System

Abstract

An object of the system according to the embodiment is to analyze a facial expression of a user and optimize a prompt of a generation AI.SOLUTION: A system according to an embodiment includes a facial expression analysis unit, a prompt generation unit, and a storage unit. The facial expression analysis unit analyzes a facial expression of the user. The prompt generation part generates addition correction information of the prompt on the basis of the expression analyzed by the expression analysis part. The storage unit stores the addition correction information of the prompt generated by the prompt 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 technologies do not adequately optimize prompts to increase satisfaction and understanding of the answers that users of AI generation receive, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze the user's facial expressions and optimize the prompts of the generation AI. [Means for solving the problem]

[0006] A system according to an embodiment includes a facial expression analysis unit, a prompt generation unit, and a storage unit. The facial expression analysis unit analyzes a user's facial expression. The prompt generation unit generates prompt revision information based on the facial expression analyzed by the facial expression analysis unit. The storage unit stores the prompt revision information generated by the prompt generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze the user's facial expressions and optimize the prompts of the generating AI. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The prompt optimization system according to an embodiment of the present invention analyzes the facial expressions of a user while using a generation AI and optimizes the generation AI's prompts based on the facial expressions. This allows the prompt optimization system to optimize prompts based on the user's facial expressions, improving the user experience of the generation AI.

[0029] A prompt optimization system according to an embodiment includes an expression analysis unit, a prompt generation unit, and a storage unit. The expression analysis unit analyzes a user's expression. For example, the expression analysis unit analyzes the user's expression in real time using facial recognition technology. The expression analysis unit can also extract facial feature points and estimate emotions. The expression analysis unit can also capture the user's expression with a camera and analyze the image data. The prompt generation unit generates prompt revision information based on the expression analyzed by the expression analysis unit. For example, if the user shows a confused expression, the prompt generation unit can simplify the prompt based on the expression. If the user shows a satisfied expression, the prompt generation unit can maintain the prompt as is based on the expression. If the user shows an angry expression, the prompt generation unit can make the prompt more polite based on the expression. The storage unit stores the prompt revision information generated by the prompt generation unit. For example, the storage unit records what prompts are generated when the user shows what expressions. The storage unit can also store the prompt revision information generated based on the user's expressions in a database. The storage unit can also analyze the relationship between the user's facial expression and the prompt's additional correction information and store the data. This allows the prompt optimization system according to the embodiment to optimize prompts based on the user's facial expression, improving the user experience of the generation AI. For example, if the user is confused, the prompt optimization system can provide a more understandable answer and increase satisfaction. Furthermore, if the user is satisfied, the system can generate a prompt to maintain that state. This is expected to improve the user experience of the generation AI and increase user satisfaction and satisfaction.

[0030] The facial expression analysis unit can analyze a user's past behavioral history and usage patterns and store the association between facial expressions and actions. For example, the facial expression analysis unit analyzes the user's past behavioral history when using the generative AI and stores the association between specific facial expressions and actions. For example, it records how often the user inputs questions with a smile and saves that pattern. The facial expression analysis unit also analyzes the user's behavioral pattern when they are confused and stores the association between facial expressions and actions. For example, it records the user's tendency to repeatedly input questions when showing a confused expression. The facial expression analysis unit also analyzes the user's behavioral history when they are satisfied and stores the association between facial expressions and actions. For example, it records the user's tendency to quickly accept the generative AI's answers when showing a satisfied expression. In this way, by analyzing the user's past behavioral history and usage patterns, it is possible to store the association between facial expressions and actions and further optimize the generative AI's prompts.

[0031] The facial expression analysis unit can analyze a user's facial expressions consistently across different devices and integrate data across devices. For example, the facial expression analysis unit records facial expression analysis data when a user uses the generative AI on a smartphone and integrates it with data from other devices. For example, facial expression data from smartphone use is integrated with data from PC use. The facial expression analysis unit also records facial expression analysis data from tablet use and integrates it with data from smartphones and PCs. For example, facial expression data from tablet use is consistently saved with data from other devices. The facial expression analysis unit also integrates facial expression analysis data from different devices in real time and consistently stores the user's emotional information. For example, data from smartphones, tablets, and PCs is integrated and comprehensive emotional information is saved. In this way, by integrating facial expression analysis data from different devices, the user's emotional information can be consistently saved and the generative AI's prompts can be further optimized.

[0032] The prompt generation unit can infer the intent and purpose of the question based on an analysis of the user's facial expression and generate additional prompt revision information accordingly. For example, if the user has a serious expression, the prompt generation unit infers the intent of the question based on the expression and generates additional prompt revision information. For example, a prompt requesting a detailed explanation is added. Also, if the user has a confused expression, the prompt generation unit infers the intent of the question based on the expression and generates additional prompt revision information. For example, a prompt requesting a concise answer is added. Also, if the user is smiling, the prompt generation unit infers the intent of the question based on the expression and generates additional prompt revision information. For example, a prompt requesting a positive answer is added. In this way, the intent and purpose of the question can be inferred based on an analysis of the user's facial expression and the corresponding additional prompt revision information can be generated, thereby improving the quality of the answers provided by the generation AI.

[0033] The prompt generation unit can compare the user's facial expression with past question history and automatically suggest the optimal prompt for a similar question. For example, when a user inputs a new question, the prompt generation unit compares the user's facial expression with past question history and suggests the optimal prompt for a similar question. For example, it refers to prompts from similar questions asked in the past. Furthermore, if the user shows a confused expression, the prompt generation unit suggests the optimal prompt based on the past question history. For example, it refers to prompts from past confused times. Furthermore, if the user shows a smiling face, the prompt generation unit suggests the optimal prompt based on the past question history. For example, it refers to prompts from past satisfied times. In this way, by comparing the user's facial expression with the past question history and automatically suggesting the optimal prompt for a similar question, the quality of the answers provided by the generation AI is improved.

