System

Abstract

An object of a system according to an embodiment is to facilitate early detection of mental illness and allow a patient to easily receive a diagnosis.SOLUTION: A system according to an embodiment includes a question generation unit, an answer reception unit, an image generation unit, and a hearing unit. The question generation unit generates a question. The answer receiving unit receives an answer based on the question generated by the question generating unit. The image generation unit generates an image based on the answer received by the answer reception unit. The hearing unit collects a user's impression of the image generated by the image generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem that it is difficult to detect mental disorders early, and patients may feel reluctant to go to the hospital.

[0005] The system according to the embodiment aims to facilitate early detection of mental disorders and to allow patients to receive diagnosis easily. [Means for solving the problem]

[0006] The system according to the embodiment includes a question generation unit, an answer acceptance unit, an image generation unit, and a hearing unit. The question generation unit generates a question. The answer acceptance unit accepts an answer based on the question generated by the question generation unit. The image generation unit generates an image based on the answer accepted by the answer acceptance unit. The hearing unit collects impressions of users who have viewed the image generated by the image generation unit. [Effects of the Invention]

[0007] Systems according to embodiments can facilitate early detection of mental disorders and make it easier for patients to receive a diagnosis. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A diagnostic system according to an embodiment of the present invention is a system for the early detection of mental disorders such as depression. This diagnostic system accumulates data on questions and answers asked by psychological counselors in conversations with patients with mental disorders. A generation AI generates appropriate questions based on the accumulated data and presents them to the user. The user answers the questions, and the generation AI creates appropriate images or drawings based on the answers. The user is then asked how they feel when viewing the generated images or drawings. This allows for the identification of mental disorders that are difficult to distinguish between normal and abnormal. For example, the diagnostic system is easy to use because users can receive a diagnosis using their smartphones. Furthermore, the generation AI generates appropriate questions and images, improving the accuracy of the diagnosis. This allows people who do not believe their illness is serious enough to warrant a hospital visit to receive a diagnosis to receive a diagnosis in a casual, game-like manner. For example, the system is easy to use because users can receive a diagnosis using their smartphones. Furthermore, the generation AI generates appropriate questions and images, improving the accuracy of the diagnosis.

[0029] A diagnostic system according to an embodiment includes a question generation unit, an answer reception unit, an image generation unit, and a hearing unit. The question generation unit generates questions using a generation AI. For example, the question generation unit generates appropriate questions based on questions and answers heard by a psychological counselor in past conversations with patients with mental disorder symptoms. The generation AI can generate questions using a text generation AI (e.g., LLM). The question generation unit can also use the generation AI to generate questions based on a user's emotions and psychological state. The answer reception unit receives a user's answer based on the question generated by the generation AI. For example, the answer reception unit can receive answers in text format or audio format. The answer reception unit can also analyze the user's answer in real time and provide appropriate feedback. The image generation unit generates an image based on the user's answer using the generation AI. For example, if the user answers "I can't sleep," the image generation unit generates an image symbolizing insomnia. The generation AI can generate an image from text data using a multimodal generation AI. The hearing unit collects user feedback after viewing the image generated by the generation AI. For example, the hearing unit presents a question such as, "How do you feel when you see this image?" and collects user feedback. This enables the diagnostic system according to the embodiment to detect mental disorders early through question generation, answer reception, image generation, and hearing. For example, the diagnostic system is easy to use because users can receive a diagnosis using their smartphone. Furthermore, the accuracy of the diagnosis is improved because the generation AI generates appropriate questions and images.

[0030] The diagnostic system includes a data storage unit that stores data. The data storage unit stores questions and answers asked by past psychological counselors through conversations with patients with symptoms of mental disorders. For example, the data storage unit can store text data, numerical data, image data, etc. The data storage unit can also use AI to store data. For example, the data storage unit stores the content of conversations as text data, and the AI ​​analyzes the data to use it as basic data for generating appropriate questions. This enables the data storage unit to generate questions based on past data. For example, the data storage unit can generate appropriate questions for the user based on past data.

[0031] The diagnostic system includes a diagnostic result providing unit that provides diagnostic results. The diagnostic result providing unit uses AI to provide the diagnostic results to the user. For example, the diagnostic result providing unit can provide the diagnostic results in the form of a numerical evaluation or a text report. The diagnostic result providing unit uses AI to analyze the diagnostic results based on the user's answers and the images generated by the image generating unit, and provides appropriate feedback. For example, if a user answers "I can't sleep" and an image symbolizing insomnia is generated, the diagnostic result providing unit provides a diagnostic result indicating the possibility of insomnia based on the results. This allows the diagnostic result providing unit to provide the diagnostic result to the user. For example, the diagnostic result providing unit can be easily used because the user can receive the diagnostic results using a smartphone. In addition, because AI analyzes the diagnostic results, the accuracy of the diagnosis is improved.

[0032] When generating a question, the question generation unit can adjust the difficulty of the question by referring to the user's past answer history. The question generation unit uses a generation AI to refer to the user's past answer history. For example, the question generation unit accumulates the past answer history as text data, and the generation AI analyzes the data to adjust the difficulty of the question. For example, if the user has answered easy questions correctly in the past, a question with a slightly higher difficulty level can be generated. Also, if the user has not been able to answer difficult questions in the past, a question with a lower difficulty level can be generated. Furthermore, the user's past answer history can be analyzed to generate questions of an appropriate level of difficulty. This makes it possible to generate questions based on the user's past answer history. For example, the question generation unit can analyze the user's past answer history in real time and generate appropriate questions.

[0033] When generating questions, the question generation unit can customize the content of the questions according to the user's age and gender. The question generation unit uses generation AI to take the user's age and gender into consideration. For example, the question generation unit accumulates the user's age and gender as data, and the generation AI analyzes that data to customize the content of the questions. For example, if the user is young, the question generation unit can generate questions that include topics aimed at young people. On the other hand, if the user is elderly, the question generation unit can generate simple and easy-to-understand questions. Furthermore, questions that include highly relevant topics can be generated according to the user's gender. This makes it possible to generate questions according to the user's age and gender. For example, the question generation unit can analyze the user's age and gender in real time and generate appropriate questions.

[0034] The question generation unit can analyze the user's current psychological state in real time when generating a question and generate an appropriate question. The question generation unit analyzes the user's current psychological state in real time using a generation AI. For example, the question generation unit can analyze the user's psychological state in real time using facial expression analysis or voice analysis. The generation AI can generate questions according to the user's psychological state using a text generation AI (e.g., LLM). For example, if the user is feeling stressed, a question related to stress reduction can be generated. Also, if the user is relaxed, a more in-depth question can be generated. Furthermore, the user's psychological state can be analyzed in real time and appropriate questions can be generated. This makes it possible to generate questions according to the user's psychological state. For example, the question generation unit can analyze the user's psychological state in real time and generate appropriate questions.

[0035] The question generation unit can generate questions based on the user's geographical and cultural background when generating questions. The question generation unit uses a generation AI to take the user's geographical and cultural background into consideration. For example, the question generation unit accumulates the user's geographical and cultural background as data, and the generation AI analyzes the data to generate questions. For example, if the user lives in a specific area, the question generation unit can generate questions related to that area. The question generation unit can also generate appropriate questions by taking the user's cultural background into consideration. Furthermore, the question generation unit can analyze the user's geographical and cultural background and generate highly relevant questions. This makes it possible to generate questions that are appropriate to the user's geographical and cultural background. For example, the question generation unit can analyze the user's geographical and cultural background in real time and generate appropriate questions.

[0036] The question generation unit can analyze the user's social media activity when generating a question and generate a related question. The question generation unit uses a generation AI to analyze the user's social media activity. For example, the question generation unit accumulates data such as the content of the user's social media posts, the number of likes, and the number of followers, and the generation AI analyzes the data to generate related questions. For example, the question generation unit can generate questions related to topics that the user frequently posts about on social media. The unit can also analyze the user's social media activity and generate questions that are likely to interest the user. Furthermore, the unit can generate related questions by referring to the activity of the user's friends on social media. This makes it possible to generate questions based on the user's social media activity. For example, the question generation unit can analyze the user's social media activity in real time and generate appropriate questions.

[0037] When generating a question, the question generation unit can improve the content of the question by reflecting the user's past feedback. The question generation unit uses a generation AI to refer to the user's past feedback. For example, the question generation unit accumulates feedback provided by the user in the past as text data, and the generation AI analyzes the data to improve the content of the question. For example, the question generation unit can improve the content of the question based on the feedback provided by the user in the past. In addition, the user's feedback can be analyzed to generate an appropriate question. Furthermore, the question content can be optimized by reflecting the user's past feedback. This makes it possible to improve the content of the question based on the user's past feedback. For example, the question generation unit can analyze the user's past feedback in real time and generate an appropriate question.

[0038] When accepting an answer, the answer acceptance unit can improve the accuracy of accepting answers by referring to the user's past answer history. The answer acceptance unit uses AI to refer to the user's past answer history. For example, the answer acceptance unit accumulates the past answer history as text data, and AI analyzes the data to improve the accuracy of accepting answers. For example, the answer acceptance unit can improve the accuracy of answers based on answers provided by the user in the past. In addition, the user's past answer history can be analyzed and appropriate feedback can be provided. Furthermore, the answer acceptance accuracy can be optimized by referring to the user's past answer history. This makes it possible to improve the accuracy of accepting answers based on the user's past answer history. For example, the answer acceptance unit can analyze the user's past answer history in real time and provide an appropriate answer acceptance method.

