System

Abstract

To provide a system which learns the knowledge, character and the characteristic of talking of a user and, based on them, supports decision making, skill improvement and prevention of dementia.SOLUTION: A system includes a collection part, an analysis part, a storage part, a decision making support part, a skill improvement part, and a dementia prevention part. The collection part collects the voice and sentence data of a user. The analysis part analyzes the data collected by the collection part, and learns the knowledge, character and the characteristic of talking of the user. The storage part stores the characteristics learned by the analysis part. The decision making support part supports the decision making of the user based on the characteristics stored by the storage part. The skill improvement part supports skill improvement of the user based on the characteristics stored by the storage part. The dementia prevention part supports the dementia prevention of the user based on the characteristics stored by the storage part.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies do not adequately address the issue of effectively learning a user's knowledge, personality, and speaking characteristics, and using that information to support decision-making, skill improvement, and dementia prevention.

[0005] The system of the embodiment aims to learn the user's knowledge, personality, and speaking characteristics, and use that information to support decision-making, skill improvement, and dementia prevention. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a storage unit, a decision-making support unit, a skill improvement unit, and a dementia prevention unit. The collection unit collects voice and text data of a user. The analysis unit analyzes the data collected by the collection unit and learns the user's knowledge, personality, and speaking characteristics. The storage unit stores the characteristics learned by the analysis unit. The decision-making support unit supports the user's decision-making based on the characteristics stored by the storage unit. The skill improvement unit supports the user's skill improvement based on the characteristics stored by the storage unit. The dementia prevention unit supports the user's dementia prevention based on the characteristics stored by the storage unit. Effect of the Invention

[0007] The system according to the embodiment can learn a user's knowledge, personality, and speaking characteristics, and use that information to support decision-making, skill improvement, and dementia prevention. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The knowledge storage system according to the embodiment of the present invention is a system that allows an AI to learn and store the characteristics of a user, such as knowledge, personality, and speaking habits, and is useful for future decision-making support, self-improvement, and dementia prevention. This knowledge storage system collects the user's voice and text data, and the AI ​​analyzes them to learn the characteristics of the user, such as knowledge, personality, and speaking habits. The learned characteristics are stored in the AI, and in the future, the user's decision-making can be supported based on the stored characteristics. For example, when a user makes an important decision, the AI ​​provides advice based on past data. In addition, the user can look back on his or her past remarks and sentences for self-improvement. Furthermore, as a dementia prevention measure, the system supports memory maintenance by reproducing the user's past characteristics. For example, the knowledge storage system collects the user's voice and text data. For example, the user's voice data can be collected using voice recognition technology. In addition, the user's text data can be collected using text processing technology. Next, the knowledge storage system uses the AI ​​to analyze the collected data and learn the characteristics of the user, such as knowledge, personality, and speaking habits. For example, the AI ​​uses natural language processing technology to analyze the voice data and text data and extract the user's characteristics. The learned features are stored in a database. For example, the database is stored in a form such as a relational database or a NoSQL database. In the future, the stored features can be used to support user decision-making. For example, the AI ​​can provide advice to the user based on past data. In addition, the user can review their past statements and writings for self-improvement. For example, the AI ​​can provide feedback to the user based on past data. In addition, to prevent dementia, the AI ​​can support memory maintenance by reproducing the user's past features. For example, the AI ​​can reproduce the user's features based on past data and perform memory training. This allows the knowledge storage system to learn the user's features such as knowledge, personality, and speaking habits in detail, and use them for future decision-making, self-improvement, and dementia prevention. This allows the knowledge storage system to learn the user's features such as knowledge, personality, and speaking habits in detail, and use them for future decision-making, self-improvement, and dementia prevention.

[0029] The knowledge storage system according to the embodiment includes a collection unit, an analysis unit, a storage unit, a decision support unit, a self-study unit, and a dementia prevention unit. The collection unit collects the user's voice and text data. The collection unit can collect the user's voice data using, for example, a voice recognition technology. The collection unit can also collect the user's text data using a text processing technology. For example, the collection unit collects the user's voice data using a voice recognition technology. The voice recognition technology can use, for example, a voice recognition algorithm or a preprocessing method for voice data. The collection unit records, for example, the user's voice data with a microphone and converts it into text data using a voice recognition algorithm. The collection unit collects the user's text data using a text processing technology. The text processing technology can use, for example, morphological analysis, grammatical analysis, semantic analysis, and the like. For example, the collection unit collects the user's text data as a text file and performs morphological analysis. The analysis unit analyzes the data collected by the collection unit and learns the user's knowledge, personality, and speaking habits. The analysis unit can use, for example, a machine learning algorithm or a natural language processing technology. The analysis unit, for example, analyzes collected voice data and text data using a machine learning algorithm to extract features of the user. The storage unit stores the features learned by the analysis unit. The storage unit can store the features using, for example, a database. The storage unit stores the features in a format such as a relational database or a NoSQL database. The decision support unit supports the user's decision-making based on the features stored by the storage unit. The decision support unit can provide advice to the user based on past data, for example. The decision support unit can analyze past data using, for example, AI, and provide advice to the user. The self-improvement unit supports the user's self-improvement based on the features stored by the storage unit. The self-improvement unit can provide, for example, a function to look back on one's own past remarks and writings. The self-improvement unit analyzes past data using, for example, AI, and provides feedback to the user. The dementia prevention unit supports the user's dementia prevention based on the features stored by the storage unit.The dementia prevention unit can support memory maintenance by, for example, reproducing the user's past characteristics. The dementia prevention unit can, for example, analyze past data using AI, reproduce the user's characteristics, and perform memory training. As a result, the knowledge storage system according to the embodiment can learn the user's knowledge, personality, speech habits, and other characteristics in detail, and use them for future decision-making, self-improvement, and dementia prevention.

[0030] The collection unit collects the user's voice and text data. The collection unit can collect the user's voice data using, for example, a voice recognition technology. The collection unit can also collect the user's text data using a text processing technology. Specifically, the collection unit collects the user's voice data using a voice recognition technology. The voice recognition technology can use, for example, a voice recognition algorithm or a pre-processing method for voice data. The collection unit, for example, records the user's voice data with a microphone and converts it into text data using a voice recognition algorithm. The voice recognition algorithm converts the voice signal into digital data and recognizes phonemes and words. This allows the user's utterance to be accurately converted into text. The collection unit also collects the user's text data using a text processing technology. The text processing technology can use, for example, morphological analysis, grammatical analysis, semantic analysis, and the like. The collection unit, for example, collects the user's text data as a text file and performs morphological analysis. Morphological analysis is a technology that divides a sentence into words and analyzes the parts of speech and meanings of each word. This allows the user's text data to be analyzed in detail and the user's intentions and emotions to be understood. Furthermore, the collection unit centrally manages the collected data and allows the analysis unit and storage unit to access it. For example, the collected data can be stored in a cloud server and linked to other systems and departments as necessary. This allows the collection unit to collect data efficiently and effectively and improve the performance of the entire system.

[0031] The analysis unit analyzes the data collected by the collection unit and learns the user's knowledge, personality, and speaking habits. The analysis unit can use, for example, a machine learning algorithm or a natural language processing technology. Specifically, the collected voice data and text data are analyzed using a machine learning algorithm to extract the user's characteristics. The machine learning algorithm learns patterns based on a large amount of data and models the characteristics of the user's remarks and text. For example, the voice data can analyze the user's tone of voice, speech rhythm, and frequency of use of specific phrases. The text data can analyze the user's writing style, vocabulary selection, text structure, and the like. Furthermore, the analysis unit uses natural language processing technology to understand the meaning of the user's remarks and text. Natural language processing technology is a technology that combines morphological analysis, grammatical analysis, semantic analysis, and the like to analyze the meaning of text. This allows the analysis unit to understand the intention and emotion of the user's remarks and text, and to grasp the user's characteristics in detail. Furthermore, the analysis unit can predict the user's behavioral patterns and tendencies by utilizing past data and statistical information. For example, based on past speech data, it can predict the user's reaction and behavior in a specific situation, and use the data to help with future decision-making and self-improvement. This allows the analysis unit to analyze collected data quickly and accurately, and learn the characteristics of the user in detail.

[0032] The storage unit stores the features learned by the analysis unit. The storage unit can store the features using, for example, a database. Specifically, the storage unit stores the features in a format such as a relational database or a NoSQL database. A relational database manages data in a table format and can search and update data using SQL. This allows the storage unit to efficiently manage the user's features and quickly access them as needed. In addition, a NoSQL database has excellent scalability and flexibility and can efficiently store large amounts of data. This allows the storage unit to store the user's features for a long period of time and prepare for future use. Furthermore, the storage unit must also take into consideration data security and privacy protection. For example, the stored data is protected using encryption technology to prevent unauthorized access and data leakage. In addition, the storage unit has a data backup and recovery function and can prepare for data loss or damage. This allows the storage unit to safely and efficiently store the features learned by the analysis unit and improve the reliability of the entire system.

[0033] The decision support unit supports the user's decision-making based on the features stored by the storage unit. The decision support unit can provide advice to the user based on past data, for example. Specifically, the decision support unit uses AI to analyze past data and provide advice to the user. The AI ​​uses a machine learning algorithm to learn patterns and trends from past data and generate advice according to the user's current situation. For example, the decision support unit can suggest optimal actions and options in a specific situation based on past utterance data. In addition, the decision support unit can analyze the results of the user's past decisions and actions and provide information that is useful for future decision-making. This allows the decision support unit to support the user's decision-making and provide information to lead to better results. Furthermore, the decision support unit can continuously improve the accuracy and effectiveness of the advice based on data updated in real time. For example, by collecting user feedback and reviewing the content and method of providing the advice, more effective support can be provided. This allows the decision support unit to provide the user with prompt and appropriate advice and improve the quality of decision-making.

[0034] The self-improvement unit supports the user's self-improvement based on the characteristics stored by the storage unit. The self-improvement unit can provide, for example, a function for reviewing one's own past remarks and writings. Specifically, the self-improvement unit uses AI to analyze past data and provide feedback to the user. The AI ​​uses a machine learning algorithm to analyze the characteristics of past remarks and writings and point out the user's growth and improvement points. For example, based on past remark data, it can point out specific speaking habits and points to be improved and provide specific advice to the user. In addition, the self-improvement unit can provide learning content and training programs according to the user's goals and interests. This allows the self-improvement unit to support the user's self-improvement and promote the improvement of skills and knowledge. Furthermore, the self-improvement unit can monitor the user's progress and provide feedback and advice at an appropriate time. For example, the self-improvement unit periodically analyzes the user's remarks and writings, evaluates the progress, and suggests new goals and training programs as necessary. This allows the self-improvement unit to continuously support the user's self-improvement and provide an effective learning environment.

[0035] The dementia prevention unit supports the user's dementia prevention based on the characteristics stored by the storage unit. The dementia prevention unit can support memory maintenance by, for example, reproducing one's own past characteristics. Specifically, the dementia prevention unit uses AI to analyze past data, reproduce the user's characteristics, and perform memory training. The AI ​​uses a machine learning algorithm to model the characteristics of past remarks and sentences, and generates a training program that stimulates the user's memory. For example, based on past remark data, it is possible to reproduce phrases and topics frequently used by the user and perform training to evoke memories. In addition, the dementia prevention unit can evaluate the user's cognitive function and provide an appropriate training program. This allows the dementia prevention unit to support the maintenance of the user's memory and cognitive function, and to be useful in preventing dementia. Furthermore, the dementia prevention unit can monitor the user's progress and evaluate the effectiveness of the training program. For example, by regularly evaluating the user's cognitive function and adjusting the content and difficulty of the training program, effective preventive measures can be provided. This allows the dementia prevention unit to continuously support the maintenance of the user's cognitive function and reduce the risk of dementia.

[0036] The knowledge storage system includes a voice recognition unit that collects user voice data using voice recognition technology. The voice recognition unit collects user voice data using, for example, voice recognition technology. The voice recognition technology can use, for example, a voice recognition algorithm or a voice data preprocessing method. The voice recognition unit, for example, records user voice data with a microphone and converts it into text data using a voice recognition algorithm. The voice recognition unit can also collect user voice data in real time using voice recognition technology. For example, the voice recognition unit generates text data simultaneously with voice input and performs analysis in real time. Furthermore, the voice recognition unit can support multiple languages ​​using voice recognition technology. For example, the voice recognition unit recognizes voice input in multiple languages ​​such as English, Japanese, and French, and converts it into text data. As a result, the voice recognition technology can be used to efficiently collect user voice data. A part or all of the above-mentioned processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice recognition unit can input voice data to a generation AI and cause the generation AI to convert the voice data into text data.

[0037] The knowledge storage system includes a text processing unit that collects text data of a user using a text processing technique. The text processing unit collects text data of a user using, for example, a text processing technique. The text processing technique can use, for example, morphological analysis, grammatical analysis, semantic analysis, and the like. The text processing unit can collect, for example, the text data of a user as a text file and perform morphological analysis. The text processing unit can also collect the text data of a user in real time using the text processing technique. For example, the text processing unit performs analysis simultaneously with text input and collects data in real time. Furthermore, the text processing unit can support multiple languages ​​using the text processing technique. For example, the text processing unit analyzes and collects text data in multiple languages ​​such as English, Japanese, and French. As a result, the text processing technique can be used to efficiently collect the text data of a user. A part or all of the above-mentioned processing in the text processing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the text processing unit can input text data to a generation AI and cause the generation AI to execute analysis of the text data.

[0038] The knowledge storage system includes a database unit that includes a database for storing the learned features. The database unit includes, for example, a database for storing the learned features. The database is stored in a format such as a relational database or a NoSQL database. The database unit uses, for example, a relational database to efficiently store the learned features. The database unit can also flexibly store the learned features using a NoSQL database. For example, the database unit uses a relational database to store the learned features in a table format. The NoSQL database is a schema-less database and allows flexible data storage. This allows the learned features to be efficiently stored. A part or all of the above-mentioned processing in the database unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the database unit can input the learned features to a generation AI and cause the generation AI to execute storage in the database.