[0034] The prompt generation unit can infer the urgency and importance of a question by analyzing the input speed and typing rhythm in addition to analyzing the user's facial expression. For example, the prompt generation unit analyzes the input speed in addition to analyzing the user's facial expression when inputting a question to infer the urgency of the question. For example, if the input speed is fast, it determines that the urgency is high. The prompt generation unit also analyzes the typing rhythm to infer the importance of the question. For example, if the typing is intermittent, it determines that the importance is high. The prompt generation unit also combines the facial expression analysis with the input speed and typing rhythm to comprehensively infer the urgency and importance of the question. For example, if the input speed is fast and the facial expression is serious, it determines that the urgency is high. In this way, by analyzing the input speed and typing rhythm in addition to analyzing the user's facial expression, the urgency and importance of a question can be inferred, improving the quality of the answer provided by the generation AI.

[0035] The prompt generation unit can provide feedback to optimize the prompts of the generation AI in real time when the user inputs a question. The prompt generation unit provides feedback to optimize the prompts of the generation AI in real time when the user inputs a question. For example, it presents suggested modifications to the prompt depending on the input content. The prompt generation unit also provides feedback in real time based on facial expression analysis when the user inputs a question. For example, if the user shows a confused expression, it presents suggested modifications to the prompt. The prompt generation unit also provides feedback in real time using an emotion estimation function when the user inputs a question. For example, if the user is nervous, it presents suggested modifications to the prompt to help them relax. In this way, by providing feedback to optimize the prompts of the generation AI in real time when the user inputs a question, the quality of the answers of the generation AI is improved.

[0036] The memory unit can analyze the user's behavior after the answer (e.g., asking a follow-up question, scrolling the page) and evaluate satisfaction with the answer. For example, the memory unit analyzes the user's behavior after receiving the answer from the generation AI and evaluates satisfaction with the answer. For example, if the user asks a follow-up question, it determines that satisfaction is low. The memory unit also analyzes the page scrolling behavior after the user receives the answer from the generation AI and evaluates satisfaction with the answer. For example, if the user scrolls the page immediately after answering, it determines that satisfaction is low. The memory unit also comprehensively analyzes the user's behavior after receiving the answer from the generation AI and evaluates satisfaction with the answer. For example, if the user frequently asks a follow-up question or scrolls the page after answering, it determines that satisfaction is low. In this way, by analyzing the user's behavior after the answer, satisfaction with the answer can be evaluated and the generation AI's prompts can be further optimized.

[0037] The memory unit can consistently analyze facial expressions after a user's answer across different devices and integrate data across devices. For example, the memory unit records facial expression analysis data after a user receives the generation AI's answer on a smartphone and integrates it with data from other devices. For example, the memory unit integrates facial expression data from use on a smartphone with data from use on a PC. The memory unit also records facial expression analysis data from use on a tablet and integrates it with data from the smartphone and PC. For example, the memory unit consistently stores facial expression data from use on a tablet with data from other devices. The memory unit also integrates facial expression analysis data from different devices in real time and consistently stores the user's emotional information. For example, the memory unit integrates data from a smartphone, tablet, and PC and stores comprehensive emotional information. In this way, by integrating facial expression analysis data from different devices, the user's emotional information can be consistently stored and the generation AI's prompts can be further optimized.

[0038] The memory unit can use the information ABC to analyze the user's past emotional patterns and predict the optimal prompt for a future question. The memory unit, for example, uses the information ABC to analyze the user's past emotional patterns and predict the optimal prompt for a future question. For example, the memory unit adjusts the next prompt based on prompts that were satisfactory in the past. The memory unit also analyzes the user's past emotional patterns and builds a system that predicts the optimal prompt for a future question. For example, the memory unit automatically generates optimal prompts based on past data. The memory unit also uses the information ABC to develop an algorithm that analyzes the user's emotional patterns and predicts the optimal prompt for a future question. For example, the memory unit predicts prompts based on past emotional data. In this way, the quality of the answers provided by the generation AI is improved by analyzing the user's past emotional patterns and predicting the optimal prompt for a future question.

[0039] The memory unit can generate customized prompts that reflect the user's individual preferences and interests based on the information ABC. The memory unit generates customized prompts that reflect the user's individual preferences and interests based on, for example, the information ABC. For example, it generates prompts related to topics that interest the user. The memory unit also builds a system that generates customized prompts that reflect the user's individual preferences and interests based on the user's past data. For example, it adjusts prompts based on past question history. The memory unit also uses the information ABC to develop an algorithm that generates customized prompts that reflect the user's preferences and interests. For example, it customizes prompts based on past emotional data. In this way, the quality of the answers provided by the generation AI is improved by generating customized prompts that reflect the user's individual preferences and interests.

[0040] The memory unit can use information ABC to optimize prompts across different generative AI platforms and maintain cross-platform consistency. The memory unit, for example, uses information ABC to optimize prompts across different generative AI platforms and build a system that maintains consistency. For example, the same prompts are used on smartphones and PCs. The memory unit also develops an algorithm that optimizes prompts across different generative AI platforms and maintains cross-platform consistency. For example, the same prompts are used on tablets and PCs. The memory unit also uses information ABC to optimize prompts across different generative AI platforms and build a system that maintains consistency. For example, the same prompts are used on smartphones, tablets, and PCs. This optimizes prompts across different generative AI platforms and maintains cross-platform consistency, thereby improving the quality of the generative AI's answers.

[0041] The memory unit can create a prompt template according to the user's emotional state based on the information ABC and quickly apply it. The memory unit, for example, creates a prompt template according to the user's emotional state based on the information ABC and builds a system that quickly applies it. For example, if the user shows a confused expression, a concise prompt is used. The memory unit also develops an algorithm that creates a prompt template based on the user's emotional state and quickly applies it. For example, if the user shows a satisfied expression, the prompt is used as is. The memory unit also uses the information ABC to create a prompt template according to the user's emotional state and builds a system that quickly applies it. For example, if the user shows anger, a polite prompt is used. In this way, by quickly applying a prompt template according to the user's emotional state, the quality of the answers provided by the generation AI is improved.