[0039] The answer accepting unit can analyze the content of the user's answer in real time when accepting the answer and provide appropriate feedback. The answer accepting unit analyzes the content of the user's answer in real time using AI. For example, the answer accepting unit can analyze the content of the user's answer in real time using text analysis and keyword extraction. The AI ​​can provide feedback based on the content of the user's answer using a text generation AI (e.g., LLM). For example, the AI ​​can analyze the content of the user's answer in real time and provide feedback immediately after the user enters the answer. The AI ​​can also analyze the content of the user's answer in real time and provide appropriate advice. Furthermore, the AI ​​can analyze the content of the user's answer in real time and generate the next question. This makes it possible to provide real-time feedback based on the content of the user's answer. For example, the AI ​​can analyze the content of the user's answer in real time and provide appropriate feedback.

[0040] The answer acceptance unit can evaluate the reliability of the user's answer when accepting the answer and filter out low-reliability answers. The answer acceptance unit evaluates the reliability of the user's answer using AI. For example, the answer acceptance unit can evaluate the reliability of the user's answer based on the consistency of the answer, the answer time, etc. The AI ​​can evaluate the reliability of the user's answer and filter out low-reliability answers using text generation AI (e.g., LLM). For example, the content of the user's answer can be analyzed and low-reliability answers can be automatically filtered. In addition, the reliability of the user's answer can be evaluated and high-reliability answers can be preferentially accepted. Furthermore, the reliability of the user's answer can be evaluated in real time and appropriate feedback can be provided. This enables filtering based on the reliability of the user's answer. For example, the answer acceptance unit can analyze the reliability of the user's answer in real time and provide appropriate feedback.

[0041] When accepting an answer, the answer acceptance unit can select an appropriate acceptance method based on the user's device information. The answer acceptance unit uses AI to consider the user's device information. For example, the answer acceptance unit accumulates the user's device information as data, and the AI ​​analyzes the data to select the optimal acceptance method. For example, if the user is using a smartphone, touch input can be prioritized. Also, if the user is using a PC, keyboard input can be prioritized. Furthermore, the user's device information can be analyzed to select the optimal acceptance method. This makes it possible to select the optimal acceptance method based on the user's device information. For example, the answer acceptance unit can analyze the user's device information in real time and provide the appropriate acceptance method.

[0042] The answer acceptance unit can accept answers in multiple languages ​​according to the user's language setting when accepting answers. The answer acceptance unit uses AI to take the user's language setting into consideration. For example, the answer acceptance unit accumulates the language setting of the user's device as data, and the AI ​​analyzes the data to accept answers in multiple languages. For example, the answer acceptance language can be automatically set based on the language setting of the user's device. In addition, if the user uses multiple languages, a language switching function can be provided. Furthermore, if the user selects a specific language, answers can be accepted in that language. This enables multilingual acceptance based on the user's language setting. For example, the answer acceptance unit can analyze the user's language setting in real time and provide acceptance in the appropriate language.

[0043] The answer acceptance unit can improve the acceptance method by reflecting the user's past feedback when accepting an answer. The answer acceptance unit uses AI to refer to the user's past feedback. For example, the answer acceptance unit accumulates feedback provided by the user in the past as text data, and the AI ​​analyzes the data to improve the acceptance method. For example, the acceptance method can be improved based on the user's past feedback. In addition, the user's feedback can be analyzed and an appropriate acceptance method can be provided. Furthermore, the acceptance method can be optimized by reflecting the user's past feedback. This makes it possible to improve the acceptance method based on the user's past feedback. For example, the answer acceptance unit can analyze the user's past feedback in real time and provide an appropriate acceptance method.

[0044] When generating an image, the image generation unit can analyze the user's answers in detail and generate an appropriate image. The image generation unit uses a generation AI to analyze the user's answers in detail. For example, the image generation unit can analyze the user's answers in detail using text analysis and keyword extraction. The generation AI can generate an image based on the user's answers using a text generation AI (e.g., LLM). For example, if a user answers "I can't sleep," an image symbolizing insomnia can be generated. Also, if a user answers "I feel stressed," an image useful for stress reduction can be generated. Furthermore, the user's answers can be analyzed in detail and an appropriate image can be generated. This makes it possible to generate optimal images based on the user's answers. For example, the image generation unit can analyze the user's answers in real time and generate an appropriate image.

[0045] When generating an image, the image generation unit can customize the content of the image by referring to the user's past image viewing history. The image generation unit uses a generation AI to refer to the user's past image viewing history. For example, the image generation unit accumulates the user's past image viewing history as data, and the generation AI analyzes that data to customize the content of the image. For example, the image generation unit can generate related images based on images the user has previously viewed. It can also analyze the user's past image viewing history and generate images that are likely to interest the user. Furthermore, it can generate optimal images by referring to the user's past image viewing history. This makes it possible to customize the image content based on the user's past image viewing history. For example, the image generation unit can analyze the user's past image viewing history in real time and generate appropriate images.

[0046] The image generation unit can analyze the user's current psychological state in real time when generating an image and generate an appropriate image. The image generation unit uses a generation AI to analyze the user's current psychological state in real time. For example, the image generation unit can analyze the user's psychological state in real time using facial expression analysis or voice analysis. The generation AI can generate an image according to the user's psychological state using a text generation AI (e.g., LLM). For example, if the user is feeling stressed, an image that helps relieve stress can be generated. Also, if the user is relaxed, an image that promotes relaxation can be generated. Furthermore, the user's psychological state can be analyzed in real time and an appropriate image can be generated. This makes it possible to generate optimal images based on the user's psychological state. For example, the image generation unit can analyze the user's psychological state in real time and generate an appropriate image.

[0047] The image generation unit can generate images taking into account the user's geographical and cultural backgrounds. The image generation unit uses a generation AI to consider the user's geographical and cultural backgrounds. For example, the image generation unit accumulates the user's geographical and cultural backgrounds as data, and the generation AI analyzes the data to generate images. For example, if the user lives in a specific area, the image generation unit can generate images related to that area. The image generation unit can also generate appropriate images taking into account the user's cultural background. Furthermore, the image generation unit can analyze the user's geographical and cultural backgrounds and generate highly relevant images. This makes it possible to generate images based on the user's geographical and cultural backgrounds. For example, the image generation unit can analyze the user's geographical and cultural backgrounds in real time and generate appropriate images.

[0048] The image generation unit can analyze the user's social media activity and generate related images when generating images. The image generation unit uses a generation AI to analyze the user's social media activity. For example, the image generation unit accumulates data such as the user's social media posts, number of likes, and number of followers, and the generation AI analyzes that data to generate related images. For example, the image generation unit can generate images related to topics that the user frequently posts about on social media. The unit can also analyze the user's social media activity and generate images that are likely to interest the user. Furthermore, the unit can generate related images based on the user's social media activity. For example, the image generation unit can analyze the user's social media activity in real time and generate appropriate images.

[0049] The image generation unit can improve the content of the image by reflecting the user's past feedback when generating an image. The image generation unit uses a generation AI to refer to the user's past feedback. For example, the image generation unit accumulates feedback provided by the user in the past as text data, and the generation AI analyzes that data to improve the content of the image. For example, the image content can be improved based on the user's past feedback. The user's feedback can also be analyzed to generate an appropriate image. Furthermore, the image content can be optimized by reflecting the user's past feedback. This makes it possible to improve the image content based on the user's past feedback. For example, the image generation unit can analyze the user's past feedback in real time and generate an appropriate image.

[0050] The hearing unit can improve the accuracy of the hearing by referring to the user's past answer history during the hearing. The hearing unit uses AI to refer to the user's past answer history. For example, the hearing unit accumulates the past answer history as text data, and the AI ​​analyzes the data to improve the accuracy of the hearing. For example, the hearing accuracy can be improved based on answers provided by the user in the past. In addition, the user's past answer history can be analyzed and appropriate feedback can be provided. Furthermore, the hearing accuracy can be optimized by referring to the user's past answer history. This makes it possible to improve the hearing accuracy based on the user's past answer history. For example, the hearing unit can analyze the user's past answer history in real time and provide an appropriate hearing method.

[0051] The hearing unit can analyze the content of the user's answers in real time during the hearing and provide appropriate feedback. The hearing unit uses AI to analyze the content of the user's answers in real time. For example, the hearing unit can analyze the content of the user's answers in real time using text analysis and keyword extraction. The AI ​​can provide feedback based on the content of the user's answers using text generation AI (e.g., LLM). For example, the AI ​​can analyze the content of the user's answers in real time and provide feedback immediately after the user enters the answer. The AI ​​can also analyze the content of the user's answers in real time and provide appropriate advice. Furthermore, the AI ​​can analyze the content of the user's answers in real time and generate the next question. This makes it possible to provide real-time feedback based on the content of the user's answers. For example, the hearing unit can analyze the content of the user's answers in real time and provide appropriate feedback.

[0052] The hearing unit can evaluate the reliability of the user's answer during the hearing and filter out low-reliability answers. The hearing unit uses AI to evaluate the reliability of the user's answer. For example, the hearing unit can evaluate the reliability of the user's answer based on the consistency of the answer, the answer time, etc. The AI ​​can evaluate the reliability of the user's answer and filter out low-reliability answers using text generation AI (e.g., LLM). For example, the content of the user's answer can be analyzed and low-reliability answers can be automatically filtered. The reliability of the user's answer can also be evaluated and high-reliability answers can be preferentially accepted. Furthermore, the reliability of the user's answer can be evaluated in real time and appropriate feedback can be provided. This enables filtering based on the reliability of the user's answer. For example, the hearing unit can analyze the reliability of the user's answer in real time and provide appropriate feedback.

