system

Abstract

The system according to the embodiment aims to enable people with hearing impairments to obtain information in multiple languages ​​in natural voices. [Solution] A system according to an embodiment includes an analysis unit, an understanding unit, a generation unit, and a provision unit. The analysis unit analyzes a user's input. The understanding unit understands the context and intent based on the input analyzed by the analysis unit. The generation unit generates information based on the context and intent understood by the understanding unit. The provision unit provides the information generated by the generation unit via bone conduction earphones.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem that it is difficult for people with hearing impairments to obtain information in multiple languages ​​in natural voices.

[0005] The system according to the embodiment aims to enable people with hearing impairments to obtain information in multiple languages ​​in natural voices. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, an understanding unit, a generation unit, and a provision unit. The analysis unit analyzes a user's input. The understanding unit understands the context and intention based on the input analyzed by the analysis unit. The generation unit generates information based on the context and intention understood by the understanding unit. The provision unit provides the information generated by the generation unit via bone conduction earphones. [Effects of the Invention]

[0007] The system according to the embodiment allows people with hearing impairments to obtain information in multiple languages ​​in natural voices. [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 system according to an embodiment of the present invention is a novel device that combines a generation AI and bone conduction earphones. This device allows people with hearing impairments to easily obtain information in multiple languages. Specifically, a user wears bone conduction earphones, and a generation AI analyzes the user's input, generates information in an appropriate language, and provides it to the user through the bone conduction earphones. This system can facilitate multilingual communication and improve access to information for people with hearing impairments. For example, a user inputs information, and a generation AI analyzes the input. Next, the generation AI understands the context and intent and generates information in the appropriate language. Finally, the generated information is provided to the user through the bone conduction earphones. In this way, the system can enable people with hearing impairments to easily obtain information in multiple languages.

[0029] The system according to the embodiment includes an analysis unit, an understanding unit, a generation unit, and a provision unit. The analysis unit analyzes a user's input. The user's input includes, but is not limited to, text input, voice input, and gesture input. The analysis unit analyzes the user's input using, for example, text analysis technology. The analysis unit can also analyze voice input using voice analysis technology. The analysis unit can also analyze gesture input using image analysis technology. For example, the analysis unit analyzes text input and understands the user's intention using natural language processing technology. Voice analysis technology converts voice input into text using voice recognition software and analyzes the text. Image analysis technology recognizes gestures using a camera and analyzes the gestures. The understanding unit understands the context and intention based on the input analyzed by the analysis unit. The understanding unit understands the context and intention using, for example, a machine learning algorithm. The understanding unit can also understand the context and intention using natural language processing technology. The understanding unit can also understand the context and intention by referring to past data. For example, the understanding unit uses a machine learning algorithm to learn patterns of a user's input and understands the context and intent based on those patterns. Natural language processing technology analyzes text data and extracts the context and intent. The past data includes the user's past input history and dialogue logs. The generation unit generates information based on the context and intent understood by the understanding unit. The generation unit generates information using, for example, text generation technology. The generation unit can also generate audio information using voice generation technology. The generation unit can also generate visual information using image generation technology. For example, the generation unit generates text information using natural language generation technology. The voice generation technology converts text information into audio using voice synthesis software. The image generation technology generates visual information using image editing software. The provision unit provides the information generated by the generation unit through bone conduction earphones. The provision unit transmits audio information to the user using, for example, bone conduction technology. The provision unit can also display visual information on a display. The provision unit can also provide information using haptic feedback.For example, the providing unit transmits audio information through the user's bones using bone conduction technology. Visual information is displayed on a display, allowing the user to visually confirm the information. Haptic feedback is provided to the user using a vibration motor. This allows the system according to the embodiment to analyze the user's input, understand the context and intent, generate information in an appropriate language, and provide it through the bone conduction earphones.

[0030] The analysis unit can analyze the user's past input history and select an analysis method. For example, the analysis unit records words and phrases frequently used by the user in the past and reflects them in the analysis using the generation AI. The analysis unit can also extract specific patterns from the user's past input history and optimize the analysis method using the generation AI. The analysis unit can also allow the generation AI to select an appropriate analysis algorithm based on the content the user has previously input. This improves the accuracy of the analysis by selecting the optimal analysis method based on the user's past input history. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's past input history data into the generation AI and have the generation AI select the analysis method.

[0031] When analyzing the input, the analysis unit can perform filtering based on the user's current situation or environment. For example, if the user is in a noisy environment, the analysis unit can use the generation AI to remove noise and perform input analysis. Furthermore, if the user is in a quiet environment, the analysis unit can also perform a detailed analysis using the generation AI to improve accuracy. Furthermore, if the user is on the move, the analysis unit can also use the generation AI to analyze the input in real time and provide appropriate feedback. This improves the accuracy of the analysis by filtering according to the user's current situation and environment. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's current situation and environmental data into the generation AI and have the generation AI perform filtering.