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

[0043] The prompt generation unit can infer the urgency and importance of a question by analyzing the user's facial expression, as well as the input speed and typing rhythm. For example, in addition to analyzing the user's facial expression when entering a question, it can analyze the input speed to infer the urgency of the question. For example, if the input speed is fast, it can determine that the urgency is high. The prompt generation unit also analyzes the typing rhythm to infer the importance of the question. For example, if the typing is intermittent, it can determine that the importance is high. The prompt generation unit also combines the facial expression analysis with the input speed and typing rhythm to comprehensively infer the urgency and importance of the question. For example, if the input speed is fast and the facial expression is serious, it can determine that the urgency is high. In this way, by analyzing the input speed and typing rhythm in addition to analyzing the user's facial expression, the urgency and importance of a question can be inferred, improving the quality of the answer provided by the generation AI.

[0044] The memory unit can analyze the user's behavior after answering an answer (e.g., asking a follow-up question, scrolling the page) and evaluate satisfaction with the answer. For example, the memory unit analyzes the user's behavior after receiving the answer from the generating AI and evaluates satisfaction with the answer. For example, if the user asks a follow-up question, it determines that satisfaction is low. The memory unit also analyzes the user's page scrolling behavior after receiving the answer from the generating AI and evaluates satisfaction with the answer. For example, if the user scrolls the page immediately after answering, it determines that satisfaction is low. The memory unit also comprehensively analyzes the user's behavior after receiving the answer from the generating AI and evaluates satisfaction with the answer. For example, if the user frequently asks a follow-up question or scrolls the page after answering, it determines that satisfaction is low. In this way, by analyzing the user's behavior after answering, satisfaction with the answer can be evaluated and the prompts of the generating AI can be further optimized.

[0045] The memory unit can consistently analyze facial expressions after a user's response across different devices and integrate data across devices. For example, it records facial expression analysis data after a user receives the generation AI's response on a smartphone and integrates it with data from other devices. For example, it integrates facial expression data from smartphone use with data from PC use. The memory unit also records facial expression analysis data from tablet use and integrates it with data from smartphones and PCs. For example, it consistently stores facial expression data from tablet use with data from other devices. The memory unit also integrates facial expression analysis data from different devices in real time and consistently stores the user's emotional information. For example, it integrates data from smartphones, tablets, and PCs and stores comprehensive emotional information. In this way, by integrating facial expression analysis data from different devices, it can consistently store the user's emotional information and further optimize the generation AI's prompts.

[0046] The processing flow of the first embodiment will be briefly explained below.

[0047] Step 1: The facial expression analysis unit analyzes the user's facial expression. For example, the facial expression analysis unit analyzes the user's facial expression in real time using face recognition technology. The facial expression analysis unit can also extract facial feature points and estimate emotions. The facial expression analysis unit can also capture the user's facial expression with a camera and analyze the image data. Step 2: The prompt generation unit generates additional correction information for the prompt based on the facial expression analyzed by the facial expression analysis unit. For example, if the user shows a confused facial expression, the prompt generation unit may simplify the prompt based on the facial expression. Alternatively, if the user shows a satisfied facial expression, the prompt generation unit may maintain the prompt as is based on the facial expression. Alternatively, if the user shows an angry facial expression, the prompt generation unit may make the prompt more polite based on the facial expression. Step 3: The storage unit stores the prompt revision information generated by the prompt generation unit. For example, the storage unit records what prompt was generated when the user showed what facial expression. The storage unit can also store the prompt revision information generated based on the user's facial expression in a database. The storage unit can also analyze the relationship between the user's facial expression and the prompt revision information and accumulate the data.

[0048] (Example 2) The prompt optimization system according to an embodiment of the present invention analyzes the facial expressions of a user while using a generation AI and optimizes the generation AI's prompts based on the facial expressions. This allows the prompt optimization system to optimize prompts based on the user's facial expressions, improving the user experience of the generation AI.

[0049] A prompt optimization system according to an embodiment includes an expression analysis unit, a prompt generation unit, and a storage unit. The expression analysis unit analyzes a user's expression. For example, the expression analysis unit analyzes the user's expression in real time using facial recognition technology. The expression analysis unit can also extract facial feature points and estimate emotions. The expression analysis unit can also capture the user's expression with a camera and analyze the image data. The prompt generation unit generates prompt revision information based on the expression analyzed by the expression analysis unit. For example, if the user shows a confused expression, the prompt generation unit can simplify the prompt based on the expression. If the user shows a satisfied expression, the prompt generation unit can maintain the prompt as is based on the expression. If the user shows an angry expression, the prompt generation unit can make the prompt more polite based on the expression. The storage unit stores the prompt revision information generated by the prompt generation unit. For example, the storage unit records what prompts are generated when the user shows what expressions. The storage unit can also store the prompt revision information generated based on the user's expressions in a database. The storage unit can also analyze the relationship between the user's facial expression and the prompt's additional correction information and store the data. This allows the prompt optimization system according to the embodiment to optimize prompts based on the user's facial expression, improving the user experience of the generation AI. For example, if the user is confused, the prompt optimization system can provide a more understandable answer and increase satisfaction. Furthermore, if the user is satisfied, the system can generate a prompt to maintain that state. This is expected to improve the user experience of the generation AI and increase user satisfaction and satisfaction.