[0039] The knowledge storage system includes an advice providing unit that provides advice to support the user's decision making. The advice providing unit provides, for example, advice to support the user's decision making. The advice is provided, for example, in a text format or a voice format. The advice providing unit provides, for example, advice to the user based on past data. The advice providing unit analyzes past data using, for example, AI and provides advice to the user. For example, the advice providing unit provides optimal advice to the user based on past data. The advice providing unit can also customize advice based on the user's current situation. For example, the advice providing unit analyzes the user's current situation and provides optimal advice. This makes it possible to provide advice to support the user's decision making. A part or all of the above-mentioned processing in the advice providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice providing unit inputs the content of the advice to a generation AI and causes the generation AI to execute the generation of the advice.

[0040] The knowledge storage system includes a review providing unit that provides a function of reviewing past statements and sentences for the user's self-improvement. The review providing unit provides, for example, a function of reviewing past statements and sentences for the user's self-improvement. The review providing unit provides, for example, feedback to the user based on past data. The review providing unit analyzes past data using, for example, AI, and provides feedback to the user. For example, the review providing unit provides optimal feedback to the user based on past data. The review providing unit can also customize feedback based on the user's current situation. For example, the review providing unit analyzes the user's current situation and provides optimal feedback. This allows the user to review past statements and sentences for self-improvement. A part or all of the above-mentioned processing in the review providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the review providing unit can input the content of the feedback to the generation AI and cause the generation AI to generate the feedback.

[0041] The knowledge storage system includes a memory reproducing unit that reproduces past characteristics of the user to prevent dementia. The memory reproducing unit reproduces past characteristics of the user to prevent dementia, for example. The memory reproducing unit reproduces the characteristics of the user based on past data, for example, and performs memory training. The memory reproducing unit analyzes past data using, for example, AI, and reproduces the characteristics of the user. For example, the memory reproducing unit provides optimal memory training to the user based on past data. The memory reproducing unit can also customize memory training based on the current situation of the user. For example, the memory reproducing unit analyzes the current situation of the user and provides optimal memory training. This makes it possible to reproduce past characteristics to prevent dementia of the user. A part or all of the above-mentioned processing in the memory reproducing unit may be performed using, for example, AI, or may be performed without using AI. For example, the memory reproducing unit can input the contents of the memory training to the generating AI and cause the generating AI to execute the generation of the memory training.

[0042] The collection unit can analyze the user's past data collection history and select the optimal collection method. The collection unit, for example, analyzes the user's past data collection history and selects the optimal collection method. The collection unit, for example, prioritizes the collection method (audio, text, etc.) that the user has used in the past. The collection unit can also suggest the most efficient collection timing from the user's past data collection history. Furthermore, the collection unit can customize the collection method based on the user's past data collection history. In this way, the optimal collection method can be selected by analyzing the past data collection history. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the past data collection history to the generation AI and cause the generation AI to select the optimal collection method.

[0043] The collection unit can perform filtering based on the user's current activity status and field of interest when collecting data. For example, the collection unit performs filtering based on the user's current activity status and field of interest when collecting data. For example, the collection unit preferentially collects data related to the activity currently being performed by the user. The collection unit can also filter related data based on the user's field of interest. Furthermore, the collection unit can adjust the type of data to be collected in consideration of the user's current activity status. This makes it possible to collect highly relevant data by filtering data based on the current activity status and field of interest. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the current activity status and field of interest to the generation AI and cause the generation AI to perform filtering.

[0044] The collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the user when collecting data. For example, the collection unit preferentially collects highly relevant data in consideration of the geographical location information of the user when collecting data. For example, when the user is in a specific location, the collection unit preferentially collects data related to the location. The collection unit can also filter highly relevant data based on the geographical location information of the user. Furthermore, the collection unit can adjust the type of data to be collected based on the current location of the user. This allows highly relevant data to be preferentially collected by considering the geographical location information. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input geographical location information to the generation AI and cause the generation AI to perform data filtering.

[0045] The collection unit can analyze the social media activity of the user at the time of data collection and collect related data. For example, the collection unit analyzes the social media activity of the user at the time of data collection and collects related data. For example, the collection unit analyzes the content of the user's social media posts and collects related data. The collection unit can also identify an area of ​​interest from the user's social media activity and collect related data. Furthermore, the collection unit can adjust the type of data to be collected based on the user's social media activity. This makes it possible to efficiently collect related data by analyzing social media activity. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input social media activity to a generation AI and cause the generation AI to collect data.

[0046] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during analysis. The analysis unit, for example, adjusts the level of detail of the analysis based on the importance of the data during analysis. The analysis unit, for example, performs a detailed analysis on data with high importance. The analysis unit can also perform a concise analysis on data with low importance. Furthermore, the analysis unit can dynamically adjust the level of detail of the analysis according to the importance of the data. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the importance of the data to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0047] The analysis unit can apply different analysis algorithms depending on the category of data during analysis. The analysis unit applies different analysis algorithms depending on the category of data during analysis, for example. The analysis unit applies a voice analysis algorithm to voice data, for example. The analysis unit can also apply a text analysis algorithm to text data. Furthermore, the analysis unit can select an optimal analysis algorithm depending on the category of data. This improves the analysis accuracy by applying an optimal analysis algorithm depending on the category of data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the category of data to the generation AI and cause the generation AI to select the analysis algorithm.

[0048] The analysis unit can determine the analysis priority based on the collection time of the data during the analysis. The analysis unit, for example, determines the analysis priority based on the collection time of the data during the analysis. The analysis unit, for example, prioritizes the analysis of the latest data. The analysis unit can also lower the analysis priority for old data. Furthermore, the analysis unit can dynamically adjust the analysis priority according to the collection time of the data. This enables efficient analysis by determining the analysis priority based on the collection time of the data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the collection time of the data to the generation AI and cause the generation AI to determine the analysis priority.

[0049] The analysis unit can adjust the order of analysis based on the relevance of data during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of data during analysis. The analysis unit, for example, prioritizes analysis of highly relevant data. The analysis unit can also postpone the order of analysis for less relevant data. Furthermore, the analysis unit can dynamically adjust the order of analysis according to the relevance of data. This enables efficient analysis by adjusting the order of analysis based on the relevance of data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance of data to the generation AI and cause the generation AI to adjust the order of analysis.

[0050] The storage unit can adjust the level of detail of the storage based on the importance of the data at the time of storage. For example, the storage unit adjusts the level of detail of the storage based on the importance of the data at the time of storage. For example, the storage unit performs detailed storage for data with high importance. In addition, the storage unit can perform concise storage for data with low importance. Furthermore, the storage unit can dynamically adjust the level of detail of the storage according to the importance of the data. As a result, efficient data storage is possible by adjusting the level of detail of the storage based on the importance of the data. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the importance of the data to the generation AI and cause the generation AI to adjust the level of detail of the storage.

[0051] The storage unit can apply different storage algorithms depending on the category of data when storing. The storage unit applies different storage algorithms depending on the category of data when storing, for example. The storage unit applies an audio storage algorithm to audio data, for example. The storage unit can also apply a text storage algorithm to text data. Furthermore, the storage unit can select an optimal storage algorithm depending on the category of data. This improves storage accuracy by applying an optimal storage algorithm depending on the category of data. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the category of data to the generation AI and cause the generation AI to select a storage algorithm.

[0052] The storage unit can determine the priority of storage based on the collection time of data at the time of storage. For example, the storage unit determines the priority of storage based on the collection time of data at the time of storage. For example, the storage unit preferentially stores the latest data. The storage unit can also lower the priority of storage for old data. Furthermore, the storage unit can dynamically adjust the priority of storage according to the collection time of data. This enables efficient data storage by determining the priority of storage based on the collection time of data. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the collection time of data to the generation AI and cause the generation AI to execute the determination of the priority of storage.

[0053] The storage unit can adjust the order of storage based on the relevance of data when storing. The storage unit, for example, adjusts the order of storage based on the relevance of data when storing. The storage unit, for example, prioritizes storage of highly relevant data. The storage unit can also postpone the order of storage for data with low relevance. Furthermore, the storage unit can dynamically adjust the order of storage according to the relevance of data. This enables efficient data storage by adjusting the order of storage based on the relevance of data. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the relevance of data to the generation AI and cause the generation AI to adjust the order of storage.

[0054] The decision support unit can select the optimal support method by referring to the past decision history during decision support. For example, the decision support unit selects the optimal support method by referring to the past decision history during decision support. The decision support unit, for example, proposes the optimal support method based on the user's past decision history. The decision support unit can also preferentially propose successful methods from the past decision history. Furthermore, the decision support unit can analyze the past decision history and select the most effective support method. As a result, the optimal support method can be selected by referring to the past decision history. A part or all of the above-mentioned processing in the decision support unit may be performed, for example, using AI, or may be performed without using AI. For example, the decision support unit can input the past decision history to the generation AI and cause the generation AI to select the support method.

[0055] The decision support unit can customize the means of support based on the user's current situation during decision support. For example, the decision support unit customizes the means of support based on the user's current situation during decision support. For example, when the user is in an emergency situation, the decision support unit provides a means of supporting quick decision making. In addition, when the user is relaxed, the decision support unit can also provide detailed information to support decision making. Furthermore, when the user is stressed, the decision support unit can also provide a visually easy-to-understand support means. This enables more appropriate support by customizing the means of support based on the user's current situation. Part or all of the above-mentioned processing in the decision support unit may be performed, for example, using AI or may be performed without using AI. For example, the decision support unit can input the current situation to the generation AI and cause the generation AI to execute customization of the support means.

[0056] The decision support unit can select the optimal support method in consideration of the geographical location information of the user during decision support. For example, the decision support unit selects the optimal support method in consideration of the geographical location information of the user during decision support. For example, when the user is in a specific location, the decision support unit provides information related to the location to support decision making. The decision support unit can also suggest the optimal support method based on the geographical location information of the user. Furthermore, the decision support unit can also customize the means of decision making based on the current location of the user. In this way, the optimal support method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the decision support unit may be performed, for example, using AI, or may be performed without using AI. For example, the decision support unit can input geographical location information to the generation AI and cause the generation AI to select the support method.

[0057] The decision support unit can analyze the user's social media activity and suggest a means of support during decision support. For example, the decision support unit analyzes the user's social media activity and suggests a means of support during decision support. For example, the decision support unit analyzes the user's social media posting content and provides related information to support decision making. The decision support unit can also identify the user's field of interest from the user's social media activity and suggest the optimal support method. Furthermore, the decision support unit can customize the means of decision making based on the user's social media activity. In this way, related support means can be suggested by analyzing the social media activity. Part or all of the above-mentioned processing in the decision support unit may be performed, for example, using AI or may be performed without using AI. For example, the decision support unit can input the social media activity to the generation AI and cause the generation AI to execute the suggestion of the support means.

[0058] The self-study unit can select the optimal training method by referring to the past self-study history during self-study. For example, the self-study unit selects the optimal training method by referring to the past self-study history during self-study. The self-study unit, for example, proposes the optimal training method based on the user's past self-study history. The self-study unit can also preferentially propose successful methods from the past self-study history. Furthermore, the self-study unit can analyze the past self-study history and select the most effective training method. As a result, the optimal training method can be selected by referring to the past self-study history. A part or all of the above-mentioned processing in the self-study unit may be performed, for example, using AI, or may be performed without using AI. For example, the self-study unit can input the past self-study history into the generation AI and cause the generation AI to select the training method.

[0059] The self-study unit can customize the means of self-study based on the current situation of the user during self-study. The self-study unit customizes the means of self-study based on the current situation of the user, for example, during self-study. The self-study unit provides a means for supporting rapid study when the user is in an emergency situation, for example. The self-study unit can also support the study by providing detailed information when the user is relaxed. Furthermore, the self-study unit can also provide a visually easy-to-understand study means when the user is feeling stressed. This enables more appropriate study by customizing the means of study based on the current situation of the user. Part or all of the above-mentioned processing in the self-study unit may be performed, for example, using AI, or may be performed without using AI. For example, the self-study unit can input the current situation to the generation AI and cause the generation AI to execute customization of the study means.

[0060] The self-study unit can select the optimal training method in consideration of the geographical location information of the user during self-study. For example, the self-study unit selects the optimal training method in consideration of the geographical location information of the user during self-study. For example, when the user is in a specific location, the self-study unit supports the training by providing information related to the location. The self-study unit can also suggest the optimal training method based on the geographical location information of the user. Furthermore, the self-study unit can also customize the means of training based on the user's current location. This makes it possible to select the optimal training method by considering the geographical location information. A part or all of the above-mentioned processing in the self-study unit may be performed, for example, using AI, or may be performed without using AI. For example, the self-study unit can input geographical location information to the generation AI and cause the generation AI to select the training method.

[0061] The self-improvement unit can analyze the social media activity of the user during self-improvement and suggest a means of self-improvement. The self-improvement unit, for example, analyzes the social media activity of the user during self-improvement and suggests a means of self-improvement. The self-improvement unit, for example, analyzes the content of the user's social media posts and provides related information to support the self-improvement. The self-improvement unit can also identify the user's field of interest from the user's social media activity and suggest an optimal method of self-improvement. Furthermore, the self-improvement unit can customize the means of self-improvement based on the user's social media activity. This makes it possible to suggest related means of self-improvement by analyzing the social media activity. A part or all of the above-mentioned processing in the self-improvement unit may be performed, for example, using AI, or may be performed without using AI. For example, the self-improvement unit can input the social media activity to the generation AI and cause the generation AI to execute the suggestion of the means of self-improvement.

[0062] The dementia prevention unit can select the optimal prevention method by referring to the past dementia prevention history when preventing dementia. For example, the dementia prevention unit selects the optimal prevention method by referring to the past dementia prevention history when preventing dementia. The dementia prevention unit, for example, proposes the optimal prevention method based on the user's past dementia prevention history. The dementia prevention unit can also preferentially propose successful methods from the past dementia prevention history. Furthermore, the dementia prevention unit can analyze the past dementia prevention history and select the most effective prevention method. As a result, the optimal prevention method can be selected by referring to the past dementia prevention history. Part or all of the above-mentioned processing in the dementia prevention unit may be performed, for example, using AI or may be performed without using AI. For example, the dementia prevention unit can input the past dementia prevention history to the generation AI and cause the generation AI to select the prevention method.