[0032] During input analysis, the analysis unit can prioritize analysis of highly relevant information based on the user's geographical location information. For example, when the user is in a specific area, the analysis unit uses the generation AI to prioritize analysis of information related to that area. Furthermore, when the user is traveling, the analysis unit can also use the generation AI to prioritize analysis of information related to the travel destination. Furthermore, when the user is at home, the analysis unit can also use the generation AI to prioritize analysis of information related to daily life. This prioritizes analysis of highly relevant information based on the user's geographical location information, thereby improving the accuracy of the analysis. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's geographical location information data to the generation AI and have the generation AI analyze highly relevant information.

[0033] The analysis unit can analyze the user's social media activities and analyze related information when analyzing the input. For example, the analysis unit can analyze information shared by the user on social media using a generation AI and provide related information. The analysis unit can also analyze information about accounts the user follows on social media using a generation AI. The analysis unit can also analyze the user's social media activity history using a generation AI and provide related information. This allows the related information to be appropriately analyzed by analyzing the user's social media activities. Some or all of the above-described processing in the analysis unit can be performed using an AI, for example, or without an AI. For example, the analysis unit can input the user's social media activity data into the generation AI and have the generation AI analyze the related information.

[0034] The understanding unit can adjust the understanding algorithm by referring to past understanding data when understanding context and intent. The understanding unit, for example, uses a generation AI to analyze past understanding data and select an optimal algorithm. The understanding unit can also use the generation AI to extract patterns from past understanding data and improve understanding accuracy. The understanding unit can also use the generation AI to optimize the method of understanding context and intent based on past understanding data. By referring to past understanding data, the understanding algorithm is optimized and understanding accuracy is improved. Some or all of the above-mentioned processing in the understanding unit may be performed, for example, using AI or without AI. For example, the understanding unit can input past understanding data into the generation AI and have the generation AI adjust the understanding algorithm.

[0035] The understanding unit can improve the accuracy of understanding based on the user's current situation or environment when understanding context and intent. The understanding unit, for example, uses a generation AI to acquire information about the user's current environment and reflect this in context understanding. The understanding unit can also use the generation AI to consider the user's current situation and select an appropriate understanding method. The understanding unit can also use the generation AI to improve the accuracy of understanding based on the user's current environment. This enables more appropriate understanding by improving the accuracy of understanding based on the user's current situation and environment. Some or all of the above-mentioned processing in the understanding unit may be performed, for example, using AI or without AI. For example, the understanding unit can input data about the user's current situation and environment into the generation AI and have the generation AI improve the accuracy of understanding.

[0036] When understanding context and intent, the understanding unit can prioritize understanding of highly relevant information based on the user's geographical location information. For example, when the user is in a specific area, the understanding unit uses the generation AI to prioritize understanding of information related to that area. Furthermore, when the user is traveling, the understanding unit can also use the generation AI to prioritize understanding of information related to the travel destination. Furthermore, when the user is at home, the understanding unit can also use the generation AI to prioritize understanding of information related to daily life. This improves the accuracy of understanding by prioritizing understanding of highly relevant information based on the user's geographical location information. Some or all of the above-described processing in the understanding unit may be performed, for example, using AI or without AI. For example, the understanding unit can input the user's geographical location information data into the generation AI and cause the generation AI to understand highly relevant information.

[0037] The understanding unit can analyze the user's social media activities and understand related information when understanding the context and intent. For example, the understanding unit can analyze information shared by the user on social media using a generation AI to understand the related information. The understanding unit can also use a generation AI to understand information about accounts the user follows on social media. The understanding unit can also analyze the user's social media activity history using a generation AI to understand related information. This allows the related information to be appropriately understood by analyzing the user's social media activities. Some or all of the above-described processing in the understanding unit can be performed using, for example, AI, or without AI. For example, the understanding unit can input the user's social media activity data into the generation AI and have the generation AI understand the related information.

[0038] When generating information, the generation unit can adjust the level of detail of the generated information based on the importance of the information to be generated. The generation unit, for example, uses a generation AI to generate important information in detail. The generation unit can also use the generation AI to generate general information in a concise manner. The generation unit can also use the generation AI to adjust the level of detail of the information in accordance with a user request. In this way, appropriate information is generated by adjusting the level of detail based on the importance of the information to be generated. Some or all of the above-described processing in the generation unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the generation unit can input importance data of the information to be generated to the generation AI and have the generation AI adjust the level of detail.