[0050] In addition to analyzing a user's facial expressions, the facial expression analysis unit also analyzes changes in voice tone and speaking style, allowing it to memorize more detailed emotional information. For example, while a user is using the generative AI, the facial expression analysis unit simultaneously analyzes their facial expressions and voice tone using a camera and microphone. For example, if the user is smiling while speaking, the unit records their smile and bright voice tone and saves them as emotional information. If the user is confused, the facial expression analysis unit not only analyzes their facial expressions but also analyzes changes in their speaking style. For example, it records changes in voice tone when the user repeats a question and quantifies the degree of confusion. If the user is angry with the generative AI, the facial expression analysis unit analyzes changes in voice intensity and speed along with their facial expressions, and memorizes the emotional information of anger in detail. For example, if the user's voice becomes louder and the speaking speed increases, the unit saves that data. This allows the generative AI to memorize the user's emotional information in more detail, further optimizing its prompts.

[0051] The facial expression analysis unit can analyze a user's past behavioral history and usage patterns and store the association between facial expressions and actions. For example, the facial expression analysis unit analyzes the user's past behavioral history when using the generative AI and stores the association between specific facial expressions and actions. For example, it records how often the user inputs questions with a smile and saves that pattern. The facial expression analysis unit also analyzes the user's behavioral pattern when they are confused and stores the association between facial expressions and actions. For example, it records the user's tendency to repeatedly input questions when showing a confused expression. The facial expression analysis unit also analyzes the user's behavioral history when they are satisfied and stores the association between facial expressions and actions. For example, it records the user's tendency to quickly accept the generative AI's answers when showing a satisfied expression. In this way, by analyzing the user's past behavioral history and usage patterns, it is possible to store the association between facial expressions and actions and further optimize the generative AI's prompts.

[0052] The facial expression analysis unit can use the emotion estimation function to track changes in the user's emotions in real time and store patterns of emotional changes. For example, the facial expression analysis unit uses the emotion estimation function to track changes in emotions in real time while the user is using the generative AI. For example, it records changes in emotions when the user inputs a question and saves the patterns. The facial expression analysis unit also tracks changes in emotions in real time when the user receives an answer from the generative AI and stores patterns of emotional changes. For example, it records changes in facial expression immediately after receiving an answer. The facial expression analysis unit also tracks changes in emotions in real time as the user uses the generative AI and stores the patterns of these changes. For example, it records in detail the process by which the user changes from confusion to satisfaction. This allows the generative AI's prompts to be further optimized by tracking changes in the user's emotions in real time and storing the patterns of these changes.

[0053] In addition to analyzing the user's facial expressions, the facial expression analysis unit can analyze biometric data such as heart rate and galvanic skin response to store emotional information. For example, while the user is using the generative AI, the facial expression analysis unit measures the heart rate and stores emotional information in combination with facial expression analysis. For example, it records facial expressions when the heart rate increases and saves emotions such as tension and excitement. The facial expression analysis unit also measures galvanic skin response and stores emotional information in combination with facial expression analysis. For example, it records facial expressions when the galvanic skin response increases and saves emotions such as stress and excitement. The facial expression analysis unit also simultaneously measures the heart rate and galvanic skin response and stores emotional information in combination with facial expression analysis. For example, it records facial expressions when the heart rate and galvanic skin response increase simultaneously and saves strong emotional changes. This allows the user's biometric data to be analyzed to store more detailed emotional information and further optimize the generative AI's prompts.

[0054] The facial expression analysis unit can analyze a user's facial expressions consistently across different devices and integrate data across devices. For example, the facial expression analysis unit records facial expression analysis data when a user uses the generative AI on a smartphone and integrates it with data from other devices. For example, facial expression data from smartphone use is integrated with data from PC use. The facial expression analysis unit also records facial expression analysis data from tablet use and integrates it with data from smartphones and PCs. For example, facial expression data from tablet use is consistently saved with data from other devices. The facial expression analysis unit also integrates facial expression analysis data from different devices in real time and consistently stores the user's emotional information. For example, data from smartphones, tablets, and PCs is integrated and comprehensive emotional information is saved. In this way, by integrating facial expression analysis data from different devices, the user's emotional information can be consistently saved and the generative AI's prompts can be further optimized.

[0055] The facial expression analysis unit can use the emotion estimation function to automatically adjust the optimal settings of the generation AI based on past data when the user shows a specific facial expression. For example, the facial expression analysis unit automatically adjusts the settings of the generation AI based on past data when the user shows a specific facial expression. For example, if the user shows a confused expression, the facial expression analysis unit can make the generation AI's responses more concise. The facial expression analysis unit also uses the emotion estimation function to adjust the settings of the generation AI based on past data when the user shows a smile. For example, if the user is satisfied, the generation AI's responses can be maintained as they are. The facial expression analysis unit also automatically adjusts the settings of the generation AI based on past data when the user shows anger. For example, if the user is angry, the generation AI's responses can be made more polite. This allows the generation AI's prompts to be further optimized by automatically adjusting the settings of the generation AI based on past data when the user shows a specific facial expression.

[0056] The prompt generation unit can infer the intent and purpose of the question based on an analysis of the user's facial expression and generate additional prompt revision information accordingly. For example, if the user has a serious expression, the prompt generation unit infers the intent of the question based on the expression and generates additional prompt revision information. For example, a prompt requesting a detailed explanation is added. Also, if the user has a confused expression, the prompt generation unit infers the intent of the question based on the expression and generates additional prompt revision information. For example, a prompt requesting a concise answer is added. Also, if the user is smiling, the prompt generation unit infers the intent of the question based on the expression and generates additional prompt revision information. For example, a prompt requesting a positive answer is added. In this way, the intent and purpose of the question can be inferred based on an analysis of the user's facial expression and the corresponding additional prompt revision information can be generated, thereby improving the quality of the answers provided by the generation AI.

[0057] The prompt generation unit can compare the user's facial expression with past question history and automatically suggest the optimal prompt for a similar question. For example, when a user inputs a new question, the prompt generation unit compares the user's facial expression with past question history and suggests the optimal prompt for a similar question. For example, it refers to prompts from similar questions asked in the past. Furthermore, if the user shows a confused expression, the prompt generation unit suggests the optimal prompt based on the past question history. For example, it refers to prompts from past confused times. Furthermore, if the user shows a smiling face, the prompt generation unit suggests the optimal prompt based on the past question history. For example, it refers to prompts from past satisfied times. In this way, by comparing the user's facial expression with the past question history and automatically suggesting the optimal prompt for a similar question, the quality of the answers provided by the generation AI is improved.

