System

Abstract

An object of a system according to an embodiment is to enable a hearing-impaired person to efficiently acquire voice information.SOLUTION: A system according to an embodiment includes a conversion unit, an analysis unit, and a provision unit. The conversion unit converts voice into text. The analysis unit analyzes the text converted by the conversion unit. The providing unit provides information based on the result analyzed by the analyzing unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem that it is difficult for hearing-impaired people to efficiently acquire audio information.

[0005] The system according to the embodiment aims to enable hearing-impaired people to efficiently acquire audio information. [Means for solving the problem]

[0006] The system according to the embodiment includes a conversion unit, an analysis unit, and a provision unit. The conversion unit converts speech into text. The analysis unit analyzes the text converted by the conversion unit. The provision unit provides information based on the results of the analysis by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can enable the hearing impaired to acquire audio information efficiently. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A life assistance system according to an embodiment of the present invention is a system that combines speech recognition and generation AI to assist the hearing-impaired in their daily lives and address the challenges they face. The life assistance system converts speech into text, and a generation AI analyzes the text to generate appropriate information and instructions. For example, the system can display subtitles of conversations in real time or visually notify emergency alerts. The generation AI can also provide appropriate advice and reminders based on the user's past behavior and preferences. For example, the life assistance system converts surrounding speech into text in real time using speech recognition technology. The generation AI then analyzes the converted text to generate appropriate information and instructions. For example, the system can visually notify emergency alerts. The generation AI can also provide appropriate advice and reminders based on the user's past behavior and preferences. This allows the hearing-impaired to communicate and obtain information easily in their daily lives, thereby improving their quality of life. This allows the hearing-impaired to communicate and obtain information easily in their daily lives, thereby improving their quality of life. For example, the life assistance system converts surrounding speech into text in real time using speech recognition technology. The generative AI then analyzes the converted text and generates appropriate information or instructions. For example, it can visually notify users of emergency alerts. The generative AI can also provide appropriate advice or reminders based on the user's past behavior and preferences. This allows the life assistance system to facilitate communication and information acquisition in daily life for the hearing impaired, improving their quality of life.

[0029] A life assistance system according to an embodiment includes a conversion unit, an analysis unit, and a provision unit. The conversion unit converts speech into text. Examples of speech include, but are not limited to, human speech, environmental sounds, and specific languages. The conversion unit converts ambient speech into text in real time using, for example, speech recognition technology. The conversion unit can also recognize specific languages ​​or dialects and appropriately convert the text into text. For example, the conversion unit converts conversation content into text in real time using speech recognition technology and displays it as subtitles. The analysis unit uses a generation AI to analyze the text converted by the conversion unit. The analysis can be performed using, for example, natural language processing technology, statistical analysis, machine learning algorithms, or other methods, but is not limited to these examples. For example, the generation AI analyzes the text using a text generation AI (e.g., LLM) and generates appropriate information or instructions. The analysis unit can also provide appropriate advice or reminders based on the user's past behavior and preferences. For example, the generation AI learns the user's past behavior history and preferences and generates appropriate advice. The provision unit provides information based on the results of the analysis by the analysis unit. The information to be provided includes, but is not limited to, for example, text information, image information, and audio information. For example, the providing unit displays subtitles of conversation content in real time. The providing unit can also visually notify an emergency alert. Furthermore, the providing unit can also provide appropriate advice and reminders based on the user's past actions and preferences. For example, the providing unit notifies the user of important appointments based on reminders previously set by the user. As a result, the life assistance system according to the embodiment facilitates communication and information acquisition in daily life for the hearing impaired, improving the quality of life.

[0030] The providing unit can display subtitles of the content of the conversation in real time. "Real time" means that the processing is performed almost immediately with minimal delay. For example, the providing unit converts the content of the conversation into text in real time and displays it as subtitles. The subtitle display may include, but is not limited to, font size, display position, color, etc. For example, the providing unit may increase the font size, set the display position to the bottom of the screen, and set the color to white to improve visibility. The providing unit may also customize the subtitle display settings according to the user's preferences. For example, the providing unit displays subtitles based on the font size and display position set by the user. In this way, displaying subtitles of the content of the conversation in real time makes it easier for hearing-impaired people to understand the conversation.

[0031] The providing unit can visually notify an emergency alert. An emergency refers to a situation that requires a rapid response, such as a fire, earthquake, or medical emergency. For example, the providing unit visually notifies an emergency alert. Examples of visual notifications include, but are not limited to, flashing, changing color, or displaying an icon. For example, the providing unit notifies an emergency by flashing the entire screen red. The providing unit can also display a specific icon to indicate the type of emergency. For example, in the case of a fire, a fire icon is displayed, and in the case of an earthquake, an earthquake icon is displayed. In this way, visual notification of an emergency alert allows hearing-impaired people to respond quickly to an emergency.

[0032] The analysis unit can provide advice and reminders based on the user's past behavior and preferences. Past behavior refers to behavior history, usage history, access logs, etc. Preferences refer to survey results, selection history, feedback, etc. For example, the analysis unit can analyze the user's past behavior and provide optimal advice. The analysis unit can also provide reminders based on the user's preferences. For example, the analysis unit can notify the user of important appointments based on reminders set by the user in the past. The analysis unit can also learn the user's behavior history and generate appropriate advice. For example, the analysis unit can provide related information based on places the user has visited or events the user has participated in in the past. This makes the user's life more convenient by providing advice and reminders based on the user's past behavior and preferences.

[0033] The conversion unit can convert ambient sounds into text in real time. Examples of ambient sounds include, but are not limited to, human voices, environmental sounds, and specific languages. Real-time refers to minimal latency and nearly instantaneous processing. For example, the conversion unit can convert ambient sounds into text in real time using speech recognition technology. The converted text can display, for example, the content of a conversation as subtitles in real time. The conversion unit can also recognize specific languages ​​or dialects and appropriately convert them into text. For example, the conversion unit can recognize specific dialects using speech recognition technology and convert them into standard Japanese. By converting ambient sounds into text in real time, hearing-impaired people can obtain information in real time.

[0034] The conversion unit can add a filtering function that automatically removes ambient noise when converting voice. Methods for automatically removing noise include, but are not limited to, filtering technology and noise canceling algorithms. For example, the conversion unit detects ambient noise in real time and removes it using noise canceling technology. The conversion unit can also filter noise in a specific frequency band to improve the accuracy of voice recognition. The conversion unit can also analyze ambient sounds and automatically apply an appropriate noise filter. This removes ambient noise, thereby improving the accuracy of voice recognition. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input ambient sound data to a generation AI and have the generation AI remove the noise.

[0035] During speech conversion, the conversion unit can identify the speaker's voice characteristics and apply an individually optimized conversion algorithm. Methods for identifying voice characteristics include, but are not limited to, voiceprint analysis and acoustic feature extraction. Optimized conversion algorithms include, but are not limited to, personalized models and adaptive learning algorithms. For example, the conversion unit can analyze the speaker's tone and pitch and apply an optimal speech recognition algorithm. The conversion unit can also learn the speaker's voice characteristics and use an individually customized speech recognition model. The conversion unit can also adjust the speech recognition algorithm in real time in response to changes in the speaker's voice. This improves the accuracy of speech recognition by applying the optimal conversion algorithm according to the speaker's voice characteristics. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or without AI. For example, the conversion unit can input the speaker's voice characteristic data into a generation AI and have the generation AI apply the optimal conversion algorithm.

[0036] The conversion unit may add a function to highlight specific keywords and phrases during speech conversion. Methods for selecting specific keywords and phrases include, but are not limited to, frequency, importance, and user settings. Methods for highlighting include, but are not limited to, changing fonts, colors, and backgrounds. For example, the conversion unit may detect important keywords and phrases and highlight them in the text. The conversion unit may also prioritize and highlight specific keywords set by the user. The conversion unit may also automatically highlight important phrases based on the context of the conversation. By highlighting specific keywords and phrases, important information is not overlooked. Some or all of the above-described processing in the conversion unit may be performed using, or without, AI. For example, the conversion unit may input text data to a generation AI and cause the generation AI to highlight important keywords and phrases.