[0053] The hearing unit can select an appropriate hearing method based on the user's device information during hearing. The hearing unit uses AI to consider the user's device information. For example, the hearing unit accumulates the user's device information as data, and the AI ​​analyzes the data to select the optimal hearing method. For example, if the user is using a smartphone, touch input can be prioritized. Also, if the user is using a PC, keyboard input can be prioritized. Furthermore, the user's device information can be analyzed to select the optimal hearing method. This makes it possible to select the optimal hearing method based on the user's device information. For example, the hearing unit can analyze the user's device information in real time and provide the appropriate hearing method.

[0054] The hearing unit can provide multilingual hearings according to the user's language settings during hearing. The hearing unit uses AI to consider the user's language settings. For example, the hearing unit accumulates the language settings of the user's device as data, and the AI ​​analyzes the data to provide multilingual hearings. For example, the hearing language can be automatically set based on the language settings of the user's device. In addition, if the user uses multiple languages, a language switching function can be provided. Furthermore, if the user selects a specific language, hearings can be conducted in that language. This enables multilingual hearings based on the user's language settings. For example, the hearing unit can analyze the user's language settings in real time and provide hearings in the appropriate language.

[0055] The hearing unit can improve the hearing method by reflecting the user's past feedback during the hearing. The hearing unit uses AI to refer to the user's past feedback. For example, the hearing unit accumulates feedback provided by the user in the past as text data, and the AI ​​analyzes the data to improve the hearing method. For example, the hearing method can be improved based on the user's past feedback. The user's feedback can also be analyzed to provide an appropriate hearing method. Furthermore, the hearing method can be optimized by reflecting the user's past feedback. This makes it possible to improve the hearing method based on the user's past feedback. For example, the hearing unit can analyze the user's past feedback in real time and provide an appropriate hearing method.

[0056] When accumulating data, the data accumulation unit can improve the accuracy of accumulation by referring to the user's past data. The data accumulation unit uses AI to refer to the user's past data. For example, the data accumulation unit accumulates the user's past data as text data, and AI analyzes the data to improve the accuracy of accumulation. For example, the accuracy of accumulation can be improved based on data previously provided by the user. In addition, the user's past data can be analyzed and appropriate data can be accumulated. Furthermore, the accuracy of accumulation can be optimized by referring to the user's past data. This makes it possible to improve the accuracy of accumulation based on the user's past data. For example, the data accumulation unit can analyze the user's past data in real time and provide an appropriate data accumulation method.

[0057] The data accumulation unit can evaluate the reliability of the user's data and filter out unreliable data when accumulating the data. The data accumulation unit uses AI to evaluate the reliability of the user's data. For example, the data accumulation unit can evaluate the reliability of the user's data based on the consistency of the data, the source of the data, etc. The AI ​​can evaluate the reliability of the user's data and filter out unreliable data using text generation AI (e.g., LLM). For example, the AI ​​can analyze the user's data and automatically filter out unreliable data. The reliability of the user's data can also be evaluated and reliable data can be preferentially accumulated. Furthermore, the reliability of the user's data can be evaluated in real time and appropriate data can be accumulated. This enables filtering based on the reliability of the user's data. For example, the data accumulation unit can analyze the reliability of the user's data in real time and provide an appropriate data accumulation method.

[0058] When storing data, the data storage unit can select an appropriate storage method based on the user's device information. The data storage unit uses AI to take the user's device information into consideration. For example, the data storage unit stores the user's device information as data, and the AI ​​analyzes that data to select the optimal storage method. For example, if the user is using a smartphone, touch input can be prioritized. Also, if the user is using a PC, keyboard input can be prioritized. Furthermore, the user's device information can be analyzed to select the optimal storage method. This makes it possible to select the optimal storage method based on the user's device information. For example, the data storage unit can analyze the user's device information in real time and provide the appropriate storage method.

[0059] The data accumulation unit can accumulate data in multiple languages ​​according to the user's language setting when accumulating data. The data accumulation unit uses AI to take the user's language setting into consideration. For example, the data accumulation unit accumulates the language setting of the user's device as data, and the AI ​​analyzes the data to accumulate data in multiple languages. For example, the data accumulation language can be automatically set based on the language setting of the user's device. In addition, if the user uses multiple languages, a language switching function can be provided. Furthermore, if the user selects a specific language, data accumulation can be performed in that language. This enables data accumulation in multiple languages ​​based on the user's language setting. For example, the data accumulation unit can analyze the user's language setting in real time and provide data accumulation in the appropriate language.

[0060] When providing a diagnostic result, the diagnostic result providing unit can improve the accuracy of the provided result by referring to the user's past diagnostic results. The diagnostic result providing unit uses AI to refer to the user's past diagnostic results. For example, the diagnostic result providing unit accumulates the user's past diagnostic results as text data, and the AI ​​analyzes the data to improve the accuracy of the provided result. For example, the accuracy of the provided result can be improved based on the diagnostic results the user has received in the past. In addition, the user's past diagnostic results can be analyzed and appropriate feedback can be provided. Furthermore, the accuracy of the provided result can be optimized by referring to the user's past diagnostic results. This makes it possible to improve the accuracy of the provided result based on the user's past diagnostic results. For example, the diagnostic result providing unit can analyze the user's past diagnostic results in real time and provide an appropriate diagnostic result.

[0061] When providing a diagnostic result, the diagnostic result providing unit can analyze the user's current psychological state in real time and provide an appropriate diagnostic result. The diagnostic result providing unit uses AI to analyze the user's current psychological state in real time. For example, the diagnostic result providing unit can analyze the user's psychological state in real time using facial expression analysis or voice analysis. The AI ​​can provide a diagnostic result according to the user's psychological state using a text generation AI (e.g., LLM). For example, if the user is feeling stressed, a diagnostic result including advice on stress reduction can be provided. Furthermore, if the user is relaxed, a detailed diagnostic result can be provided. Furthermore, the user's psychological state can be analyzed in real time and an appropriate diagnostic result can be provided. This makes it possible to provide an optimal diagnostic result based on the user's psychological state. For example, the diagnostic result providing unit can analyze the user's psychological state in real time and provide an appropriate diagnostic result.

[0062] When providing diagnostic results, the diagnostic result providing unit can select an appropriate delivery method based on the user's device information. The diagnostic result providing unit uses AI to take the user's device information into consideration. For example, the diagnostic result providing unit accumulates the user's device information as data, and the AI ​​analyzes the data to select the optimal delivery method. For example, if the user is using a smartphone, a display method tailored to the screen size can be provided. Also, if the user is using a PC, a display method optimized for a large screen can be provided. Furthermore, the user's device information can be analyzed to select the optimal delivery method. This makes it possible to select the optimal delivery method based on the user's device information. For example, the diagnostic result providing unit can analyze the user's device information in real time and provide the appropriate delivery method.

[0063] When providing diagnostic results, the diagnostic result providing unit can provide multilingual diagnostic results according to the user's language setting. The diagnostic result providing unit uses AI to take the user's language setting into consideration. For example, the diagnostic result providing unit accumulates the language setting of the user's device as data, and the AI ​​analyzes the data to provide multilingual diagnostic results. For example, the language of the diagnostic results can be automatically set based on the language setting of the user's device. In addition, if the user uses multiple languages, a language switching function can be provided. Furthermore, if the user selects a specific language, the diagnostic results can be provided in that language. This makes it possible to provide multilingual diagnostic results based on the user's language setting. For example, the diagnostic result providing unit can analyze the user's language setting in real time and provide diagnostic results in the appropriate language.

[0064] When providing a diagnostic result, the diagnostic result providing unit can analyze the user's social media activity and provide related information. The diagnostic result providing unit uses AI to analyze the user's social media activity. For example, the diagnostic result providing unit accumulates data such as the user's social media posts, the number of likes, and the number of followers, and the AI ​​analyzes the data to provide related information. For example, the diagnostic result providing unit can provide information about the locations where the user checked in on social media. The diagnostic result providing unit can also analyze the user's social media posts and provide related advice. Furthermore, the diagnostic result providing unit can provide related information by referring to the activities of the user's friends on social media. This makes it possible to provide related information based on the user's social media activity. For example, the diagnostic result providing unit can analyze the user's social media activity in real time and provide appropriate information.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The diagnostic system may further include a behavior analysis unit. The behavior analysis unit analyzes data acquired from the user's smartphone or wearable device to understand the user's daily behavioral patterns and activity level. For example, the behavior analysis unit can collect data such as the user's number of steps, sleep time, and heart rate, and estimate the user's health and psychological state based on this data. The behavior analysis unit can also detect changes in the user's behavioral patterns and issue an alert if an abnormality is detected. Furthermore, the behavior analysis unit can accumulate the user's behavioral data and analyze long-term trends to help with early detection of mental abnormalities. This allows the behavior analysis unit to provide a highly accurate diagnosis based on the user's behavioral data.