[0039] When generating information, the generation unit can apply different generation algorithms depending on the category of the information to be generated. For example, the generation unit can apply a specialized algorithm when generating technical information using the generation AI. The generation unit can also apply a creative algorithm when generating entertainment information using the generation AI. The generation unit can also apply a rapid algorithm when generating news information using the generation AI. This improves the accuracy of information generation by applying an appropriate generation algorithm depending on the category of the information to be generated. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the generation unit can input category data of the information to be generated to the generation AI and cause the generation AI to apply the generation algorithm.

[0040] When generating information, the generation unit can determine the priority of generation based on the submission time of the information to be generated. The generation unit, for example, uses a generation AI to generate urgent information as a priority. The generation unit can also use a generation AI to generate regular information at a later date. The generation unit can also use a generation AI to adjust the order of information generation in accordance with a user request. In this way, by determining the priority based on the submission time of the information to be generated, information is generated at the appropriate time. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the generation unit can input information submission time data into the generation AI and have the generation AI determine the priority.

[0041] When generating information, the generation unit can adjust the order of generation based on the relevance of the information to be generated. For example, the generation unit uses a generation AI to prioritize the generation of highly relevant information. The generation unit can also use the generation AI to postpone the generation of less relevant information. The generation unit can also use the generation AI to adjust the order of generation of information in accordance with a user request. In this way, by adjusting the order based on the relevance of the information to be generated, information is generated in an appropriate order. Some or all of the above-described processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input relevance data of information to the generation AI and cause the generation AI to adjust the generation order.

[0042] When providing information, the providing unit can select a delivery method by referring to the user's past information reception history. The providing unit, for example, uses a generation AI to analyze the information format that the user has preferred in the past and selects the optimal delivery method. The providing unit can also use the generation AI to select the most effective delivery method from the user's past information reception history. The providing unit can also use the generation AI to optimize the timing of information provision based on the user's past information reception history. This improves the accuracy of information provision by selecting the optimal delivery method based on the user's past information reception history. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input past information reception history data into the generation AI and have the generation AI select the delivery method.

[0043] When providing information, the providing unit can improve the accuracy of the information provided based on the user's current situation or environment. The providing unit, for example, uses a generation AI to acquire information about the user's current environment and reflects the information provided. The providing unit can also use the generation AI to consider the user's current situation and select an appropriate information provision method. The providing unit can also use the generation AI to improve the accuracy of the information provided based on the user's current environment. This enables more appropriate information to be provided by improving the accuracy of the information provided based on the user's current situation or environment. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input data about the user's current situation or environment into the generation AI and cause the generation AI to improve the accuracy of the information provided.

[0044] When providing information, the providing unit can prioritize providing highly relevant information based on the user's geographical location information. For example, when the user is in a specific area, the providing unit can use the generation AI to prioritize providing information related to that area. Furthermore, when the user is traveling, the providing unit can also use the generation AI to prioritize providing information related to the travel destination. Furthermore, when the user is at home, the providing unit can also use the generation AI to prioritize providing information related to daily life. This improves the accuracy of information provision by prioritizing highly relevant information based on the user's geographical location information. Some or all of the above-described processing in the providing unit can be performed, for example, using AI or without AI. For example, the providing unit can input the user's geographical location information data to the generation AI and cause the generation AI to provide highly relevant information.

[0045] When providing information, the providing unit can analyze the user's social media activities and provide related information. For example, the providing unit can analyze information shared by the user on social media using a generation AI and provide the related information. The providing unit can also use the generation AI to provide information on accounts the user follows on social media. The providing unit can also analyze the user's social media activity history using a generation AI and provide the related information. In this way, by analyzing the user's social media activities, the related information can be appropriately provided. Some or all of the above-described processing in the providing unit may be performed using an AI, for example, or may be performed without using an AI. For example, the providing unit can input the user's social media activity data into the generation AI and cause the generation AI to provide the related information.

[0046] When transmitting voice, the bone conduction unit can select a transmission method by referring to the user's past voice reception history. For example, the bone conduction unit uses a generation AI to analyze the user's preferred voice reception format in the past and select the optimal transmission method. The bone conduction unit can also use the generation AI to select the most effective transmission method from the user's past voice reception history. The bone conduction unit can also use the generation AI to optimize the timing of voice transmission based on the user's past voice reception history. This improves the accuracy of voice transmission by selecting the optimal transmission method based on the user's past voice reception history. Some or all of the above-described processing in the bone conduction unit may be performed using, for example, AI, or may be performed without using AI. For example, the bone conduction unit can input past voice reception history data into the generation AI and have the generation AI select the transmission method.

