are used appropriately in the sentences generated by the generative AI. The evaluation unit can also evaluate whether the sentences generated by the generative AI convey consideration for others. The evaluation unit can also evaluate whether knowledge of history, culture, science, and the like is appropriately reflected in the sentences generated by the generative AI. The evaluation unit can also evaluate whether the sentences generated by the generative AI contain positive expressions and encouraging words. The evaluation unit can also evaluate whether the sentences generated by the generative AI convey consistent beliefs. The scoring unit scores the quality of the generative AI evaluated by the evaluation unit. For example, the scoring department comprehensively scores the generative AI's quality based on the scores assigned by the evaluation department. The scoring department can also aggregate the scores for each aspect and calculate an overall score. The scoring department can also set standards for quantitatively evaluating the quality of the generative AI. The disclosure department regularly publishes the evaluation results scored by the scoring department. For example, the disclosure department publishes the evaluation results on an online platform. The disclosure department can also categorize and publish the evaluation results by different industries or applications. The disclosure department can also translate and publish the evaluation results into different languages. The disclosure department can also publish the evaluation results in a format that clearly shows the generative AI's areas for improvement and strengths. The disclosure department can also use an emotion estimation function to analyze what emotions the publication of the evaluation results evokes in users and adjust the results to evoke positive emotions. In this way, the generative AI evaluation system can contribute to the development of generative AI by evaluating the quality of generative AI and publishing the results.

[0048] The evaluation unit can evaluate the language used in sentences or dialogues generated by the generation AI. For example, the evaluation unit evaluates regional language use, such as Kansai dialect or Tohoku dialect, in sentences generated by the generation AI. For example, it checks whether honorific expressions in the Kansai dialect are used appropriately. The evaluation unit also takes into account regional differences in language use and evaluates whether regional expressions are used appropriately in sentences generated by the generation AI. For example, it checks whether the Hokkaido dialect is accurately reflected. The evaluation unit also evaluates whether regional honorific language and expressions are used appropriately in sentences generated by the generation AI. For example, it checks whether honorific expressions in the Kyushu region are used accurately. In this way, by evaluating the language used by the generation AI, appropriate language use can be promoted.

[0049] The evaluation unit can evaluate the consideration shown in the text or dialogue generated by the generative AI. For example, the evaluation unit evaluates the appropriate use of language in specialized fields such as the medical or legal industry in the text generated by the generative AI. For example, it checks whether medical terminology is used accurately. In addition, to evaluate the appropriate use of language in a specific industry or specialized field, the evaluation unit checks whether industry-specific terms and expressions are used accurately in the text generated by the generative AI. For example, it evaluates whether IT industry terminology is used appropriately. In addition, the evaluation unit evaluates the appropriate use of language in a specific industry or specialized field in the text generated by the generative AI. For example, it checks whether financial industry terminology is used accurately. In this way, by evaluating the consideration shown in the generative AI, consideration for others can be promoted.

[0050] The evaluation unit can evaluate the sophistication of the sentences or dialogue generated by the generation AI. The evaluation unit, for example, uses an emotion estimation function to evaluate what emotions the sentences generated by the generation AI evoke in the other person. For example, it checks whether the sentences evoke positive emotions in the other person. The evaluation unit also performs emotion estimation on the sentences generated by the generation AI and recommends appropriate language usage for the other person. For example, it avoids expressions that evoke negative emotions. The evaluation unit also uses the emotion estimation function to evaluate what emotions the sentences generated by the generation AI evoke in the other person and recommends appropriate language usage. For example, it recommends expressions that give the other person a sense of security. In this way, by evaluating the sophistication of the generation AI, it is possible to promote the depth of knowledge.

[0051] The evaluation unit can evaluate positive thinking in sentences or dialogues generated by the generative AI. For example, the evaluation unit evaluates expressions in sentences generated by the generative AI that propose positive solutions to specific difficult situations. For example, it checks whether specific proposals for problem solving are made. In addition, to evaluate expressions that propose positive solutions to specific difficult situations, the evaluation unit checks whether a positive approach is taken in the sentences generated by the generative AI. For example, it evaluates whether a proactive response is made to a difficult situation. In addition, the evaluation unit evaluates whether a sentence generated by the generative AI contains expressions that propose positive solutions to specific difficult situations. For example, it checks whether constructive proposals for problem solving are made. In this way, positive expression can be promoted by evaluating the generative AI's positive thinking.