[0067] The diagnostic system may further include a biometrics analysis unit. The biometrics analysis unit may analyze the user's biometric data and estimate the user's health and psychological state. For example, the biometrics analysis unit may collect data such as the user's heart rate, blood pressure, and electrodermal activity, and evaluate the user's stress level and relaxation level based on this data. The biometrics analysis unit may also monitor changes in the user's biometric data in real time and issue an alert if an abnormality is detected. Furthermore, the biometrics analysis unit may accumulate the user's biometric data and analyze long-term health trends, which may be useful for early detection of mental abnormalities. This allows the biometrics analysis unit to provide highly accurate diagnoses based on the user's biometric data.

[0068] The diagnostic system may further include an environmental data analysis unit. The environmental data analysis unit may collect and analyze environmental data surrounding the user. For example, the environmental data analysis unit may collect data such as temperature, humidity, noise level, and light intensity of the user's living environment and evaluate the impact on the user's psychological state and health based on this data. The environmental data analysis unit may also monitor changes in the user's environmental data in real time and issue an alert if an abnormality is detected. Furthermore, the environmental data analysis unit may accumulate the user's environmental data and analyze long-term trends to help with early detection of mental abnormalities. This allows the environmental data analysis unit to provide a highly accurate diagnosis based on the user's environmental data.

[0069] The diagnostic system may further include a social interaction analysis unit. The social interaction analysis unit may analyze data from the user's social media and messaging apps to understand the user's social interaction patterns. For example, the social interaction analysis unit may analyze how frequently the user exchanges messages with friends and the content of their posts, and based on this data, the system may evaluate the user's psychological state and level of social isolation. The social interaction analysis unit may also detect changes in the user's interaction patterns and issue an alert if an abnormality is detected. Furthermore, the social interaction analysis unit may accumulate user interaction data and analyze long-term trends to help with early detection of mental disorders. This allows the social interaction analysis unit to provide highly accurate diagnoses based on the user's social interaction data.

[0070] The processing flow of the first embodiment will be briefly explained below.

[0071] Step 1: The question generation unit generates questions using generation AI. For example, it generates appropriate questions based on questions and answers that psychological counselors have heard in conversations with patients with mental disorders. The generation AI can generate questions using text generation AI (e.g., LLM). It can also generate questions that correspond to the user's emotions and psychological state. Step 2: The answer acceptance unit accepts the user's answer based on the question generated by the generation AI. For example, answers can be accepted in text or audio format. It can also analyze the user's answer in real time and provide appropriate feedback. Step 3: The image generation unit uses generation AI to generate an image based on the user's response. For example, if the user responds "I can't sleep," it generates an image that symbolizes insomnia. The generation AI can generate images from text data using multimodal generation AI. Step 4: The hearing department collects user feedback after viewing the image generated by the AI. For example, they ask questions such as, "How do you feel when you see this image?"

[0072] (Example 2) A diagnostic system according to an embodiment of the present invention is a system for the early detection of mental disorders such as depression. This diagnostic system accumulates data on questions and answers asked by psychological counselors in conversations with patients with mental disorders. A generation AI generates appropriate questions based on the accumulated data and presents them to the user. The user answers the questions, and the generation AI creates appropriate images or drawings based on the answers. The user is then asked how they feel when viewing the generated images or drawings. This allows for the identification of mental disorders that are difficult to distinguish between normal and abnormal. For example, the diagnostic system is easy to use because users can receive a diagnosis using their smartphones. Furthermore, the generation AI generates appropriate questions and images, improving the accuracy of the diagnosis. This allows people who do not believe their illness is serious enough to warrant a hospital visit to receive a diagnosis to receive a diagnosis in a casual, game-like manner. For example, the system is easy to use because users can receive a diagnosis using their smartphones. Furthermore, the generation AI generates appropriate questions and images, improving the accuracy of the diagnosis.

[0073] A diagnostic system according to an embodiment includes a question generation unit, an answer reception unit, an image generation unit, and a hearing unit. The question generation unit generates questions using a generation AI. For example, the question generation unit generates appropriate questions based on questions and answers heard by a psychological counselor in past conversations with patients with mental disorder symptoms. The generation AI can generate questions using a text generation AI (e.g., LLM). The question generation unit can also use the generation AI to generate questions based on a user's emotions and psychological state. The answer reception unit receives a user's answer based on the question generated by the generation AI. For example, the answer reception unit can receive answers in text format or audio format. The answer reception unit can also analyze the user's answer in real time and provide appropriate feedback. The image generation unit generates an image based on the user's answer using the generation AI. For example, if the user answers "I can't sleep," the image generation unit generates an image symbolizing insomnia. The generation AI can generate an image from text data using a multimodal generation AI. The hearing unit collects user feedback after viewing the image generated by the generation AI. For example, the hearing unit presents a question such as, "How do you feel when you see this image?" and collects user feedback. This enables the diagnostic system according to the embodiment to detect mental disorders early through question generation, answer reception, image generation, and hearing. For example, the diagnostic system is easy to use because users can receive a diagnosis using their smartphone. Furthermore, the accuracy of the diagnosis is improved because the generation AI generates appropriate questions and images.

[0074] The diagnostic system includes a data storage unit that stores data. The data storage unit stores questions and answers asked by past psychological counselors through conversations with patients with symptoms of mental disorders. For example, the data storage unit can store text data, numerical data, image data, etc. The data storage unit can also use AI to store data. For example, the data storage unit stores the content of conversations as text data, and the AI ​​analyzes the data to use it as basic data for generating appropriate questions. This enables the data storage unit to generate questions based on past data. For example, the data storage unit can generate appropriate questions for the user based on past data.

[0075] The diagnostic system includes a diagnostic result providing unit that provides diagnostic results. The diagnostic result providing unit uses AI to provide the diagnostic results to the user. For example, the diagnostic result providing unit can provide the diagnostic results in the form of a numerical evaluation or a text report. The diagnostic result providing unit uses AI to analyze the diagnostic results based on the user's answers and the images generated by the image generating unit, and provides appropriate feedback. For example, if a user answers "I can't sleep" and an image symbolizing insomnia is generated, the diagnostic result providing unit provides a diagnostic result indicating the possibility of insomnia based on the results. This allows the diagnostic result providing unit to provide the diagnostic result to the user. For example, the diagnostic result providing unit can be easily used because the user can receive the diagnostic results using a smartphone. In addition, because AI analyzes the diagnostic results, the accuracy of the diagnosis is improved.

[0076] The question generation unit can estimate the user's emotions and adjust the content and wording of the question based on the estimated user's emotions. The question generation unit estimates the user's emotions using a generation AI. For example, the question generation unit can estimate the user's emotions using facial expression analysis or voice analysis. The generation AI can generate questions according to the user's emotions using a text generation AI (e.g., LLM). For example, if the user is feeling anxious, the generation AI can generate questions in a gentle tone to help the user relax. Also, if the user is excited, the generation AI can generate questions in a calm tone to calm the user's emotions. Furthermore, if the user is tired, the generation AI can generate concise and easy-to-understand questions to reduce the user's burden. This makes it possible to generate questions according to the user's emotions. For example, the question generation unit can analyze the user's emotions in real time and generate appropriate questions.

[0077] When generating a question, the question generation unit can adjust the difficulty of the question by referring to the user's past answer history. The question generation unit uses a generation AI to refer to the user's past answer history. For example, the question generation unit accumulates the past answer history as text data, and the generation AI analyzes the data to adjust the difficulty of the question. For example, if the user has answered easy questions correctly in the past, a question with a slightly higher difficulty level can be generated. Also, if the user has not been able to answer difficult questions in the past, a question with a lower difficulty level can be generated. Furthermore, the user's past answer history can be analyzed to generate questions of an appropriate level of difficulty. This makes it possible to generate questions based on the user's past answer history. For example, the question generation unit can analyze the user's past answer history in real time and generate appropriate questions.

[0078] When generating questions, the question generation unit can customize the content of the questions according to the user's age and gender. The question generation unit uses generation AI to take the user's age and gender into consideration. For example, the question generation unit accumulates the user's age and gender as data, and the generation AI analyzes that data to customize the content of the questions. For example, if the user is young, the question generation unit can generate questions that include topics aimed at young people. On the other hand, if the user is elderly, the question generation unit can generate simple and easy-to-understand questions. Furthermore, questions that include highly relevant topics can be generated according to the user's gender. This makes it possible to generate questions according to the user's age and gender. For example, the question generation unit can analyze the user's age and gender in real time and generate appropriate questions.

[0079] The question generation unit can analyze the user's current psychological state in real time when generating a question and generate an appropriate question. The question generation unit analyzes the user's current psychological state in real time using a generation AI. For example, the question generation unit can analyze the user's psychological state in real time using facial expression analysis or voice analysis. The generation AI can generate questions according to the user's psychological state using a text generation AI (e.g., LLM). For example, if the user is feeling stressed, a question related to stress reduction can be generated. Also, if the user is relaxed, a more in-depth question can be generated. Furthermore, the user's psychological state can be analyzed in real time and appropriate questions can be generated. This makes it possible to generate questions according to the user's psychological state. For example, the question generation unit can analyze the user's psychological state in real time and generate appropriate questions.

[0080] The question generation unit can estimate the user's emotions and adjust the order of questions based on the estimated user's emotions. The question generation unit estimates the user's emotions using a generation AI. For example, the question generation unit can estimate the user's emotions using facial expression analysis or voice analysis. The generation AI can adjust the order of questions according to the user's emotions using a text generation AI (e.g., LLM). For example, if the user is feeling anxious, the system can start with easy questions and gradually increase the difficulty level. Also, if the user is relaxed, the system can start with more difficult questions. Furthermore, the order of questions can be adjusted according to the user's emotions. This makes it possible to adjust the order of questions according to the user's emotions. For example, the question generation unit can analyze the user's emotions in real time and generate an appropriate order of questions.