[0037] The conversion unit can appropriately convert regional words and dialects based on the user's geographical location information when converting speech. Methods for acquiring geographical location information include, but are not limited to, GPS data and location-based services. Methods for converting regional words and dialects include, but are not limited to, regional dictionaries and dialect conversion algorithms. For example, the conversion unit recognizes regional words and dialects based on the user's current location and appropriately converts them. The conversion unit can also learn regional words and dialects by referring to the user's past location information and improve conversion accuracy. The conversion unit can also automatically apply regional words and dialects to each region the user visits. This improves speech recognition accuracy by appropriately converting regional words and dialects. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or without AI. For example, the conversion unit can input geographical location information data to a generation AI and cause the generation AI to convert regional words and dialects.

[0038] The conversion unit can improve conversion accuracy by referring to the user's past conversation history when converting speech. Methods for collecting past conversation history include, but are not limited to, log data and conversation records. Methods for improving conversion accuracy include, but are not limited to, algorithm improvements and additional data learning. For example, the conversion unit analyzes the user's past conversation history and prioritizes recognition of frequently used words and phrases. The conversion unit can also learn the meaning of words in specific contexts from the user's past conversation history to improve conversion accuracy. The conversion unit can also use an individually customized speech recognition model based on the user's past conversation history. By referring to the past conversation history, the accuracy of speech recognition is improved. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or without AI. For example, the conversion unit can input past conversation history data into a generation AI and cause the generation AI to improve conversion accuracy.

[0039] The conversion unit can analyze the user's social media activity and add relevant information to the text when converting the voice. Methods for collecting social media activity include, but are not limited to, post content, number of likes, and comments. Methods for selecting relevant information include, but are not limited to, topic matching and relevance scores. For example, the conversion unit can analyze the user's social media posts and add relevant information to the text. The conversion unit can also add relevant information to the text based on the activity of the user's friends on social media. The conversion unit can also add information about relevant places and events to the text based on the user's social media check-in information. In this way, relevant information can be added to the text by analyzing social media activity. Some or all of the above-described processing by the conversion unit can be performed using, for example, AI, or without AI. For example, the conversion unit can input social media activity data to a generation AI and cause the generation AI to add relevant information.

[0040] During analysis, the analysis unit can enhance natural language processing technology to understand the context of the text and extract appropriate information. Methods for understanding the context include, but are not limited to, natural language processing technology and context analysis algorithms. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit enhances natural language processing algorithms to understand the context of the text and extract important information. The analysis unit can also automatically extract relevant information based on the context of the text. The analysis unit can also use machine learning models to analyze the context of the text and extract appropriate information. This enhances the natural language processing technology, thereby improving the accuracy of extracting appropriate information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input text data to a generation AI and have the generation AI understand the context and extract information.

[0041] The analysis unit may add a function to automatically generate a summary based on the content of the text during analysis. Methods for generating a summary include, but are not limited to, summarization algorithms and importance scoring. For example, the analysis unit may analyze the content of the text and extract important points to generate a summary. The analysis unit may also automatically generate a concise and easy-to-understand summary based on the content of the text. The analysis unit may also use an algorithm to understand the content of the text and generate a summary that captures the main points. This makes it easier to grasp the key points of the information by generating a summary based on the content of the text. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may input text data into a generation AI and have the generation AI generate a summary.

[0042] During analysis, the analysis unit can optimize the analysis algorithm based on the user's past behavior and preferences. Past behavior refers to behavior history, usage history, access logs, etc. Preferences refer to survey results, selection history, feedback, etc. For example, the analysis unit analyzes the user's past behavior and selects the optimal analysis algorithm. The analysis unit can also customize the analysis algorithm based on the user's preferences. The analysis unit can also learn the user's past behavior and preferences and optimize the analysis algorithm. This improves analysis accuracy by optimizing the analysis algorithm based on the user's past behavior and preferences. 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 past behavior data into a generation AI and have the generation AI optimize the analysis algorithm.

[0043] During analysis, the analysis unit can adjust the analysis priority based on the time of submission of the text. Definitions of the submission time include, but are not limited to, a timestamp, a submission date and time, etc. Methods for adjusting the priority include, but are not limited to, the priority of the latest information, urgency, etc. For example, the analysis unit prioritizes analysis of text submitted more recently. The analysis unit can also analyze text submitted earlier later. The analysis unit can also automatically adjust the analysis priority based on the time of submission of the text. By adjusting the analysis priority based on the time of submission of the text, the latest information can be prioritized for analysis. Some or all of the above-described 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 submission time data into the generation AI and cause the generation AI to adjust the priority.

[0044] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the text. Definitions of relevance include, but are not limited to, topic consistency and relevance scores. Methods for adjusting the order include, but are not limited to, importance scores and urgency scores. For example, the analysis unit prioritizes analyzing text with high relevance. The analysis unit can also postpone analyzing text with low relevance. The analysis unit can also automatically adjust the order of analysis based on the relevance of the text. By adjusting the order of analysis based on the relevance of the text, important information can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input relevance data to a generation AI and have the generation AI adjust the order.

[0045] During analysis, the analysis unit can adjust the use of technical terms in the analysis results according to the user's level of expertise. Definitions of expertise level include, but are not limited to, qualification information, past learning history, etc. Methods for adjusting the use of technical terms include, but are not limited to, the difficulty level of terms, the presence or absence of explanations, etc. For example, if the user's level of expertise is high, the analysis unit can provide analysis results that use a lot of technical terms. Furthermore, if the user's level of expertise is low, the analysis unit can also provide analysis results that avoid technical terms. The analysis unit can also automatically adjust the use of technical terms according to the user's level of expertise. Adjusting the use of technical terms according to the user's level of expertise makes the analysis results easier to understand. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input expertise level data into a generation AI to adjust the use of technical terms.

[0046] When providing information, the providing unit can select optimal information based on the user's past behavior and preferences. Past behavior refers to behavior history, usage history, access logs, etc. Preferences refer to survey results, selection history, feedback, etc. For example, the providing unit analyzes the user's past behavior and selects optimal information. The providing unit can also customize information based on the user's preferences. The providing unit can also learn the user's past behavior and preferences and provide optimal information. This improves the accuracy of information provision by selecting optimal information based on the user's past behavior and preferences. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input past behavior data into a generation AI and cause the generation AI to select optimal information.

[0047] When providing information, the providing unit can customize the information display method based on the user's current situation. Definitions of the current situation include, but are not limited to, location information, activity status, and environmental information. Methods for customizing the display method include, but are not limited to, changing font size, color, and layout. For example, the providing unit provides concise, highly visible information when the user is moving. The providing unit can also provide detailed information when the user is stationary. The providing unit can also automatically customize the information display method based on the user's current situation. Customizing the information display method based on the user's current situation allows the information to be communicated more effectively. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit may input current situation data into a generating AI and cause the generating AI to customize the display method.

[0048] The providing unit can improve the information provision method by reflecting user feedback when providing information. Methods for collecting feedback include, but are not limited to, survey results, user comments, and evaluation scores. Methods for improving the information provision method include, but are not limited to, changing the display format, changing the notification method, and adjusting the timing. For example, the providing unit can analyze user feedback and improve the information provision method. The providing unit can also customize the information display method based on user feedback. The providing unit can also collect user feedback and optimize the information provision algorithm. This improves the information provision method by reflecting user feedback. Some or all of the above-described processing in the providing unit can be performed using, or without, AI. For example, the providing unit can input feedback data into a generating AI and cause the generating AI to improve the information provision method.

[0049] When providing information, the providing unit can provide optimal information by taking into account the user's geographical location information. Methods for acquiring geographical location information include, but are not limited to, GPS data and location information services. Methods for selecting optimal information include, but are not limited to, information based on the user's current situation, past behavioral history, preferences, etc. For example, the providing unit provides relevant information based on the user's current location. The providing unit can also provide optimal information by referring to the user's past location information. The providing unit can also automatically provide information specific to each area the user visits. This allows for providing highly relevant information by taking the user's geographical location information into consideration. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or without AI. For example, the providing unit can input geographical location information data to a generation AI and cause the generation AI to provide optimal information.