[0047] The bone conduction unit can improve the accuracy of voice transmission based on the user's current situation or environment. For example, the bone conduction unit acquires information about the user's current environment using a generation AI and reflects this information in the voice transmission. The bone conduction unit can also use the generation AI to select an appropriate transmission method taking the user's current situation into consideration. The bone conduction unit can also use the generation AI to improve the transmission accuracy based on the user's current environment. This enables more appropriate voice transmission by improving the transmission accuracy based on the user's current situation and environment. Some or all of the above-described processing in the bone conduction unit may be performed using, for example, AI, or may be performed without using AI. For example, the bone conduction unit can input data about the user's current situation and environment into the generation AI and have the generation AI improve the transmission accuracy.

[0048] When transmitting voice, the bone conduction unit can prioritize relevant voice based on the user's geographical location information. For example, when the user is in a specific area, the bone conduction unit uses a generation AI to prioritize voice related to that area. Furthermore, when the user is traveling, the bone conduction unit can also use a generation AI to prioritize voice related to the user's travel destination. Furthermore, when the user is at home, the bone conduction unit can also use a generation AI to prioritize voice related to daily life. This prioritizes the transmission of relevant voice based on the user's geographical location information, thereby improving the accuracy of voice transmission. Some or all of the above-described processing in the bone conduction unit may be performed using AI, for example, or without AI. For example, the bone conduction unit can input the user's geographical location information data into the generation AI and have the generation AI transmit relevant voice.

[0049] The bone conduction unit can analyze the user's social media activities and transmit related audio when transmitting audio. For example, the bone conduction unit can analyze information shared by the user on social media using a generation AI and transmit related audio. The bone conduction unit can also transmit information about accounts the user follows on social media using a generation AI. The bone conduction unit can also analyze the user's social media activity history using a generation AI and transmit related audio. This allows for appropriate transmission of related audio by analyzing the user's social media activities. Some or all of the above-described processing in the bone conduction unit can be performed using, for example, AI, or without AI. For example, the bone conduction unit can input the user's social media activity data into a generation AI and have the generation AI transmit related audio.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The analysis unit can take the user's health condition data into account when analyzing the user's input. For example, if the user is tired, the analysis unit can use the generation AI to tolerate input errors and perform flexible analysis. If the user is healthy, the analysis unit can also use the generation AI to perform a detailed analysis and improve accuracy. Furthermore, if the user is ill, the analysis unit can use the generation AI to perform a quick analysis and provide immediate feedback. This allows for more appropriate analysis by adjusting the accuracy of input analysis according to the user's health condition.

[0052] The analysis unit can analyze the user's past input history and take the user's learning style into consideration when selecting an analysis method. For example, if the user is a visual learner, it can use a generation AI to provide visual feedback. If the user is an auditory learner, it can also use a generation AI to provide audio feedback. Furthermore, if the user is an experiential learner, it can also use a generation AI to provide interactive feedback. This improves the accuracy of analysis by selecting an analysis method according to the user's learning style.

[0053] When analyzing input, the analysis unit can filter the input based on the user's current activity level. For example, if the user is exercising, the generation AI can be used to remove noise and analyze the input. If the user is resting, the generation AI can be used to perform a detailed analysis to improve accuracy. Furthermore, if the user is working, the generation AI can be used to perform a quick analysis and provide immediate feedback. This improves the accuracy of the analysis by filtering according to the user's current activity level.

[0054] During input analysis, the analysis unit can take the user's cultural background into consideration when prioritizing analysis of highly relevant information based on the user's geographical location information. For example, if the user belongs to a specific cultural sphere, the generation AI can be used to prioritize analysis of information related to that culture. Also, if the user has a multicultural background, the generation AI can be used to prioritize analysis of multicultural information. Furthermore, if the user is interested in different cultures, the generation AI can be used to prioritize analysis of information related to different cultures. This improves the accuracy of analysis by prioritizing analysis of highly relevant information based on the user's cultural background.

[0055] When analyzing input, the analysis unit can analyze the user's social media activity and take into account the influence of the user's social network when analyzing related information. For example, if the user has influential followers, the generation AI can be used to prioritize analysis of information related to those followers. Also, if the user belongs to a specific community, the generation AI can be used to prioritize analysis of information related to that community. Furthermore, if the user is active on social media, the generation AI can be used to prioritize analysis of information related to that activity. This allows related information to be appropriately analyzed based on the influence of the user's social network.

[0056] When understanding context and intent, the understanding unit can take the user's learning history into consideration when adjusting the understanding algorithm by referring to past understanding data. For example, the generation AI can be used to select the optimal algorithm based on what the user has learned in the past. The generation AI can also be used to improve understanding accuracy based on patterns the user has learned in the past. Furthermore, the generation AI can be used to optimize the method of understanding context and intent based on data the user has learned in the past. In this way, by referring to the user's learning history, the understanding algorithm can be optimized and understanding accuracy improved.

