System

Abstract

An object of a system according to an embodiment is to evaluate the accuracy of an answer of a AI model and provide an improvement.SOLUTION: A system according to an embodiment includes an answer examination unit, an evaluation unit, a feedback providing unit, and an other-company AI model use unit. The answer examination unit examines an answer of the AI model. The evaluation part evaluates the accuracy of the answer examined by the answer examination part. The feedback providing unit provides a basis of evaluation and an improvement point based on a result evaluated by the evaluation unit. The counterpart company AI model using unit performs an examination using a plurality of counterpart company AI models.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, it is difficult to ensure the accuracy of the answers given by AI models, and there is a risk that incorrect information will be provided.

[0005] The system according to the embodiment aims to evaluate the accuracy of the answers of the AI ​​model and provide suggestions for improvement. [Means for solving the problem]

[0006] The system according to the embodiment includes an answer review unit, an evaluation unit, a feedback providing unit, and a third-party AI model using unit. The answer review unit reviews answers from the AI ​​model. The evaluation unit evaluates the accuracy of the answers reviewed by the answer review unit. The feedback providing unit provides the basis for the evaluation and points for improvement based on the results of the evaluation by the evaluation unit. The third-party AI model using unit performs the review using multiple third-party AI models. [Effects of the Invention]

[0007] The system according to the embodiment can evaluate the accuracy of the AI ​​model's answers and provide suggestions for improvement. [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 AI ​​model evaluation system according to an embodiment of the present invention is a system that reviews answers provided by AI models, evaluates their accuracy, and provides feedback, thereby ensuring the quality of answers provided by AI models and enabling users to trust the information obtained from AI.

[0029] An AI model evaluation system according to an embodiment includes an answer review unit, an evaluation unit, a feedback providing unit, and a third-party AI model using unit. The answer review unit reviews answers from AI models. For example, the answer review unit generates answers to user questions using a generation AI and compares the answers with other AI models. The answer review unit can also refer to answers from other AI models to evaluate the accuracy of the answers provided by the generation AI. The evaluation unit evaluates the accuracy of the answers reviewed by the answer review unit. For example, the evaluation unit evaluates the answers provided by the generation AI by comparing them with expert opinions and academic papers. The evaluation unit can also compare the answers provided by the generation AI with the user's past question history to evaluate consistency. The feedback providing unit provides the basis for the evaluation and points for improvement based on the results of the evaluation by the evaluation unit. For example, the feedback providing unit provides detailed feedback on the answers provided by the generation AI, explaining how they are superior to answers from other AI models. The feedback providing unit can also suggest points for improvement to the answers provided by the generation AI. The third-party AI model using unit performs evaluation using multiple third-party AI models. For example, the third-party AI model usage unit compares the answer provided by the generation AI with other AI models and evaluates the accuracy of each answer. The third-party AI model usage unit can also integrate answers provided by multiple AI models and select the most accurate answer. This allows the AI ​​model evaluation system according to the embodiment to improve the accuracy and reliability of the answers of the AI ​​models. For example, in the field of education, the system can provide accurate information when students use AI to study. Furthermore, in the field of business, the system can provide reliable information when companies use AI to make decisions.

[0030] The evaluation department can increase reliability by comparing the AI ​​model's answers with expert opinions and academic papers. For example, the evaluation department will build a system to evaluate the AI ​​model's answers by comparing them with expert opinions. For example, answers in the medical field will be evaluated by comparing them with the opinions of doctors. The evaluation department will also refer to academic papers to evaluate the accuracy of the AI ​​model's answers. For example, answers to scientific questions will be evaluated by comparing them with the latest research results. The evaluation department will also develop a system to evaluate the reliability of the AI ​​model's answers based on expert opinions and academic papers. For example, answers in the legal field will be evaluated by comparing them with the opinions of lawyers. This will increase the reliability of the answers by comparing them with expert opinions and academic papers.

[0031] The evaluation unit can compare the AI ​​model's answers with the user's past question history and evaluate the consistency of the answers. The evaluation unit, for example, builds a system to evaluate the consistency of the AI ​​model's answers based on the user's past question history. For example, it compares and evaluates the current answer with questions previously asked by the same user. The evaluation unit also analyzes the past question history and evaluates whether the AI ​​model's answers are consistent. For example, it checks whether the same answer is provided for questions asked repeatedly by the user. The evaluation unit also develops an algorithm to evaluate the consistency of the AI ​​model's answers based on the user's question history. For example, it evaluates whether the past answer and the current answer are consistent. This makes it possible to evaluate the consistency of the answers by comparing them with the user's past question history.

[0032] The evaluation unit can translate the AI ​​model's answers into different languages ​​and evaluate them from an international perspective. For example, the evaluation unit builds a system that translates the AI ​​model's answers into different languages ​​and evaluates them from an international perspective. For example, the answers are evaluated in multiple languages, such as English, Japanese, and French. The evaluation unit also collects and evaluates feedback from users with different cultures and backgrounds based on the translated answers. For example, it determines the accuracy of the answers based on the evaluations from users in different language-speaking regions. In addition, to evaluate from an international perspective, the evaluation unit inputs the translated answers into a multilingual evaluation system and integrates the evaluation results in each language. For example, the evaluation scores in each language are averaged to form a final evaluation. In this way, translating into different languages ​​allows evaluation from an international perspective.