[0081] The question generation unit can generate questions based on the user's geographical and cultural background when generating questions. The question generation unit uses a generation AI to take the user's geographical and cultural background into consideration. For example, the question generation unit accumulates the user's geographical and cultural background as data, and the generation AI analyzes the data to generate questions. For example, if the user lives in a specific area, the question generation unit can generate questions related to that area. The question generation unit can also generate appropriate questions by taking the user's cultural background into consideration. Furthermore, the question generation unit can analyze the user's geographical and cultural background and generate highly relevant questions. This makes it possible to generate questions that are appropriate to the user's geographical and cultural background. For example, the question generation unit can analyze the user's geographical and cultural background in real time and generate appropriate questions.

[0082] The question generation unit can analyze the user's social media activity when generating a question and generate a related question. The question generation unit uses a generation AI to analyze the user's social media activity. For example, the question generation unit accumulates data such as the content of the user's social media posts, the number of likes, and the number of followers, and the generation AI analyzes the data to generate related questions. For example, the question generation unit can generate questions related to topics that the user frequently posts about on social media. The unit can also analyze the user's social media activity and generate questions that are likely to interest the user. Furthermore, the unit can generate related questions by referring to the activity of the user's friends on social media. This makes it possible to generate questions based on the user's social media activity. For example, the question generation unit can analyze the user's social media activity in real time and generate appropriate questions.

[0083] When generating a question, the question generation unit can improve the content of the question by reflecting the user's past feedback. The question generation unit uses a generation AI to refer to the user's past feedback. For example, the question generation unit accumulates feedback provided by the user in the past as text data, and the generation AI analyzes the data to improve the content of the question. For example, the question generation unit can improve the content of the question based on the feedback provided by the user in the past. In addition, the user's feedback can be analyzed to generate an appropriate question. Furthermore, the question content can be optimized by reflecting the user's past feedback. This makes it possible to improve the content of the question based on the user's past feedback. For example, the question generation unit can analyze the user's past feedback in real time and generate an appropriate question.

[0084] The answer acceptance unit can estimate the user's emotions and adjust the answer acceptance method based on the estimated user's emotions. The answer acceptance unit estimates the user's emotions using AI. For example, the answer acceptance unit can estimate the user's emotions using facial expression analysis or voice analysis. The AI ​​can adjust the answer acceptance method according to the user's emotions using text generation AI (e.g., LLM). For example, if the user is feeling anxious, the AI ​​can encourage the user to answer in a gentle tone. If the user is relaxed, the AI ​​can request a detailed answer. If the user is in a hurry, the AI ​​can request a concise answer. This makes it possible to adjust the answer acceptance method according to the user's emotions. For example, the answer acceptance unit can analyze the user's emotions in real time and provide an appropriate answer acceptance method.

[0085] When accepting an answer, the answer acceptance unit can improve the accuracy of accepting answers by referring to the user's past answer history. The answer acceptance unit uses AI to refer to the user's past answer history. For example, the answer acceptance unit accumulates the past answer history as text data, and AI analyzes the data to improve the accuracy of accepting answers. For example, the answer acceptance unit can improve the accuracy of answers based on answers provided by the user in the past. In addition, the user's past answer history can be analyzed and appropriate feedback can be provided. Furthermore, the answer acceptance accuracy can be optimized by referring to the user's past answer history. This makes it possible to improve the accuracy of accepting answers based on the user's past answer history. For example, the answer acceptance unit can analyze the user's past answer history in real time and provide an appropriate answer acceptance method.

[0086] The answer accepting unit can analyze the content of the user's answer in real time when accepting the answer and provide appropriate feedback. The answer accepting unit analyzes the content of the user's answer in real time using AI. For example, the answer accepting unit can analyze the content of the user's answer in real time using text analysis and keyword extraction. The AI ​​can provide feedback based on the content of the user's answer using a text generation AI (e.g., LLM). For example, the AI ​​can analyze the content of the user's answer in real time and provide feedback immediately after the user enters the answer. The AI ​​can also analyze the content of the user's answer in real time and provide appropriate advice. Furthermore, the AI ​​can analyze the content of the user's answer in real time and generate the next question. This makes it possible to provide real-time feedback based on the content of the user's answer. For example, the AI ​​can analyze the content of the user's answer in real time and provide appropriate feedback.

[0087] The answer acceptance unit can evaluate the reliability of the user's answer when accepting the answer and filter out low-reliability answers. The answer acceptance unit evaluates the reliability of the user's answer using AI. For example, the answer acceptance unit can evaluate the reliability of the user's answer based on the consistency of the answer, the answer time, etc. The AI ​​can evaluate the reliability of the user's answer and filter out low-reliability answers using text generation AI (e.g., LLM). For example, the content of the user's answer can be analyzed and low-reliability answers can be automatically filtered. In addition, the reliability of the user's answer can be evaluated and high-reliability answers can be preferentially accepted. Furthermore, the reliability of the user's answer can be evaluated in real time and appropriate feedback can be provided. This enables filtering based on the reliability of the user's answer. For example, the answer acceptance unit can analyze the reliability of the user's answer in real time and provide appropriate feedback.

[0088] The answer acceptance unit can estimate the user's emotions and adjust the timing of accepting answers based on the estimated user's emotions. The answer acceptance unit estimates the user's emotions using AI. For example, the answer acceptance unit can estimate the user's emotions using facial expression analysis or voice analysis. The AI ​​can adjust the timing of accepting answers according to the user's emotions using a text generation AI (e.g., LLM). For example, if the user is feeling anxious, the user can be prompted to answer at a slower pace. On the other hand, if the user is relaxed, the user can be prompted to answer quickly. Furthermore, the timing of accepting answers can be adjusted according to the user's emotions. This makes it possible to adjust the timing of accepting answers according to the user's emotions. For example, the answer acceptance unit can analyze the user's emotions in real time and provide an appropriate timing of accepting answers.

[0089] When accepting an answer, the answer acceptance unit can select an appropriate acceptance method based on the user's device information. The answer acceptance unit uses AI to consider the user's device information. For example, the answer acceptance unit accumulates the user's device information as data, and the AI ​​analyzes the data to select the optimal acceptance method. For example, if the user is using a smartphone, touch input can be prioritized. Also, if the user is using a PC, keyboard input can be prioritized. Furthermore, the user's device information can be analyzed to select the optimal acceptance method. This makes it possible to select the optimal acceptance method based on the user's device information. For example, the answer acceptance unit can analyze the user's device information in real time and provide the appropriate acceptance method.

[0090] The answer acceptance unit can accept answers in multiple languages ​​according to the user's language setting when accepting answers. The answer acceptance unit uses AI to take the user's language setting into consideration. For example, the answer acceptance unit accumulates the language setting of the user's device as data, and the AI ​​analyzes the data to accept answers in multiple languages. For example, the answer acceptance language can be automatically set based on the language setting of the user's device. In addition, if the user uses multiple languages, a language switching function can be provided. Furthermore, if the user selects a specific language, answers can be accepted in that language. This enables multilingual acceptance based on the user's language setting. For example, the answer acceptance unit can analyze the user's language setting in real time and provide acceptance in the appropriate language.

[0091] The answer acceptance unit can improve the acceptance method by reflecting the user's past feedback when accepting an answer. The answer acceptance unit uses AI to refer to the user's past feedback. For example, the answer acceptance unit accumulates feedback provided by the user in the past as text data, and the AI ​​analyzes the data to improve the acceptance method. For example, the acceptance method can be improved based on the user's past feedback. In addition, the user's feedback can be analyzed and an appropriate acceptance method can be provided. Furthermore, the acceptance method can be optimized by reflecting the user's past feedback. This makes it possible to improve the acceptance method based on the user's past feedback. For example, the answer acceptance unit can analyze the user's past feedback in real time and provide an appropriate acceptance method.

[0092] The image generation unit can estimate the user's emotions and adjust the content of the generated image based on the estimated user's emotions. The image generation unit estimates the user's emotions using a generation AI. For example, the image generation unit can estimate the user's emotions using facial expression analysis or voice analysis. The generation AI can adjust the content of the image according to the user's emotions using a text generation AI (e.g., LLM). For example, if the user is feeling anxious, a relaxing image can be generated. Also, if the user is excited, a calming image can be generated. Furthermore, if the user is tired, a soothing image can be generated. This makes it possible to adjust the image content according to the user's emotions. For example, the image generation unit can analyze the user's emotions in real time and generate an appropriate image.

[0093] When generating an image, the image generation unit can analyze the user's answers in detail and generate an appropriate image. The image generation unit uses a generation AI to analyze the user's answers in detail. For example, the image generation unit can analyze the user's answers in detail using text analysis and keyword extraction. The generation AI can generate an image based on the user's answers using a text generation AI (e.g., LLM). For example, if a user answers "I can't sleep," an image symbolizing insomnia can be generated. Also, if a user answers "I feel stressed," an image useful for stress reduction can be generated. Furthermore, the user's answers can be analyzed in detail and an appropriate image can be generated. This makes it possible to generate optimal images based on the user's answers. For example, the image generation unit can analyze the user's answers in real time and generate an appropriate image.