[0057] The understanding unit can take the user's psychological state into account when understanding context and intent, improving the accuracy of understanding based on the user's current situation or environment. For example, if the user is nervous, the generation AI can be used to provide a concise context understanding. Alternatively, if the user is relaxed, the generation AI can be used to provide a detailed context understanding. Furthermore, if the user is focused, the generation AI can be used to provide a quick context understanding. This allows for more appropriate understanding by improving the accuracy of understanding based on the user's psychological state.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The analysis unit analyzes the user's input. User input includes text input, voice input, gesture input, etc. The analysis unit analyzes these inputs using text analysis technology, voice analysis technology, and image analysis technology. For example, the analysis unit analyzes text input using natural language processing technology, converts voice input into text using voice recognition software, and analyzes the text. Furthermore, the analysis unit recognizes gestures using a camera and analyzes the gestures. Step 2: The understanding unit understands the context and intent based on the input analyzed by the analysis unit. The understanding unit uses machine learning algorithms and natural language processing technology to understand the context and intent. It can also understand the context and intent by referring to past data. For example, it uses machine learning algorithms to learn the patterns of the user's input and understands the context and intent based on those patterns. Step 3: The generator generates information based on the context and intent understood by the understander. The generator generates information using text generation technology, speech generation technology, and image generation technology. For example, natural language generation technology is used to generate text information, and speech synthesis software is used to convert the text information into speech. Furthermore, image editing software is used to generate visual information. Step 4: The providing unit provides the information generated by the generating unit through the bone conduction earphone. The providing unit transmits audio information to the user using bone conduction technology. The providing unit can also display visual information on a display or provide information using haptic feedback. For example, audio information is transmitted through the user's bones using bone conduction technology, visual information is displayed on a display, and haptic feedback is provided using a vibration motor.

[0060] (Example 2) A system according to an embodiment of the present invention is a novel device that combines a generation AI and bone conduction earphones. This device allows people with hearing impairments to easily obtain information in multiple languages. Specifically, a user wears bone conduction earphones, and a generation AI analyzes the user's input, generates information in an appropriate language, and provides it to the user through the bone conduction earphones. This system can facilitate multilingual communication and improve access to information for people with hearing impairments. For example, a user inputs information, and a generation AI analyzes the input. Next, the generation AI understands the context and intent and generates information in the appropriate language. Finally, the generated information is provided to the user through the bone conduction earphones. In this way, the system can enable people with hearing impairments to easily obtain information in multiple languages.

[0061] The system according to the embodiment includes an analysis unit, an understanding unit, a generation unit, and a provision unit. The analysis unit analyzes a user's input. The user's input includes, but is not limited to, text input, voice input, and gesture input. The analysis unit analyzes the user's input using, for example, text analysis technology. The analysis unit can also analyze voice input using voice analysis technology. The analysis unit can also analyze gesture input using image analysis technology. For example, the analysis unit analyzes text input and understands the user's intention using natural language processing technology. Voice analysis technology converts voice input into text using voice recognition software and analyzes the text. Image analysis technology recognizes gestures using a camera and analyzes the gestures. The understanding unit understands the context and intention based on the input analyzed by the analysis unit. The understanding unit understands the context and intention using, for example, a machine learning algorithm. The understanding unit can also understand the context and intention using natural language processing technology. The understanding unit can also understand the context and intention by referring to past data. For example, the understanding unit uses a machine learning algorithm to learn patterns of a user's input and understands the context and intent based on those patterns. Natural language processing technology analyzes text data and extracts the context and intent. The past data includes the user's past input history and dialogue logs. The generation unit generates information based on the context and intent understood by the understanding unit. The generation unit generates information using, for example, text generation technology. The generation unit can also generate audio information using voice generation technology. The generation unit can also generate visual information using image generation technology. For example, the generation unit generates text information using natural language generation technology. The voice generation technology converts text information into audio using voice synthesis software. The image generation technology generates visual information using image editing software. The provision unit provides the information generated by the generation unit through bone conduction earphones. The provision unit transmits audio information to the user using, for example, bone conduction technology. The provision unit can also display visual information on a display. The provision unit can also provide information using haptic feedback.For example, the providing unit transmits audio information through the user's bones using bone conduction technology. Visual information is displayed on a display, allowing the user to visually confirm the information. Haptic feedback is provided to the user using a vibration motor. This allows the system according to the embodiment to analyze the user's input, understand the context and intent, generate information in an appropriate language, and provide it through the bone conduction earphones.