[0050] The providing unit may analyze the user's social media activity and provide related information when providing information. Methods for collecting social media activity include, but are not limited to, post content, number of likes, and comments. Methods for selecting related information include, but are not limited to, topic consistency and relevance scores. For example, the providing unit may analyze the user's social media posts and provide related information. The providing unit may also provide related information by referring to the activities of the user's friends on social media. The providing unit may also provide information on related places and events based on the user's social media check-in information. This allows related information to be provided by analyzing social media activity. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input social media activity data into a generation AI and cause the generation AI to provide related information.

[0051] When providing information, the providing unit can customize the information provision method by reflecting the user's past feedback. Methods of collecting feedback include, but are not limited to, survey results, user comments, and evaluation scores. Methods of customizing the information provision method include, but are not limited to, changing the display format, changing the notification method, and adjusting the timing. For example, the providing unit analyzes the user's past feedback and customizes the information provision method. The providing unit can also optimize the information display method based on the user's past feedback. The providing unit can also collect the user's past feedback and improve the information provision algorithm. In this way, the information provision method is customized by reflecting the user's past feedback. Some or all of the above-described processing by the providing unit may be performed using, or without, AI. For example, the providing unit can input past feedback data into the generation AI and cause the generation AI to customize the information provision method.

[0052] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0053] When providing information, the providing unit can select optimal information based on the user's past behavior and preferences. Past behavior refers to behavior history, usage history, access logs, etc. Preferences refer to survey results, selection history, feedback, etc. For example, the providing unit analyzes the user's past behavior and selects optimal information. The providing unit can also customize information based on the user's preferences. The providing unit can also learn the user's past behavior and preferences and provide optimal information. This improves the accuracy of information provision by selecting optimal information based on the user's past behavior and preferences. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input past behavior data into a generation AI and cause the generation AI to select optimal information.

[0054] When providing information, the providing unit can customize the information display method based on the user's current situation. Definitions of the current situation include, but are not limited to, location information, activity status, and environmental information. Methods for customizing the display method include, but are not limited to, changing font size, color, and layout. For example, the providing unit provides concise, highly visible information when the user is moving. The providing unit can also provide detailed information when the user is stationary. The providing unit can also automatically customize the information display method based on the user's current situation. Customizing the information display method based on the user's current situation allows the information to be communicated more effectively. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit may input current situation data into a generating AI and cause the generating AI to customize the display method.

[0055] The providing unit can improve the information provision method by reflecting user feedback when providing information. Methods for collecting feedback include, but are not limited to, survey results, user comments, and evaluation scores. Methods for improving the information provision method include, but are not limited to, changing the display format, changing the notification method, and adjusting the timing. For example, the providing unit can analyze user feedback and improve the information provision method. The providing unit can also customize the information display method based on user feedback. The providing unit can also collect user feedback and optimize the information provision algorithm. This improves the information provision method by reflecting user feedback. Some or all of the above-described processing in the providing unit can be performed using, or without, AI. For example, the providing unit can input feedback data into a generating AI and cause the generating AI to improve the information provision method.

[0056] During analysis, the analysis unit can enhance natural language processing technology to understand the context of the text and extract appropriate information. Methods for understanding the context include, but are not limited to, natural language processing technology and context analysis algorithms. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit enhances natural language processing algorithms to understand the context of the text and extract important information. The analysis unit can also automatically extract relevant information based on the context of the text. The analysis unit can also use machine learning models to analyze the context of the text and extract appropriate information. This enhances the natural language processing technology, thereby improving the accuracy of extracting appropriate information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input text data to a generation AI and have the generation AI understand the context and extract information.

[0057] The analysis unit may add a function to automatically generate a summary based on the content of the text during analysis. Methods for generating a summary include, but are not limited to, summarization algorithms and importance scoring. For example, the analysis unit may analyze the content of the text and extract important points to generate a summary. The analysis unit may also automatically generate a concise and easy-to-understand summary based on the content of the text. The analysis unit may also use an algorithm to understand the content of the text and generate a summary that captures the main points. This makes it easier to grasp the key points of the information by generating a summary based on the content of the text. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may input text data into a generation AI and have the generation AI generate a summary.

[0058] During analysis, the analysis unit can optimize the analysis algorithm based on the user's past behavior and preferences. Past behavior refers to behavior history, usage history, access logs, etc. Preferences refer to survey results, selection history, feedback, etc. For example, the analysis unit analyzes the user's past behavior and selects the optimal analysis algorithm. The analysis unit can also customize the analysis algorithm based on the user's preferences. The analysis unit can also learn the user's past behavior and preferences and optimize the analysis algorithm. This improves analysis accuracy by optimizing the analysis algorithm based on the user's past behavior and preferences. 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 past behavior data into a generation AI and have the generation AI optimize the analysis algorithm.

[0059] During analysis, the analysis unit can adjust the analysis priority based on the time of submission of the text. Definitions of the submission time include, but are not limited to, a timestamp, a submission date and time, etc. Methods for adjusting the priority include, but are not limited to, the priority of the latest information, urgency, etc. For example, the analysis unit prioritizes analysis of text submitted more recently. The analysis unit can also analyze text submitted earlier later. The analysis unit can also automatically adjust the analysis priority based on the time of submission of the text. By adjusting the analysis priority based on the time of submission of the text, the latest information can be prioritized for analysis. Some or all of the above-described 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 submission time data into the generation AI and cause the generation AI to adjust the priority.

[0060] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the text. Definitions of relevance include, but are not limited to, topic consistency and relevance scores. Methods for adjusting the order include, but are not limited to, importance scores and urgency scores. For example, the analysis unit prioritizes analyzing text with high relevance. The analysis unit can also postpone analyzing text with low relevance. The analysis unit can also automatically adjust the order of analysis based on the relevance of the text. By adjusting the order of analysis based on the relevance of the text, important information can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input relevance data to a generation AI and have the generation AI adjust the order.

[0061] During analysis, the analysis unit can adjust the use of technical terms in the analysis results according to the user's level of expertise. Definitions of expertise level include, but are not limited to, qualification information, past learning history, etc. Methods for adjusting the use of technical terms include, but are not limited to, the difficulty level of terms, the presence or absence of explanations, etc. For example, if the user's level of expertise is high, the analysis unit can provide analysis results that use a lot of technical terms. Furthermore, if the user's level of expertise is low, the analysis unit can also provide analysis results that avoid technical terms. The analysis unit can also automatically adjust the use of technical terms according to the user's level of expertise. Adjusting the use of technical terms according to the user's level of expertise makes the analysis results easier to understand. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input expertise level data into a generation AI to adjust the use of technical terms.

[0062] When providing information, the providing unit can select optimal information based on the user's past behavior and preferences. Past behavior refers to behavior history, usage history, access logs, etc. Preferences refer to survey results, selection history, feedback, etc. For example, the providing unit analyzes the user's past behavior and selects optimal information. The providing unit can also customize information based on the user's preferences. The providing unit can also learn the user's past behavior and preferences and provide optimal information. This improves the accuracy of information provision by selecting optimal information based on the user's past behavior and preferences. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input past behavior data into a generation AI and cause the generation AI to select optimal information.

[0063] When providing information, the providing unit can customize the information display method based on the user's current situation. Definitions of the current situation include, but are not limited to, location information, activity status, and environmental information. Methods for customizing the display method include, but are not limited to, changing font size, color, and layout. For example, the providing unit provides concise, highly visible information when the user is moving. The providing unit can also provide detailed information when the user is stationary. The providing unit can also automatically customize the information display method based on the user's current situation. Customizing the information display method based on the user's current situation allows the information to be communicated more effectively. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit may input current situation data into a generating AI and cause the generating AI to customize the display method.

[0064] The providing unit can improve the information provision method by reflecting user feedback when providing information. Methods for collecting feedback include, but are not limited to, survey results, user comments, and evaluation scores. Methods for improving the information provision method include, but are not limited to, changing the display format, changing the notification method, and adjusting the timing. For example, the providing unit can analyze user feedback and improve the information provision method. The providing unit can also customize the information display method based on user feedback. The providing unit can also collect user feedback and optimize the information provision algorithm. This improves the information provision method by reflecting user feedback. Some or all of the above-described processing in the providing unit can be performed using, or without, AI. For example, the providing unit can input feedback data into a generating AI and cause the generating AI to improve the information provision method.