[0052] The evaluation unit can evaluate the beliefs in the sentences or dialogues generated by the generation AI. For example, the evaluation unit evaluates whether the sentences generated by the generation AI contain consistent expressions based on specific values ​​or principles. For example, it checks whether the expressions are consistent based on specific ethics or beliefs. In addition, to evaluate consistent expressions based on specific values ​​or principles, the evaluation unit checks whether the sentences generated by the generation AI contain consistent expressions. For example, it evaluates whether the expressions are consistent based on specific values. In addition, the evaluation unit evaluates whether the sentences generated by the generation AI contain consistent expressions based on specific values ​​or principles. For example, it checks whether the expressions are consistent based on specific beliefs. In this way, consistent values ​​can be promoted by evaluating the beliefs of the generation AI.

[0053] The publication unit can publish the evaluation results on an online platform. For example, the publication unit publishes the evaluation results on an online platform such as a website or social media. The publication unit can also categorize and publish the evaluation results by different industries or applications. For example, evaluation results for the medical industry and the education industry can be displayed separately. The publication unit can also translate and publish the evaluation results into different languages. For example, the publication unit can translate and publish the evaluation results into languages ​​such as English and French. The publication unit can also publish the evaluation results in a format that clearly shows the strengths and areas for improvement of the generative AI. For example, the publication unit can visually display the evaluation results in graphs or charts. The publication unit can also use emotion estimation functionality to analyze what emotions the publication of the evaluation results evokes in users and adjust the expressions to evoke positive emotions. For example, the publication unit can change the wording of the evaluation results to be more positive. By publishing the evaluation results on an online platform, the evaluation results of the generative AI can be widely shared.

[0054] The summary generation unit can refer to background information and topic models to understand the context. For example, when the generation AI creates a summary, the summary generation unit automatically collects related background information and refers to it to understand the context. For example, it collects related news articles and academic papers. The summary generation unit also uses topic models to understand the context when the generation AI creates a summary. For example, it extracts related keywords and phrases based on the topic model. The summary generation unit also references related background information and topic models when the generation AI creates a summary, building a system for understanding the context. For example, it automatically collects related information and reflects it in the summary. This enables more accurate summaries by referring to background information and topic models to understand the context.

[0055] The summary generation unit can analyze the logical structure of an answer and the development of the arguments to generate a logical summary. For example, the summary generation unit uses a generation AI to analyze the logical structure of an answer and generate a logical summary. For example, it analyzes the development of arguments and logical consistency and reflects this in the summary. The summary generation unit also analyzes the development of arguments in an answer and builds a system in which the generation AI generates a logical summary. For example, it generates a summary based on the importance and relevance of arguments. The summary generation unit also develops an algorithm for the generation AI to analyze the logical structure of an answer and the development of arguments to generate a logical summary. For example, it evaluates the logical consistency and the importance of arguments. This makes it possible to generate a logical summary by analyzing the logical structure of an answer and the development of arguments in a question.

[0056] The summary generation unit uses the emotion estimation function to generate a summary that captures the emotional nuances of the answer, allowing the emotional elements to be reflected in the evaluation. For example, when the generation AI summarizes, the summary generation unit uses the emotion estimation function to capture the emotional nuances of the answer. For example, it generates a summary based on an emotion score. The summary generation unit also uses the emotion estimation function to build a system in which the generation AI reflects the emotional elements of the answer in the evaluation. For example, it performs the evaluation based on the emotion score. The summary generation unit also develops an algorithm for the generation AI to use the emotion estimation function to generate a summary that captures the emotional nuances of the answer. For example, it generates a summary based on the emotion score and reflects that in the evaluation. In this way, by generating a summary that captures the emotional nuances, the emotional elements can also be reflected in the evaluation.