[0033] The evaluation unit can evaluate the AI ​​model's answer in combination with visual data to promote visual understanding. The evaluation unit, for example, builds a system that evaluates the AI ​​model's answer in combination with visual data. For example, it displays figures and graphs related to the answer to make it easier to understand visually. The evaluation unit also uses the visual data to evaluate the accuracy of the AI ​​model's answer. For example, it determines the reliability of the answer based on statistical data and graphs. The evaluation unit also develops a system that visually evaluates the AI ​​model's answer using figures and graphs. For example, it automatically generates visual data related to the answer and uses it for evaluation. This makes it possible to promote visual understanding by combining it with visual data.

[0034] The feedback providing unit can refer to the answers of other AI models and clarify the differences. For example, the feedback providing unit builds a system in which the generation AI refers to the answers of other AI models and clarifies the differences as the basis for evaluation. For example, the answers of multiple AI models are compared and the differences are highlighted. The feedback providing unit also provides the basis for evaluation based on the answers of other AI models. For example, the answers of different AI models are compared and which answer is most accurate. The feedback providing unit also develops a system in which the generation AI refers to the answers of other AI models and clarifies the differences to provide the basis for evaluation. For example, the reliability of different answers is compared and reflected in the evaluation. In this way, the basis for evaluation can be provided by referring to the answers of other AI models and clarifying the differences.

[0035] The feedback providing unit can analyze failure cases and suggest specific improvement measures. For example, the feedback providing unit builds a system in which the generation AI analyzes past failure cases and suggests specific improvement measures. For example, it suggests how to improve answers based on past failure cases. The feedback providing unit also analyzes past failure cases and the generation AI suggests areas for improvement. For example, it identifies the cause of failure and suggests specific measures to avoid it. The feedback providing unit also develops a system in which the generation AI analyzes past failure cases and suggests specific improvement measures. For example, it suggests how to correct answers based on failure cases. In this way, by analyzing past failure cases and suggesting specific improvement measures, it is possible to promote the improvement of the AI ​​model.

[0036] The feedback providing unit can perform an evaluation that reflects the user's opinion in conjunction with the user's feedback. The feedback providing unit, for example, builds a system that provides the basis for the evaluation based on the user's feedback. For example, it performs an evaluation that reflects the user's opinion and suggests areas for improvement. The feedback providing unit also analyzes the user's feedback and provides the basis for the evaluation based on the results. For example, it determines which answer is most appropriate based on the user's evaluation. The feedback providing unit also develops a system that performs an evaluation that reflects the user's opinion. For example, it provides the basis for the evaluation and suggests areas for improvement based on the user's feedback. In this way, user satisfaction can be improved by performing an evaluation that reflects the user's opinion.

[0037] The feedback providing unit can compare with best practices from different industries and suggest industry-specific improvements. For example, the feedback providing unit builds a system that provides evaluation grounds based on best practices from different industries. For example, healthcare-related answers are evaluated based on best practices from the healthcare industry. The feedback providing unit also provides evaluation grounds by referring to industry-specific best practices. For example, finance-related answers are evaluated based on best practices from the finance industry. The feedback providing unit also develops a system that compares best practices from different industries and provides evaluation grounds. For example, education-related answers are evaluated based on best practices from the education industry. This makes it possible to suggest industry-specific improvements by comparing with best practices from different industries.

[0038] The feedback providing unit can perform simulations to predict the effects of proposals. For example, the feedback providing unit constructs a system in which a generation AI performs simulations to predict the effects of proposed improvements. For example, the simulation confirms how effective the proposed improvements are. The feedback providing unit also uses simulations to predict the effects of proposed improvements. For example, the simulation evaluates what results the proposed improvements will actually bring. The feedback providing unit also develops a system in which a generation AI performs simulations to predict the effects of proposals. For example, the simulation verifies how effective the proposed improvements are. In this way, the simulation can predict the effects of the proposals.

[0039] The third-party AI model usage unit can statistically analyze the answers of other company's AI models and select the most reliable answer. The third-party AI model usage unit, for example, statistically analyzes the answers of other company's AI models and builds a system that selects the most reliable answer. For example, it compares the answers of multiple AI models and selects the most reliable answer. The third-party AI model usage unit also uses statistical methods to evaluate the reliability of the answers of other company's AI models. For example, it determines reliability based on the degree of agreement of the answers and the past accuracy rate. The third-party AI model usage unit also develops an algorithm that statistically analyzes the answers of other company's AI models and selects the most reliable answer. For example, it calculates a reliability score for the answer and selects the answer with the highest score. In this way, the most reliable answer can be selected by statistically analyzing the answers of other company's AI models.