[0058] The prompt generation unit can use the emotion estimation function to analyze the emotional state of the user when inputting a question and generate additional correction information for the prompt according to that emotion. The prompt generation unit, for example, analyzes the emotional state of the user when inputting a question and generates additional correction information for the prompt according to that emotion. For example, if the user is nervous, it adds a prompt to relax. The prompt generation unit also analyzes the emotional state of the user when inputting a question using the emotion estimation function and generates additional correction information for the prompt according to that emotion. For example, if the user is excited, it adds a prompt to calm down. The prompt generation unit also analyzes the emotional state of the user when inputting a question in real time and generates additional correction information for the prompt according to that emotion. For example, if the user is sad, it adds a prompt to encourage them. In this way, by analyzing the emotional state of the user when inputting a question and generating additional correction information for the prompt according to that emotion, the quality of the answers provided by the generation AI is improved.

[0059] The prompt generation unit can infer the urgency and importance of a question by analyzing the input speed and typing rhythm in addition to analyzing the user's facial expression. For example, the prompt generation unit analyzes the input speed in addition to analyzing the user's facial expression when inputting a question to infer the urgency of the question. For example, if the input speed is fast, it determines that the urgency is high. The prompt generation unit also analyzes the typing rhythm to infer the importance of the question. For example, if the typing is intermittent, it determines that the importance is high. The prompt generation unit also combines the facial expression analysis with the input speed and typing rhythm to comprehensively infer the urgency and importance of the question. For example, if the input speed is fast and the facial expression is serious, it determines that the urgency is high. In this way, by analyzing the input speed and typing rhythm in addition to analyzing the user's facial expression, the urgency and importance of a question can be inferred, improving the quality of the answer provided by the generation AI.

[0060] The prompt generation unit can provide feedback to optimize the prompts of the generation AI in real time when the user inputs a question. The prompt generation unit provides feedback to optimize the prompts of the generation AI in real time when the user inputs a question. For example, it presents suggested modifications to the prompt depending on the input content. The prompt generation unit also provides feedback in real time based on facial expression analysis when the user inputs a question. For example, if the user shows a confused expression, it presents suggested modifications to the prompt. The prompt generation unit also provides feedback in real time using an emotion estimation function when the user inputs a question. For example, if the user is nervous, it presents suggested modifications to the prompt to help them relax. In this way, by providing feedback to optimize the prompts of the generation AI in real time when the user inputs a question, the quality of the answers of the generation AI is improved.

[0061] The prompt generation unit can use the emotion estimation function to adjust the response style of the generation AI based on the emotional state of the user when inputting a question. The prompt generation unit, for example, analyzes the emotional state of the user when inputting a question and adjusts the response style of the generation AI based on that emotion. For example, if the user is relaxed, it selects a casual response style. The prompt generation unit also uses the emotion estimation function to adjust the response style of the generation AI based on the emotional state of the user when inputting a question. For example, if the user is nervous, it selects a formal response style. The prompt generation unit also analyzes the emotional state of the user when inputting a question in real time and adjusts the response style of the generation AI based on that emotion. For example, if the user is excited, it selects a calm response style. In this way, adjusting the response style of the generation AI based on the emotional state of the user when inputting a question improves the quality of the answers of the generation AI.

[0062] The memory unit can analyze changes in voice tone and speaking style after an answer, in addition to analyzing the user's facial expressions, and store changes in emotion. For example, after a user receives an answer from the generation AI, the memory unit analyzes changes in voice tone along with facial expression analysis, and stores changes in emotion. For example, if the user's voice becomes brighter after an answer, the memory unit stores that data. The memory unit also analyzes changes in speaking style after a user receives an answer from the generation AI, and stores changes in emotion. For example, if the user's speaking speed increases after an answer, the memory unit stores that data. The memory unit also comprehensively analyzes changes in facial expression, voice tone, and speaking style after a user receives an answer from the generation AI, and stores changes in emotion. For example, if the user smiles after answering, the memory unit stores that data. This allows the memory unit to store changes in emotion by analyzing changes in voice tone and speaking style after an answer, in addition to analyzing the user's facial expressions, and to further optimize the generation AI's prompts.

[0063] The memory unit can analyze the user's behavior after the answer (e.g., asking a follow-up question, scrolling the page) and evaluate satisfaction with the answer. For example, the memory unit analyzes the user's behavior after receiving the answer from the generation AI and evaluates satisfaction with the answer. For example, if the user asks a follow-up question, it determines that satisfaction is low. The memory unit also analyzes the page scrolling behavior after the user receives the answer from the generation AI and evaluates satisfaction with the answer. For example, if the user scrolls the page immediately after answering, it determines that satisfaction is low. The memory unit also comprehensively analyzes the user's behavior after receiving the answer from the generation AI and evaluates satisfaction with the answer. For example, if the user frequently asks a follow-up question or scrolls the page after answering, it determines that satisfaction is low. In this way, by analyzing the user's behavior after the answer, satisfaction with the answer can be evaluated and the generation AI's prompts can be further optimized.

[0064] The memory unit can use the emotion estimation function to track the user's emotional state in real time after an answer is given and store the changes. For example, after the user receives an answer from the generation AI, the memory unit uses the emotion estimation function to track the emotional state in real time and store the changes. For example, if the user shows a satisfied expression after an answer, the memory unit stores the data. The memory unit also uses the emotion estimation function to track the emotional state in real time after the user receives an answer from the generation AI and store the changes. For example, if the user shows a confused expression after an answer, the memory unit stores the data. The memory unit also uses the emotion estimation function to track the emotional state in real time after the user receives an answer from the generation AI and store the changes. For example, if the user shows anger after an answer, the memory unit stores the data. This allows the memory unit to track the user's emotional state in real time after an answer is given and store the changes, thereby further optimizing the generation AI's prompts.