[0063] The dementia prevention unit can customize preventive measures based on the user's current situation during dementia prevention. The dementia prevention unit customizes preventive measures based on the user's current situation during dementia prevention, for example. The dementia prevention unit provides a means to support rapid prevention when the user is in an emergency situation, for example. The dementia prevention unit can also provide detailed information to support prevention when the user is relaxed. Furthermore, the dementia prevention unit can also provide visually easy-to-understand preventive measures when the user is feeling stressed. This enables more appropriate prevention by customizing preventive measures based on the user's current situation. Part or all of the above-mentioned processing in the dementia prevention unit may be performed, for example, using AI or may be performed without using AI. For example, the dementia prevention unit can input the current situation to the generation AI and cause the generation AI to execute customization of preventive measures.

[0064] The dementia prevention unit can select the optimal prevention method in consideration of the geographical location information of the user during dementia prevention. For example, the dementia prevention unit selects the optimal prevention method in consideration of the geographical location information of the user during dementia prevention. For example, when the user is in a specific location, the dementia prevention unit supports prevention by providing information related to the location. The dementia prevention unit can also suggest the optimal prevention method based on the geographical location information of the user. Furthermore, the dementia prevention unit can also customize the means of prevention based on the user's current location. In this way, the optimal prevention method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the dementia prevention unit may be performed, for example, using AI or may be performed without using AI. For example, the dementia prevention unit can input geographical location information to the generation AI and cause the generation AI to select a prevention method.

[0065] The dementia prevention unit can analyze the social media activity of the user and suggest preventive measures when preventing dementia. For example, the dementia prevention unit analyzes the social media activity of the user and suggests preventive measures when preventing dementia. For example, the dementia prevention unit analyzes the content of the user's social media posts and provides related information to support prevention. The dementia prevention unit can also identify areas of interest from the user's social media activities and suggest optimal preventive methods. Furthermore, the dementia prevention unit can customize preventive measures based on the user's social media activities. As a result, related preventive measures can be suggested by analyzing social media activities. Some or all of the above-mentioned processing in the dementia prevention unit may be performed, for example, using AI or may be performed without using AI. For example, the dementia prevention unit can input social media activities to the generation AI and cause the generation AI to execute the proposal of preventive measures.

[0066] The voice recognition unit can optimize the recognition algorithm by referring to past voice data during voice recognition. The voice recognition unit optimizes the recognition algorithm by referring to past voice data during voice recognition, for example. The voice recognition unit selects an optimal recognition algorithm based on, for example, the user's past voice data. The voice recognition unit can also preferentially apply a successful recognition algorithm from the past voice data. Furthermore, the voice recognition unit can analyze past voice data and select the most effective recognition algorithm. As a result, the optimal recognition algorithm can be selected by referring to the past voice data. A part or all of the above-mentioned processing in the voice recognition unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice recognition unit can input past voice data to a generation AI and cause the generation AI to optimize the recognition algorithm.

[0067] The voice recognition unit can select the optimal recognition method in consideration of the geographical location information of the user during voice recognition. For example, the voice recognition unit selects the optimal recognition method in consideration of the geographical location information of the user during voice recognition. For example, when the user is in a specific location, the voice recognition unit preferentially recognizes voice data related to the location. The voice recognition unit can also suggest the optimal recognition method based on the geographical location information of the user. Furthermore, the voice recognition unit can also customize the means of voice recognition based on the current location of the user. This makes it possible to select the optimal recognition method by considering the geographical location information. A part or all of the above-mentioned processing in the voice recognition unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice recognition unit can input geographical location information to the generation AI and cause the generation AI to select the recognition method.

[0068] The text processing unit can optimize the processing algorithm by referring to past text data during text processing. The text processing unit optimizes the processing algorithm by referring to past text data during text processing, for example. The text processing unit selects an optimal processing algorithm based on the user's past text data, for example. The text processing unit can also preferentially apply a successful processing algorithm from the past text data. Furthermore, the text processing unit can analyze the past text data and select the most effective processing algorithm. In this way, the optimal processing algorithm can be selected by referring to the past text data. A part or all of the above-mentioned processing in the text processing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the text processing unit can input past text data to a generation AI and cause the generation AI to optimize the processing algorithm.

[0069] The text processing unit can select the optimal processing method in consideration of the geographical location information of the user when processing text. The text processing unit, for example, selects the optimal processing method in consideration of the geographical location information of the user when processing text. For example, when the user is in a specific location, the text processing unit preferentially processes text data related to the location. The text processing unit can also suggest the optimal processing method based on the geographical location information of the user. Furthermore, the text processing unit can also customize the means of text processing based on the current location of the user. In this way, the optimal processing method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the text processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the text processing unit can input geographical location information to the generation AI and cause the generation AI to select the processing method.

[0070] The database unit can select an optimal structure by referring to past database usage history when constructing a database. For example, the database unit selects an optimal structure by referring to past database usage history when constructing a database. The database unit, for example, proposes an optimal structure based on the user's past database usage history. The database unit can also preferentially apply a successful structure from the past database usage history. Furthermore, the database unit can analyze the past database usage history and select the most effective structure. In this way, the optimal database structure can be selected by referring to the past database usage history. A part or all of the above-mentioned processing in the database unit may be performed, for example, using AI, or may be performed without using AI. For example, the database unit can input the past database usage history to the generation AI and cause the generation AI to select a structure.

[0071] The database unit can select an optimal structure in consideration of the geographical location information of the user when constructing the database. For example, the database unit selects an optimal structure in consideration of the geographical location information of the user when constructing the database. For example, when the user is in a specific location, the database unit preferentially stores data related to the location. The database unit can also propose an optimal database structure based on the geographical location information of the user. Furthermore, the database unit can also customize the structure of the database based on the current location of the user. In this way, the optimal database structure can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the database unit may be performed, for example, using AI, or may be performed without using AI. For example, the database unit can input geographical location information to the generation AI and cause the generation AI to select the structure.

[0072] The advice providing unit can select the optimal advice method by referring to the past advice history when providing advice. For example, the advice providing unit selects the optimal advice method by referring to the past advice history when providing advice. The advice providing unit proposes the optimal advice method based on the user's past advice history, for example. The advice providing unit can also preferentially propose a successful method from the past advice history. Furthermore, the advice providing unit can analyze the past advice history and select the most effective advice method. In this way, the optimal advice method can be selected by referring to the past advice history. A part or all of the above-mentioned processing in the advice providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the advice providing unit can input the past advice history to the generation AI and cause the generation AI to select the advice method.

[0073] The advice providing unit can select the optimal advice method in consideration of the geographical location information of the user when providing advice. For example, the advice providing unit selects the optimal advice method in consideration of the geographical location information of the user when providing advice. For example, when the user is in a specific location, the advice providing unit preferentially provides advice related to the location. The advice providing unit can also suggest the optimal advice method based on the geographical location information of the user. Furthermore, the advice providing unit can also customize the means of advice based on the current location of the user. In this way, the optimal advice method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the advice providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the advice providing unit can input geographical location information to the generation AI and cause the generation AI to select the advice method.

[0074] The review providing unit can select the optimal review method by referring to the past review history when providing the review. For example, the review providing unit selects the optimal review method by referring to the past review history when providing the review. The review providing unit, for example, proposes the optimal review method based on the user's past review history. In addition, the review providing unit can preferentially propose successful methods from the past review history. Furthermore, the review providing unit can analyze the past review history and select the most effective review method. In this way, the optimal review method can be selected by referring to the past review history. A part or all of the above-mentioned processing in the review providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the review providing unit can input the past review history to the generation AI and cause the generation AI to select the review method.

[0075] The review providing unit can select the optimal review method in consideration of the geographical location information of the user when providing the review. For example, the review providing unit selects the optimal review method in consideration of the geographical location information of the user when providing the review. For example, when the user is in a specific location, the review providing unit preferentially provides reviews related to the location. In addition, the review providing unit can also suggest the optimal review method based on the geographical location information of the user. Furthermore, the review providing unit can also customize the means of review based on the current location of the user. In this way, the optimal review method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the review providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the review providing unit can input geographical location information to the generation AI and cause the generation AI to select the review method.

[0076] The memory reproduction unit can select the optimal reproduction method by referring to the past memory reproduction history when reproducing a memory. For example, the memory reproduction unit selects the optimal reproduction method by referring to the past memory reproduction history when reproducing a memory. The memory reproduction unit, for example, proposes the optimal reproduction method based on the user's past memory reproduction history. The memory reproduction unit can also preferentially propose successful methods from the past memory reproduction history. Furthermore, the memory reproduction unit can analyze the past memory reproduction history and select the most effective reproduction method. In this way, the optimal reproduction method can be selected by referring to the past memory reproduction history. Part or all of the above-mentioned processing in the memory reproduction unit may be performed, for example, using AI or may be performed without using AI. For example, the memory reproduction unit can input the past memory reproduction history to the generation AI and cause the generation AI to select the reproduction method.

[0077] The memory reproduction unit can customize the means of reproduction based on the user's current situation when reproducing the memory. The memory reproduction unit customizes the means of reproduction based on the user's current situation when reproducing the memory, for example. The memory reproduction unit provides a means to support rapid memory reproduction when the user is in an emergency situation, for example. The memory reproduction unit can also support memory reproduction by providing detailed information when the user is relaxed. Furthermore, the memory reproduction unit can also provide a visually easy-to-understand memory reproduction means when the user is stressed. This enables more appropriate memory reproduction by customizing the means of reproduction based on the user's current situation. Part or all of the above-mentioned processing in the memory reproduction unit may be performed, for example, using AI or may be performed without using AI. For example, the memory reproduction unit can input the current situation to the generation AI and cause the generation AI to execute customization of the reproduction means.

[0078] The memory reproduction unit can select the optimal reproduction method in consideration of the geographical location information of the user when reproducing a memory. For example, the memory reproduction unit selects the optimal reproduction method in consideration of the geographical location information of the user when reproducing a memory. For example, when the user is in a specific location, the memory reproduction unit preferentially provides memory reproduction related to that location. The memory reproduction unit can also suggest the optimal memory reproduction method based on the geographical location information of the user. Furthermore, the memory reproduction unit can also customize the means of memory reproduction based on the user's current location. In this way, the optimal reproduction method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the memory reproduction unit may be performed, for example, using AI, or may be performed without using AI. For example, the memory reproduction unit can input geographical location information to the generation AI and cause the generation AI to select the reproduction method.

[0079] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0080] The knowledge storage system can analyze the user's past data collection history and select the optimal collection method. For example, it can prioritize collection methods (audio, text, etc.) that the user has used favorably in the past. It can also suggest the most efficient collection timing based on the user's past data collection history. Furthermore, it can customize the collection method based on the user's past data collection history. This makes it possible to select the optimal collection method by analyzing past data collection history.

[0081] When collecting data, the knowledge storage system can filter the data based on the user's current activity status and areas of interest. For example, data related to the user's current activity can be preferentially collected. Also, the knowledge storage system can filter relevant data based on the user's areas of interest. Furthermore, the knowledge storage system can adjust the type of data to be collected taking into account the user's current activity status. In this way, highly relevant data can be collected by filtering the data based on the user's current activity status and areas of interest.

[0082] The knowledge storage system can preferentially collect highly relevant data by taking into account the geographic location information of the user. For example, when the user is in a specific location, data related to that location is preferentially collected. Also, based on the geographic location information of the user, highly relevant data can be filtered. Furthermore, the type of data to be collected can be adjusted based on the user's current location. In this way, highly relevant data can be preferentially collected by taking into account the geographic location information.

[0083] The knowledge storage system can analyze the user's social media activities and collect relevant data. For example, the knowledge storage system can analyze the content of the user's social media posts and collect relevant data. It can also identify areas of interest from the user's social media activities and collect relevant data. It can also adjust the type of data to be collected based on the user's social media activities. This allows for efficient collection of relevant data by analyzing social media activities.

[0084] During analysis, the knowledge storage system can adjust the level of detail of the analysis based on the importance of the data. For example, a detailed analysis can be performed on data with high importance. Also, a simple analysis can be performed on data with low importance. Furthermore, the level of detail of the analysis can be dynamically adjusted according to the importance of the data. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data.

[0085] During analysis, the knowledge storage system can apply different analysis algorithms depending on the category of data. For example, a voice analysis algorithm can be applied to voice data, and a text analysis algorithm can be applied to text data. Furthermore, the most suitable analysis algorithm can be selected depending on the data category. This improves the accuracy of analysis by applying the most suitable analysis algorithm depending on the data category.

[0086] During analysis, the knowledge storage system can determine the analysis priority based on when the data was collected. For example, the most recent data can be analyzed first. The analysis priority can also be lowered for older data. Furthermore, the analysis priority can be dynamically adjusted according to when the data was collected. This allows for efficient analysis by determining the analysis priority based on when the data was collected.

[0087] The process flow of the first embodiment will be briefly described below.

[0088] Step 1: The collection unit collects user voice and text data. For example, the collection unit collects user voice data using voice recognition technology, and converts it into text data using a voice recognition algorithm or a pre-processing method for the voice data. In addition, the collection unit collects user text data using text processing technology, and performs morphological analysis, grammatical analysis, semantic analysis, etc. Step 2: The analysis unit analyzes the data collected by the collection unit and learns the user's knowledge, personality, and speaking habits. For example, the analysis unit uses machine learning algorithms and natural language processing technology to analyze the collected voice data and text data and extract the user's characteristics. Step 3: The storage unit stores the features learned by the analysis unit, for example, in a form such as a relational database or a NoSQL database. Step 4: The decision support unit supports the user in making decisions based on the features stored by the storage unit, for example by providing advice to the user based on past data. Step 5: The skill improvement unit supports the user in improving their skills based on the features stored by the storage unit. For example, it provides a function to look back on one's past statements and writings, analyzes past data using AI, and provides feedback to the user. Step 6: The dementia prevention unit supports the user's dementia prevention based on the characteristics stored by the storage unit. For example, it supports memory maintenance by reproducing the user's past characteristics, analyzes past data using AI, reproduces the user's characteristics, and performs memory training.