[0040] The third-party AI model usage unit can compare answers from other companies' AI models in real time and perform instant evaluation. The third-party AI model usage unit, for example, builds a system that compares answers from other companies' AI models in real time and performs instant evaluation. For example, it obtains answers from multiple AI models simultaneously and performs instant evaluation. The third-party AI model usage unit also allows the generation AI to compare answers from other companies' AI models in real time and perform evaluation. For example, it evaluates the accuracy and consistency of answers in real time. The third-party AI model usage unit also develops an algorithm that compares answers from other companies' AI models in real time and performs instant evaluation. For example, it evaluates the degree of agreement and reliability of answers in real time. This allows answers from other companies' AI models to be compared in real time and perform instant evaluation.

[0041] The third-party AI model usage unit can compare the answers of the third-party AI model with past data to evaluate historical accuracy. The third-party AI model usage unit, for example, builds a system that compares the answers of the third-party AI model with past data to evaluate historical accuracy. For example, it evaluates the accuracy of the answers by comparing them with past correct answer data. The third-party AI model usage unit also has a generation AI that compares the answers of the third-party AI model with past data to evaluate historical accuracy. For example, it determines accuracy by comparing it with past answer history. The third-party AI model usage unit also develops an algorithm that compares the answers of the third-party AI model with past data to evaluate historical accuracy. For example, it evaluates the accuracy of the answers by comparing them with a past database. This makes it possible to evaluate historical accuracy by comparing them with past data.

[0042] The third-party AI model usage unit can reevaluate the answers of the third-party AI model with different datasets to ensure dataset diversity. The third-party AI model usage unit, for example, builds a system that reevaluates the answers of the third-party AI model with different datasets to ensure dataset diversity. For example, it evaluates answers using datasets from different fields. The third-party AI model usage unit also reevaluates the answers of the third-party AI model using different datasets. For example, it evaluates the accuracy of the answers based on datasets from different industries or fields. The third-party AI model usage unit also develops an algorithm that reevaluates the answers of the third-party AI model with different datasets to ensure dataset diversity. For example, it evaluates the reliability of the answers using multiple datasets. In this way, dataset diversity can be ensured by reevaluating with different datasets.

[0043] The third-party AI model using unit can reevaluate the answers of the third-party AI model using different algorithms to ensure algorithm diversity. The third-party AI model using unit, for example, builds a system that reevaluates the answers of the third-party AI model using different algorithms to ensure algorithm diversity. For example, it evaluates answers using different machine learning algorithms. The third-party AI model using unit also reevaluates the answers of the third-party AI model using different algorithms. For example, it evaluates the accuracy of the answers based on different algorithms such as deep learning and decision trees. The third-party AI model using unit also develops an algorithm that reevaluates the answers of the third-party AI model using different algorithms to ensure algorithm diversity. For example, it evaluates the reliability of the answers using multiple algorithms. In this way, algorithm diversity can be ensured by reevaluating using different algorithms.

[0044] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0045] The AI ​​model evaluation system can further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit analyzes, for example, what questions the user has asked in the past and what actions the user took in response to the answers. This allows the system to understand the user's behavioral patterns and provide more appropriate feedback. For example, if a user frequently asks the same question in response to a specific answer, the answer may be insufficient, and the system can suggest areas for improvement. The behavior analysis unit can also analyze what answers the user is satisfied with and adjust the evaluation criteria based on that information. This allows the system to provide more accurate evaluations and feedback based on the user's behavioral history.

[0046] The AI ​​model evaluation system may further include a feedback collection unit that collects user feedback and adjusts evaluation criteria based on the feedback. The feedback collection unit, for example, collects feedback provided by users and analyzes the content of the feedback. This makes it possible to set evaluation criteria that reflect the user's opinions. For example, if a user expresses dissatisfaction with a particular answer, the evaluation criteria for that answer may be revised. The feedback collection unit may also dynamically adjust the evaluation criteria based on the user's feedback. This makes it possible to set evaluation criteria that reflect the user's opinions and provide more appropriate evaluations and feedback.

[0047] The AI ​​model evaluation system can further include a learning history analysis unit that analyzes the user's learning history and performs evaluation based on that history. The learning history analysis unit, for example, analyzes what kind of learning the user has done in the past and what kind of results they have achieved. This allows the system to understand the user's learning situation and perform more appropriate evaluation. For example, if the user has achieved high results in a particular field, it can give high evaluations to questions related to that field. The learning history analysis unit can also adjust the evaluation criteria based on the user's learning history. This allows the system to provide more accurate evaluations based on the user's learning history.

[0048] The AI ​​model evaluation system may further include a behavior pattern analysis unit that analyzes the user's behavior patterns and performs evaluation based on those patterns. The behavior pattern analysis unit, for example, analyzes the user's past behavior and understands those behavior patterns. This allows evaluation to be performed based on the user's behavior patterns. For example, if the user frequently asks questions about a particular answer, the answer may be insufficient, so the evaluation may be revised. The behavior pattern analysis unit may also adjust the evaluation criteria based on the user's behavior patterns. This allows for a more appropriate evaluation to be provided based on the user's behavior patterns.