[0094] When generating an image, the image generation unit can customize the content of the image by referring to the user's past image viewing history. The image generation unit uses a generation AI to refer to the user's past image viewing history. For example, the image generation unit accumulates the user's past image viewing history as data, and the generation AI analyzes that data to customize the content of the image. For example, the image generation unit can generate related images based on images the user has previously viewed. It can also analyze the user's past image viewing history and generate images that are likely to interest the user. Furthermore, it can generate optimal images by referring to the user's past image viewing history. This makes it possible to customize the image content based on the user's past image viewing history. For example, the image generation unit can analyze the user's past image viewing history in real time and generate appropriate images.

[0095] The image generation unit can analyze the user's current psychological state in real time when generating an image and generate an appropriate image. The image generation unit uses a generation AI to analyze the user's current psychological state in real time. For example, the image generation unit can analyze the user's psychological state in real time using facial expression analysis or voice analysis. The generation AI can generate an image according to the user's psychological state using a text generation AI (e.g., LLM). For example, if the user is feeling stressed, an image that helps relieve stress can be generated. Also, if the user is relaxed, an image that promotes relaxation can be generated. Furthermore, the user's psychological state can be analyzed in real time and an appropriate image can be generated. This makes it possible to generate optimal images based on the user's psychological state. For example, the image generation unit can analyze the user's psychological state in real time and generate an appropriate image.

[0096] The image generation unit can estimate the user's emotions and adjust the style of the generated image based on the estimated user's emotions. The image generation unit estimates the user's emotions using a generation AI. For example, the image generation unit can estimate the user's emotions using facial expression analysis or voice analysis. The generation AI can adjust the style of the image according to the user's emotions using a text generation AI (e.g., LLM). For example, if the user is feeling anxious, an image with soft colors can be generated. Also, if the user is excited, an image with calm colors can be generated. Furthermore, if the user is tired, an image with soothing colors can be generated. This makes it possible to adjust the image style according to the user's emotions. For example, the image generation unit can analyze the user's emotions in real time and generate an appropriate image style.

[0097] The image generation unit can generate images taking into account the user's geographical and cultural backgrounds. The image generation unit uses a generation AI to consider the user's geographical and cultural backgrounds. For example, the image generation unit accumulates the user's geographical and cultural backgrounds as data, and the generation AI analyzes the data to generate images. For example, if the user lives in a specific area, the image generation unit can generate images related to that area. The image generation unit can also generate appropriate images taking into account the user's cultural background. Furthermore, the image generation unit can analyze the user's geographical and cultural backgrounds and generate highly relevant images. This makes it possible to generate images based on the user's geographical and cultural backgrounds. For example, the image generation unit can analyze the user's geographical and cultural backgrounds in real time and generate appropriate images.

[0098] The image generation unit can analyze the user's social media activity and generate related images when generating images. The image generation unit uses a generation AI to analyze the user's social media activity. For example, the image generation unit accumulates data such as the user's social media posts, number of likes, and number of followers, and the generation AI analyzes that data to generate related images. For example, the image generation unit can generate images related to topics that the user frequently posts about on social media. The unit can also analyze the user's social media activity and generate images that are likely to interest the user. Furthermore, the unit can generate related images based on the user's social media activity. For example, the image generation unit can analyze the user's social media activity in real time and generate appropriate images.

[0099] The image generation unit can improve the content of the image by reflecting the user's past feedback when generating an image. The image generation unit uses a generation AI to refer to the user's past feedback. For example, the image generation unit accumulates feedback provided by the user in the past as text data, and the generation AI analyzes that data to improve the content of the image. For example, the image content can be improved based on the user's past feedback. The user's feedback can also be analyzed to generate an appropriate image. Furthermore, the image content can be optimized by reflecting the user's past feedback. This makes it possible to improve the image content based on the user's past feedback. For example, the image generation unit can analyze the user's past feedback in real time and generate an appropriate image.

[0100] The hearing unit can estimate the user's emotions and adjust the hearing method based on the estimated user's emotions. The hearing unit estimates the user's emotions using AI. For example, the hearing unit can estimate the user's emotions using facial expression analysis or voice analysis. The AI ​​can adjust the hearing method according to the user's emotions using text generation AI (e.g., LLM). For example, if the user is feeling anxious, the hearing can be performed in a gentle tone. If the user is relaxed, the hearing can be performed in detail. Furthermore, if the user is in a hurry, the hearing can be performed in a concise tone. This makes it possible to adjust the hearing method according to the user's emotions. For example, the hearing unit can analyze the user's emotions in real time and provide an appropriate hearing method.

[0101] The hearing unit can improve the accuracy of the hearing by referring to the user's past answer history during the hearing. The hearing unit uses AI to refer to the user's past answer history. For example, the hearing unit accumulates the past answer history as text data, and the AI ​​analyzes the data to improve the accuracy of the hearing. For example, the hearing accuracy can be improved based on answers provided by the user in the past. In addition, the user's past answer history can be analyzed and appropriate feedback can be provided. Furthermore, the hearing accuracy can be optimized by referring to the user's past answer history. This makes it possible to improve the hearing accuracy based on the user's past answer history. For example, the hearing unit can analyze the user's past answer history in real time and provide an appropriate hearing method.

[0102] The hearing unit can analyze the content of the user's answers in real time during the hearing and provide appropriate feedback. The hearing unit uses AI to analyze the content of the user's answers in real time. For example, the hearing unit can analyze the content of the user's answers in real time using text analysis and keyword extraction. The AI ​​can provide feedback based on the content of the user's answers using text generation AI (e.g., LLM). For example, the AI ​​can analyze the content of the user's answers in real time and provide feedback immediately after the user enters the answer. The AI ​​can also analyze the content of the user's answers in real time and provide appropriate advice. Furthermore, the AI ​​can analyze the content of the user's answers in real time and generate the next question. This makes it possible to provide real-time feedback based on the content of the user's answers. For example, the hearing unit can analyze the content of the user's answers in real time and provide appropriate feedback.

[0103] The hearing unit can evaluate the reliability of the user's answer during the hearing and filter out low-reliability answers. The hearing unit uses AI to evaluate the reliability of the user's answer. For example, the hearing unit can evaluate the reliability of the user's answer based on the consistency of the answer, the answer time, etc. The AI ​​can evaluate the reliability of the user's answer and filter out low-reliability answers using text generation AI (e.g., LLM). For example, the content of the user's answer can be analyzed and low-reliability answers can be automatically filtered. The reliability of the user's answer can also be evaluated and high-reliability answers can be preferentially accepted. Furthermore, the reliability of the user's answer can be evaluated in real time and appropriate feedback can be provided. This enables filtering based on the reliability of the user's answer. For example, the hearing unit can analyze the reliability of the user's answer in real time and provide appropriate feedback.

[0104] The hearing unit can estimate the user's emotions and adjust the timing of the hearing based on the estimated user's emotions. The hearing unit estimates the user's emotions using AI. For example, the hearing unit can estimate the user's emotions using facial expression analysis or voice analysis. The AI ​​can adjust the timing of the hearing according to the user's emotions using a text generation AI (e.g., LLM). For example, if the user is feeling anxious, the hearing can be performed at a slow pace. On the other hand, if the user is relaxed, the hearing can be performed quickly. Furthermore, the timing of the hearing can be adjusted according to the user's emotions. This makes it possible to adjust the timing of the hearing according to the user's emotions. For example, the hearing unit can analyze the user's emotions in real time and provide appropriate timing for the hearing.

[0105] The hearing unit can select an appropriate hearing method based on the user's device information during hearing. The hearing unit uses AI to consider the user's device information. For example, the hearing unit accumulates the user's device information as data, and the AI ​​analyzes the data to select the optimal hearing method. For example, if the user is using a smartphone, touch input can be prioritized. Also, if the user is using a PC, keyboard input can be prioritized. Furthermore, the user's device information can be analyzed to select the optimal hearing method. This makes it possible to select the optimal hearing method based on the user's device information. For example, the hearing unit can analyze the user's device information in real time and provide the appropriate hearing method.

[0106] The hearing unit can provide multilingual hearings according to the user's language settings during hearing. The hearing unit uses AI to consider the user's language settings. For example, the hearing unit accumulates the language settings of the user's device as data, and the AI ​​analyzes the data to provide multilingual hearings. For example, the hearing language can be automatically set based on the language settings of the user's device. In addition, if the user uses multiple languages, a language switching function can be provided. Furthermore, if the user selects a specific language, hearings can be conducted in that language. This enables multilingual hearings based on the user's language settings. For example, the hearing unit can analyze the user's language settings in real time and provide hearings in the appropriate language.

[0107] The hearing unit can improve the hearing method by reflecting the user's past feedback during the hearing. The hearing unit uses AI to refer to the user's past feedback. For example, the hearing unit accumulates feedback provided by the user in the past as text data, and the AI ​​analyzes the data to improve the hearing method. For example, the hearing method can be improved based on the user's past feedback. The user's feedback can also be analyzed to provide an appropriate hearing method. Furthermore, the hearing method can be optimized by reflecting the user's past feedback. This makes it possible to improve the hearing method based on the user's past feedback. For example, the hearing unit can analyze the user's past feedback in real time and provide an appropriate hearing method.

[0108] The data accumulation unit can estimate the user's emotions and adjust the data accumulation method based on the estimated user's emotions. The data accumulation unit estimates the user's emotions using AI. For example, the data accumulation unit can estimate the user's emotions using facial expression analysis or voice analysis. The AI ​​can adjust the data accumulation method according to the user's emotions using text generation AI (e.g., LLM). For example, if the user is feeling anxious, data can be accumulated quickly. Also, if the user is relaxed, detailed data can be accumulated. Furthermore, the data accumulation method can be adjusted according to the user's emotions. This makes it possible to adjust the data accumulation method according to the user's emotions. For example, the data accumulation unit can analyze the user's emotions in real time and provide an appropriate data accumulation method.