[0065] When providing information, the providing unit can provide optimal information by taking into account the user's geographical location information. Methods for acquiring geographical location information include, but are not limited to, GPS data and location information services. Methods for selecting optimal information include, but are not limited to, information based on the user's current situation, past behavioral history, preferences, etc. For example, the providing unit provides relevant information based on the user's current location. The providing unit can also provide optimal information by referring to the user's past location information. The providing unit can also automatically provide information specific to each area the user visits. This allows for providing highly relevant information by taking the user's geographical location information into consideration. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or without AI. For example, the providing unit can input geographical location information data to a generation AI and cause the generation AI to provide optimal information.

[0066] The providing unit may analyze the user's social media activity and provide related information when providing information. Methods for collecting social media activity include, but are not limited to, post content, number of likes, and comments. Methods for selecting related information include, but are not limited to, topic consistency and relevance scores. For example, the providing unit may analyze the user's social media posts and provide related information. The providing unit may also provide related information by referring to the activities of the user's friends on social media. The providing unit may also provide information on related places and events based on the user's social media check-in information. This allows related information to be provided by analyzing social media activity. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input social media activity data into a generation AI and cause the generation AI to provide related information.

[0067] When providing information, the providing unit can customize the information provision method by reflecting the user's past feedback. Methods of collecting feedback include, but are not limited to, survey results, user comments, and evaluation scores. Methods of customizing the information provision method include, but are not limited to, changing the display format, changing the notification method, and adjusting the timing. For example, the providing unit analyzes the user's past feedback and customizes the information provision method. The providing unit can also optimize the information display method based on the user's past feedback. The providing unit can also collect the user's past feedback and improve the information provision algorithm. In this way, the information provision method is customized by reflecting the user's past feedback. Some or all of the above-described processing by the providing unit may be performed using, or without, AI. For example, the providing unit can input past feedback data into the generation AI and cause the generation AI to customize the information provision method.

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

[0069] Step 1: The conversion unit converts speech into text. Speech can include human speech, environmental sounds, and specific languages. The conversion unit uses speech recognition technology to convert surrounding speech into text in real time. It can also recognize specific languages ​​and dialects and convert them appropriately into text. For example, the content of a conversation can be converted into text in real time and displayed as subtitles. Step 2: The analysis unit uses a generation AI to analyze the text converted by the conversion unit. The analysis is performed using methods such as natural language processing technology, statistical analysis, and machine learning algorithms. For example, a text generation AI (e.g., LLM) can be used to analyze the text and generate appropriate information or instructions. It can also provide appropriate advice or reminders based on the user's past behavior and preferences. Step 3: The providing unit provides information based on the results of the analysis by the analyzing unit. The provided information includes text information, image information, and audio information. For example, it can display subtitles of conversation content in real time. It can also provide visual notifications of emergency alerts. It can also provide appropriate advice and reminders based on the user's past behavior and preferences. For example, it can notify the user of important appointments based on reminders set by the user in the past.

[0070] (Example 2) A life assistance system according to an embodiment of the present invention is a system that combines speech recognition and generation AI to assist the hearing-impaired in their daily lives and address the challenges they face. The life assistance system converts speech into text, and a generation AI analyzes the text to generate appropriate information and instructions. For example, the system can display subtitles of conversations in real time or visually notify emergency alerts. The generation AI can also provide appropriate advice and reminders based on the user's past behavior and preferences. For example, the life assistance system converts surrounding speech into text in real time using speech recognition technology. The generation AI then analyzes the converted text to generate appropriate information and instructions. For example, the system can visually notify emergency alerts. The generation AI can also provide appropriate advice and reminders based on the user's past behavior and preferences. This allows the hearing-impaired to communicate and obtain information easily in their daily lives, thereby improving their quality of life. This allows the hearing-impaired to communicate and obtain information easily in their daily lives, thereby improving their quality of life. For example, the life assistance system converts surrounding speech into text in real time using speech recognition technology. The generative AI then analyzes the converted text and generates appropriate information or instructions. For example, it can visually notify users of emergency alerts. The generative AI can also provide appropriate advice or reminders based on the user's past behavior and preferences. This allows the life assistance system to facilitate communication and information acquisition in daily life for the hearing impaired, improving their quality of life.

[0071] A life assistance system according to an embodiment includes a conversion unit, an analysis unit, and a provision unit. The conversion unit converts speech into text. Examples of speech include, but are not limited to, human speech, environmental sounds, and specific languages. The conversion unit converts ambient speech into text in real time using, for example, speech recognition technology. The conversion unit can also recognize specific languages ​​or dialects and appropriately convert the text into text. For example, the conversion unit converts conversation content into text in real time using speech recognition technology and displays it as subtitles. The analysis unit uses a generation AI to analyze the text converted by the conversion unit. The analysis can be performed using, for example, natural language processing technology, statistical analysis, machine learning algorithms, or other methods, but is not limited to these examples. For example, the generation AI analyzes the text using a text generation AI (e.g., LLM) and generates appropriate information or instructions. The analysis unit can also provide appropriate advice or reminders based on the user's past behavior and preferences. For example, the generation AI learns the user's past behavior history and preferences and generates appropriate advice. The provision unit provides information based on the results of the analysis by the analysis unit. The information to be provided includes, but is not limited to, for example, text information, image information, and audio information. For example, the providing unit displays subtitles of conversation content in real time. The providing unit can also visually notify an emergency alert. Furthermore, the providing unit can also provide appropriate advice and reminders based on the user's past actions and preferences. For example, the providing unit notifies the user of important appointments based on reminders previously set by the user. As a result, the life assistance system according to the embodiment facilitates communication and information acquisition in daily life for the hearing impaired, improving the quality of life.

[0072] The providing unit can display subtitles of the content of the conversation in real time. "Real time" means that the processing is performed almost immediately with minimal delay. For example, the providing unit converts the content of the conversation into text in real time and displays it as subtitles. The subtitle display may include, but is not limited to, font size, display position, color, etc. For example, the providing unit may increase the font size, set the display position to the bottom of the screen, and set the color to white to improve visibility. The providing unit may also customize the subtitle display settings according to the user's preferences. For example, the providing unit displays subtitles based on the font size and display position set by the user. In this way, displaying subtitles of the content of the conversation in real time makes it easier for hearing-impaired people to understand the conversation.

[0073] The providing unit can visually notify an emergency alert. An emergency refers to a situation that requires a rapid response, such as a fire, earthquake, or medical emergency. For example, the providing unit visually notifies an emergency alert. Examples of visual notifications include, but are not limited to, flashing, changing color, or displaying an icon. For example, the providing unit notifies an emergency by flashing the entire screen red. The providing unit can also display a specific icon to indicate the type of emergency. For example, in the case of a fire, a fire icon is displayed, and in the case of an earthquake, an earthquake icon is displayed. In this way, visual notification of an emergency alert allows hearing-impaired people to respond quickly to an emergency.

[0074] The analysis unit can provide advice and reminders based on the user's past behavior and preferences. Past behavior refers to behavior history, usage history, access logs, etc. Preferences refer to survey results, selection history, feedback, etc. For example, the analysis unit can analyze the user's past behavior and provide optimal advice. The analysis unit can also provide reminders based on the user's preferences. For example, the analysis unit can notify the user of important appointments based on reminders set by the user in the past. The analysis unit can also learn the user's behavior history and generate appropriate advice. For example, the analysis unit can provide related information based on places the user has visited or events the user has participated in in the past. This makes the user's life more convenient by providing advice and reminders based on the user's past behavior and preferences.

[0075] The conversion unit can convert ambient sounds into text in real time. Examples of ambient sounds include, but are not limited to, human voices, environmental sounds, and specific languages. Real-time refers to minimal latency and nearly instantaneous processing. For example, the conversion unit can convert ambient sounds into text in real time using speech recognition technology. The converted text can display, for example, the content of a conversation as subtitles in real time. The conversion unit can also recognize specific languages ​​or dialects and appropriately convert them into text. For example, the conversion unit can recognize specific dialects using speech recognition technology and convert them into standard Japanese. By converting ambient sounds into text in real time, hearing-impaired people can obtain information in real time.