[0049] The AI ​​model evaluation system may further include a feedback collection unit that collects user feedback and adjusts evaluation criteria based on the feedback. The feedback collection unit, for example, collects feedback provided by users and analyzes the content of the feedback. This makes it possible to set evaluation criteria that reflect the user's opinions. For example, if a user expresses dissatisfaction with a particular answer, the evaluation criteria for that answer may be revised. The feedback collection unit may also dynamically adjust the evaluation criteria based on the user's feedback. This makes it possible to set evaluation criteria that reflect the user's opinions and provide more appropriate evaluations and feedback.

[0050] The AI ​​model evaluation system can further include a learning history analysis unit that analyzes the user's learning history and performs evaluation based on that history. The learning history analysis unit, for example, analyzes what kind of learning the user has done in the past and what kind of results they have achieved. This allows the system to understand the user's learning situation and perform more appropriate evaluation. For example, if the user has achieved high results in a particular field, it can give high evaluations to questions related to that field. The learning history analysis unit can also adjust the evaluation criteria based on the user's learning history. This allows the system to provide more accurate evaluations based on the user's learning history.

[0051] The processing flow of the first embodiment will be briefly explained below.

[0052] Step 1: The answer review unit reviews the answer of the AI ​​model. For example, the answer review unit uses the generation AI to generate an answer to a question from a user and compares the answer with other AI models. The answer review unit can also refer to the answers of other AI models to evaluate the accuracy of the answer provided by the generation AI. Step 2: The evaluation unit evaluates the accuracy of the answers reviewed by the answer review unit. For example, the evaluation unit evaluates the answers provided by the generation AI by comparing them with expert opinions and academic papers. The evaluation unit can also compare the answers provided by the generation AI with the user's past question history to evaluate the consistency of the answers. Step 3: The feedback providing unit provides the basis for the evaluation and points for improvement based on the results evaluated by the evaluation unit. For example, the feedback providing unit provides detailed feedback on the answer provided by the generation AI, explaining how it compares with the answers of other AI models. The feedback providing unit can also suggest points for improving the answer provided by the generation AI. Step 4: The third-party AI model usage unit performs an evaluation using multiple third-party AI models. For example, the third-party AI model usage unit compares the answers provided by the generation AI with other AI models and evaluates the accuracy of each answer. The third-party AI model usage unit can also integrate answers provided by multiple AI models and select the most accurate answer.

[0053] (Example 2) The AI ​​model evaluation system according to an embodiment of the present invention is a system that reviews answers provided by AI models, evaluates their accuracy, and provides feedback, thereby ensuring the quality of answers provided by AI models and enabling users to trust the information obtained from AI.

[0054] An AI model evaluation system according to an embodiment includes an answer review unit, an evaluation unit, a feedback providing unit, and a third-party AI model using unit. The answer review unit reviews answers from AI models. For example, the answer review unit generates answers to user questions using a generation AI and compares the answers with other AI models. The answer review unit can also refer to answers from other AI models to evaluate the accuracy of the answers provided by the generation AI. The evaluation unit evaluates the accuracy of the answers reviewed by the answer review unit. For example, the evaluation unit evaluates the answers provided by the generation AI by comparing them with expert opinions and academic papers. The evaluation unit can also compare the answers provided by the generation AI with the user's past question history to evaluate consistency. The feedback providing unit provides the basis for the evaluation and points for improvement based on the results of the evaluation by the evaluation unit. For example, the feedback providing unit provides detailed feedback on the answers provided by the generation AI, explaining how they are superior to answers from other AI models. The feedback providing unit can also suggest points for improvement to the answers provided by the generation AI. The third-party AI model using unit performs evaluation using multiple third-party AI models. For example, the third-party AI model usage unit compares the answer provided by the generation AI with other AI models and evaluates the accuracy of each answer. The third-party AI model usage unit can also integrate answers provided by multiple AI models and select the most accurate answer. This allows the AI ​​model evaluation system according to the embodiment to improve the accuracy and reliability of the answers of the AI ​​models. For example, in the field of education, the system can provide accurate information when students use AI to study. Furthermore, in the field of business, the system can provide reliable information when companies use AI to make decisions.

[0055] The answer review unit can perform sentiment analysis on the answers of each AI model and prioritize emotionally positive answers. The answer review unit, for example, performs sentiment analysis on the answers of each AI model and prioritizes answers with positive sentiment. For example, the evaluation criteria are whether the answer gives the user a sense of security and trust. The answer review unit also uses sentiment analysis to evaluate the emotional impact the answer has on the user and highly evaluates answers that elicit positive sentiment. For example, it evaluates whether the answer resolves the user's questions and gives the user a sense of satisfaction. The answer review unit also builds a system that prioritizes answers with positive sentiment based on the results of the sentiment analysis. For example, it evaluates whether the answer evokes positive sentiment in the user. This allows for the prioritized evaluation of emotionally positive answers to improve user satisfaction.