[0062] The analysis unit can estimate the user's emotions and adjust the accuracy of input analysis based on the estimated user emotions. For example, if the user is nervous, the analysis unit can use the generation AI to tolerate input errors and perform flexible analysis. Furthermore, if the user is relaxed, the analysis unit can use the generation AI to perform detailed analysis and improve accuracy. Furthermore, if the user is in a hurry, the analysis unit can use the generation AI to perform quick analysis and provide immediate feedback. This enables more appropriate analysis by adjusting the accuracy of input analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the analysis accuracy based on the emotion.

[0063] The analysis unit can analyze the user's past input history and select an analysis method. For example, the analysis unit records words and phrases frequently used by the user in the past and reflects them in the analysis using the generation AI. The analysis unit can also extract specific patterns from the user's past input history and optimize the analysis method using the generation AI. The analysis unit can also allow the generation AI to select an appropriate analysis algorithm based on the content the user has previously input. This improves the accuracy of the analysis by selecting the optimal analysis method based on the user's past input history. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's past input history data into the generation AI and have the generation AI select the analysis method.

[0064] When analyzing the input, the analysis unit can perform filtering based on the user's current situation or environment. For example, if the user is in a noisy environment, the analysis unit can use the generation AI to remove noise and perform input analysis. Furthermore, if the user is in a quiet environment, the analysis unit can also perform a detailed analysis using the generation AI to improve accuracy. Furthermore, if the user is on the move, the analysis unit can also use the generation AI to analyze the input in real time and provide appropriate feedback. This improves the accuracy of the analysis by filtering according to the user's current situation and environment. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's current situation and environmental data into the generation AI and have the generation AI perform filtering.

[0065] The analysis unit can estimate the user's emotions and determine the priority of inputs to be analyzed based on the estimated user emotions. For example, when the user is stressed, the analysis unit uses the generation AI to prioritize analyzing important inputs. Furthermore, when the user is relaxed, the analysis unit can also use the generation AI to analyze all inputs equally. Furthermore, when the user is in a hurry, the analysis unit can also use the generation AI to prioritize analyzing inputs that are immediately required. This allows important inputs to be analyzed preferentially by determining the priority of inputs according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of the inputs.

[0066] During input analysis, the analysis unit can prioritize analysis of highly relevant information based on the user's geographical location information. For example, when the user is in a specific area, the analysis unit uses the generation AI to prioritize analysis of information related to that area. Furthermore, when the user is traveling, the analysis unit can also use the generation AI to prioritize analysis of information related to the travel destination. Furthermore, when the user is at home, the analysis unit can also use the generation AI to prioritize analysis of information related to daily life. This prioritizes analysis of highly relevant information based on the user's geographical location information, thereby improving the accuracy of the analysis. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's geographical location information data to the generation AI and have the generation AI analyze highly relevant information.

[0067] The analysis unit can analyze the user's social media activities and analyze related information when analyzing the input. For example, the analysis unit can analyze information shared by the user on social media using a generation AI and provide related information. The analysis unit can also analyze information about accounts the user follows on social media using a generation AI. The analysis unit can also analyze the user's social media activity history using a generation AI and provide related information. This allows the related information to be appropriately analyzed by analyzing the user's social media activities. Some or all of the above-described processing in the analysis unit can be performed using an AI, for example, or without an AI. For example, the analysis unit can input the user's social media activity data into the generation AI and have the generation AI analyze the related information.

[0068] The understanding unit can estimate the user's emotions and adjust how the context and intent are understood based on the estimated user emotions. For example, if the user is nervous, the understanding unit can use the generation AI to perform concise context understanding. Furthermore, if the user is relaxed, the understanding unit can also use the generation AI to perform detailed context understanding. Furthermore, if the user is in a hurry, the understanding unit can use the generation AI to quickly understand the context and provide immediate feedback. This enables more appropriate understanding by adjusting how the context and intent are understood according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, 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 understanding unit can be performed using, for example, an AI, or without an AI. For example, the understanding unit can input the user's emotion data into the generation AI and have the generation AI adjust how the context and intent are understood.

[0069] The understanding unit can adjust the understanding algorithm by referring to past understanding data when understanding context and intent. The understanding unit, for example, uses a generation AI to analyze past understanding data and select an optimal algorithm. The understanding unit can also use the generation AI to extract patterns from past understanding data and improve understanding accuracy. The understanding unit can also use the generation AI to optimize the method of understanding context and intent based on past understanding data. By referring to past understanding data, the understanding algorithm is optimized and understanding accuracy is improved. Some or all of the above-mentioned processing in the understanding unit may be performed, for example, using AI or without AI. For example, the understanding unit can input past understanding data into the generation AI and have the generation AI adjust the understanding algorithm.