[0076] The conversion unit can estimate the user's emotion and adjust the speech conversion accuracy based on the estimated emotion. Methods for estimating emotion include, but are not limited to, facial expression recognition, speech tone analysis, and biometric sensors. Methods for adjusting the conversion accuracy include, but are not limited to, algorithm parameter adjustment and filtering. For example, when the user is nervous, the conversion unit adjusts the speech recognition accuracy to increase accuracy and reduce erroneous recognition. When the user is relaxed, the conversion unit can also return the speech recognition accuracy to normal and prioritize processing speed. When the user is in a hurry, the conversion unit can also increase speech recognition accuracy and quickly convert text. This enables more accurate speech recognition by adjusting the speech conversion accuracy according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI or without AI. For example, the conversion unit can input the user's facial expression data into the generation AI and have the generation AI estimate the emotion.

[0077] The conversion unit can add a filtering function that automatically removes ambient noise when converting voice. Methods for automatically removing noise include, but are not limited to, filtering technology and noise canceling algorithms. For example, the conversion unit detects ambient noise in real time and removes it using noise canceling technology. The conversion unit can also filter noise in a specific frequency band to improve the accuracy of voice recognition. The conversion unit can also analyze ambient sounds and automatically apply an appropriate noise filter. This removes ambient noise, thereby improving the accuracy of voice recognition. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input ambient sound data to a generation AI and have the generation AI remove the noise.

[0078] During speech conversion, the conversion unit can identify the speaker's voice characteristics and apply an individually optimized conversion algorithm. Methods for identifying voice characteristics include, but are not limited to, voiceprint analysis and acoustic feature extraction. Optimized conversion algorithms include, but are not limited to, personalized models and adaptive learning algorithms. For example, the conversion unit can analyze the speaker's tone and pitch and apply an optimal speech recognition algorithm. The conversion unit can also learn the speaker's voice characteristics and use an individually customized speech recognition model. The conversion unit can also adjust the speech recognition algorithm in real time in response to changes in the speaker's voice. This improves the accuracy of speech recognition by applying the optimal conversion algorithm according to the speaker's voice characteristics. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or without AI. For example, the conversion unit can input the speaker's voice characteristic data into a generation AI and have the generation AI apply the optimal conversion algorithm.

[0079] The conversion unit may add a function to highlight specific keywords and phrases during speech conversion. Methods for selecting specific keywords and phrases include, but are not limited to, frequency, importance, and user settings. Methods for highlighting include, but are not limited to, changing fonts, colors, and backgrounds. For example, the conversion unit may detect important keywords and phrases and highlight them in the text. The conversion unit may also prioritize and highlight specific keywords set by the user. The conversion unit may also automatically highlight important phrases based on the context of the conversation. By highlighting specific keywords and phrases, important information is not overlooked. Some or all of the above-described processing in the conversion unit may be performed using, or without, AI. For example, the conversion unit may input text data to a generation AI and cause the generation AI to highlight important keywords and phrases.

[0080] The conversion unit can estimate the user's emotion and adjust the display method of the converted text based on the estimated user emotion. Methods for estimating emotion include, but are not limited to, facial expression recognition, voice tone analysis, and biometric sensors. Methods for adjusting the display method include, but are not limited to, changing the font size, color, and layout. For example, if the user is nervous, the conversion unit can provide a simple, highly visible display method. If the user is relaxed, the conversion unit can provide a display method that includes detailed information. If the user is in a hurry, the conversion unit can provide a display method that focuses on the main points. This improves legibility by adjusting the text display method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the conversion unit can be performed using, for example, AI, or without AI. For example, the conversion unit can input the user's emotional data into the generation AI and have the generation AI adjust the display method.

[0081] The conversion unit can appropriately convert regional words and dialects based on the user's geographical location information when converting speech. Methods for acquiring geographical location information include, but are not limited to, GPS data and location-based services. Methods for converting regional words and dialects include, but are not limited to, regional dictionaries and dialect conversion algorithms. For example, the conversion unit recognizes regional words and dialects based on the user's current location and appropriately converts them. The conversion unit can also learn regional words and dialects by referring to the user's past location information and improve conversion accuracy. The conversion unit can also automatically apply regional words and dialects to each region the user visits. This improves speech recognition accuracy by appropriately converting regional words and dialects. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or without AI. For example, the conversion unit can input geographical location information data to a generation AI and cause the generation AI to convert regional words and dialects.

[0082] The conversion unit can improve conversion accuracy by referring to the user's past conversation history when converting speech. Methods for collecting past conversation history include, but are not limited to, log data and conversation records. Methods for improving conversion accuracy include, but are not limited to, algorithm improvements and additional data learning. For example, the conversion unit analyzes the user's past conversation history and prioritizes recognition of frequently used words and phrases. The conversion unit can also learn the meaning of words in specific contexts from the user's past conversation history to improve conversion accuracy. The conversion unit can also use an individually customized speech recognition model based on the user's past conversation history. By referring to the past conversation history, the accuracy of speech recognition is improved. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or without AI. For example, the conversion unit can input past conversation history data into a generation AI and cause the generation AI to improve conversion accuracy.

[0083] The conversion unit can analyze the user's social media activity and add relevant information to the text when converting the voice. Methods for collecting social media activity include, but are not limited to, post content, number of likes, and comments. Methods for selecting relevant information include, but are not limited to, topic matching and relevance scores. For example, the conversion unit can analyze the user's social media posts and add relevant information to the text. The conversion unit can also add relevant information to the text based on the activity of the user's friends on social media. The conversion unit can also add information about relevant places and events to the text based on the user's social media check-in information. In this way, relevant information can be added to the text by analyzing social media activity. Some or all of the above-described processing by the conversion unit can be performed using, for example, AI, or without AI. For example, the conversion unit can input social media activity data to a generation AI and cause the generation AI to add relevant information.

[0084] The analysis unit can estimate the user's emotion and adjust the presentation method of the analysis results based on the estimated user emotion. Methods for estimating emotion include, but are not limited to, facial expression recognition, voice tone analysis, and biometric sensors. Methods for adjusting the presentation method include, but are not limited to, changing font size, color, and layout. For example, if the user is nervous, the analysis unit can provide a simple, highly visible analysis result. If the user is relaxed, the analysis unit can provide an analysis result with detailed information. If the user is in a hurry, the analysis unit can provide an analysis result that focuses on the main points. This improves visibility by adjusting the presentation method of the analysis results according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotional data into the generation AI and have the generation AI adjust the expression method.

[0085] During analysis, the analysis unit can enhance natural language processing technology to understand the context of the text and extract appropriate information. Methods for understanding the context include, but are not limited to, natural language processing technology and context analysis algorithms. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit enhances natural language processing algorithms to understand the context of the text and extract important information. The analysis unit can also automatically extract relevant information based on the context of the text. The analysis unit can also use machine learning models to analyze the context of the text and extract appropriate information. This enhances the natural language processing technology, thereby improving the accuracy of extracting appropriate information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input text data to a generation AI and have the generation AI understand the context and extract information.

[0086] The analysis unit may add a function to automatically generate a summary based on the content of the text during analysis. Methods for generating a summary include, but are not limited to, summarization algorithms and importance scoring. For example, the analysis unit may analyze the content of the text and extract important points to generate a summary. The analysis unit may also automatically generate a concise and easy-to-understand summary based on the content of the text. The analysis unit may also use an algorithm to understand the content of the text and generate a summary that captures the main points. This makes it easier to grasp the key points of the information by generating a summary based on the content of the text. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may input text data into a generation AI and have the generation AI generate a summary.

[0087] During analysis, the analysis unit can optimize the analysis algorithm based on the user's past behavior and preferences. Past behavior refers to behavior history, usage history, access logs, etc. Preferences refer to survey results, selection history, feedback, etc. For example, the analysis unit analyzes the user's past behavior and selects the optimal analysis algorithm. The analysis unit can also customize the analysis algorithm based on the user's preferences. The analysis unit can also learn the user's past behavior and preferences and optimize the analysis algorithm. This improves analysis accuracy by optimizing the analysis algorithm based on the user's past behavior and preferences. 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 past behavior data into a generation AI and have the generation AI optimize the analysis algorithm.