[0056] The evaluation department can increase reliability by comparing the AI ​​model's answers with expert opinions and academic papers. For example, the evaluation department will build a system to evaluate the AI ​​model's answers by comparing them with expert opinions. For example, answers in the medical field will be evaluated by comparing them with the opinions of doctors. The evaluation department will also refer to academic papers to evaluate the accuracy of the AI ​​model's answers. For example, answers to scientific questions will be evaluated by comparing them with the latest research results. The evaluation department will also develop a system to evaluate the reliability of the AI ​​model's answers based on expert opinions and academic papers. For example, answers in the legal field will be evaluated by comparing them with the opinions of lawyers. This will increase the reliability of the answers by comparing them with expert opinions and academic papers.

[0057] The evaluation unit can compare the AI ​​model's answers with the user's past question history and evaluate the consistency of the answers. The evaluation unit, for example, builds a system to evaluate the consistency of the AI ​​model's answers based on the user's past question history. For example, it compares and evaluates the current answer with questions previously asked by the same user. The evaluation unit also analyzes the past question history and evaluates whether the AI ​​model's answers are consistent. For example, it checks whether the same answer is provided for questions asked repeatedly by the user. The evaluation unit also develops an algorithm to evaluate the consistency of the AI ​​model's answers based on the user's question history. For example, it evaluates whether the past answer and the current answer are consistent. This makes it possible to evaluate the consistency of the answers by comparing them with the user's past question history.

[0058] The evaluation unit can translate the AI ​​model's answers into different languages ​​and evaluate them from an international perspective. For example, the evaluation unit builds a system that translates the AI ​​model's answers into different languages ​​and evaluates them from an international perspective. For example, the answers are evaluated in multiple languages, such as English, Japanese, and French. The evaluation unit also collects and evaluates feedback from users with different cultures and backgrounds based on the translated answers. For example, it determines the accuracy of the answers based on the evaluations from users in different language-speaking regions. In addition, to evaluate from an international perspective, the evaluation unit inputs the translated answers into a multilingual evaluation system and integrates the evaluation results in each language. For example, the evaluation scores in each language are averaged to form a final evaluation. In this way, translating into different languages ​​allows evaluation from an international perspective.

[0059] The evaluation unit can evaluate the AI ​​model's answer in combination with visual data to promote visual understanding. The evaluation unit, for example, builds a system that evaluates the AI ​​model's answer in combination with visual data. For example, it displays figures and graphs related to the answer to make it easier to understand visually. The evaluation unit also uses the visual data to evaluate the accuracy of the AI ​​model's answer. For example, it determines the reliability of the answer based on statistical data and graphs. The evaluation unit also develops a system that visually evaluates the AI ​​model's answer using figures and graphs. For example, it automatically generates visual data related to the answer and uses it for evaluation. This makes it possible to promote visual understanding by combining it with visual data.

[0060] The evaluation unit can use the emotion estimation function to estimate the emotion a user is feeling when inputting a question in real time and generate an answer based on that emotion. The evaluation unit, for example, builds a system that estimates the emotion a user is feeling when inputting a question in real time and generates an answer based on that emotion. For example, if the user is feeling anxious, it provides an answer that gives a sense of security. The evaluation unit also uses the emotion estimation function to generate an answer based on the user's emotion. For example, if the user is excited, it provides a calm answer. The evaluation unit also develops a system that analyzes the user's emotion in real time and generates an answer based on the emotion based on the results. For example, if the user is sad, it provides an answer that includes words of encouragement. In this way, by generating an answer based on the user's emotion, it is possible to improve user satisfaction.

[0061] The feedback providing unit can refer to the answers of other AI models and clarify the differences. For example, the feedback providing unit builds a system in which the generation AI refers to the answers of other AI models and clarifies the differences as the basis for evaluation. For example, the answers of multiple AI models are compared and the differences are highlighted. The feedback providing unit also provides the basis for evaluation based on the answers of other AI models. For example, the answers of different AI models are compared and which answer is most accurate. The feedback providing unit also develops a system in which the generation AI refers to the answers of other AI models and clarifies the differences to provide the basis for evaluation. For example, the reliability of different answers is compared and reflected in the evaluation. In this way, the basis for evaluation can be provided by referring to the answers of other AI models and clarifying the differences.

[0062] The feedback providing unit can analyze failure cases and suggest specific improvement measures. For example, the feedback providing unit builds a system in which the generation AI analyzes past failure cases and suggests specific improvement measures. For example, it suggests how to improve answers based on past failure cases. The feedback providing unit also analyzes past failure cases and the generation AI suggests areas for improvement. For example, it identifies the cause of failure and suggests specific measures to avoid it. The feedback providing unit also develops a system in which the generation AI analyzes past failure cases and suggests specific improvement measures. For example, it suggests how to correct answers based on failure cases. In this way, by analyzing past failure cases and suggesting specific improvement measures, it is possible to promote the improvement of the AI ​​model.