[0057] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0058] The generative AI evaluation system can further include a user feedback collection unit. The user feedback collection unit collects user feedback on the evaluation results of the generative AI. For example, it provides an interface where users can leave comments on the evaluation results. The user feedback collection unit can also analyze the collected feedback and use it to improve the evaluation criteria of the generative AI. For example, it can review the evaluation criteria based on user opinions. The user feedback collection unit can also periodically publish the collected feedback to ensure transparency. This makes it possible to build an evaluation system that reflects user opinions.

[0059] The evaluation unit can also evaluate the humor in the text generated by the generation AI. For example, it can check whether the jokes and humorous expressions generated by the generation AI are appropriate. The evaluation unit can also evaluate whether the humor in the text generated by the generation AI has a positive impact on the other person. For example, it can check whether the humor makes the other person feel good. The evaluation unit can also evaluate whether the humor in the text generated by the generation AI is culturally appropriate. For example, it can check whether the humor is inappropriate for a particular culture or background. In this way, by evaluating the quality of the humor in the generation AI, it is possible to promote more friendly dialogue.

[0060] The evaluation unit can also evaluate the creativity of the texts generated by the generative AI. For example, it checks whether the generative AI provides new ideas and unique perspectives. The evaluation unit can also evaluate whether the texts generated by the generative AI contain creative expressions. For example, it checks whether metaphors and symbolic expressions are used appropriately. The evaluation unit can also evaluate whether the creativity of the texts generated by the generative AI has a positive impact on the other person. For example, it checks whether the creative expressions attract the other person's interest. In this way, evaluating the creativity of the generative AI can promote more engaging dialogue.

[0061] The evaluation unit can also evaluate the ethics of the text generated by the generative AI. For example, it can check whether the text generated by the generative AI contains any ethically questionable language. The evaluation unit can also evaluate whether the text generated by the generative AI contains socially acceptable language. For example, it can check whether it contains discriminatory language or prejudice. The evaluation unit can also evaluate whether the text generated by the generative AI complies with ethical guidelines. For example, it can check whether language regarding privacy and data protection is appropriate. In this way, evaluating the ethics of the generative AI can promote socially responsible dialogue.

[0062] The evaluation unit can also evaluate the diversity of emotions in the text generated by the generation AI. For example, it checks whether various emotions are appropriately expressed in the text generated by the generation AI. The evaluation unit can also evaluate whether the emotional expression in the text generated by the generation AI is appropriate for the other person. For example, it checks whether emotions such as sadness and joy are properly conveyed. The evaluation unit can also evaluate whether the emotional expression in the text generated by the generation AI is culturally appropriate. For example, it checks whether the text contains emotional expressions that are inappropriate for a particular culture or background. In this way, by evaluating the quality of the emotional expression of the generation AI, it is possible to promote richer dialogue.

[0063] The generative AI evaluation system can further include a user profile management unit. The user profile management unit manages user profile information and reflects it in the evaluation results of the generative AI. For example, it collects information such as the user's age, occupation, and interests and reflects it in the evaluation results. The user profile management unit can also provide individually customized evaluation results based on the user's profile information. For example, it can provide evaluation results specialized for a specific industry or occupation. The user profile management unit can also periodically update the user's profile information to reflect the latest information. This allows for more personalized evaluations by providing evaluation results based on the user's profile information.

[0064] The evaluation unit can also evaluate the cultural sensitivity of the text generated by the generation AI. For example, it can check whether the text generated by the generation AI shows understanding of different cultures and backgrounds. The evaluation unit can also evaluate whether the text generated by the generation AI uses culturally appropriate expressions. For example, it can check whether respect is shown for specific cultures and backgrounds. The evaluation unit can also evaluate whether the text generated by the generation AI uses expressions to avoid cultural misunderstandings. For example, it can check whether cultural stereotypes or prejudices are included. In this way, by evaluating the cultural sensitivity of the generation AI, it is possible to promote dialogue that takes diversity into consideration.

[0065] The generative AI evaluation system can further include a data security management unit. The data security management unit manages the security of the data handled by the generative AI. For example, it encrypts the data and controls access. The data security management unit can also take measures to ensure privacy protection of the data handled by the generative AI. For example, it can set guidelines for handling personal information. The data security management unit can also evaluate the security risks of the data handled by the generative AI and take appropriate measures. For example, it can evaluate the risk of data leakage and implement measures. This ensures the security of the data handled by the generative AI, making it possible to build a highly reliable evaluation system.