[0088] The analysis unit can estimate the user's emotions and prioritize the analysis results based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice tone analysis, and biometric sensors. Methods for determining priorities include, but are not limited to, importance scores and urgency scores. For example, the analysis unit can prioritize displaying important information when the user is nervous. The analysis unit can also prioritize displaying detailed information when the user is relaxed. The analysis unit can also prioritize displaying key information when the user is in a hurry. This allows important information to be prioritized by prioritizing the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotional data into the generation AI and have the generation AI determine the priorities.

[0089] During analysis, the analysis unit can adjust the analysis priority based on the time of submission of the text. Definitions of the submission time include, but are not limited to, a timestamp, a submission date and time, etc. Methods for adjusting the priority include, but are not limited to, the priority of the latest information, urgency, etc. For example, the analysis unit prioritizes analysis of text submitted more recently. The analysis unit can also analyze text submitted earlier later. The analysis unit can also automatically adjust the analysis priority based on the time of submission of the text. By adjusting the analysis priority based on the time of submission of the text, the latest information can be prioritized for analysis. Some or all of the above-described 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 submission time data into the generation AI and cause the generation AI to adjust the priority.

[0090] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the text. Definitions of relevance include, but are not limited to, topic consistency and relevance scores. Methods for adjusting the order include, but are not limited to, importance scores and urgency scores. For example, the analysis unit prioritizes analyzing text with high relevance. The analysis unit can also postpone analyzing text with low relevance. The analysis unit can also automatically adjust the order of analysis based on the relevance of the text. By adjusting the order of analysis based on the relevance of the text, important information can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input relevance data to a generation AI and have the generation AI adjust the order.

[0091] During analysis, the analysis unit can adjust the use of technical terms in the analysis results according to the user's level of expertise. Definitions of expertise level include, but are not limited to, qualification information, past learning history, etc. Methods for adjusting the use of technical terms include, but are not limited to, the difficulty level of terms, the presence or absence of explanations, etc. For example, if the user's level of expertise is high, the analysis unit can provide analysis results that use a lot of technical terms. Furthermore, if the user's level of expertise is low, the analysis unit can also provide analysis results that avoid technical terms. The analysis unit can also automatically adjust the use of technical terms according to the user's level of expertise. Adjusting the use of technical terms according to the user's level of expertise makes the analysis results easier to understand. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input expertise level data into a generation AI to adjust the use of technical terms.

[0092] The providing unit can estimate the user's emotion and adjust the information provision method based on the estimated user emotion. Methods for estimating emotion include, but are not limited to, facial expression recognition, voice tone analysis, and biometric sensors. Methods for adjusting the information provision method include, but are not limited to, display format, notification method, and timing. For example, if the user is nervous, the providing unit can provide a simple, highly visible information provision method. Furthermore, if the user is relaxed, the providing unit can provide an information provision method that includes detailed information. Furthermore, if the user is in a hurry, the providing unit can provide an information provision method that focuses on the main points. This allows information to be communicated more effectively by adjusting the information provision method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the user's emotional data into the generating AI and adjust the way information is provided.

[0093] When providing information, the providing unit can select optimal information based on the user's past behavior and preferences. Past behavior refers to behavior history, usage history, access logs, etc. Preferences refer to survey results, selection history, feedback, etc. For example, the providing unit analyzes the user's past behavior and selects optimal information. The providing unit can also customize information based on the user's preferences. The providing unit can also learn the user's past behavior and preferences and provide optimal information. This improves the accuracy of information provision by selecting optimal information based on the user's past behavior and preferences. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input past behavior data into a generation AI and cause the generation AI to select optimal information.

[0094] When providing information, the providing unit can customize the information display method based on the user's current situation. Definitions of the current situation include, but are not limited to, location information, activity status, and environmental information. Methods for customizing the display method include, but are not limited to, changing font size, color, and layout. For example, the providing unit provides concise, highly visible information when the user is moving. The providing unit can also provide detailed information when the user is stationary. The providing unit can also automatically customize the information display method based on the user's current situation. Customizing the information display method based on the user's current situation allows the information to be communicated more effectively. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit may input current situation data into a generating AI and cause the generating AI to customize the display method.

[0095] The providing unit can improve the information provision method by reflecting user feedback when providing information. Methods for collecting feedback include, but are not limited to, survey results, user comments, and evaluation scores. Methods for improving the information provision method include, but are not limited to, changing the display format, changing the notification method, and adjusting the timing. For example, the providing unit can analyze user feedback and improve the information provision method. The providing unit can also customize the information display method based on user feedback. The providing unit can also collect user feedback and optimize the information provision algorithm. This improves the information provision method by reflecting user feedback. Some or all of the above-described processing in the providing unit can be performed using, or without, AI. For example, the providing unit can input feedback data into a generating AI and cause the generating AI to improve the information provision method.

[0096] The providing unit can estimate the user's emotions and determine the priority of information provision based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice tone analysis, and biometric sensors. Methods for determining the priority include, but are not limited to, importance scores and urgency scores. For example, if the user is nervous, the providing unit can prioritize providing important information. Furthermore, if the user is relaxed, the providing unit can prioritize providing detailed information. Furthermore, if the user is in a hurry, the providing unit can prioritize providing information that covers the main points. In this way, by determining the priority of information provision according to the user's emotions, important information can be prioritized. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the providing unit may be performed using, for example, an AI, or without using an AI. For example, the providing unit can input the user's emotional data into the generating AI and determine the priority of information provision.

[0097] When providing information, the providing unit can provide optimal information by taking into account the user's geographical location information. Methods for acquiring geographical location information include, but are not limited to, GPS data and location information services. Methods for selecting optimal information include, but are not limited to, information based on the user's current situation, past behavioral history, preferences, etc. For example, the providing unit provides relevant information based on the user's current location. The providing unit can also provide optimal information by referring to the user's past location information. The providing unit can also automatically provide information specific to each area the user visits. This allows for providing highly relevant information by taking the user's geographical location information into consideration. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or without AI. For example, the providing unit can input geographical location information data to a generation AI and cause the generation AI to provide optimal information.

[0098] The providing unit may analyze the user's social media activity and provide related information when providing information. Methods for collecting social media activity include, but are not limited to, post content, number of likes, and comments. Methods for selecting related information include, but are not limited to, topic consistency and relevance scores. For example, the providing unit may analyze the user's social media posts and provide related information. The providing unit may also provide related information by referring to the activities of the user's friends on social media. The providing unit may also provide information on related places and events based on the user's social media check-in information. This allows related information to be provided by analyzing social media activity. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input social media activity data into a generation AI and cause the generation AI to provide related information.

[0099] When providing information, the providing unit can customize the information provision method by reflecting the user's past feedback. Methods of collecting feedback include, but are not limited to, survey results, user comments, and evaluation scores. Methods of customizing the information provision method include, but are not limited to, changing the display format, changing the notification method, and adjusting the timing. For example, the providing unit analyzes the user's past feedback and customizes the information provision method. The providing unit can also optimize the information display method based on the user's past feedback. The providing unit can also collect the user's past feedback and improve the information provision algorithm. In this way, the information provision method is customized by reflecting the user's past feedback. Some or all of the above-described processing by the providing unit may be performed using, or without, AI. For example, the providing unit can input past feedback data into the generation AI and cause the generation AI to customize the information provision method. === Hard Collateral 1-1 === Each of the multiple elements including the conversion unit, analysis unit, and provision unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the conversion unit acquires voice using the microphone 38B of the smart device 14 and converts the voice into text using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the text using a generation AI, and generates appropriate information and instructions. The provision unit displays subtitles in real time using the display 40A of the smart device 14, for example, to visually notify emergency alerts. === Hard Collateral 1-2 === Each of the multiple elements, including the conversion unit, analysis unit, and provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the conversion unit acquires voice using the microphone 238 of the smart glasses 214 and converts the voice into text using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the text using a generation AI to generate appropriate information and instructions. The provision unit, for example, displays subtitles in real time using the display of the smart glasses 214 to visually notify emergency alerts. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned conversion unit, analysis unit, and provision unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the conversion unit acquires voice using the microphone 238 of the headset-type terminal 314 and converts the voice into text using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the text using a generation AI, and generates appropriate information and instructions. The provision unit displays subtitles in real time using the display 343 of the headset-type terminal 314, for example, to visually notify emergency alerts. === Hard Collateral 1-4 === Each of the multiple elements including the conversion unit, analysis unit, and provision unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the conversion unit acquires voice using the microphone 238 of the robot 414 and converts the voice into text using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the text using a generation AI to generate appropriate information and instructions. The provision unit, for example, displays subtitles in real time using the display of the robot 414 to visually notify emergency alerts.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The analysis unit can estimate the user's emotion and adjust the presentation method of the analysis results based on the estimated user emotion. Methods for estimating emotion include, but are not limited to, facial expression recognition, voice tone analysis, and biometric sensors. Methods for adjusting the presentation method include, but are not limited to, changing font size, color, and layout. For example, if the user is nervous, the analysis unit can provide a simple, highly visible analysis result. If the user is relaxed, the analysis unit can provide an analysis result with detailed information. If the user is in a hurry, the analysis unit can provide an analysis result that focuses on the main points. This improves visibility by adjusting the presentation method of the analysis results according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotional data into the generation AI and have the generation AI adjust the expression method.