[0063] The feedback providing unit can perform an evaluation that reflects the user's opinion in conjunction with the user's feedback. The feedback providing unit, for example, builds a system that provides the basis for the evaluation based on the user's feedback. For example, it performs an evaluation that reflects the user's opinion and suggests areas for improvement. The feedback providing unit also analyzes the user's feedback and provides the basis for the evaluation based on the results. For example, it determines which answer is most appropriate based on the user's evaluation. The feedback providing unit also develops a system that performs an evaluation that reflects the user's opinion. For example, it provides the basis for the evaluation and suggests areas for improvement based on the user's feedback. In this way, user satisfaction can be improved by performing an evaluation that reflects the user's opinion.

[0064] The feedback providing unit can compare with best practices from different industries and suggest industry-specific improvements. For example, the feedback providing unit builds a system that provides evaluation grounds based on best practices from different industries. For example, healthcare-related answers are evaluated based on best practices from the healthcare industry. The feedback providing unit also provides evaluation grounds by referring to industry-specific best practices. For example, finance-related answers are evaluated based on best practices from the finance industry. The feedback providing unit also develops a system that compares best practices from different industries and provides evaluation grounds. For example, education-related answers are evaluated based on best practices from the education industry. This makes it possible to suggest industry-specific improvements by comparing with best practices from different industries.

[0065] The feedback providing unit can perform simulations to predict the effects of proposals. For example, the feedback providing unit constructs a system in which a generation AI performs simulations to predict the effects of proposed improvements. For example, the simulation confirms how effective the proposed improvements are. The feedback providing unit also uses simulations to predict the effects of proposed improvements. For example, the simulation evaluates what results the proposed improvements will actually bring. The feedback providing unit also develops a system in which a generation AI performs simulations to predict the effects of proposals. For example, the simulation verifies how effective the proposed improvements are. In this way, the simulation can predict the effects of the proposals.

[0066] The feedback providing unit can use the emotion estimation function to suggest improvements based on the user's emotions. The feedback providing unit, for example, uses the emotion estimation function to build a system that suggests improvements based on the user's emotions. For example, if the user is dissatisfied, the feedback providing unit suggests improvements to resolve the dissatisfaction. The feedback providing unit also analyzes the user's emotions and suggests improvements based on the results. For example, it identifies areas where the user is dissatisfied and makes specific suggestions to improve those areas. The feedback providing unit also uses the emotion estimation function to develop a system that suggests improvements based on the user's emotions. For example, it suggests improvements that will make the user feel positive emotions. In this way, by suggesting improvements based on the user's emotions, user satisfaction can be improved.

[0067] The third-party AI model usage unit can statistically analyze the answers of other company's AI models and select the most reliable answer. The third-party AI model usage unit, for example, statistically analyzes the answers of other company's AI models and builds a system that selects the most reliable answer. For example, it compares the answers of multiple AI models and selects the most reliable answer. The third-party AI model usage unit also uses statistical methods to evaluate the reliability of the answers of other company's AI models. For example, it determines reliability based on the degree of agreement of the answers and the past accuracy rate. The third-party AI model usage unit also develops an algorithm that statistically analyzes the answers of other company's AI models and selects the most reliable answer. For example, it calculates a reliability score for the answer and selects the answer with the highest score. In this way, the most reliable answer can be selected by statistically analyzing the answers of other company's AI models.

[0068] The third-party AI model usage unit can compare answers from other companies' AI models in real time and perform instant evaluation. The third-party AI model usage unit, for example, builds a system that compares answers from other companies' AI models in real time and performs instant evaluation. For example, it obtains answers from multiple AI models simultaneously and performs instant evaluation. The third-party AI model usage unit also allows the generation AI to compare answers from other companies' AI models in real time and perform evaluation. For example, it evaluates the accuracy and consistency of answers in real time. The third-party AI model usage unit also develops an algorithm that compares answers from other companies' AI models in real time and performs instant evaluation. For example, it evaluates the degree of agreement and reliability of answers in real time. This allows answers from other companies' AI models to be compared in real time and perform instant evaluation.

[0069] The third-party AI model usage unit can compare the answers of the third-party AI model with past data to evaluate historical accuracy. The third-party AI model usage unit, for example, builds a system that compares the answers of the third-party AI model with past data to evaluate historical accuracy. For example, it evaluates the accuracy of the answers by comparing them with past correct answer data. The third-party AI model usage unit also has a generation AI that compares the answers of the third-party AI model with past data to evaluate historical accuracy. For example, it determines accuracy by comparing it with past answer history. The third-party AI model usage unit also develops an algorithm that compares the answers of the third-party AI model with past data to evaluate historical accuracy. For example, it evaluates the accuracy of the answers by comparing them with a past database. This makes it possible to evaluate historical accuracy by comparing them with past data.

[0070] The third-party AI model usage unit can reevaluate the answers of the third-party AI model with different datasets to ensure dataset diversity. The third-party AI model usage unit, for example, builds a system that reevaluates the answers of the third-party AI model with different datasets to ensure dataset diversity. For example, it evaluates answers using datasets from different fields. The third-party AI model usage unit also reevaluates the answers of the third-party AI model using different datasets. For example, it evaluates the accuracy of the answers based on datasets from different industries or fields. The third-party AI model usage unit also develops an algorithm that reevaluates the answers of the third-party AI model with different datasets to ensure dataset diversity. For example, it evaluates the reliability of the answers using multiple datasets. In this way, dataset diversity can be ensured by reevaluating with different datasets.