[0089] (Example 2) The knowledge storage system according to the embodiment of the present invention is a system that allows an AI to learn and store the characteristics of a user, such as knowledge, personality, and speaking habits, and is useful for future decision-making support, self-improvement, and dementia prevention. This knowledge storage system collects the user's voice and text data, and the AI ​​analyzes them to learn the characteristics of the user, such as knowledge, personality, and speaking habits. The learned characteristics are stored in the AI, and in the future, the user's decision-making can be supported based on the stored characteristics. For example, when a user makes an important decision, the AI ​​provides advice based on past data. In addition, the user can look back on his or her past remarks and sentences for self-improvement. Furthermore, as a dementia prevention measure, the system supports memory maintenance by reproducing the user's past characteristics. For example, the knowledge storage system collects the user's voice and text data. For example, the user's voice data can be collected using voice recognition technology. In addition, the user's text data can be collected using text processing technology. Next, the knowledge storage system uses the AI ​​to analyze the collected data and learn the characteristics of the user, such as knowledge, personality, and speaking habits. For example, the AI ​​uses natural language processing technology to analyze the voice data and text data and extract the user's characteristics. The learned features are stored in a database. For example, the database is stored in a form such as a relational database or a NoSQL database. In the future, the stored features can be used to support user decision-making. For example, the AI ​​can provide advice to the user based on past data. In addition, the user can review their past statements and writings for self-improvement. For example, the AI ​​can provide feedback to the user based on past data. In addition, to prevent dementia, the AI ​​can support memory maintenance by reproducing the user's past features. For example, the AI ​​can reproduce the user's features based on past data and perform memory training. This allows the knowledge storage system to learn the user's features such as knowledge, personality, and speaking habits in detail, and use them for future decision-making, self-improvement, and dementia prevention. This allows the knowledge storage system to learn the user's features such as knowledge, personality, and speaking habits in detail, and use them for future decision-making, self-improvement, and dementia prevention.

[0090] The knowledge storage system according to the embodiment includes a collection unit, an analysis unit, a storage unit, a decision support unit, a self-study unit, and a dementia prevention unit. The collection unit collects the user's voice and text data. The collection unit can collect the user's voice data using, for example, a voice recognition technology. The collection unit can also collect the user's text data using a text processing technology. For example, the collection unit collects the user's voice data using a voice recognition technology. The voice recognition technology can use, for example, a voice recognition algorithm or a preprocessing method for voice data. The collection unit records, for example, the user's voice data with a microphone and converts it into text data using a voice recognition algorithm. The collection unit collects the user's text data using a text processing technology. The text processing technology can use, for example, morphological analysis, grammatical analysis, semantic analysis, and the like. For example, the collection unit collects the user's text data as a text file and performs morphological analysis. The analysis unit analyzes the data collected by the collection unit and learns the user's knowledge, personality, and speaking habits. The analysis unit can use, for example, a machine learning algorithm or a natural language processing technology. The analysis unit, for example, analyzes collected voice data and text data using a machine learning algorithm to extract features of the user. The storage unit stores the features learned by the analysis unit. The storage unit can store the features using, for example, a database. The storage unit stores the features in a format such as a relational database or a NoSQL database. The decision support unit supports the user's decision-making based on the features stored by the storage unit. The decision support unit can provide advice to the user based on past data, for example. The decision support unit can analyze past data using, for example, AI, and provide advice to the user. The self-improvement unit supports the user's self-improvement based on the features stored by the storage unit. The self-improvement unit can provide, for example, a function to look back on one's own past remarks and writings. The self-improvement unit analyzes past data using, for example, AI, and provides feedback to the user. The dementia prevention unit supports the user's dementia prevention based on the features stored by the storage unit.The dementia prevention unit can support memory maintenance by, for example, reproducing the user's past characteristics. The dementia prevention unit can, for example, analyze past data using AI, reproduce the user's characteristics, and perform memory training. As a result, the knowledge storage system according to the embodiment can learn the user's knowledge, personality, speech habits, and other characteristics in detail, and use them for future decision-making, self-improvement, and dementia prevention.

[0091] The collection unit collects the user's voice and text data. The collection unit can collect the user's voice data using, for example, a voice recognition technology. The collection unit can also collect the user's text data using a text processing technology. Specifically, the collection unit collects the user's voice data using a voice recognition technology. The voice recognition technology can use, for example, a voice recognition algorithm or a pre-processing method for voice data. The collection unit, for example, records the user's voice data with a microphone and converts it into text data using a voice recognition algorithm. The voice recognition algorithm converts the voice signal into digital data and recognizes phonemes and words. This allows the user's utterance to be accurately converted into text. The collection unit also collects the user's text data using a text processing technology. The text processing technology can use, for example, morphological analysis, grammatical analysis, semantic analysis, and the like. The collection unit, for example, collects the user's text data as a text file and performs morphological analysis. Morphological analysis is a technology that divides a sentence into words and analyzes the parts of speech and meanings of each word. This allows the user's text data to be analyzed in detail and the user's intentions and emotions to be understood. Furthermore, the collection unit centrally manages the collected data and allows the analysis unit and storage unit to access it. For example, the collected data can be stored in a cloud server and linked to other systems and departments as necessary. This allows the collection unit to collect data efficiently and effectively and improve the performance of the entire system.

[0092] The analysis unit analyzes the data collected by the collection unit and learns the user's knowledge, personality, and speaking habits. The analysis unit can use, for example, a machine learning algorithm or a natural language processing technology. Specifically, the collected voice data and text data are analyzed using a machine learning algorithm to extract the user's characteristics. The machine learning algorithm learns patterns based on a large amount of data and models the characteristics of the user's remarks and text. For example, the voice data can analyze the user's tone of voice, speech rhythm, and frequency of use of specific phrases. The text data can analyze the user's writing style, vocabulary selection, text structure, and the like. Furthermore, the analysis unit uses natural language processing technology to understand the meaning of the user's remarks and text. Natural language processing technology is a technology that combines morphological analysis, grammatical analysis, semantic analysis, and the like to analyze the meaning of text. This allows the analysis unit to understand the intention and emotion of the user's remarks and text, and to grasp the user's characteristics in detail. Furthermore, the analysis unit can predict the user's behavioral patterns and tendencies by utilizing past data and statistical information. For example, based on past speech data, it can predict the user's reaction and behavior in a specific situation, and use the data to help with future decision-making and self-improvement. This allows the analysis unit to analyze collected data quickly and accurately, and learn the characteristics of the user in detail.

[0093] The storage unit stores the features learned by the analysis unit. The storage unit can store the features using, for example, a database. Specifically, the storage unit stores the features in a format such as a relational database or a NoSQL database. A relational database manages data in a table format and can search and update data using SQL. This allows the storage unit to efficiently manage the user's features and quickly access them as needed. In addition, a NoSQL database has excellent scalability and flexibility and can efficiently store large amounts of data. This allows the storage unit to store the user's features for a long period of time and prepare for future use. Furthermore, the storage unit must also take into consideration data security and privacy protection. For example, the stored data is protected using encryption technology to prevent unauthorized access and data leakage. In addition, the storage unit has a data backup and recovery function and can prepare for data loss or damage. This allows the storage unit to safely and efficiently store the features learned by the analysis unit and improve the reliability of the entire system.

[0094] The decision support unit supports the user's decision-making based on the features stored by the storage unit. The decision support unit can provide advice to the user based on past data, for example. Specifically, the decision support unit uses AI to analyze past data and provide advice to the user. The AI ​​uses a machine learning algorithm to learn patterns and trends from past data and generate advice according to the user's current situation. For example, the decision support unit can suggest optimal actions and options in a specific situation based on past utterance data. In addition, the decision support unit can analyze the results of the user's past decisions and actions and provide information that is useful for future decision-making. This allows the decision support unit to support the user's decision-making and provide information to lead to better results. Furthermore, the decision support unit can continuously improve the accuracy and effectiveness of the advice based on data updated in real time. For example, by collecting user feedback and reviewing the content and method of providing the advice, more effective support can be provided. This allows the decision support unit to provide the user with prompt and appropriate advice and improve the quality of decision-making.

[0095] The self-improvement unit supports the user's self-improvement based on the characteristics stored by the storage unit. The self-improvement unit can provide, for example, a function for reviewing one's own past remarks and writings. Specifically, the self-improvement unit uses AI to analyze past data and provide feedback to the user. The AI ​​uses a machine learning algorithm to analyze the characteristics of past remarks and writings and point out the user's growth and improvement points. For example, based on past remark data, it can point out specific speaking habits and points to be improved and provide specific advice to the user. In addition, the self-improvement unit can provide learning content and training programs according to the user's goals and interests. This allows the self-improvement unit to support the user's self-improvement and promote the improvement of skills and knowledge. Furthermore, the self-improvement unit can monitor the user's progress and provide feedback and advice at an appropriate time. For example, the self-improvement unit periodically analyzes the user's remarks and writings, evaluates the progress, and suggests new goals and training programs as necessary. This allows the self-improvement unit to continuously support the user's self-improvement and provide an effective learning environment.

[0096] The dementia prevention unit supports the user's dementia prevention based on the characteristics stored by the storage unit. The dementia prevention unit can support memory maintenance by, for example, reproducing one's own past characteristics. Specifically, the dementia prevention unit uses AI to analyze past data, reproduce the user's characteristics, and perform memory training. The AI ​​uses a machine learning algorithm to model the characteristics of past remarks and sentences, and generates a training program that stimulates the user's memory. For example, based on past remark data, it is possible to reproduce phrases and topics frequently used by the user and perform training to evoke memories. In addition, the dementia prevention unit can evaluate the user's cognitive function and provide an appropriate training program. This allows the dementia prevention unit to support the maintenance of the user's memory and cognitive function, and to be useful in preventing dementia. Furthermore, the dementia prevention unit can monitor the user's progress and evaluate the effectiveness of the training program. For example, by regularly evaluating the user's cognitive function and adjusting the content and difficulty of the training program, effective preventive measures can be provided. This allows the dementia prevention unit to continuously support the maintenance of the user's cognitive function and reduce the risk of dementia.

[0097] The knowledge storage system includes a voice recognition unit that collects user voice data using voice recognition technology. The voice recognition unit collects user voice data using, for example, voice recognition technology. The voice recognition technology can use, for example, a voice recognition algorithm or a voice data preprocessing method. The voice recognition unit, for example, records user voice data with a microphone and converts it into text data using a voice recognition algorithm. The voice recognition unit can also collect user voice data in real time using voice recognition technology. For example, the voice recognition unit generates text data simultaneously with voice input and performs analysis in real time. Furthermore, the voice recognition unit can support multiple languages ​​using voice recognition technology. For example, the voice recognition unit recognizes voice input in multiple languages ​​such as English, Japanese, and French, and converts it into text data. As a result, the voice recognition technology can be used to efficiently collect user voice data. A part or all of the above-mentioned processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice recognition unit can input voice data to a generation AI and cause the generation AI to convert the voice data into text data.

[0098] The knowledge storage system includes a text processing unit that collects text data of a user using a text processing technique. The text processing unit collects text data of a user using, for example, a text processing technique. The text processing technique can use, for example, morphological analysis, grammatical analysis, semantic analysis, and the like. The text processing unit can collect, for example, the text data of a user as a text file and perform morphological analysis. The text processing unit can also collect the text data of a user in real time using the text processing technique. For example, the text processing unit performs analysis simultaneously with text input and collects data in real time. Furthermore, the text processing unit can support multiple languages ​​using the text processing technique. For example, the text processing unit analyzes and collects text data in multiple languages ​​such as English, Japanese, and French. As a result, the text processing technique can be used to efficiently collect the text data of a user. A part or all of the above-mentioned processing in the text processing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the text processing unit can input text data to a generation AI and cause the generation AI to execute analysis of the text data.

[0099] The knowledge storage system includes a database unit that includes a database for storing the learned features. The database unit includes, for example, a database for storing the learned features. The database is stored in a format such as a relational database or a NoSQL database. The database unit uses, for example, a relational database to efficiently store the learned features. The database unit can also flexibly store the learned features using a NoSQL database. For example, the database unit uses a relational database to store the learned features in a table format. The NoSQL database is a schema-less database and allows flexible data storage. This allows the learned features to be efficiently stored. A part or all of the above-mentioned processing in the database unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the database unit can input the learned features to a generation AI and cause the generation AI to execute storage in the database.

[0100] The knowledge storage system includes an advice providing unit that provides advice to support the user's decision making. The advice providing unit provides, for example, advice to support the user's decision making. The advice is provided, for example, in a text format or a voice format. The advice providing unit provides, for example, advice to the user based on past data. The advice providing unit analyzes past data using, for example, AI and provides advice to the user. For example, the advice providing unit provides optimal advice to the user based on past data. The advice providing unit can also customize advice based on the user's current situation. For example, the advice providing unit analyzes the user's current situation and provides optimal advice. This makes it possible to provide advice to support the user's decision making. A part or all of the above-mentioned processing in the advice providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice providing unit inputs the content of the advice to a generation AI and causes the generation AI to execute the generation of the advice.

[0101] The knowledge storage system includes a review providing unit that provides a function of reviewing past statements and sentences for the user's self-improvement. The review providing unit provides, for example, a function of reviewing past statements and sentences for the user's self-improvement. The review providing unit provides, for example, feedback to the user based on past data. The review providing unit analyzes past data using, for example, AI, and provides feedback to the user. For example, the review providing unit provides optimal feedback to the user based on past data. The review providing unit can also customize feedback based on the user's current situation. For example, the review providing unit analyzes the user's current situation and provides optimal feedback. This allows the user to review past statements and sentences for self-improvement. A part or all of the above-mentioned processing in the review providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the review providing unit can input the content of the feedback to the generation AI and cause the generation AI to generate the feedback.

[0102] The knowledge storage system includes a memory reproducing unit that reproduces past characteristics of the user to prevent dementia. The memory reproducing unit reproduces past characteristics of the user to prevent dementia, for example. The memory reproducing unit reproduces the characteristics of the user based on past data, for example, and performs memory training. The memory reproducing unit analyzes past data using, for example, AI, and reproduces the characteristics of the user. For example, the memory reproducing unit provides optimal memory training to the user based on past data. The memory reproducing unit can also customize memory training based on the current situation of the user. For example, the memory reproducing unit analyzes the current situation of the user and provides optimal memory training. This makes it possible to reproduce past characteristics to prevent dementia of the user. A part or all of the above-mentioned processing in the memory reproducing unit may be performed using, for example, AI, or may be performed without using AI. For example, the memory reproducing unit can input the contents of the memory training to the generating AI and cause the generating AI to execute the generation of the memory training.