[0102] The providing unit can estimate the user's emotion and adjust the information provision method based on the estimated user emotion. Methods for estimating emotion include, but are not limited to, facial expression recognition, voice tone analysis, and biometric sensors. Methods for adjusting the information provision method include, but are not limited to, display format, notification method, and timing. For example, if the user is nervous, the providing unit can provide a simple, highly visible information provision method. Furthermore, if the user is relaxed, the providing unit can provide an information provision method that includes detailed information. Furthermore, if the user is in a hurry, the providing unit can provide an information provision method that focuses on the main points. This allows information to be communicated more effectively by adjusting the information provision method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the user's emotional data into the generating AI and adjust the way information is provided.

[0103] When providing information, the providing unit can select optimal information based on the user's past behavior and preferences. Past behavior refers to behavior history, usage history, access logs, etc. Preferences refer to survey results, selection history, feedback, etc. For example, the providing unit analyzes the user's past behavior and selects optimal information. The providing unit can also customize information based on the user's preferences. The providing unit can also learn the user's past behavior and preferences and provide optimal information. This improves the accuracy of information provision by selecting optimal information based on the user's past behavior and preferences. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input past behavior data into a generation AI and cause the generation AI to select optimal information.

[0104] When providing information, the providing unit can customize the information display method based on the user's current situation. Definitions of the current situation include, but are not limited to, location information, activity status, and environmental information. Methods for customizing the display method include, but are not limited to, changing font size, color, and layout. For example, the providing unit provides concise, highly visible information when the user is moving. The providing unit can also provide detailed information when the user is stationary. The providing unit can also automatically customize the information display method based on the user's current situation. Customizing the information display method based on the user's current situation allows the information to be communicated more effectively. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit may input current situation data into a generating AI and cause the generating AI to customize the display method.

[0105] The providing unit can improve the information provision method by reflecting user feedback when providing information. Methods for collecting feedback include, but are not limited to, survey results, user comments, and evaluation scores. Methods for improving the information provision method include, but are not limited to, changing the display format, changing the notification method, and adjusting the timing. For example, the providing unit can analyze user feedback and improve the information provision method. The providing unit can also customize the information display method based on user feedback. The providing unit can also collect user feedback and optimize the information provision algorithm. This improves the information provision method by reflecting user feedback. Some or all of the above-described processing in the providing unit can be performed using, or without, AI. For example, the providing unit can input feedback data into a generating AI and cause the generating AI to improve the information provision method.

[0106] The providing unit can estimate the user's emotions and determine the priority of information provision based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice tone analysis, and biometric sensors. Methods for determining the priority include, but are not limited to, importance scores and urgency scores. For example, if the user is nervous, the providing unit can prioritize providing important information. Furthermore, if the user is relaxed, the providing unit can prioritize providing detailed information. Furthermore, if the user is in a hurry, the providing unit can prioritize providing information that covers the main points. In this way, by determining the priority of information provision according to the user's emotions, important information can be prioritized. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the providing unit may be performed using, for example, an AI, or without using an AI. For example, the providing unit can input the user's emotional data into the generating AI and determine the priority of information provision.

[0107] During analysis, the analysis unit can enhance natural language processing technology to understand the context of the text and extract appropriate information. Methods for understanding the context include, but are not limited to, natural language processing technology and context analysis algorithms. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit enhances natural language processing algorithms to understand the context of the text and extract important information. The analysis unit can also automatically extract relevant information based on the context of the text. The analysis unit can also use machine learning models to analyze the context of the text and extract appropriate information. This enhances the natural language processing technology, thereby improving the accuracy of extracting appropriate information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input text data to a generation AI and have the generation AI understand the context and extract information.

[0108] The analysis unit may add a function to automatically generate a summary based on the content of the text during analysis. Methods for generating a summary include, but are not limited to, summarization algorithms and importance scoring. For example, the analysis unit may analyze the content of the text and extract important points to generate a summary. The analysis unit may also automatically generate a concise and easy-to-understand summary based on the content of the text. The analysis unit may also use an algorithm to understand the content of the text and generate a summary that captures the main points. This makes it easier to grasp the key points of the information by generating a summary based on the content of the text. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may input text data into a generation AI and have the generation AI generate a summary.

[0109] During analysis, the analysis unit can optimize the analysis algorithm based on the user's past behavior and preferences. Past behavior refers to behavior history, usage history, access logs, etc. Preferences refer to survey results, selection history, feedback, etc. For example, the analysis unit analyzes the user's past behavior and selects the optimal analysis algorithm. The analysis unit can also customize the analysis algorithm based on the user's preferences. The analysis unit can also learn the user's past behavior and preferences and optimize the analysis algorithm. This improves analysis accuracy by optimizing the analysis algorithm based on the user's past behavior and preferences. 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 past behavior data into a generation AI and have the generation AI optimize the analysis algorithm.

[0110] The analysis unit can estimate the user's emotions and prioritize the analysis results based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice tone analysis, and biometric sensors. Methods for determining priorities include, but are not limited to, importance scores and urgency scores. For example, the analysis unit can prioritize displaying important information when the user is nervous. The analysis unit can also prioritize displaying detailed information when the user is relaxed. The analysis unit can also prioritize displaying key information when the user is in a hurry. This allows important information to be prioritized by prioritizing the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotional data into the generation AI and have the generation AI determine the priorities.

[0111] During analysis, the analysis unit can adjust the analysis priority based on the time of submission of the text. Definitions of the submission time include, but are not limited to, a timestamp, a submission date and time, etc. Methods for adjusting the priority include, but are not limited to, the priority of the latest information, urgency, etc. For example, the analysis unit prioritizes analysis of text submitted more recently. The analysis unit can also analyze text submitted earlier later. The analysis unit can also automatically adjust the analysis priority based on the time of submission of the text. By adjusting the analysis priority based on the time of submission of the text, the latest information can be prioritized for analysis. Some or all of the above-described 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 submission time data into the generation AI and cause the generation AI to adjust the priority.

[0112] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the text. Definitions of relevance include, but are not limited to, topic consistency and relevance scores. Methods for adjusting the order include, but are not limited to, importance scores and urgency scores. For example, the analysis unit prioritizes analyzing text with high relevance. The analysis unit can also postpone analyzing text with low relevance. The analysis unit can also automatically adjust the order of analysis based on the relevance of the text. By adjusting the order of analysis based on the relevance of the text, important information can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input relevance data to a generation AI and have the generation AI adjust the order.

[0113] During analysis, the analysis unit can adjust the use of technical terms in the analysis results according to the user's level of expertise. Definitions of expertise level include, but are not limited to, qualification information, past learning history, etc. Methods for adjusting the use of technical terms include, but are not limited to, the difficulty level of terms, the presence or absence of explanations, etc. For example, if the user's level of expertise is high, the analysis unit can provide analysis results that use a lot of technical terms. Furthermore, if the user's level of expertise is low, the analysis unit can also provide analysis results that avoid technical terms. The analysis unit can also automatically adjust the use of technical terms according to the user's level of expertise. Adjusting the use of technical terms according to the user's level of expertise makes the analysis results easier to understand. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input expertise level data into a generation AI to adjust the use of technical terms.