[0071] The third-party AI model using unit can reevaluate the answers of the third-party AI model using different algorithms to ensure algorithm diversity. The third-party AI model using unit, for example, builds a system that reevaluates the answers of the third-party AI model using different algorithms to ensure algorithm diversity. For example, it evaluates answers using different machine learning algorithms. The third-party AI model using unit also reevaluates the answers of the third-party AI model using different algorithms. For example, it evaluates the accuracy of the answers based on different algorithms such as deep learning and decision trees. The third-party AI model using unit also develops an algorithm that reevaluates the answers of the third-party AI model using different algorithms to ensure algorithm diversity. For example, it evaluates the reliability of the answers using multiple algorithms. In this way, algorithm diversity can be ensured by reevaluating using different algorithms.

[0072] The third-party AI model usage unit can use the emotion estimation function to analyze the user's emotional response to the answers of the third-party AI model and select the answer that is most relatable. For example, the third-party AI model usage unit uses the emotion estimation function to analyze the user's emotional response to the answers of the third-party AI model and build a system that selects the answer that is most relatable. For example, it selects an answer based on the user's emotion score. The third-party AI model usage unit also analyzes the user's emotional response and evaluates the degree of relatability of the answers of the third-party AI model. For example, it preferentially selects answers with a high number of positive emotional responses. The third-party AI model usage unit also uses the emotion estimation function to analyze the user's emotional response to the answers of the third-party AI model and develops an algorithm that selects the answer that is most relatable. For example, it evaluates the degree of relatability of the answer based on the emotion score. In this way, it is possible to select the answer that is most relatable by analyzing the user's emotional response.

[0073] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0074] The AI ​​model evaluation system can further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit analyzes, for example, what questions the user has asked in the past and what actions the user took in response to the answers. This allows the system to understand the user's behavioral patterns and provide more appropriate feedback. For example, if a user frequently asks the same question in response to a specific answer, the answer may be insufficient, and the system can suggest areas for improvement. The behavior analysis unit can also analyze what answers the user is satisfied with and adjust the evaluation criteria based on that information. This allows the system to provide more accurate evaluations and feedback based on the user's behavioral history.

[0075] The AI ​​model evaluation system may further include an emotion feedback unit that estimates the user's emotions and provides feedback based on those emotions. The emotion feedback unit, for example, estimates the user's emotions in real time when inputting a question and provides feedback based on those emotions. For example, if the user is feeling anxious, it provides feedback that gives a sense of security. The emotion feedback unit also analyzes the user's emotions and adjusts the content of the feedback based on the results. For example, if the user is dissatisfied, it suggests specific improvements. In this way, by providing feedback based on the user's emotions, it is possible to improve user satisfaction.

[0076] The AI ​​model evaluation system may further include a feedback collection unit that collects user feedback and adjusts evaluation criteria based on the feedback. The feedback collection unit, for example, collects feedback provided by users and analyzes the content of the feedback. This makes it possible to set evaluation criteria that reflect the user's opinions. For example, if a user expresses dissatisfaction with a particular answer, the evaluation criteria for that answer may be revised. The feedback collection unit may also dynamically adjust the evaluation criteria based on the user's feedback. This makes it possible to set evaluation criteria that reflect the user's opinions and provide more appropriate evaluations and feedback.

[0077] The AI ​​model evaluation system can further include a learning history analysis unit that analyzes the user's learning history and performs evaluation based on that history. The learning history analysis unit, for example, analyzes what kind of learning the user has done in the past and what kind of results they have achieved. This allows the system to understand the user's learning situation and perform more appropriate evaluation. For example, if the user has achieved high results in a particular field, it can give high evaluations to questions related to that field. The learning history analysis unit can also adjust the evaluation criteria based on the user's learning history. This allows the system to provide more accurate evaluations based on the user's learning history.

[0078] The AI ​​model evaluation system can further include an emotion evaluation unit that estimates the user's emotions and performs evaluation based on those emotions. The emotion evaluation unit, for example, estimates the user's emotions in real time when inputting a question and performs evaluation based on those emotions. For example, if the user is feeling anxious, it will highly evaluate answers that alleviate that anxiety. The emotion evaluation unit also analyzes the user's emotions and adjusts the evaluation criteria based on the results. For example, if the user is not satisfied, it will review the evaluation of the answer. In this way, user satisfaction can be improved by performing evaluation based on the user's emotions.

[0079] The AI ​​model evaluation system may further include a behavior pattern analysis unit that analyzes the user's behavior patterns and performs evaluation based on those patterns. The behavior pattern analysis unit, for example, analyzes the user's past behavior and understands those behavior patterns. This allows evaluation to be performed based on the user's behavior patterns. For example, if the user frequently asks questions about a particular answer, the answer may be insufficient, so the evaluation may be revised. The behavior pattern analysis unit may also adjust the evaluation criteria based on the user's behavior patterns. This allows for a more appropriate evaluation to be provided based on the user's behavior patterns.