[0103] The collection unit can estimate the user's emotion and adjust the timing of collecting voice and text data based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and adjusts the timing of collecting voice and text data based on the estimated user's emotion. For example, when the user is relaxed, the collection unit collects voice data in a natural conversation. In addition, when the user is concentrating, the collection unit can also prioritize the collection of text data. Furthermore, when the user is stressed, the collection unit can delay the collection timing. This allows more appropriate data collection by adjusting the collection timing based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the result of the emotion estimation to the generation AI and cause the generation AI to adjust the collection timing.

[0104] The collection unit can analyze the user's past data collection history and select the optimal collection method. The collection unit, for example, analyzes the user's past data collection history and selects the optimal collection method. The collection unit, for example, prioritizes the collection method (audio, text, etc.) that the user has used in the past. The collection unit can also suggest the most efficient collection timing from the user's past data collection history. Furthermore, the collection unit can customize the collection method based on the user's past data collection history. In this way, the optimal collection method can be selected by analyzing the past data collection history. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the past data collection history to the generation AI and cause the generation AI to select the optimal collection method.

[0105] The collection unit can perform filtering based on the user's current activity status and field of interest when collecting data. For example, the collection unit performs filtering based on the user's current activity status and field of interest when collecting data. For example, the collection unit preferentially collects data related to the activity currently being performed by the user. The collection unit can also filter related data based on the user's field of interest. Furthermore, the collection unit can adjust the type of data to be collected in consideration of the user's current activity status. This makes it possible to collect highly relevant data by filtering data based on the current activity status and field of interest. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the current activity status and field of interest to the generation AI and cause the generation AI to perform filtering.

[0106] The collection unit can estimate the user's emotion and determine the priority of data to be collected based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and determines the priority of data to be collected based on the estimated user's emotion. For example, when the user is relaxed, the collection unit prioritizes the collection of voice data. Also, when the user is concentrating, the collection unit can prioritize the collection of text data. Furthermore, when the user is stressed, the collection unit can adjust the priority of data to be collected. In this way, by determining the priority of data based on the user's emotion, more important data can be preferentially collected. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the result of the emotion estimation to the generation AI and cause the generation AI to execute the determination of the priority of data.

[0107] The collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the user when collecting data. For example, the collection unit preferentially collects highly relevant data in consideration of the geographical location information of the user when collecting data. For example, when the user is in a specific location, the collection unit preferentially collects data related to the location. The collection unit can also filter highly relevant data based on the geographical location information of the user. Furthermore, the collection unit can adjust the type of data to be collected based on the current location of the user. This allows highly relevant data to be preferentially collected by considering the geographical location information. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input geographical location information to the generation AI and cause the generation AI to perform data filtering.

[0108] The collection unit can analyze the social media activity of the user at the time of data collection and collect related data. For example, the collection unit analyzes the social media activity of the user at the time of data collection and collects related data. For example, the collection unit analyzes the content of the user's social media posts and collects related data. The collection unit can also identify an area of ​​interest from the user's social media activity and collect related data. Furthermore, the collection unit can adjust the type of data to be collected based on the user's social media activity. This makes it possible to efficiently collect related data by analyzing social media activity. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input social media activity to a generation AI and cause the generation AI to collect data.

[0109] The analysis unit can estimate the user's emotion and adjust the expression method of the analysis based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the expression method of the analysis based on the estimated user's emotion. The analysis unit provides a detailed analysis result when the user is relaxed, for example. The analysis unit can also provide a concise analysis result when the user is in a hurry. Furthermore, the analysis unit can also provide a visually easy-to-understand analysis result when the user is stressed. This makes it possible to provide a more appropriate analysis result by adjusting the expression method of the analysis based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the result of the emotion estimation to the generation AI and cause the generation AI to adjust the expression method of the analysis.

[0110] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during analysis. The analysis unit, for example, adjusts the level of detail of the analysis based on the importance of the data during analysis. The analysis unit, for example, performs a detailed analysis on data with high importance. The analysis unit can also perform a concise analysis on data with low importance. Furthermore, the analysis unit can dynamically adjust the level of detail of the analysis according to the importance of the data. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the importance of the data to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0111] The analysis unit can apply different analysis algorithms depending on the category of data during analysis. The analysis unit applies different analysis algorithms depending on the category of data during analysis, for example. The analysis unit applies a voice analysis algorithm to voice data, for example. The analysis unit can also apply a text analysis algorithm to text data. Furthermore, the analysis unit can select an optimal analysis algorithm depending on the category of data. This improves the analysis accuracy by applying an optimal analysis algorithm depending on the category of data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the category of data to the generation AI and cause the generation AI to select the analysis algorithm.

[0112] The analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the length of the analysis based on the estimated user's emotion. For example, when the user is in a hurry, the analysis unit provides a short and to the point analysis result. In addition, the analysis unit can also provide a detailed analysis result when the user is relaxed. Furthermore, when the user is stressed, the analysis unit can also provide a visually easy-to-understand analysis result. This makes it possible to provide a more appropriate analysis result by adjusting the length of the analysis based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the result of the emotion estimation to the generation AI and cause the generation AI to adjust the length of the analysis.

[0113] The analysis unit can determine the analysis priority based on the collection time of the data during the analysis. The analysis unit, for example, determines the analysis priority based on the collection time of the data during the analysis. The analysis unit, for example, prioritizes the analysis of the latest data. The analysis unit can also lower the analysis priority for old data. Furthermore, the analysis unit can dynamically adjust the analysis priority according to the collection time of the data. This enables efficient analysis by determining the analysis priority based on the collection time of the data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the collection time of the data to the generation AI and cause the generation AI to determine the analysis priority.

[0114] The analysis unit can adjust the order of analysis based on the relevance of data during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of data during analysis. The analysis unit, for example, prioritizes analysis of highly relevant data. The analysis unit can also postpone the order of analysis for less relevant data. Furthermore, the analysis unit can dynamically adjust the order of analysis according to the relevance of data. This enables efficient analysis by adjusting the order of analysis based on the relevance of data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance of data to the generation AI and cause the generation AI to adjust the order of analysis.

[0115] The storage unit can estimate the user's emotion and determine the priority of data to be stored based on the estimated user's emotion. The storage unit, for example, estimates the user's emotion and determines the priority of data to be stored based on the estimated user's emotion. For example, when the user is relaxed, the storage unit preferentially stores important data. In addition, when the user is in a hurry, the storage unit can also preferentially store concise data. Furthermore, when the user is stressed, the storage unit can adjust the priority of data to be stored. In this way, by determining the priority of data based on the user's emotion, more important data can be preferentially stored. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the storage unit can input the result of the emotion estimation to the generation AI and cause the generation AI to execute the determination of the priority of data.

[0116] The storage unit can adjust the level of detail of the storage based on the importance of the data at the time of storage. For example, the storage unit adjusts the level of detail of the storage based on the importance of the data at the time of storage. For example, the storage unit performs detailed storage for data with high importance. In addition, the storage unit can perform concise storage for data with low importance. Furthermore, the storage unit can dynamically adjust the level of detail of the storage according to the importance of the data. As a result, efficient data storage is possible by adjusting the level of detail of the storage based on the importance of the data. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the importance of the data to the generation AI and cause the generation AI to adjust the level of detail of the storage.

[0117] The storage unit can apply different storage algorithms depending on the category of data when storing. The storage unit applies different storage algorithms depending on the category of data when storing, for example. The storage unit applies an audio storage algorithm to audio data, for example. The storage unit can also apply a text storage algorithm to text data. Furthermore, the storage unit can select an optimal storage algorithm depending on the category of data. This improves storage accuracy by applying an optimal storage algorithm depending on the category of data. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the category of data to the generation AI and cause the generation AI to select a storage algorithm.

[0118] The storage unit can estimate the user's emotion and adjust the display method of the data to be stored based on the estimated user's emotion. The storage unit, for example, estimates the user's emotion and adjusts the display method of the data to be stored based on the estimated user's emotion. The storage unit provides a detailed display method when the user is relaxed, for example. The storage unit can also provide a concise display method when the user is in a hurry. Furthermore, the storage unit can also provide a visually easy-to-understand display method when the user is stressed. This enables more appropriate data display by adjusting the data display method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the storage unit can input the result of the emotion estimation to the generation AI and cause the generation AI to adjust the data display method.

[0119] The storage unit can determine the priority of storage based on the collection time of data at the time of storage. For example, the storage unit determines the priority of storage based on the collection time of data at the time of storage. For example, the storage unit preferentially stores the latest data. The storage unit can also lower the priority of storage for old data. Furthermore, the storage unit can dynamically adjust the priority of storage according to the collection time of data. This enables efficient data storage by determining the priority of storage based on the collection time of data. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the collection time of data to the generation AI and cause the generation AI to execute the determination of the priority of storage.

[0120] The storage unit can adjust the order of storage based on the relevance of data when storing. The storage unit, for example, adjusts the order of storage based on the relevance of data when storing. The storage unit, for example, prioritizes storage of highly relevant data. The storage unit can also postpone the order of storage for data with low relevance. Furthermore, the storage unit can dynamically adjust the order of storage according to the relevance of data. This enables efficient data storage by adjusting the order of storage based on the relevance of data. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the relevance of data to the generation AI and cause the generation AI to adjust the order of storage.

[0121] The decision support unit can estimate the user's emotion and adjust the decision support method based on the estimated user's emotion. The decision support unit, for example, estimates the user's emotion and adjusts the decision support method based on the estimated user's emotion. The decision support unit provides a detailed support method when the user is relaxed, for example. The decision support unit can also provide a concise support method when the user is in a hurry. Furthermore, the decision support unit can also provide a visually easy-to-understand support method when the user is stressed. This enables more appropriate support by adjusting the decision support method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the decision support unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the decision support unit can input the result of the emotion estimation to the generation AI and cause the generation AI to execute the adjustment of the support method.

[0122] The decision support unit can select the optimal support method by referring to the past decision history during decision support. For example, the decision support unit selects the optimal support method by referring to the past decision history during decision support. The decision support unit, for example, proposes the optimal support method based on the user's past decision history. The decision support unit can also preferentially propose successful methods from the past decision history. Furthermore, the decision support unit can analyze the past decision history and select the most effective support method. As a result, the optimal support method can be selected by referring to the past decision history. A part or all of the above-mentioned processing in the decision support unit may be performed, for example, using AI, or may be performed without using AI. For example, the decision support unit can input the past decision history to the generation AI and cause the generation AI to select the support method.

[0123] The decision support unit can customize the means of support based on the user's current situation during decision support. For example, the decision support unit customizes the means of support based on the user's current situation during decision support. For example, when the user is in an emergency situation, the decision support unit provides a means of supporting quick decision making. In addition, when the user is relaxed, the decision support unit can also provide detailed information to support decision making. Furthermore, when the user is stressed, the decision support unit can also provide a visually easy-to-understand support means. This enables more appropriate support by customizing the means of support based on the user's current situation. Part or all of the above-mentioned processing in the decision support unit may be performed, for example, using AI or may be performed without using AI. For example, the decision support unit can input the current situation to the generation AI and cause the generation AI to execute customization of the support means.

[0124] The decision support unit can estimate the user's emotions and determine the priority of decision making based on the estimated user's emotions. The decision support unit can, for example, estimate the user's emotions and determine the priority of decision making based on the estimated user's emotions. The decision support unit can, for example, prioritize important decision making when the user is relaxed. The decision support unit can also prioritize matters that can be quickly decided when the user is in a hurry. Furthermore, the decision support unit can adjust the priority of decision making when the user is stressed. In this way, by determining the priority of decision making based on the user's emotions, it is possible to preferentially support more important decision making. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the decision support unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the decision support unit can input the result of the emotion estimation to the generation AI and cause the generation AI to execute the determination of the priority of decision making.

[0125] The decision support unit can select the optimal support method in consideration of the geographical location information of the user during decision support. For example, the decision support unit selects the optimal support method in consideration of the geographical location information of the user during decision support. For example, when the user is in a specific location, the decision support unit provides information related to the location to support decision making. The decision support unit can also suggest the optimal support method based on the geographical location information of the user. Furthermore, the decision support unit can also customize the means of decision making based on the current location of the user. In this way, the optimal support method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the decision support unit may be performed, for example, using AI, or may be performed without using AI. For example, the decision support unit can input geographical location information to the generation AI and cause the generation AI to select the support method.

[0126] The decision support unit can analyze the user's social media activity and suggest a means of support during decision support. For example, the decision support unit analyzes the user's social media activity and suggests a means of support during decision support. For example, the decision support unit analyzes the user's social media posting content and provides related information to support decision making. The decision support unit can also identify the user's field of interest from the user's social media activity and suggest the optimal support method. Furthermore, the decision support unit can customize the means of decision making based on the user's social media activity. In this way, related support means can be suggested by analyzing the social media activity. Part or all of the above-mentioned processing in the decision support unit may be performed, for example, using AI or may be performed without using AI. For example, the decision support unit can input the social media activity to the generation AI and cause the generation AI to execute the suggestion of the support means.

[0127] The self-study unit can estimate the user's emotions and adjust the self-study method based on the estimated user's emotions. The self-study unit, for example, estimates the user's emotions and adjusts the self-study method based on the estimated user's emotions. The self-study unit provides a detailed training method when the user is relaxed, for example. The self-study unit can also provide a concise training method when the user is in a hurry. Furthermore, the self-study unit can also provide a visually easy-to-understand training method when the user is stressed. This allows for more appropriate training by adjusting the self-study method based on the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the self-study unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the self-improvement unit can input the results of emotion estimation to the generation AI and cause the generation AI to adjust the training method.

[0128] The self-study unit can select the optimal training method by referring to the past self-study history during self-study. For example, the self-study unit selects the optimal training method by referring to the past self-study history during self-study. The self-study unit, for example, proposes the optimal training method based on the user's past self-study history. The self-study unit can also preferentially propose successful methods from the past self-study history. Furthermore, the self-study unit can analyze the past self-study history and select the most effective training method. As a result, the optimal training method can be selected by referring to the past self-study history. A part or all of the above-mentioned processing in the self-study unit may be performed, for example, using AI, or may be performed without using AI. For example, the self-study unit can input the past self-study history into the generation AI and cause the generation AI to select the training method.