[0065] In addition to analyzing the user's facial expressions, the memory unit can analyze biometric data (heart rate, galvanic skin response) after the user answers and store changes in emotion. For example, the memory unit measures the user's heart rate after receiving the AI's answer and stores changes in emotion in combination with facial expression analysis. For example, if the user's heart rate increases after the answer, the memory unit stores the data. The memory unit also measures the user's galvanic skin response after receiving the AI's answer and stores changes in emotion in combination with facial expression analysis. For example, if the galvanic skin response increases after the answer, the memory unit stores the data. The memory unit also simultaneously measures the user's heart rate and galvanic skin response after receiving the AI's answer and stores changes in emotion in combination with facial expression analysis. For example, if the heart rate and galvanic skin response increase simultaneously after the answer, the memory unit stores the data. This allows the AI's prompts to be further optimized by analyzing the user's facial expressions and analyzing the biometric data after the answer.

[0066] The memory unit can consistently analyze facial expressions after a user's answer across different devices and integrate data across devices. For example, the memory unit records facial expression analysis data after a user receives the generation AI's answer on a smartphone and integrates it with data from other devices. For example, the memory unit integrates facial expression data from use on a smartphone with data from use on a PC. The memory unit also records facial expression analysis data from use on a tablet and integrates it with data from the smartphone and PC. For example, the memory unit consistently stores facial expression data from use on a tablet with data from other devices. The memory unit also integrates facial expression analysis data from different devices in real time and consistently stores the user's emotional information. For example, the memory unit integrates data from a smartphone, tablet, and PC and stores comprehensive emotional information. In this way, by integrating facial expression analysis data from different devices, the user's emotional information can be consistently stored and the generation AI's prompts can be further optimized.

[0067] The memory unit can use the emotion estimation function to suggest the optimal prompt for the next question based on the user's emotional state after answering the question. For example, the memory unit analyzes the user's emotional state after receiving the generation AI's answer and suggests the optimal prompt for the next question based on that data. For example, if the user shows a satisfied expression, the memory unit adjusts the next prompt based on that data. Furthermore, the memory unit uses the emotion estimation function to suggest the optimal prompt for the next question based on the data if the user shows a confused expression. For example, if the user shows a confused expression, the memory unit makes the next prompt shorter. Furthermore, the memory unit analyzes the user's emotional state after receiving the generation AI's answer in real time and suggests the optimal prompt for the next question based on that data. For example, if the user shows anger, the memory unit makes the next prompt more polite. In this way, the memory unit suggests the optimal prompt for the next question based on the user's emotional state after answering the question, thereby improving the quality of the generation AI's answers.

[0068] The memory unit can use the information ABC to analyze the user's past emotional patterns and predict the optimal prompt for a future question. The memory unit, for example, uses the information ABC to analyze the user's past emotional patterns and predict the optimal prompt for a future question. For example, the memory unit adjusts the next prompt based on prompts that were satisfactory in the past. The memory unit also analyzes the user's past emotional patterns and builds a system that predicts the optimal prompt for a future question. For example, the memory unit automatically generates optimal prompts based on past data. The memory unit also uses the information ABC to develop an algorithm that analyzes the user's emotional patterns and predicts the optimal prompt for a future question. For example, the memory unit predicts prompts based on past emotional data. In this way, the quality of the answers provided by the generation AI is improved by analyzing the user's past emotional patterns and predicting the optimal prompt for a future question.

[0069] The memory unit can generate customized prompts that reflect the user's individual preferences and interests based on the information ABC. The memory unit generates customized prompts that reflect the user's individual preferences and interests based on, for example, the information ABC. For example, it generates prompts related to topics that interest the user. The memory unit also builds a system that generates customized prompts that reflect the user's individual preferences and interests based on the user's past data. For example, it adjusts prompts based on past question history. The memory unit also uses the information ABC to develop an algorithm that generates customized prompts that reflect the user's preferences and interests. For example, it customizes prompts based on past emotional data. In this way, the quality of the answers provided by the generation AI is improved by generating customized prompts that reflect the user's individual preferences and interests.

[0070] The memory unit can use the emotion estimation function to develop a prompt optimization algorithm according to the user's emotional state and apply it in real time. The memory unit, for example, uses the emotion estimation function to develop a prompt optimization algorithm according to the user's emotional state and apply it in real time. For example, if the user is confused, the prompt is made brief. The memory unit also analyzes the user's emotional state in real time and applies a prompt optimization algorithm based on that data. For example, if the user is satisfied, the prompt is maintained as is. The memory unit also uses the emotion estimation function to build a system that applies a prompt optimization algorithm according to the user's emotional state in real time. For example, if the user is angry, the prompt is made more polite. In this way, by applying a prompt optimization algorithm according to the user's emotional state in real time, the quality of the answers provided by the generation AI is improved.

[0071] The memory unit can use information ABC to optimize prompts across different generative AI platforms and maintain cross-platform consistency. The memory unit, for example, uses information ABC to optimize prompts across different generative AI platforms and build a system that maintains consistency. For example, the same prompts are used on smartphones and PCs. The memory unit also develops an algorithm that optimizes prompts across different generative AI platforms and maintains cross-platform consistency. For example, the same prompts are used on tablets and PCs. The memory unit also uses information ABC to optimize prompts across different generative AI platforms and build a system that maintains consistency. For example, the same prompts are used on smartphones, tablets, and PCs. This optimizes prompts across different generative AI platforms and maintains cross-platform consistency, thereby improving the quality of the generative AI's answers.