[0080] The AI ​​model evaluation system can further include an emotion evaluation unit that estimates the user's emotions and performs evaluation based on those emotions. The emotion evaluation unit, for example, estimates the user's emotions in real time when inputting a question and performs evaluation based on those emotions. For example, if the user is feeling anxious, it will highly evaluate answers that alleviate that anxiety. The emotion evaluation unit also analyzes the user's emotions and adjusts the evaluation criteria based on the results. For example, if the user is not satisfied, it will review the evaluation of the answer. In this way, user satisfaction can be improved by performing evaluation based on the user's emotions.

[0081] The AI ​​model evaluation system may further include a feedback collection unit that collects user feedback and adjusts evaluation criteria based on the feedback. The feedback collection unit, for example, collects feedback provided by users and analyzes the content of the feedback. This makes it possible to set evaluation criteria that reflect the user's opinions. For example, if a user expresses dissatisfaction with a particular answer, the evaluation criteria for that answer may be revised. The feedback collection unit may also dynamically adjust the evaluation criteria based on the user's feedback. This makes it possible to set evaluation criteria that reflect the user's opinions and provide more appropriate evaluations and feedback.

[0082] The AI ​​model evaluation system can further include a learning history analysis unit that analyzes the user's learning history and performs evaluation based on that history. The learning history analysis unit, for example, analyzes what kind of learning the user has done in the past and what kind of results they have achieved. This allows the system to understand the user's learning situation and perform more appropriate evaluation. For example, if the user has achieved high results in a particular field, it can give high evaluations to questions related to that field. The learning history analysis unit can also adjust the evaluation criteria based on the user's learning history. This allows the system to provide more accurate evaluations based on the user's learning history.

[0083] The AI ​​model evaluation system can further include an emotion evaluation unit that estimates the user's emotions and performs evaluation based on those emotions. The emotion evaluation unit, for example, estimates the user's emotions in real time when inputting a question and performs evaluation based on those emotions. For example, if the user is feeling anxious, it will highly evaluate answers that alleviate that anxiety. The emotion evaluation unit also analyzes the user's emotions and adjusts the evaluation criteria based on the results. For example, if the user is not satisfied, it will review the evaluation of the answer. In this way, user satisfaction can be improved by performing evaluation based on the user's emotions.

[0084] The processing flow of the second embodiment will be briefly explained below.

[0085] Step 1: The answer review unit reviews the answer of the AI ​​model. For example, the answer review unit uses the generation AI to generate an answer to a question from a user and compares the answer with other AI models. The answer review unit can also refer to the answers of other AI models to evaluate the accuracy of the answer provided by the generation AI. Step 2: The evaluation unit evaluates the accuracy of the answers reviewed by the answer review unit. For example, the evaluation unit evaluates the answers provided by the generation AI by comparing them with expert opinions and academic papers. The evaluation unit can also compare the answers provided by the generation AI with the user's past question history to evaluate the consistency of the answers. Step 3: The feedback providing unit provides the basis for the evaluation and points for improvement based on the results evaluated by the evaluation unit. For example, the feedback providing unit provides detailed feedback on the answer provided by the generation AI, explaining how it compares with the answers of other AI models. The feedback providing unit can also suggest points for improving the answer provided by the generation AI. Step 4: The third-party AI model usage unit performs an evaluation using multiple third-party AI models. For example, the third-party AI model usage unit compares the answers provided by the generation AI with other AI models and evaluates the accuracy of each answer. The third-party AI model usage unit can also integrate answers provided by multiple AI models and select the most accurate answer.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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).

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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).

[0110] 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.

[0111] 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.

[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 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.

[0114] 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.

[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 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.

[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 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.

[0119] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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."

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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]

[0153] 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 answer review department that reviews the answers of the AI ​​model; an evaluation unit that evaluates the accuracy of the answers reviewed by the answer review unit; a feedback providing unit that provides the basis of evaluation and points for improvement based on the evaluation result by the evaluation unit; and a third-party AI model usage unit that performs screening using multiple third-party AI models. A system characterized by:

2. The Response Review Department shall: Sentiment analysis is performed on each AI model's response, and emotionally positive responses are prioritized.

2. The system of claim 1.

3. The evaluation unit The AI ​​model's answers will be evaluated against expert opinions and academic papers to increase reliability.

2. The system of claim 1.

4. The evaluation unit The AI ​​model's answers are compared with the user's past question history to assess consistency of answers.

2. The system of claim 1.

5. The evaluation unit Translate the AI ​​model's answers into different languages ​​and evaluate them from an international perspective 2. The system of claim 1.

6. The evaluation unit The AI ​​model's answers are combined with visual data to evaluate and facilitate visual understanding.

2. The system of claim 1.

7. The evaluation unit Estimates the user's emotions in real time when they enter a question and generates an answer based on those emotions.

2. The system of claim 1.

8. The feedback providing unit: See the answers of other AI models and clarify the differences 2. The system of claim 1.

Images