[0129] The self-study unit can customize the means of self-study based on the current situation of the user during self-study. The self-study unit customizes the means of self-study based on the current situation of the user, for example, during self-study. The self-study unit provides a means for supporting rapid study when the user is in an emergency situation, for example. The self-study unit can also support the study by providing detailed information when the user is relaxed. Furthermore, the self-study unit can also provide a visually easy-to-understand study means when the user is feeling stressed. This enables more appropriate study by customizing the means of study based on the current situation of the user. Part or all of the above-mentioned processing in the self-study unit may be performed, for example, using AI, or may be performed without using AI. For example, the self-study unit can input the current situation to the generation AI and cause the generation AI to execute customization of the study means.

[0130] The self-study unit can estimate the user's emotions and determine the priority of self-study based on the estimated user's emotions. The self-study unit, for example, estimates the user's emotions and determines the priority of self-study based on the estimated user's emotions. For example, when the user is relaxed, the self-study unit prioritizes important training. In addition, when the user is in a hurry, the self-study unit can also prioritize matters that can be trained quickly. Furthermore, when the user is stressed, the self-study unit can adjust the priority of training. In this way, by determining the priority of self-study based on the user's emotions, more important training can be prioritized. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the self-study unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the self-improvement unit can input the results of emotion estimation to the generation AI and have the generation AI determine the priorities of training.

[0131] The self-study unit can select the optimal training method in consideration of the geographical location information of the user during self-study. For example, the self-study unit selects the optimal training method in consideration of the geographical location information of the user during self-study. For example, when the user is in a specific location, the self-study unit supports the training by providing information related to the location. The self-study unit can also suggest the optimal training method based on the geographical location information of the user. Furthermore, the self-study unit can also customize the means of training based on the user's current location. This makes it possible to select the optimal training method by considering the geographical location information. A part or all of the above-mentioned processing in the self-study unit may be performed, for example, using AI, or may be performed without using AI. For example, the self-study unit can input geographical location information to the generation AI and cause the generation AI to select the training method.

[0132] The self-improvement unit can analyze the social media activity of the user during self-improvement and suggest a means of self-improvement. The self-improvement unit, for example, analyzes the social media activity of the user during self-improvement and suggests a means of self-improvement. The self-improvement unit, for example, analyzes the content of the user's social media posts and provides related information to support the self-improvement. The self-improvement unit can also identify the user's field of interest from the user's social media activity and suggest an optimal method of self-improvement. Furthermore, the self-improvement unit can customize the means of self-improvement based on the user's social media activity. This makes it possible to suggest related means of self-improvement by analyzing the social media activity. A part or all of the above-mentioned processing in the self-improvement unit may be performed, for example, using AI, or may be performed without using AI. For example, the self-improvement unit can input the social media activity to the generation AI and cause the generation AI to execute the suggestion of the means of self-improvement.

[0133] The dementia prevention unit can estimate the user's emotion and adjust the dementia prevention method based on the estimated user's emotion. The dementia prevention unit, for example, estimates the user's emotion and adjusts the dementia prevention method based on the estimated user's emotion. The dementia prevention unit, for example, provides a detailed prevention method when the user is relaxed. The dementia prevention unit can also provide a concise prevention method when the user is in a hurry. Furthermore, the dementia prevention unit can also provide a visually easy-to-understand prevention method when the user is stressed. This enables more appropriate prevention by adjusting the dementia prevention method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the dementia prevention unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the dementia prevention unit can input the result of the emotion estimation to the generation AI and cause the generation AI to execute the adjustment of the prevention method.

[0134] The dementia prevention unit can select the optimal prevention method by referring to the past dementia prevention history when preventing dementia. For example, the dementia prevention unit selects the optimal prevention method by referring to the past dementia prevention history when preventing dementia. The dementia prevention unit, for example, proposes the optimal prevention method based on the user's past dementia prevention history. The dementia prevention unit can also preferentially propose successful methods from the past dementia prevention history. Furthermore, the dementia prevention unit can analyze the past dementia prevention history and select the most effective prevention method. As a result, the optimal prevention method can be selected by referring to the past dementia prevention history. Part or all of the above-mentioned processing in the dementia prevention unit may be performed, for example, using AI or may be performed without using AI. For example, the dementia prevention unit can input the past dementia prevention history to the generation AI and cause the generation AI to select the prevention method.

[0135] The dementia prevention unit can customize preventive measures based on the user's current situation during dementia prevention. The dementia prevention unit customizes preventive measures based on the user's current situation during dementia prevention, for example. The dementia prevention unit provides a means to support rapid prevention when the user is in an emergency situation, for example. The dementia prevention unit can also provide detailed information to support prevention when the user is relaxed. Furthermore, the dementia prevention unit can also provide visually easy-to-understand preventive measures when the user is feeling stressed. This enables more appropriate prevention by customizing preventive measures based on the user's current situation. Part or all of the above-mentioned processing in the dementia prevention unit may be performed, for example, using AI or may be performed without using AI. For example, the dementia prevention unit can input the current situation to the generation AI and cause the generation AI to execute customization of preventive measures.

[0136] The dementia prevention unit can estimate the user's emotions and determine the priority of dementia prevention based on the estimated user's emotions. The dementia prevention unit, for example, estimates the user's emotions and determines the priority of dementia prevention based on the estimated user's emotions. For example, when the user is relaxed, the dementia prevention unit prioritizes important prevention. In addition, when the user is in a hurry, the dementia prevention unit can also prioritize matters that can be prevented quickly. Furthermore, when the user is stressed, the dementia prevention unit can adjust the priority of prevention. As a result, by determining the priority of dementia prevention based on the user's emotions, more important prevention can be prioritized. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the dementia prevention unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the dementia prevention unit can input the result of the emotion estimation to the generation AI and cause the generation AI to execute the determination of the priority of prevention.

[0137] The dementia prevention unit can select the optimal prevention method in consideration of the geographical location information of the user during dementia prevention. For example, the dementia prevention unit selects the optimal prevention method in consideration of the geographical location information of the user during dementia prevention. For example, when the user is in a specific location, the dementia prevention unit supports prevention by providing information related to the location. The dementia prevention unit can also suggest the optimal prevention method based on the geographical location information of the user. Furthermore, the dementia prevention unit can also customize the means of prevention based on the user's current location. In this way, the optimal prevention method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the dementia prevention unit may be performed, for example, using AI or may be performed without using AI. For example, the dementia prevention unit can input geographical location information to the generation AI and cause the generation AI to select a prevention method.

[0138] The dementia prevention unit can analyze the social media activity of the user and suggest preventive measures when preventing dementia. For example, the dementia prevention unit analyzes the social media activity of the user and suggests preventive measures when preventing dementia. For example, the dementia prevention unit analyzes the content of the user's social media posts and provides related information to support prevention. The dementia prevention unit can also identify areas of interest from the user's social media activities and suggest optimal preventive methods. Furthermore, the dementia prevention unit can customize preventive measures based on the user's social media activities. As a result, related preventive measures can be suggested by analyzing social media activities. Some or all of the above-mentioned processing in the dementia prevention unit may be performed, for example, using AI or may be performed without using AI. For example, the dementia prevention unit can input social media activities to the generation AI and cause the generation AI to execute the proposal of preventive measures.

[0139] The voice recognition unit can estimate the user's emotion and adjust the accuracy of the voice recognition based on the estimated user's emotion. The voice recognition unit, for example, estimates the user's emotion and adjusts the accuracy of the voice recognition based on the estimated user's emotion. The voice recognition unit, for example, performs detailed voice recognition when the user is relaxed. The voice recognition unit can also perform concise voice recognition when the user is in a hurry. Furthermore, the voice recognition unit can also perform visually easy-to-understand voice recognition when the user is stressed. This enables more appropriate voice recognition by adjusting the accuracy of the voice recognition based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the voice recognition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the voice recognition unit can input the result of the emotion estimation to the generation AI and cause the generation AI to adjust the accuracy of the voice recognition.

[0140] The voice recognition unit can optimize the recognition algorithm by referring to past voice data during voice recognition. The voice recognition unit optimizes the recognition algorithm by referring to past voice data during voice recognition, for example. The voice recognition unit selects an optimal recognition algorithm based on, for example, the user's past voice data. The voice recognition unit can also preferentially apply a successful recognition algorithm from the past voice data. Furthermore, the voice recognition unit can analyze past voice data and select the most effective recognition algorithm. As a result, the optimal recognition algorithm can be selected by referring to the past voice data. A part or all of the above-mentioned processing in the voice recognition unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice recognition unit can input past voice data to a generation AI and cause the generation AI to optimize the recognition algorithm.

[0141] The voice recognition unit can estimate the user's emotion and determine the priority of voice recognition based on the estimated user's emotion. The voice recognition unit can estimate the user's emotion and determine the priority of voice recognition based on the estimated user's emotion. For example, when the user is relaxed, the voice recognition unit preferentially recognizes important voice data. In addition, when the user is in a hurry, the voice recognition unit can also prioritize voice data that can be quickly recognized. Furthermore, when the user is stressed, the voice recognition unit can adjust the priority of voice recognition. As a result, by determining the priority of voice recognition based on the user's emotion, more important voice data can be preferentially recognized. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the voice recognition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the voice recognition unit can input the result of emotion estimation to the generation AI and cause the generation AI to execute the determination of the priority of voice recognition.

[0142] The voice recognition unit can select the optimal recognition method in consideration of the geographical location information of the user during voice recognition. For example, the voice recognition unit selects the optimal recognition method in consideration of the geographical location information of the user during voice recognition. For example, when the user is in a specific location, the voice recognition unit preferentially recognizes voice data related to the location. The voice recognition unit can also suggest the optimal recognition method based on the geographical location information of the user. Furthermore, the voice recognition unit can also customize the means of voice recognition based on the current location of the user. This makes it possible to select the optimal recognition method by considering the geographical location information. A part or all of the above-mentioned processing in the voice recognition unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice recognition unit can input geographical location information to the generation AI and cause the generation AI to select the recognition method.

[0143] The text processing unit can estimate the user's emotion and adjust the accuracy of text processing based on the estimated user's emotion. The text processing unit, for example, estimates the user's emotion and adjusts the accuracy of text processing based on the estimated user's emotion. The text processing unit, for example, performs detailed text processing when the user is relaxed. The text processing unit can also perform concise text processing when the user is in a hurry. Furthermore, the text processing unit can also perform visually easy-to-understand text processing when the user is stressed. This enables more appropriate text processing by adjusting the accuracy of text processing based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the text processing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the text processing unit can input the result of emotion estimation to the generation AI and cause the generation AI to adjust the accuracy of text processing.

[0144] The text processing unit can optimize the processing algorithm by referring to past text data during text processing. The text processing unit optimizes the processing algorithm by referring to past text data during text processing, for example. The text processing unit selects an optimal processing algorithm based on the user's past text data, for example. The text processing unit can also preferentially apply a successful processing algorithm from the past text data. Furthermore, the text processing unit can analyze the past text data and select the most effective processing algorithm. In this way, the optimal processing algorithm can be selected by referring to the past text data. A part or all of the above-mentioned processing in the text processing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the text processing unit can input past text data to a generation AI and cause the generation AI to optimize the processing algorithm.

[0145] The text processing unit can estimate the user's emotion and determine the priority of text processing based on the estimated user's emotion. The text processing unit, for example, estimates the user's emotion and determines the priority of text processing based on the estimated user's emotion. The text processing unit, for example, processes important text data preferentially when the user is relaxed. Also, the text processing unit can prioritize text data that can be processed quickly when the user is in a hurry. Furthermore, the text processing unit can adjust the priority of text processing when the user is stressed. As a result, more important text data can be processed preferentially by determining the priority of text processing based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the text processing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the text processing unit can input the result of emotion estimation to the generation AI and cause the generation AI to execute the determination of the priority of text processing.

[0146] The text processing unit can select the optimal processing method in consideration of the geographical location information of the user when processing text. The text processing unit, for example, selects the optimal processing method in consideration of the geographical location information of the user when processing text. For example, when the user is in a specific location, the text processing unit preferentially processes text data related to the location. The text processing unit can also suggest the optimal processing method based on the geographical location information of the user. Furthermore, the text processing unit can also customize the means of text processing based on the current location of the user. In this way, the optimal processing method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the text processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the text processing unit can input geographical location information to the generation AI and cause the generation AI to select the processing method.

[0147] The database unit can estimate the user's emotion and adjust the structure of the database based on the estimated user's emotion. The database unit, for example, estimates the user's emotion and adjusts the structure of the database based on the estimated user's emotion. The database unit provides a detailed database structure when the user is relaxed, for example. The database unit can also provide a concise database structure when the user is in a hurry. Furthermore, the database unit can also provide a visually easy-to-understand database structure when the user is stressed. This allows a more appropriate database structure to be provided by adjusting the structure of the database based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the database unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the database unit can input the result of the emotion estimation to the generation AI and cause the generation AI to adjust the database structure.

[0148] The database unit can select an optimal structure by referring to past database usage history when constructing a database. For example, the database unit selects an optimal structure by referring to past database usage history when constructing a database. The database unit, for example, proposes an optimal structure based on the user's past database usage history. The database unit can also preferentially apply a successful structure from the past database usage history. Furthermore, the database unit can analyze the past database usage history and select the most effective structure. In this way, the optimal database structure can be selected by referring to the past database usage history. A part or all of the above-mentioned processing in the database unit may be performed, for example, using AI, or may be performed without using AI. For example, the database unit can input the past database usage history to the generation AI and cause the generation AI to select a structure.

[0149] The database unit can estimate the user's emotion and determine the priority of the database based on the estimated user's emotion. The database unit, for example, estimates the user's emotion and determines the priority of the database based on the estimated user's emotion. For example, when the user is relaxed, the database unit preferentially saves important data. In addition, when the user is in a hurry, the database unit can also prioritize data that can be saved quickly. Furthermore, when the user is stressed, the database unit can adjust the priority of the database. As a result, by determining the priority of the database based on the user's emotion, more important data can be preferentially saved. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the database unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the database unit can input the result of the emotion estimation to the generation AI and cause the generation AI to execute the determination of the priority of the database.