[0072] The memory unit can create a prompt template according to the user's emotional state based on the information ABC and quickly apply it. The memory unit, for example, creates a prompt template according to the user's emotional state based on the information ABC and builds a system that quickly applies it. For example, if the user shows a confused expression, a concise prompt is used. The memory unit also develops an algorithm that creates a prompt template based on the user's emotional state and quickly applies it. For example, if the user shows a satisfied expression, the prompt is used as is. The memory unit also uses the information ABC to create a prompt template according to the user's emotional state and builds a system that quickly applies it. For example, if the user shows anger, a polite prompt is used. In this way, by quickly applying a prompt template according to the user's emotional state, the quality of the answers provided by the generation AI is improved.

[0073] The memory unit can use the emotion estimation function to dynamically adjust the response style and tone of the generation AI based on the user's emotional state. For example, the memory unit uses the emotion estimation function to build a system that dynamically adjusts the response style and tone of the generation AI based on the user's emotional state. For example, if the user is relaxed, a casual tone is used. The memory unit also analyzes the user's emotional state in real time and dynamically adjusts the response style and tone of the generation AI based on that data. For example, if the user is nervous, a formal tone is used. The memory unit also uses the emotion estimation function to develop an algorithm that dynamically adjusts the response style and tone of the generation AI based on the user's emotional state. For example, if the user is excited, a calm tone is used. In this way, the quality of the generation AI's answers is improved by dynamically adjusting the response style and tone of the generation AI based on the user's emotional state.

[0074] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0075] The prompt generation unit can infer the intent and purpose of the question based on an analysis of the user's facial expression and generate additional prompt revision information accordingly. For example, if the user has a serious expression, the prompt generation unit infers the intent of the question based on that expression and generates additional prompt revision information. For example, a prompt requesting a detailed explanation is added. Furthermore, if the user has a confused expression, the prompt generation unit infers the purpose of the question based on that expression and generates additional prompt revision information. For example, a prompt requesting a concise answer is added. Furthermore, if the user is smiling, the prompt generation unit infers the intent of the question based on that expression and generates additional prompt revision information. For example, a prompt requesting a positive answer is added. In this way, the intent and purpose of the question can be inferred based on an analysis of the user's facial expression and the corresponding additional prompt revision information can be generated, thereby improving the quality of the answers provided by the generation AI.

[0076] The prompt generation unit can compare the user's facial expression with past question history and automatically suggest the optimal prompt for a similar question. For example, when a user inputs a new question, the prompt generation unit compares the user's facial expression with past question history and suggests the optimal prompt for a similar question. For example, it refers to prompts from similar questions asked in the past. Furthermore, if the user shows a confused expression, the prompt generation unit suggests the optimal prompt based on the user's past question history. For example, it refers to prompts from past confused times. Furthermore, if the user shows a smiling face, the prompt generation unit suggests the optimal prompt based on the user's past question history. For example, it refers to prompts from past satisfied times. In this way, by comparing the user's facial expression with the user's past question history and automatically suggesting the optimal prompt for a similar question, the quality of the answers provided by the generation AI is improved.

[0077] The prompt generation unit can infer the urgency and importance of a question by analyzing the user's facial expression, as well as the input speed and typing rhythm. For example, in addition to analyzing the user's facial expression when entering a question, it can analyze the input speed to infer the urgency of the question. For example, if the input speed is fast, it can determine that the urgency is high. The prompt generation unit also analyzes the typing rhythm to infer the importance of the question. For example, if the typing is intermittent, it can determine that the importance is high. The prompt generation unit also combines the facial expression analysis with the input speed and typing rhythm to comprehensively infer the urgency and importance of the question. For example, if the input speed is fast and the facial expression is serious, it can determine that the urgency is high. In this way, by analyzing the input speed and typing rhythm in addition to analyzing the user's facial expression, the urgency and importance of a question can be inferred, improving the quality of the answer provided by the generation AI.

[0078] The prompt generation unit can provide feedback to optimize the prompts of the generation AI in real time when the user inputs a question. For example, when the user inputs a question, feedback to optimize the prompts of the generation AI is provided in real time. For example, suggested modifications to the prompt are presented depending on the input content. The prompt generation unit also provides feedback in real time based on facial expression analysis when the user inputs a question. For example, if the user shows a confused expression, suggested modifications to the prompt are presented. The prompt generation unit also provides feedback in real time using an emotion estimation function when the user inputs a question. For example, if the user is nervous, suggested modifications to the prompt are presented to relax the user. In this way, feedback to optimize the prompts of the generation AI in real time is provided when the user inputs a question, thereby improving the quality of the answers of the generation AI.

[0079] The prompt generation unit can use the emotion estimation function to adjust the response style of the generation AI based on the emotional state of the user when they input a question. For example, the prompt generation unit analyzes the emotional state of the user when they input a question and adjusts the response style of the generation AI based on that emotion. For example, if the user is relaxed, it selects a casual response style. The prompt generation unit also uses the emotion estimation function to adjust the response style of the generation AI based on the emotional state of the user when they input a question. For example, if the user is nervous, it selects a formal response style. The prompt generation unit also analyzes the emotional state of the user when they input a question in real time and adjusts the response style of the generation AI based on that emotion. For example, if the user is excited, it selects a calm response style. In this way, adjusting the response style of the generation AI based on the emotional state of the user when they input a question improves the quality of the answers provided by the generation AI.

[0080] The memory unit can analyze the user's behavior after answering an answer (e.g., asking a follow-up question, scrolling the page) and evaluate satisfaction with the answer. For example, the memory unit analyzes the user's behavior after receiving the answer from the generating AI and evaluates satisfaction with the answer. For example, if the user asks a follow-up question, it determines that satisfaction is low. The memory unit also analyzes the user's page scrolling behavior after receiving the answer from the generating AI and evaluates satisfaction with the answer. For example, if the user scrolls the page immediately after answering, it determines that satisfaction is low. The memory unit also comprehensively analyzes the user's behavior after receiving the answer from the generating AI and evaluates satisfaction with the answer. For example, if the user frequently asks a follow-up question or scrolls the page after answering, it determines that satisfaction is low. In this way, by analyzing the user's behavior after answering, satisfaction with the answer can be evaluated and the prompts of the generating AI can be further optimized.