[0114] The providing unit can estimate the user's emotion and adjust the information provision method based on the estimated user emotion. Methods for estimating emotion include, but are not limited to, facial expression recognition, voice tone analysis, and biometric sensors. Methods for adjusting the information provision method include, but are not limited to, display format, notification method, and timing. For example, if the user is nervous, the providing unit can provide a simple, highly visible information provision method. Furthermore, if the user is relaxed, the providing unit can provide an information provision method that includes detailed information. Furthermore, if the user is in a hurry, the providing unit can provide an information provision method that focuses on the main points. This allows information to be communicated more effectively by adjusting the information provision method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the user's emotional data into the generating AI and adjust the way information is provided.

[0115] When providing information, the providing unit can select optimal information based on the user's past behavior and preferences. Past behavior refers to behavior history, usage history, access logs, etc. Preferences refer to survey results, selection history, feedback, etc. For example, the providing unit analyzes the user's past behavior and selects optimal information. The providing unit can also customize information based on the user's preferences. The providing unit can also learn the user's past behavior and preferences and provide optimal information. This improves the accuracy of information provision by selecting optimal information based on the user's past behavior and preferences. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input past behavior data into a generation AI and cause the generation AI to select optimal information.

[0116] When providing information, the providing unit can customize the information display method based on the user's current situation. Definitions of the current situation include, but are not limited to, location information, activity status, and environmental information. Methods for customizing the display method include, but are not limited to, changing font size, color, and layout. For example, the providing unit provides concise, highly visible information when the user is moving. The providing unit can also provide detailed information when the user is stationary. The providing unit can also automatically customize the information display method based on the user's current situation. Customizing the information display method based on the user's current situation allows the information to be communicated more effectively. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit may input current situation data into a generating AI and cause the generating AI to customize the display method.

[0117] The providing unit can improve the information provision method by reflecting user feedback when providing information. Methods for collecting feedback include, but are not limited to, survey results, user comments, and evaluation scores. Methods for improving the information provision method include, but are not limited to, changing the display format, changing the notification method, and adjusting the timing. For example, the providing unit can analyze user feedback and improve the information provision method. The providing unit can also customize the information display method based on user feedback. The providing unit can also collect user feedback and optimize the information provision algorithm. This improves the information provision method by reflecting user feedback. Some or all of the above-described processing in the providing unit can be performed using, or without, AI. For example, the providing unit can input feedback data into a generating AI and cause the generating AI to improve the information provision method.

[0118] The providing unit can estimate the user's emotions and determine the priority of information provision based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice tone analysis, and biometric sensors. Methods for determining the priority include, but are not limited to, importance scores and urgency scores. For example, if the user is nervous, the providing unit can prioritize providing important information. Furthermore, if the user is relaxed, the providing unit can prioritize providing detailed information. Furthermore, if the user is in a hurry, the providing unit can prioritize providing information that covers the main points. In this way, by determining the priority of information provision according to the user's emotions, important information can be prioritized. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the providing unit may be performed using, for example, an AI, or without using an AI. For example, the providing unit can input the user's emotional data into the generating AI and determine the priority of information provision.

[0119] When providing information, the providing unit can provide optimal information by taking into account the user's geographical location information. Methods for acquiring geographical location information include, but are not limited to, GPS data and location information services. Methods for selecting optimal information include, but are not limited to, information based on the user's current situation, past behavioral history, preferences, etc. For example, the providing unit provides relevant information based on the user's current location. The providing unit can also provide optimal information by referring to the user's past location information. The providing unit can also automatically provide information specific to each area the user visits. This allows for providing highly relevant information by taking the user's geographical location information into consideration. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or without AI. For example, the providing unit can input geographical location information data to a generation AI and cause the generation AI to provide optimal information.

[0120] The providing unit may analyze the user's social media activity and provide related information when providing information. Methods for collecting social media activity include, but are not limited to, post content, number of likes, and comments. Methods for selecting related information include, but are not limited to, topic consistency and relevance scores. For example, the providing unit may analyze the user's social media posts and provide related information. The providing unit may also provide related information by referring to the activities of the user's friends on social media. The providing unit may also provide information on related places and events based on the user's social media check-in information. This allows related information to be provided by analyzing social media activity. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input social media activity data into a generation AI and cause the generation AI to provide related information.

[0121] When providing information, the providing unit can customize the information provision method by reflecting the user's past feedback. Methods of collecting feedback include, but are not limited to, survey results, user comments, and evaluation scores. Methods of customizing the information provision method include, but are not limited to, changing the display format, changing the notification method, and adjusting the timing. For example, the providing unit analyzes the user's past feedback and customizes the information provision method. The providing unit can also optimize the information display method based on the user's past feedback. The providing unit can also collect the user's past feedback and improve the information provision algorithm. In this way, the information provision method is customized by reflecting the user's past feedback. Some or all of the above-described processing by the providing unit may be performed using, or without, AI. For example, the providing unit can input past feedback data into the generation AI and cause the generation AI to customize the information provision method.

[0122] The processing flow of the second embodiment will be briefly explained below.

[0123] Step 1: The conversion unit converts speech into text. Speech can include human speech, environmental sounds, and specific languages. The conversion unit uses speech recognition technology to convert surrounding speech into text in real time. It can also recognize specific languages ​​and dialects and convert them appropriately into text. For example, the content of a conversation can be converted into text in real time and displayed as subtitles. Step 2: The analysis unit uses a generation AI to analyze the text converted by the conversion unit. The analysis is performed using methods such as natural language processing technology, statistical analysis, and machine learning algorithms. For example, a text generation AI (e.g., LLM) can be used to analyze the text and generate appropriate information or instructions. It can also provide appropriate advice or reminders based on the user's past behavior and preferences. Step 3: The providing unit provides information based on the results of the analysis by the analyzing unit. The provided information includes text information, image information, and audio information. For example, it can display subtitles of conversation content in real time. It can also provide visual notifications of emergency alerts. It can also provide appropriate advice and reminders based on the user's past behavior and preferences. For example, it can notify the user of important appointments based on reminders set by the user in the past.

[0124] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0125] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0126] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0127] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0128] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0129] 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.

[0130] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0131] 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.

[0132] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0134] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0135] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0136] 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.

[0137] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0138] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0139] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0140] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0141] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0142] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0143] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0144] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0145] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0146] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0147] 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.

[0148] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0150] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0151] 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.

[0152] 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.

[0153] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0154] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0155] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0156] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0157] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0158] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0159] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0160] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0161] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0162] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0163] 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.

[0164] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0165] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0166] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0167] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0168] 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.

[0169] 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.

[0170] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0171] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0172] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0173] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0174] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0175] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0176] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0177] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0178] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0179] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0180] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0181] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0182] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0183] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0184] 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.

[0185] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0186] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0187] 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.

[0188] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0189] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0190] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0191] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0192] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0193] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0194] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0195] [Explanation of symbols]

[0196] 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 converter for converting speech to text; an analysis unit that analyzes the text converted by the conversion unit; a providing unit that provides information based on the results of the analysis by the analyzing unit. A system characterized by:

2. The providing unit Display conversations in real time with subtitles 2. The system of claim 1.

3. The providing unit Visual notification of emergency alerts 2. The system of claim 1.

4. The analysis unit Demonstrate specific ways to provide advice and reminders based on users' past behavior and preferences 2. The system of claim 1.

5. The conversion unit Converts surrounding audio into text in real time 2. The system of claim 1.

6. The conversion unit Estimate the user's emotions and adjust the speech conversion accuracy based on the estimated user emotions.

2. The system of claim 1.

7. The conversion unit Add a filtering function to automatically remove ambient noise when converting audio.

2. The system of claim 1.

8. The conversion unit When converting voice, identify the speaker's vocal characteristics and apply an individually optimized conversion algorithm 2. The system of claim 1.

9. The conversion unit Add the ability to highlight specific keywords or phrases when converting audio 2. The system of claim 1.

10. The conversion unit Inferring user sentiment and adjusting the presentation of the converted text based on the estimated user sentiment 2. The system of claim 1.

Images