[0150] The database unit can select an optimal structure in consideration of the geographical location information of the user when constructing the database. For example, the database unit selects an optimal structure in consideration of the geographical location information of the user when constructing the database. For example, when the user is in a specific location, the database unit preferentially stores data related to the location. The database unit can also propose an optimal database structure based on the geographical location information of the user. Furthermore, the database unit can also customize the structure of the database based on the current location of the user. In this way, the optimal database structure can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the database unit may be performed, for example, using AI, or may be performed without using AI. For example, the database unit can input geographical location information to the generation AI and cause the generation AI to select the structure.

[0151] The advice providing unit can estimate the user's emotion and adjust the way of expressing advice based on the estimated user's emotion. The advice providing unit, for example, estimates the user's emotion and adjusts the way of expressing advice based on the estimated user's emotion. The advice providing unit provides detailed advice, for example, when the user is relaxed. Furthermore, the advice providing unit can also provide concise advice when the user is in a hurry. Furthermore, the advice providing unit can also provide visually easy-to-understand advice when the user is stressed. As a result, more appropriate advice can be provided by adjusting the way of expressing advice based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the advice providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the advice providing unit can input the result of the emotion estimation to the generation AI and cause the generation AI to adjust the way of expressing advice.

[0152] The advice providing unit can select the optimal advice method by referring to the past advice history when providing advice. For example, the advice providing unit selects the optimal advice method by referring to the past advice history when providing advice. The advice providing unit proposes the optimal advice method based on the user's past advice history, for example. The advice providing unit can also preferentially propose a successful method from the past advice history. Furthermore, the advice providing unit can analyze the past advice history and select the most effective advice method. In this way, the optimal advice method can be selected by referring to the past advice history. A part or all of the above-mentioned processing in the advice providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the advice providing unit can input the past advice history to the generation AI and cause the generation AI to select the advice method.

[0153] The advice providing unit can estimate the user's emotion and determine the priority of advice based on the estimated user's emotion. The advice providing unit can, for example, estimate the user's emotion and determine the priority of advice based on the estimated user's emotion. The advice providing unit can, for example, provide important advice preferentially when the user is relaxed. Also, when the user is in a hurry, the advice providing unit can also prioritize advice that can be provided quickly. Furthermore, when the user is stressed, the advice providing unit can adjust the priority of advice. As a result, by determining the priority of advice based on the user's emotion, more important advice can be provided preferentially. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the advice providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the advice providing unit can input the result of the emotion estimation to the generation AI and cause the generation AI to execute the determination of the priority of advice.

[0154] The advice providing unit can select the optimal advice method in consideration of the geographical location information of the user when providing advice. For example, the advice providing unit selects the optimal advice method in consideration of the geographical location information of the user when providing advice. For example, when the user is in a specific location, the advice providing unit preferentially provides advice related to the location. The advice providing unit can also suggest the optimal advice method based on the geographical location information of the user. Furthermore, the advice providing unit can also customize the means of advice based on the current location of the user. In this way, the optimal advice method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the advice providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the advice providing unit can input geographical location information to the generation AI and cause the generation AI to select the advice method.

[0155] The review providing unit can estimate the user's emotion and adjust the method of review based on the estimated user's emotion. The review providing unit, for example, estimates the user's emotion and adjusts the method of review based on the estimated user's emotion. The review providing unit provides a detailed review method, for example, when the user is relaxed. Furthermore, the review providing unit can also provide a concise review method when the user is in a hurry. Furthermore, the review providing unit can also provide a visually easy-to-understand review method when the user is stressed. This allows for more appropriate review by adjusting the method of review based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the review providing unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the review providing unit can input the result of the emotion estimation to the generation AI and cause the generation AI to adjust the method of review.

[0156] The review providing unit can select the optimal review method by referring to the past review history when providing the review. For example, the review providing unit selects the optimal review method by referring to the past review history when providing the review. The review providing unit, for example, proposes the optimal review method based on the user's past review history. In addition, the review providing unit can preferentially propose successful methods from the past review history. Furthermore, the review providing unit can analyze the past review history and select the most effective review method. In this way, the optimal review method can be selected by referring to the past review history. A part or all of the above-mentioned processing in the review providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the review providing unit can input the past review history to the generation AI and cause the generation AI to select the review method.

[0157] The review providing unit can estimate the user's emotion and determine the priority of the review based on the estimated user's emotion. The review providing unit can, for example, estimate the user's emotion and determine the priority of the review based on the estimated user's emotion. For example, when the user is relaxed, the review providing unit can provide important reviews with priority. In addition, when the user is in a hurry, the review providing unit can also prioritize reviews that can be provided quickly. Furthermore, when the user is stressed, the review providing unit can adjust the priority of the review. In this way, by determining the priority of the review based on the user's emotion, it is possible to provide more important reviews with priority. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the review providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the review providing unit can input the result of the emotion estimation to the generation AI and cause the generation AI to execute the determination of the priority of the review.

[0158] The review providing unit can select the optimal review method in consideration of the geographical location information of the user when providing the review. For example, the review providing unit selects the optimal review method in consideration of the geographical location information of the user when providing the review. For example, when the user is in a specific location, the review providing unit preferentially provides reviews related to the location. In addition, the review providing unit can also suggest the optimal review method based on the geographical location information of the user. Furthermore, the review providing unit can also customize the means of review based on the current location of the user. In this way, the optimal review method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the review providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the review providing unit can input geographical location information to the generation AI and cause the generation AI to select the review method.

[0159] The memory reproduction unit can estimate the user's emotion and adjust the memory reproduction method based on the estimated user's emotion. The memory reproduction unit, for example, estimates the user's emotion and adjusts the memory reproduction method based on the estimated user's emotion. The memory reproduction unit provides a detailed memory reproduction method when the user is relaxed, for example. The memory reproduction unit can also provide a concise memory reproduction method when the user is in a hurry. Furthermore, the memory reproduction unit can also provide a visually easy-to-understand memory reproduction method when the user is stressed. This enables more appropriate memory reproduction by adjusting the memory reproduction method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the memory reproduction unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the memory reproduction unit can input the result of the emotion estimation to the generation AI and cause the generation AI to execute the adjustment of the memory reproduction method.

[0160] The memory reproduction unit can select the optimal reproduction method by referring to the past memory reproduction history when reproducing a memory. For example, the memory reproduction unit selects the optimal reproduction method by referring to the past memory reproduction history when reproducing a memory. The memory reproduction unit, for example, proposes the optimal reproduction method based on the user's past memory reproduction history. The memory reproduction unit can also preferentially propose successful methods from the past memory reproduction history. Furthermore, the memory reproduction unit can analyze the past memory reproduction history and select the most effective reproduction method. In this way, the optimal reproduction method can be selected by referring to the past memory reproduction history. Part or all of the above-mentioned processing in the memory reproduction unit may be performed, for example, using AI or may be performed without using AI. For example, the memory reproduction unit can input the past memory reproduction history to the generation AI and cause the generation AI to select the reproduction method.

[0161] The memory reproduction unit can customize the means of reproduction based on the user's current situation when reproducing the memory. The memory reproduction unit customizes the means of reproduction based on the user's current situation when reproducing the memory, for example. The memory reproduction unit provides a means to support rapid memory reproduction when the user is in an emergency situation, for example. The memory reproduction unit can also support memory reproduction by providing detailed information when the user is relaxed. Furthermore, the memory reproduction unit can also provide a visually easy-to-understand memory reproduction means when the user is stressed. This enables more appropriate memory reproduction by customizing the means of reproduction based on the user's current situation. Part or all of the above-mentioned processing in the memory reproduction unit may be performed, for example, using AI or may be performed without using AI. For example, the memory reproduction unit can input the current situation to the generation AI and cause the generation AI to execute customization of the reproduction means.

[0162] The memory reproducing unit can estimate the user's emotion and determine the priority of memory reproduction based on the estimated user's emotion. The memory reproducing unit can, for example, estimate the user's emotion and determine the priority of memory reproduction based on the estimated user's emotion. For example, when the user is relaxed, the memory reproducing unit can prioritize important memory reproduction. Also, when the user is in a hurry, the memory reproducing unit can prioritize memory reproduction that can be provided quickly. Furthermore, when the user is stressed, the memory reproducing unit can adjust the priority of memory reproduction. In this way, by determining the priority of memory reproduction based on the user's emotion, more important memory reproduction can be provided preferentially. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the memory reproducing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the memory reproducing unit can input the result of emotion estimation to the generation AI and cause the generation AI to execute the determination of the priority of memory reproduction.

[0163] The memory reproduction unit can select the optimal reproduction method in consideration of the geographical location information of the user when reproducing a memory. For example, the memory reproduction unit selects the optimal reproduction method in consideration of the geographical location information of the user when reproducing a memory. For example, when the user is in a specific location, the memory reproduction unit preferentially provides memory reproduction related to that location. The memory reproduction unit can also suggest the optimal memory reproduction method based on the geographical location information of the user. Furthermore, the memory reproduction unit can also customize the means of memory reproduction based on the user's current location. In this way, the optimal reproduction method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the memory reproduction unit may be performed, for example, using AI, or may be performed without using AI. For example, the memory reproduction unit can input geographical location information to the generation AI and cause the generation AI to select the reproduction method.

[0164] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0165] The knowledge storage system can estimate the user's emotions and adjust the data collection method based on the estimated emotions. For example, if the user is relaxed, priority can be given to the collection of voice data. Also, if the user is concentrating, priority can be given to the collection of text data. Furthermore, if the user is feeling stressed, the collection timing can be delayed. In this way, more appropriate data collection is possible by adjusting the collection method based on the user's emotions.

[0166] The knowledge storage system can analyze the user's past data collection history and select the optimal collection method. For example, it can prioritize collection methods (audio, text, etc.) that the user has used favorably in the past. It can also suggest the most efficient collection timing based on the user's past data collection history. Furthermore, it can customize the collection method based on the user's past data collection history. This makes it possible to select the optimal collection method by analyzing past data collection history.

[0167] When collecting data, the knowledge storage system can filter the data based on the user's current activity status and areas of interest. For example, data related to the user's current activity can be preferentially collected. Also, the knowledge storage system can filter relevant data based on the user's areas of interest. Furthermore, the knowledge storage system can adjust the type of data to be collected taking into account the user's current activity status. In this way, highly relevant data can be collected by filtering the data based on the user's current activity status and areas of interest.

[0168] The knowledge storage system can preferentially collect highly relevant data by taking into account the geographic location information of the user. For example, when the user is in a specific location, data related to that location is preferentially collected. Also, based on the geographic location information of the user, highly relevant data can be filtered. Furthermore, the type of data to be collected can be adjusted based on the user's current location. In this way, highly relevant data can be preferentially collected by taking into account the geographic location information.

[0169] The knowledge storage system can analyze the user's social media activities and collect relevant data. For example, the knowledge storage system can analyze the content of the user's social media posts and collect relevant data. It can also identify areas of interest from the user's social media activities and collect relevant data. It can also adjust the type of data to be collected based on the user's social media activities. This allows for efficient collection of relevant data by analyzing social media activities.

[0170] The knowledge storage system can estimate the user's emotions and adjust the way the analysis is presented based on the estimated emotions. For example, if the user is relaxed, a detailed analysis result can be provided. If the user is in a hurry, a concise analysis result can be provided. Furthermore, if the user is stressed, a visually easy-to-understand analysis result can be provided. In this way, by adjusting the way the analysis is presented based on the user's emotions, more appropriate analysis results can be provided.

[0171] During analysis, the knowledge storage system can adjust the level of detail of the analysis based on the importance of the data. For example, a detailed analysis can be performed on data with high importance. Also, a simple analysis can be performed on data with low importance. Furthermore, the level of detail of the analysis can be dynamically adjusted according to the importance of the data. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data.

[0172] During analysis, the knowledge storage system can apply different analysis algorithms depending on the category of data. For example, a voice analysis algorithm can be applied to voice data, and a text analysis algorithm can be applied to text data. Furthermore, the most suitable analysis algorithm can be selected depending on the data category. This improves the accuracy of analysis by applying the most suitable analysis algorithm depending on the data category.

[0173] The knowledge storage system can estimate the user's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the user is in a hurry, a short and to the point analysis result can be provided. If the user is relaxed, a detailed analysis result can be provided. Furthermore, if the user is stressed, a visually easy-to-understand analysis result can be provided. In this way, by adjusting the length of the analysis based on the user's emotions, more appropriate analysis results can be provided.

[0174] During analysis, the knowledge storage system can determine the analysis priority based on when the data was collected. For example, the most recent data can be analyzed first. The analysis priority can also be lowered for older data. Furthermore, the analysis priority can be dynamically adjusted according to when the data was collected. This allows for efficient analysis by determining the analysis priority based on when the data was collected.

[0175] The process flow of the second embodiment will be briefly described below.

[0176] Step 1: The collection unit collects user voice and text data. For example, the collection unit collects user voice data using voice recognition technology, and converts it into text data using a voice recognition algorithm or a pre-processing method for the voice data. In addition, the collection unit collects user text data using text processing technology, and performs morphological analysis, grammatical analysis, semantic analysis, etc. Step 2: The analysis unit analyzes the data collected by the collection unit and learns the user's knowledge, personality, and speaking habits. For example, the analysis unit uses machine learning algorithms and natural language processing technology to analyze the collected voice data and text data and extract the user's characteristics. Step 3: The storage unit stores the features learned by the analysis unit, for example, in a form such as a relational database or a NoSQL database. Step 4: The decision support unit supports the user in making decisions based on the features stored by the storage unit, for example by providing advice to the user based on past data. Step 5: The skill improvement unit supports the user in improving their skills based on the features stored by the storage unit. For example, it provides a function to look back on one's past statements and writings, analyzes past data using AI, and provides feedback to the user. Step 6: The dementia prevention unit supports the user's dementia prevention based on the characteristics stored by the storage unit. For example, it supports memory maintenance by reproducing the user's past characteristics, analyzes past data using AI, reproduces the user's characteristics, and performs memory training.