[0081] The memory unit can use the emotion estimation function to track the user's emotional state in real time after an answer and store changes therein. For example, after a user receives an answer from the generation AI, the memory unit can use the emotion estimation function to track the emotional state in real time and store changes therein. For example, if the user shows a satisfied expression after an answer, the memory unit can store that data. The memory unit can also use the emotion estimation function to track the emotional state in real time after a user receives an answer from the generation AI and store changes therein. For example, if the user shows a confused expression after an answer, the memory unit can store that data. The memory unit can also use the emotion estimation function to track the emotional state in real time after a user receives an answer from the generation AI and store changes therein. For example, if the user shows anger after an answer, the memory unit can store that data. This allows the memory unit to track the user's emotional state in real time after an answer and store changes therein, thereby further optimizing the generation AI's prompts.

[0082] In addition to analyzing the user's facial expressions, the memory unit can analyze biometric data (heart rate, galvanic skin response) after the user answers and memorize changes in emotion. For example, after the user receives the AI's answer, the memory unit measures the user's heart rate and memorizes changes in emotion in combination with facial expression analysis. For example, if the user's heart rate increases after the answer, the memory unit stores that data. The memory unit also measures the user's galvanic skin response after the user receives the AI's answer and memorizes changes in emotion in combination with facial expression analysis. For example, if the user's galvanic skin response increases after the answer, the memory unit stores that data. The memory unit also simultaneously measures the user's heart rate and galvanic skin response after the user receives the AI's answer and memorizes changes in emotion in combination with facial expression analysis. For example, if the user's heart rate and galvanic skin response increase simultaneously after the answer, the memory unit stores that data. This allows the AI's prompts to be further optimized by analyzing the user's facial expressions and analyzing the biometric data after the answer.

[0083] The memory unit can consistently analyze facial expressions after a user's response across different devices and integrate data across devices. For example, it records facial expression analysis data after a user receives the generation AI's response on a smartphone and integrates it with data from other devices. For example, it integrates facial expression data from smartphone use with data from PC use. The memory unit also records facial expression analysis data from tablet use and integrates it with data from smartphones and PCs. For example, it consistently stores facial expression data from tablet use with data from other devices. The memory unit also integrates facial expression analysis data from different devices in real time and consistently stores the user's emotional information. For example, it integrates data from smartphones, tablets, and PCs and stores comprehensive emotional information. In this way, by integrating facial expression analysis data from different devices, it can consistently store the user's emotional information and further optimize the generation AI's prompts.

[0084] The memory unit can use the emotion estimation function to suggest the optimal prompt for the next question based on the user's emotional state after answering the question. For example, it can analyze the user's emotional state after receiving the AI's answer and suggest the optimal prompt for the next question based on that data. For example, if the user shows a satisfied expression, it can adjust the next prompt based on that data. The memory unit can also use the emotion estimation function to suggest the optimal prompt for the next question based on the data if the user shows a confused expression. For example, if the user shows a confused expression, it can make the next prompt more concise. The memory unit can also analyze the user's emotional state after receiving the AI's answer in real time and suggest the optimal prompt for the next question based on that data. For example, if the user shows anger, it can make the next prompt more polite. This improves the quality of the AI's answers by suggesting the optimal prompt for the next question based on the user's emotional state after answering the question.

[0085] The processing flow of the second embodiment will be briefly explained below.

[0086] Step 1: The facial expression analysis unit analyzes the user's facial expression. For example, the facial expression analysis unit analyzes the user's facial expression in real time using face recognition technology. The facial expression analysis unit can also extract facial feature points and estimate emotions. The facial expression analysis unit can also capture the user's facial expression with a camera and analyze the image data. Step 2: The prompt generation unit generates additional correction information for the prompt based on the facial expression analyzed by the facial expression analysis unit. For example, if the user shows a confused facial expression, the prompt generation unit may simplify the prompt based on the facial expression. Alternatively, if the user shows a satisfied facial expression, the prompt generation unit may maintain the prompt as is based on the facial expression. Alternatively, if the user shows an angry facial expression, the prompt generation unit may make the prompt more polite based on the facial expression. Step 3: The storage unit stores the prompt revision information generated by the prompt generation unit. For example, the storage unit records what prompt was generated when the user showed what facial expression. The storage unit can also store the prompt revision information generated based on the user's facial expression in a database. The storage unit can also analyze the relationship between the user's facial expression and the prompt revision information and accumulate the data.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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).

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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 AI 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.

[0104] 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.

[0105] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0116] 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.

[0117] 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.

[0118] 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 AI 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.

[0119] 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.

[0120] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0121] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0131] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 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 processing similar to that of the specific processing unit 290 using these models.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] The data processing system 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0141] 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."

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0154] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an expression analysis unit that analyzes a user's expression; a prompt generation unit that generates additional correction information for a prompt based on the facial expression analyzed by the facial expression analysis unit; a storage unit that stores additional correction information for the prompt generated by the prompt generation unit; A system characterized by:

2. The facial expression analysis unit In addition to analyzing the user's facial expressions, it also analyzes changes in voice tone and speaking style to memorize more detailed emotional information. The system of claim 1 .

3. The facial expression analysis unit Analyze the user's past behavior history and usage patterns, and memorize the association between the facial expression and the behavior. The system of claim 1 .

4. The facial expression analysis unit Tracking changes in the user's emotions in real time and memorizing patterns of such changes in emotions The system of claim 1 .

5. The facial expression analysis unit In addition to analyzing the user's facial expressions, it also analyzes biometric data such as heart rate and skin galvanic response to memorize emotional information. The system of claim 1 .

Images