[0070] The understanding unit can improve the accuracy of understanding based on the user's current situation or environment when understanding context and intent. The understanding unit, for example, uses a generation AI to acquire information about the user's current environment and reflect this in context understanding. The understanding unit can also use the generation AI to consider the user's current situation and select an appropriate understanding method. The understanding unit can also use the generation AI to improve the accuracy of understanding based on the user's current environment. This enables more appropriate understanding by improving the accuracy of understanding based on the user's current situation and environment. Some or all of the above-mentioned processing in the understanding unit may be performed, for example, using AI or without AI. For example, the understanding unit can input data about the user's current situation and environment into the generation AI and have the generation AI improve the accuracy of understanding.

[0071] The understanding unit can estimate the user's emotions and determine the priority of contexts and intentions to be understood based on the estimated user emotions. For example, when the user is stressed, the understanding unit uses the generation AI to prioritize understanding important contexts and intentions. Furthermore, when the user is relaxed, the understanding unit can also use the generation AI to understand all contexts and intentions equally. Furthermore, when the user is in a hurry, the understanding unit can also use the generation AI to prioritize understanding contexts and intentions that are immediately necessary. Thus, by determining the priority of contexts and intentions according to the user's emotions, important contexts and intentions 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, 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 understanding unit may be performed using, for example, an AI. For example, the understanding unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of contexts and intentions.

[0072] When understanding context and intent, the understanding unit can prioritize understanding of highly relevant information based on the user's geographical location information. For example, when the user is in a specific area, the understanding unit uses the generation AI to prioritize understanding of information related to that area. Furthermore, when the user is traveling, the understanding unit can also use the generation AI to prioritize understanding of information related to the travel destination. Furthermore, when the user is at home, the understanding unit can also use the generation AI to prioritize understanding of information related to daily life. This improves the accuracy of understanding by prioritizing understanding of highly relevant information based on the user's geographical location information. Some or all of the above-described processing in the understanding unit may be performed, for example, using AI or without AI. For example, the understanding unit can input the user's geographical location information data into the generation AI and cause the generation AI to understand highly relevant information.

[0073] The understanding unit can analyze the user's social media activities and understand related information when understanding the context and intent. For example, the understanding unit can analyze information shared by the user on social media using a generation AI to understand the related information. The understanding unit can also use a generation AI to understand information about accounts the user follows on social media. The understanding unit can also analyze the user's social media activity history using a generation AI to understand related information. This allows the related information to be appropriately understood by analyzing the user's social media activities. Some or all of the above-described processing in the understanding unit can be performed using, for example, AI, or without AI. For example, the understanding unit can input the user's social media activity data into the generation AI and have the generation AI understand the related information.

[0074] The generation unit can estimate the user's emotions and adjust the expression method for generating information based on the estimated user emotions. For example, if the user is nervous, the generation unit can use the generation AI to select a concise and easy-to-understand expression method. Furthermore, if the user is relaxed, the generation unit can also use the generation AI to select an expression method that includes detailed information. Furthermore, if the user is in a hurry, the generation unit can also use the generation AI to quickly generate information and provide immediate feedback. This allows for more appropriate information to be generated by adjusting the expression method for generating information according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, 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 generation unit can be performed using, for example, an AI, or without an AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the expression method for generating information.

[0075] When generating information, the generation unit can adjust the level of detail of the generated information based on the importance of the information to be generated. The generation unit, for example, uses a generation AI to generate important information in detail. The generation unit can also use the generation AI to generate general information in a concise manner. The generation unit can also use the generation AI to adjust the level of detail of the information in accordance with a user request. In this way, appropriate information is generated by adjusting the level of detail based on the importance of the information to be generated. Some or all of the above-described processing in the generation unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the generation unit can input importance data of the information to be generated to the generation AI and have the generation AI adjust the level of detail.

[0076] When generating information, the generation unit can apply different generation algorithms depending on the category of the information to be generated. For example, the generation unit can apply a specialized algorithm when generating technical information using the generation AI. The generation unit can also apply a creative algorithm when generating entertainment information using the generation AI. The generation unit can also apply a rapid algorithm when generating news information using the generation AI. This improves the accuracy of information generation by applying an appropriate generation algorithm depending on the category of the information to be generated. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the generation unit can input category data of the information to be generated to the generation AI and cause the generation AI to apply the generation algorithm.

[0077] The generation unit can estimate the user's emotions and adjust the length of the information to be generated based on the estimated user emotions. For example, if the user is in a hurry, the generation unit can use the generation AI to generate short, to-the-point information. Furthermore, if the user is relaxed, the generation unit can use the generation AI to generate longer information with detailed explanations. Furthermore, if the user is excited, the generation unit can use the generation AI to generate information with visually stimulating effects. By adjusting the length of the information according to the user's emotions, more appropriate information can be generated. The 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 such examples. Some or all of the above-described processing in the generation unit can be performed using, for example, an AI, or without an AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the length of the information.