[0109] When accumulating data, the data accumulation unit can improve the accuracy of accumulation by referring to the user's past data. The data accumulation unit uses AI to refer to the user's past data. For example, the data accumulation unit accumulates the user's past data as text data, and AI analyzes the data to improve the accuracy of accumulation. For example, the accuracy of accumulation can be improved based on data previously provided by the user. In addition, the user's past data can be analyzed and appropriate data can be accumulated. Furthermore, the accuracy of accumulation can be optimized by referring to the user's past data. This makes it possible to improve the accuracy of accumulation based on the user's past data. For example, the data accumulation unit can analyze the user's past data in real time and provide an appropriate data accumulation method.

[0110] The data accumulation unit can evaluate the reliability of the user's data and filter out unreliable data when accumulating the data. The data accumulation unit uses AI to evaluate the reliability of the user's data. For example, the data accumulation unit can evaluate the reliability of the user's data based on the consistency of the data, the source of the data, etc. The AI ​​can evaluate the reliability of the user's data and filter out unreliable data using text generation AI (e.g., LLM). For example, the AI ​​can analyze the user's data and automatically filter out unreliable data. The reliability of the user's data can also be evaluated and reliable data can be preferentially accumulated. Furthermore, the reliability of the user's data can be evaluated in real time and appropriate data can be accumulated. This enables filtering based on the reliability of the user's data. For example, the data accumulation unit can analyze the reliability of the user's data in real time and provide an appropriate data accumulation method.

[0111] The data accumulation unit can estimate the user's emotions and adjust the timing of data accumulation based on the estimated user's emotions. The data accumulation unit estimates the user's emotions using AI. For example, the data accumulation unit can estimate the user's emotions using facial expression analysis or voice analysis. The AI ​​can adjust the timing of data accumulation according to the user's emotions using text generation AI (e.g., LLM). For example, if the user is feeling anxious, data can be accumulated quickly. Also, if the user is relaxed, detailed data can be accumulated. Furthermore, the timing of data accumulation can be adjusted according to the user's emotions. This makes it possible to adjust the timing of data accumulation according to the user's emotions. For example, the data accumulation unit can analyze the user's emotions in real time and provide appropriate timing for data accumulation.

[0112] When storing data, the data storage unit can select an appropriate storage method based on the user's device information. The data storage unit uses AI to take the user's device information into consideration. For example, the data storage unit stores the user's device information as data, and the AI ​​analyzes that data to select the optimal storage method. For example, if the user is using a smartphone, touch input can be prioritized. Also, if the user is using a PC, keyboard input can be prioritized. Furthermore, the user's device information can be analyzed to select the optimal storage method. This makes it possible to select the optimal storage method based on the user's device information. For example, the data storage unit can analyze the user's device information in real time and provide the appropriate storage method.

[0113] The data accumulation unit can accumulate data in multiple languages ​​according to the user's language setting when accumulating data. The data accumulation unit uses AI to take the user's language setting into consideration. For example, the data accumulation unit accumulates the language setting of the user's device as data, and the AI ​​analyzes the data to accumulate data in multiple languages. For example, the data accumulation language can be automatically set based on the language setting of the user's device. In addition, if the user uses multiple languages, a language switching function can be provided. Furthermore, if the user selects a specific language, data accumulation can be performed in that language. This enables data accumulation in multiple languages ​​based on the user's language setting. For example, the data accumulation unit can analyze the user's language setting in real time and provide data accumulation in the appropriate language.

[0114] The diagnostic result providing unit can estimate the user's emotions and adjust the method of providing the diagnostic results based on the estimated user's emotions. The diagnostic result providing unit estimates the user's emotions using AI. For example, the diagnostic result providing unit can estimate the user's emotions using facial expression analysis or voice analysis. The AI ​​can adjust the method of providing the diagnostic results according to the user's emotions using text generation AI (e.g., LLM). For example, if the user is feeling anxious, the diagnostic results can be provided in a gentle tone. Furthermore, if the user is relaxed, detailed diagnostic results can be provided. Furthermore, if the user is in a hurry, concise diagnostic results can be provided. This makes it possible to adjust the method of providing the diagnostic results according to the user's emotions. For example, the diagnostic result providing unit can analyze the user's emotions in real time and provide an appropriate method of providing the diagnostic results.

[0115] When providing a diagnostic result, the diagnostic result providing unit can improve the accuracy of the provided result by referring to the user's past diagnostic results. The diagnostic result providing unit uses AI to refer to the user's past diagnostic results. For example, the diagnostic result providing unit accumulates the user's past diagnostic results as text data, and the AI ​​analyzes the data to improve the accuracy of the provided result. For example, the accuracy of the provided result can be improved based on the diagnostic results the user has received in the past. In addition, the user's past diagnostic results can be analyzed and appropriate feedback can be provided. Furthermore, the accuracy of the provided result can be optimized by referring to the user's past diagnostic results. This makes it possible to improve the accuracy of the provided result based on the user's past diagnostic results. For example, the diagnostic result providing unit can analyze the user's past diagnostic results in real time and provide an appropriate diagnostic result.

[0116] When providing a diagnostic result, the diagnostic result providing unit can analyze the user's current psychological state in real time and provide an appropriate diagnostic result. The diagnostic result providing unit uses AI to analyze the user's current psychological state in real time. For example, the diagnostic result providing unit can analyze the user's psychological state in real time using facial expression analysis or voice analysis. The AI ​​can provide a diagnostic result according to the user's psychological state using a text generation AI (e.g., LLM). For example, if the user is feeling stressed, a diagnostic result including advice on stress reduction can be provided. Furthermore, if the user is relaxed, a detailed diagnostic result can be provided. Furthermore, the user's psychological state can be analyzed in real time and an appropriate diagnostic result can be provided. This makes it possible to provide an optimal diagnostic result based on the user's psychological state. For example, the diagnostic result providing unit can analyze the user's psychological state in real time and provide an appropriate diagnostic result.

[0117] The diagnostic result providing unit can estimate the user's emotions and adjust the timing of providing the diagnostic result based on the estimated user's emotions. The diagnostic result providing unit estimates the user's emotions using AI. For example, the diagnostic result providing unit can estimate the user's emotions using facial expression analysis or voice analysis. The AI ​​can adjust the timing of providing the diagnostic result according to the user's emotions using a text generation AI (e.g., LLM). For example, if the user is feeling anxious, the diagnostic result can be provided at a slower pace. On the other hand, if the user is relaxed, the diagnostic result can be provided quickly. Furthermore, the timing of providing the diagnostic result can be adjusted according to the user's emotions. This makes it possible to adjust the timing of providing the diagnostic result according to the user's emotions. For example, the diagnostic result providing unit can analyze the user's emotions in real time and provide an appropriate timing for providing the diagnostic result.

[0118] When providing diagnostic results, the diagnostic result providing unit can select an appropriate delivery method based on the user's device information. The diagnostic result providing unit uses AI to take the user's device information into consideration. For example, the diagnostic result providing unit accumulates the user's device information as data, and the AI ​​analyzes the data to select the optimal delivery method. For example, if the user is using a smartphone, a display method tailored to the screen size can be provided. Also, if the user is using a PC, a display method optimized for a large screen can be provided. Furthermore, the user's device information can be analyzed to select the optimal delivery method. This makes it possible to select the optimal delivery method based on the user's device information. For example, the diagnostic result providing unit can analyze the user's device information in real time and provide the appropriate delivery method.

[0119] When providing diagnostic results, the diagnostic result providing unit can provide multilingual diagnostic results according to the user's language setting. The diagnostic result providing unit uses AI to take the user's language setting into consideration. For example, the diagnostic result providing unit accumulates the language setting of the user's device as data, and the AI ​​analyzes the data to provide multilingual diagnostic results. For example, the language of the diagnostic results can be automatically set based on the language setting of the user's device. In addition, if the user uses multiple languages, a language switching function can be provided. Furthermore, if the user selects a specific language, the diagnostic results can be provided in that language. This makes it possible to provide multilingual diagnostic results based on the user's language setting. For example, the diagnostic result providing unit can analyze the user's language setting in real time and provide diagnostic results in the appropriate language.