[0066] The evaluation unit can also evaluate the environmental awareness of the text generated by the generation AI. For example, it can check whether the text generated by the generation AI shows awareness of environmental protection. The evaluation unit can also evaluate whether the text generated by the generation AI contains environmentally friendly expressions. For example, it can check whether the text contains expressions related to sustainable development and eco-friendly initiatives. The evaluation unit can also evaluate whether the text generated by the generation AI proposes specific solutions to environmental problems. For example, it can check whether the text includes suggestions for recycling and improving energy efficiency. In this way, evaluating the environmental awareness of the generation AI can promote a more sustainable society.

[0067] The evaluation unit can also evaluate the social impact of the text generated by the generative AI. For example, it checks whether the text generated by the generative AI contains expressions that will have a beneficial social impact. The evaluation unit can also evaluate whether the text generated by the generative AI shows awareness of social issues. For example, it checks whether it contains expressions addressing social issues such as poverty and educational inequality. The evaluation unit can also evaluate whether the text generated by the generative AI proposes specific solutions to social issues. For example, it checks whether it includes suggestions for community support or volunteer activities. In this way, evaluating the social impact of the generative AI can promote dialogue that contributes more to society.

[0068] The processing flow of the second embodiment will be briefly explained below.

[0069] Step 1: The evaluation unit evaluates the generation AI. For example, the evaluation unit evaluates the sentences and dialogues generated by the generation AI from five perspectives: language use, compassion, culture, positive thinking, and beliefs. The evaluation unit can also analyze the content of the sentences and dialogues generated by the generation AI and assign a score based on each perspective. For example, the evaluation unit evaluates whether honorific language and polite expressions are used appropriately in the sentences generated by the generation AI. The evaluation unit can also evaluate whether the sentences generated by the generation AI convey consideration for the other person. The evaluation unit can also evaluate whether knowledge of history, culture, science, etc. is appropriately reflected in the sentences generated by the generation AI. The evaluation unit can also evaluate whether the sentences generated by the generation AI contain positive expressions and encouraging words. The evaluation unit can also evaluate whether the sentences generated by the generation AI convey consistent beliefs. Step 2: The scoring unit scores the quality of the generative AI evaluated by the evaluation unit. For example, the scoring unit comprehensively scores the quality of the generative AI based on the scores assigned by the evaluation unit. The scoring unit can also aggregate the scores for each aspect and calculate an overall score. The scoring unit can also set standards for quantitatively evaluating the quality of the generative AI. Step 3: The publishing department periodically publishes the evaluation results scored by the scoring department. For example, the publishing department may publish the evaluation results on an online platform. The publishing department may also categorize and publish the evaluation results by different industries or applications. The publishing department may also translate and publish the evaluation results into different languages. The publishing department may also publish the evaluation results in a format that clearly shows the strengths and areas for improvement of the generation AI. The publishing department may also use an emotion estimation function to analyze what emotions the publication of the evaluation results evokes in users and adjust the results to evoke positive emotions.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0074] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0075] 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.

[0076] 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.

[0077] 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.

[0078] 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).

[0079] 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.

[0080] 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.

[0081] 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.

[0082] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0083] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0089] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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).

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0098] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0104] 7, a 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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).

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0114] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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."

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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]

[0137] 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. an evaluation unit that evaluates the generation AI; a scoring unit that scores the quality of the generated AI evaluated by the evaluation unit; and a publication department that periodically publishes the evaluation results scored by the scoring department. A system characterized by:

2. The evaluation section Evaluating the language used in sentences or dialogues generated by generative AI 2. The system of claim 1.

3. The public section is Publish the evaluation results on an online platform 2. The system of claim 1.

4. The evaluation section Evaluating how considerate the sentences generated by the generative AI are to the other person 4. The system of claim 3.

5. The evaluation section Evaluate how cultured the sentences generated by the AI ​​make the other person feel 5. The system of claim 4.

Images