[0177] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0178] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0179] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0180] Each of the multiple elements including the above-mentioned collection unit, analysis unit, storage unit, decision support unit, self-improvement unit, and dementia prevention unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects the user's voice and text data using the microphone 38B and touch panel 38A of the smart device 14. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data and learns the user's characteristics. The storage unit stores the learned characteristics in the database 24 of the data processing device 12, for example. The decision support unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides advice to the user based on the stored characteristics. The self-improvement unit is realized, for example, by the control unit 46A of the smart device 14, and provides feedback to the user based on past data. The dementia prevention unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and reproduces past characteristics and performs memory training. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0181] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0182] 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.

[0183] 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, the RAM 30, and the 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.

[0184] 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.

[0185] 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 the voice according to instructions from the processor 46.

[0186] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0187] 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 performed in a secure state.

[0188] Fig. 4 shows an example of 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.

[0189] 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.

[0190] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0191] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0192] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0193] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0194] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0195] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0196] Each of the multiple elements including the above-mentioned collection unit, analysis unit, storage unit, decision support unit, self-improvement unit, and dementia prevention unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects voice and text data of the user using the microphone 238 and the camera 42 of the smart glasses 214. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data and learns the characteristics of the user. The storage unit stores the learned characteristics in the database 24 of the data processing device 12, for example. The decision support unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides advice to the user based on the stored characteristics. The self-improvement unit is realized, for example, by the control unit 46A of the smart glasses 214, and provides feedback to the user based on past data. The dementia prevention unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and reproduces past characteristics and performs memory training. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0197] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0198] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0199] 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, the RAM 30, and the 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.

[0200] 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.

[0201] 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 the voice according to instructions from the processor 46.

[0202] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0203] 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 performed in a secure state.

[0204] 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.

[0205] 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.

[0206] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0207] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0208] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0209] 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 voice indicating a user input for 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.

[0210] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0211] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0212] Each of the multiple elements including the above-mentioned collection unit, analysis unit, storage unit, decision support unit, self-improvement unit, and dementia prevention unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects the user's voice and text data using the microphone 238 and the camera 42 of the headset type terminal 314. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data and learns the user's characteristics. The storage unit stores the learned characteristics in the database 24 of the data processing device 12, for example. The decision support unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides advice to the user based on the stored characteristics. The self-improvement unit is realized, for example, by the control unit 46A of the headset type terminal 314, and provides feedback to the user based on past data. The dementia prevention unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and reproduces past characteristics and performs memory training. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0213] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0214] 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.

[0215] 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, the RAM 30, and the 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.

[0216] 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.

[0217] 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 the voice according to instructions from the processor 46.

[0218] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0219] 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 performed in a secure state.

[0220] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0221] 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.

[0222] 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.

[0223] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0224] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0225] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0226] 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 a voice indicating a user input for 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.

[0227] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0228] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0229] Each of the multiple elements including the above-mentioned collection unit, analysis unit, storage unit, decision support unit, self-improvement unit, and dementia prevention unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects voice and text data of the user using the microphone 238 and the camera 42 of the robot 414. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data and learns the characteristics of the user. The storage unit stores the learned characteristics in the database 24 of the data processing device 12, for example. The decision support unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides advice to the user based on the stored characteristics. The self-improvement unit is realized, for example, by the control unit 46A of the robot 414, and provides feedback to the user based on past data. The dementia prevention unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and reproduces past characteristics and performs memory training. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0230] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0231] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0232] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0233] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0234] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0235] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0236] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0237] 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.

[0238] 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 Universal Serial Bus (USB) 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.

[0239] In addition, 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 upon request from the data processing device 12.

[0240] 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.

[0241] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0242] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0243] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0244] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0245] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0246] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0247] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0248] (Appendix 1) A collection unit that collects user voice and text data; an analysis unit that analyzes the data collected by the collection unit and learns the knowledge, personality, and speaking characteristics of the user; A storage unit for storing the features learned by the analysis unit; a decision support unit that supports a user in making decisions based on the characteristics stored by the storage unit; a skill improvement unit that supports a user in improving a skill based on the characteristics stored by the storage unit; A dementia prevention unit that supports dementia prevention for a user based on the features stored by the storage unit. A system characterized by: (Appendix 2) Equipped with a voice recognition unit that collects user voice data using voice recognition technology 2. The system of claim 1, (Appendix 3) A text processing unit is provided that uses text processing technology to collect text data from users. 2. The system of claim 1, (Appendix 4) A database unit having a database for storing the learned features. 2. The system of claim 1, (Appendix 5) An advice providing unit is provided to provide advice to support the user's decision making. 2. The system of claim 1, (Appendix 6) Equipped with a review section that provides a function to review past statements and writings in order to improve users' skills 2. The system of claim 1, (Appendix 7) Equipped with a memory reproducing section that reproduces the user's past characteristics to prevent dementia 2. The system of claim 1, (Appendix 8) The collecting unit includes: The system estimates the user's emotions and adjusts the timing of collecting voice and text data based on the estimated user emotions. 2. The system of claim 1, (Appendix 9) The collecting unit includes: Analyze the user's past data collection history and select the optimal collection method 2. The system of claim 1, (Appendix 10) The collecting unit includes: Filter data collection based on the user's current activity and interests 2. The system of claim 1, (Appendix 11) The collecting unit includes: Infer user sentiment and prioritize data to be collected based on the inferred user sentiment 2. The system of claim 1, (Appendix 12) The collecting unit includes: When collecting data, prioritize collecting data that is more relevant by taking into account the user's geographic location. 2. The system of claim 1, (Appendix 13) The collecting unit includes: When collecting data, analyze your social media activity and collect relevant data 2. The system of claim 1, (Appendix 14) The analysis unit is Infer user emotions and adjust the presentation of analytics based on the inferred user emotions 2. The system of claim 1, (Appendix 15) The analysis unit is During analysis, adjust the level of detail based on the importance of the data 2. The system of claim 1, (Appendix 16) The analysis unit is During analysis, apply different analysis algorithms depending on the category of data 2. The system of claim 1, (Appendix 17) The analysis unit is Infer user sentiment and adjust the length of the analysis based on the inferred user sentiment 2. The system of claim 1, (Appendix 18) The analysis unit is During analysis, prioritize analysis based on when the data was collected 2. The system of claim 1, (Appendix 19) The analysis unit is During analysis, adjust the order of analysis based on data relevance 2. The system of claim 1, (Appendix 20) The storage unit includes: Infer user emotions and prioritize data to be stored based on the inferred user emotions 2. The system of claim 1, (Appendix 21) The storage unit includes: When saving, adjust the granularity of the save based on the importance of the data 2. The system of claim 1, (Appendix 22) The storage unit includes: When storing, apply different storage algorithms depending on the category of data 2. The system of claim 1, (Appendix 23) The storage unit includes: Infer user emotions and adjust the way data is displayed based on the inferred user emotions 2. The system of claim 1, (Appendix 24) The storage unit includes: When storing, prioritize storage based on when the data was collected 2. The system of claim 1, (Appendix 25) The storage unit includes: When saving, adjust the order of saving based on data relevance 2. The system of claim 1, (Appendix 26) The decision support unit includes: Inferring user emotions and adjusting a decision support method based on the inferred user emotions 2. The system of claim 1, (Appendix 27) The decision support unit includes: When providing decision support, select the most appropriate support method by referring to past decision-making history 2. The system of claim 1, (Appendix 28) The decision support unit includes: During decision support, tailor support measures based on the user's current situation 2. The system of claim 1, (Appendix 29) The decision support unit includes: Inferring user emotions and prioritizing decision making based on the inferred user emotions 2. The system of claim 1, (Appendix 30) The decision support unit includes: When providing decision support, select the most appropriate support method by taking into account the user's geographic location information 2. The system of claim 1, (Appendix 31) The decision support unit includes: Analyze users' social media activity to suggest support measures during decision-making 2. The system of claim 1, (Appendix 32) The self-improvement section includes: Inferring a user's emotions and adjusting the method of self-improvement based on the estimated user's emotions 2. The system of claim 1, (Appendix 33) The self-improvement section includes: When self-improvement is required, select the most appropriate method by referring to past self-improvement history. 2. The system of claim 1, (Appendix 34) The self-improvement section includes: During self-improvement, customize the training method based on the user's current situation 2. The system of claim 1, (Appendix 35) The self-improvement section includes: Estimating a user's emotions and determining the priority of self-improvement based on the estimated user's emotions 2. The system of claim 1, (Appendix 36) The self-improvement section includes: When self-improvement is performed, the optimal training method is selected taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 37) The self-improvement section includes: Analyze users' social media activity and suggest ways to improve themselves 2. The system of claim 1, (Appendix 38) The Dementia Prevention Department is To estimate a user's emotion and adjust a dementia prevention method based on the estimated user's emotion. 2. The system of claim 1, (Appendix 39) The Dementia Prevention Department is When preventing dementia, select the most appropriate prevention method by referring to past dementia prevention history. 2. The system of claim 1, (Appendix 40) The Dementia Prevention Department is When preventing dementia, customize prevention measures based on the user's current situation 2. The system of claim 1, (Appendix 41) The Dementia Prevention Department is Estimating a user's emotions and determining the priority of dementia prevention based on the estimated user's emotions 2. The system of claim 1, (Appendix 42) The Dementia Prevention Department is When preventing dementia, the optimal prevention method is selected taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 43) The Dementia Prevention Department is Analyzing users' social media activities to suggest preventive measures for dementia prevention 2. The system of claim 1, (Appendix 44) The voice recognition unit Estimating a user's emotion and adjusting the accuracy of speech recognition based on the estimated user's emotion 3. The system of claim 2, (Appendix 45) The voice recognition unit When performing voice recognition, the recognition algorithm is optimized by referencing past voice data. 3. The system of claim 2, (Appendix 46) The voice recognition unit Estimating a user's emotion and determining a priority of speech recognition based on the estimated user's emotion 3. The system of claim 2, (Appendix 47) The voice recognition unit When performing voice recognition, the most appropriate recognition method is selected taking into account the user's geographic location information. 3. The system of claim 2, (Appendix 48) The text processing unit includes: Inferring user emotions and adjusting the accuracy of text processing based on the estimated user emotions 4. The system of claim 3. (Appendix 49) The text processing unit includes: When processing text, the processing algorithm is optimized by referencing past text data. 4. The system of claim 3. (Appendix 50) The text processing unit includes: Inferring user emotions and prioritizing text processing based on the estimated user emotions 4. The system of claim 3. (Appendix 51) The text processing unit includes: When processing text, the optimal processing method is selected taking into account the user's geographic location information. 4. The system of claim 3. (Appendix 52) The database unit includes: Infer user emotions and adjust the structure of the database based on the estimated user emotions 5. The system of claim 4. (Appendix 53) The database unit includes: When building a database, select the optimal structure by referring to past database usage history. 5. The system of claim 4. (Appendix 54) The database unit includes: Infer user emotions and prioritize databases based on the estimated user emotions 5. The system of claim 4. (Appendix 55) The database unit includes: When building a database, select the optimal structure by taking into account the geographic location information of the user. 5. The system of claim 4. (Appendix 56) The advice providing unit, Inferring the user's emotions and adjusting the way advice is presented based on the estimated user's emotions 6. The system of claim 5, (Appendix 57) The advice providing unit, When providing advice, the most appropriate advice method is selected by referring to past advice history. 6. The system of claim 5, (Appendix 58) The advice providing unit, Estimate the user's emotions and prioritize advice based on the estimated user emotions. 6. The system of claim 5, (Appendix 59) The advice providing unit, When providing advice, the system selects the most appropriate advice method based on the user's geographic location information. 6. The system of claim 5, (Appendix 60) The review providing unit is Estimate the user's emotions and adjust the review method based on the estimated user's emotions. 7. The system of claim 6, (Appendix 61) The review providing unit is When providing a retrospective, select the most appropriate method by referring to past retrospective history 7. The system of claim 6, (Appendix 62) The review providing unit is Estimate the user's emotions and determine the priority of reviews based on the estimated user emotions. 7. The system of claim 6, (Appendix 63) The review providing unit is When providing a review, the optimal review method is selected taking into account the user's geographic location information. 7. The system of claim 6, (Appendix 64) The memory reproducing unit, The user's emotions are estimated, and the memory reproduction method is adjusted based on the estimated user's emotions. 8. The system of claim 7, (Appendix 65) The memory reproducing unit, When reproducing a memory, the optimal reproduction method is selected by referring to past reproduction history. 8. The system of claim 7, (Appendix 66) The memory reproducing unit, Customize the recall method based on the user's current situation during memory recall 8. The system of claim 7, (Appendix 67) The memory reproducing unit, Estimate the user's emotions and determine the priority of memory recall based on the estimated user's emotions. 8. The system of claim 7, (Appendix 68) The memory reproducing unit, When recalling a memory, the system selects the optimal recall method by taking into account the user's geographic location information. 8. The system of claim 7, [Explanation of symbols]

[0249] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that collects user voice and text data; an analysis unit that analyzes the data collected by the collection unit and learns the knowledge, personality, and speaking characteristics of the user; A storage unit for storing the features learned by the analysis unit; a decision support unit that supports a user in making decisions based on the characteristics stored by the storage unit; a skill improvement unit that supports a user in improving a skill based on the characteristics stored by the storage unit; A dementia prevention unit that supports dementia prevention for a user based on the features stored by the storage unit. A system characterized by:

2. Equipped with a voice recognition unit that collects user voice data using voice recognition technology 2. The system of claim 1 .

3. A text processing unit is provided that uses text processing technology to collect text data from users.

2. The system of claim 1 .

4. A database unit having a database for storing the learned features.

2. The system of claim 1 .

5. An advice providing unit is provided to provide advice to support the user's decision making.

2. The system of claim 1 .

6. Equipped with a review section that provides a function to review past statements and writings in order to improve users' skills 2. The system of claim 1 .

7. Equipped with a memory reproducing section that reproduces the user's past characteristics to prevent dementia 2. The system of claim 1 .

8. The collecting unit includes: The system estimates the user's emotions and adjusts the timing of collecting voice and text data based on the estimated user emotions.

2. The system of claim 1 .

9. The collecting unit includes: Analyze the user's past data collection history and select the optimal collection method 2. The system of claim 1 .

10. The collecting unit includes: Filter data collection based on the user's current activity and interests 2. The system of claim 1 .

Images