[0120] When providing a diagnostic result, the diagnostic result providing unit can analyze the user's social media activity and provide related information. The diagnostic result providing unit uses AI to analyze the user's social media activity. For example, the diagnostic result providing unit accumulates data such as the user's social media posts, the number of likes, and the number of followers, and the AI ​​analyzes the data to provide related information. For example, the diagnostic result providing unit can provide information about the locations where the user checked in on social media. The diagnostic result providing unit can also analyze the user's social media posts and provide related advice. Furthermore, the diagnostic result providing unit can provide related information by referring to the activities of the user's friends on social media. This makes it possible to provide related information based on the user's social media activity. For example, the diagnostic result providing unit can analyze the user's social media activity in real time and provide appropriate information. === Hard Collateral 1-1 === Each of the multiple elements including the question generation unit, answer reception unit, image generation unit, hearing unit, data accumulation unit, and diagnostic result providing unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the question generation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The answer reception unit is realized by the reception device 38 of the smart device 14 or the specific processing unit 290 of the data processing device 12. The image generation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The hearing unit is realized by the microphone 38B of the smart device 14 or the specific processing unit 290 of the data processing device 12. The data accumulation unit is realized by the database 24 of the data processing device 12. The diagnostic result providing unit is realized by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the question generation unit, answer reception unit, image generation unit, hearing unit, data accumulation unit, and diagnostic result provision unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the question generation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The answer reception unit is realized by the microphone 238 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The image generation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The hearing unit is realized by the microphone 238 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The data accumulation unit is realized by the database 24 of the data processing device 12. The diagnostic result provision unit is realized by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the question generation unit, answer reception unit, image generation unit, hearing unit, data accumulation unit, and diagnostic result provision unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the question generation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The answer reception unit is realized by the microphone 238 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The image generation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The hearing unit is realized by the microphone 238 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The data accumulation unit is realized by the database 24 of the data processing device 12. The diagnostic result provision unit is realized by the display 343 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the question generation unit, answer reception unit, image generation unit, hearing unit, data accumulation unit, and diagnostic result provision unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the question generation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The answer reception unit is realized by the microphone 238 of the robot 414 or the specific processing unit 290 of the data processing device 12. The image generation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The hearing unit is realized by the microphone 238 of the robot 414 or the specific processing unit 290 of the data processing device 12. The data accumulation unit is realized by the database 24 of the data processing device 12. The diagnostic result provision unit is realized by the speaker 240 of the robot 414 or the specific processing unit 290 of the data processing device 12.

[0121] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0122] The diagnostic system may further include a voice analysis unit. The voice analysis unit analyzes the user's voice data and can infer the user's emotions and psychological state from the tone, speed, rhythm, etc. of the voice. For example, if the user's voice tone is low and the speed is slow when answering questions, the voice analysis unit can infer that the user may be depressed. Furthermore, if the voice rhythm is irregular, it can determine that the user may be feeling stressed or anxious. Furthermore, the voice analysis unit can monitor changes in the user's voice in real time and provide data to improve the accuracy of the entire diagnostic system. This allows the voice analysis unit to more accurately grasp the user's emotions and psychological state and provide appropriate questions and feedback.

[0123] The diagnostic system may further include a behavior analysis unit. The behavior analysis unit analyzes data acquired from the user's smartphone or wearable device to understand the user's daily behavioral patterns and activity level. For example, the behavior analysis unit can collect data such as the user's number of steps, sleep time, and heart rate, and estimate the user's health and psychological state based on this data. The behavior analysis unit can also detect changes in the user's behavioral patterns and issue an alert if an abnormality is detected. Furthermore, the behavior analysis unit can accumulate the user's behavioral data and analyze long-term trends to help with early detection of mental abnormalities. This allows the behavior analysis unit to provide a highly accurate diagnosis based on the user's behavioral data.

[0124] The diagnostic system may further include a biometrics analysis unit. The biometrics analysis unit may analyze the user's biometric data and estimate the user's health and psychological state. For example, the biometrics analysis unit may collect data such as the user's heart rate, blood pressure, and electrodermal activity, and evaluate the user's stress level and relaxation level based on this data. The biometrics analysis unit may also monitor changes in the user's biometric data in real time and issue an alert if an abnormality is detected. Furthermore, the biometrics analysis unit may accumulate the user's biometric data and analyze long-term health trends, which may be useful for early detection of mental abnormalities. This allows the biometrics analysis unit to provide highly accurate diagnoses based on the user's biometric data.

[0125] The diagnostic system may further include an environmental data analysis unit. The environmental data analysis unit may collect and analyze environmental data surrounding the user. For example, the environmental data analysis unit may collect data such as temperature, humidity, noise level, and light intensity of the user's living environment and evaluate the impact on the user's psychological state and health based on this data. The environmental data analysis unit may also monitor changes in the user's environmental data in real time and issue an alert if an abnormality is detected. Furthermore, the environmental data analysis unit may accumulate the user's environmental data and analyze long-term trends to help with early detection of mental abnormalities. This allows the environmental data analysis unit to provide a highly accurate diagnosis based on the user's environmental data.

[0126] The diagnostic system may further include a social interaction analysis unit. The social interaction analysis unit may analyze data from the user's social media and messaging apps to understand the user's social interaction patterns. For example, the social interaction analysis unit may analyze how frequently the user exchanges messages with friends and the content of their posts, and based on this data, the system may evaluate the user's psychological state and level of social isolation. The social interaction analysis unit may also detect changes in the user's interaction patterns and issue an alert if an abnormality is detected. Furthermore, the social interaction analysis unit may accumulate user interaction data and analyze long-term trends to help with early detection of mental disorders. This allows the social interaction analysis unit to provide highly accurate diagnoses based on the user's social interaction data.

[0127] The diagnostic system may further include an emotion feedback unit. The emotion feedback unit may estimate the user's emotion and provide feedback based on the estimated emotion. For example, if the user feels anxious, the emotion feedback unit may provide relaxation advice or relaxation music. If the user feels stressed, the emotion feedback unit may suggest breathing techniques or simple exercises to reduce stress. If the user feels depressed, the emotion feedback unit may provide positive messages or words of encouragement. In this way, the emotion feedback unit may provide appropriate feedback according to the user's emotion and improve the user's psychological state.

[0128] The diagnostic system may further include an emotion history analysis unit. The emotion history analysis unit can accumulate and analyze the user's past emotion data. For example, it can analyze the emotion patterns of the user's past emotions. The emotion history analysis unit can also grasp the user's emotion trends based on the past emotion data and issue an alert if an abnormality is detected. Furthermore, the emotion history analysis unit can predict future emotion changes based on the user's emotion data and provide appropriate feedback. This allows the emotion history analysis unit to provide a highly accurate diagnosis based on the user's past emotion data.

[0129] The diagnostic system may further include an emotion prediction unit. The emotion prediction unit can predict future changes in emotion based on the user's current emotion data. For example, if the user is currently feeling stressed, it can predict that stress may increase in the future and take measures early. Also, if the user is currently relaxed, it can provide advice on how to maintain that state. Furthermore, the emotion prediction unit can provide appropriate feedback in accordance with changes in emotion based on the user's emotion data. In this way, the emotion prediction unit can predict changes in the user's emotion and take measures early, thereby helping to prevent mental disorders.

[0130] The diagnostic system may further include an emotion sharing unit. The emotion sharing unit may provide a function for a user to share his / her emotions with others. For example, the user may share his / her emotions with family and friends and receive support. The emotion sharing unit may also provide a platform for a user to connect with other users who are experiencing similar emotions. Furthermore, the emotion sharing unit may reduce a user's sense of isolation by sharing his / her emotions and allow the user to receive psychological support. In this way, the emotion sharing unit may allow a user to maintain mental health by sharing his / her emotions with others and receiving support.

[0131] The diagnostic system may further include an emotion training unit. The emotion training unit may provide training to help the user control their emotions. For example, when the user feels stressed, the user may learn breathing and relaxation techniques to reduce stress. Also, when the user feels anxious, the user may learn cognitive behavioral therapy techniques to relieve anxiety. Furthermore, the emotion training unit may provide the user with mindfulness and meditation methods to increase positive emotions. In this way, the emotion training unit allows the user to acquire skills to control their emotions and maintain mental health.

[0132] The processing flow of the second embodiment will be briefly explained below.

[0133] Step 1: The question generation unit generates questions using generation AI. For example, it generates appropriate questions based on questions and answers that psychological counselors have heard in conversations with patients with mental disorders. The generation AI can generate questions using text generation AI (e.g., LLM). It can also generate questions that correspond to the user's emotions and psychological state. Step 2: The answer acceptance unit accepts the user's answer based on the question generated by the generation AI. For example, answers can be accepted in text or audio format. It can also analyze the user's answer in real time and provide appropriate feedback. Step 3: The image generation unit uses generation AI to generate an image based on the user's response. For example, if the user responds "I can't sleep," it generates an image that symbolizes insomnia. The generation AI can generate images from text data using multimodal generation AI. Step 4: The hearing department collects user feedback after viewing the image generated by the AI. For example, they ask questions such as, "How do you feel when you see this image?"

[0134] 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.

[0135] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0136] 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.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0155] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 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 identification processing unit 290 using these models.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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).

[0191] 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.

[0192] 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."

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] [Explanation of symbols]

[0206] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a question generator that generates a question; an answer receiving unit that receives an answer based on the question generated by the question generating unit; an image generating unit that generates an image based on the answer received by the answer receiving unit; A hearing unit is provided to collect user feedback on the image generated by the image generating unit. A system characterized by:

2. Equipped with a data storage unit that stores data 2. The system of claim 1.

3. A diagnostic result providing unit is provided to provide diagnostic results.

2. The system of claim 1.

4. The question generation unit Estimate the user's emotions and adjust the content and wording of questions based on the estimated user emotions.

2. The system of claim 1.

5. The question generation unit When generating questions, adjust the difficulty of the questions by referring to the user's past answer history.

2. The system of claim 1.

6. The question generation unit When generating questions, customize the content of the questions according to the user's age and gender.

2. The system of claim 1.

7. The question generation unit When generating questions, the system analyzes the user's current psychological state in real time and generates appropriate questions.

2. The system of claim 1.

8. The question generation unit Infer user sentiment and adjust question order based on the estimated sentiment 2. The system of claim 1.

9. The question generation unit Generate questions based on the user's geographic and cultural background 2. The system of claim 1.

Images