[0078] When generating information, the generation unit can determine the priority of generation based on the submission time of the information to be generated. The generation unit, for example, uses a generation AI to generate urgent information as a priority. The generation unit can also use a generation AI to generate regular information at a later date. The generation unit can also use a generation AI to adjust the order of information generation in accordance with a user request. In this way, by determining the priority based on the submission time of the information to be generated, information is generated at the appropriate time. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the generation unit can input information submission time data into the generation AI and have the generation AI determine the priority.

[0079] When generating information, the generation unit can adjust the order of generation based on the relevance of the information to be generated. For example, the generation unit uses a generation AI to prioritize the generation of highly relevant information. The generation unit can also use the generation AI to postpone the generation of less relevant information. The generation unit can also use the generation AI to adjust the order of generation of information in accordance with a user request. In this way, by adjusting the order based on the relevance of the information to be generated, information is generated in an appropriate order. Some or all of the above-described processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input relevance data of information to the generation AI and cause the generation AI to adjust the generation order.

[0080] The providing unit can estimate the user's emotions and adjust the information provision method based on the estimated user emotions. For example, if the user is nervous, the providing unit can use the generation AI to provide information in a concise and easy-to-understand manner. Furthermore, if the user is relaxed, the providing unit can also use the generation AI to provide information in a manner including detailed information. Furthermore, if the user is in a hurry, the providing unit can also use the generation AI to quickly provide information and provide immediate feedback. This enables more appropriate information provision by adjusting the information provision method according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, 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, an AI, or without an AI. For example, the providing unit can input the user's emotion data into the generation AI and have the generation AI adjust the information provision method.

[0081] When providing information, the providing unit can select a delivery method by referring to the user's past information reception history. The providing unit, for example, uses a generation AI to analyze the information format that the user has preferred in the past and selects the optimal delivery method. The providing unit can also use the generation AI to select the most effective delivery method from the user's past information reception history. The providing unit can also use the generation AI to optimize the timing of information provision based on the user's past information reception history. This improves the accuracy of information provision by selecting the optimal delivery method based on the user's past information reception history. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input past information reception history data into the generation AI and have the generation AI select the delivery method.

[0082] When providing information, the providing unit can improve the accuracy of the information provided based on the user's current situation or environment. The providing unit, for example, uses a generation AI to acquire information about the user's current environment and reflects the information provided. The providing unit can also use the generation AI to consider the user's current situation and select an appropriate information provision method. The providing unit can also use the generation AI to improve the accuracy of the information provided based on the user's current environment. This enables more appropriate information to be provided by improving the accuracy of the information provided based on the user's current situation or environment. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input data about the user's current situation or environment into the generation AI and cause the generation AI to improve the accuracy of the information provided.

[0083] The providing unit can estimate the user's emotions and determine the priority of information to be provided based on the estimated user emotions. For example, when the user is feeling stressed, the providing unit can use the generation AI to provide important information preferentially. Furthermore, when the user is relaxed, the providing unit can also use the generation AI to provide all information equally. Furthermore, when the user is in a hurry, the providing unit can also use the generation AI to provide information that is immediately needed preferentially. This allows important information to be provided preferentially by determining the priority of information according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, 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, an AI, or without an AI. For example, the providing unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of information.

[0084] When providing information, the providing unit can prioritize providing highly relevant information based on the user's geographical location information. For example, when the user is in a specific area, the providing unit can use the generation AI to prioritize providing information related to that area. Furthermore, when the user is traveling, the providing unit can also use the generation AI to prioritize providing information related to the travel destination. Furthermore, when the user is at home, the providing unit can also use the generation AI to prioritize providing information related to daily life. This improves the accuracy of information provision by prioritizing highly relevant information based on the user's geographical location information. Some or all of the above-described processing in the providing unit can be performed, for example, using AI or without AI. For example, the providing unit can input the user's geographical location information data to the generation AI and cause the generation AI to provide highly relevant information.

[0085] When providing information, the providing unit can analyze the user's social media activities and provide related information. For example, the providing unit can analyze information shared by the user on social media using a generation AI and provide the related information. The providing unit can also use the generation AI to provide information on accounts the user follows on social media. The providing unit can also analyze the user's social media activity history using a generation AI and provide the related information. In this way, by analyzing the user's social media activities, the related information can be appropriately provided. Some or all of the above-described processing in the providing unit may be performed using an AI, for example, or may be performed without using an AI. For example, the providing unit can input the user's social media activity data into the generation AI and cause the generation AI to provide the related information.

[0086] The bone conduction unit can estimate the user's emotions and adjust the method of voice transmission based on the estimated user's emotions. For example, if the user is nervous, the bone conduction unit can use the generation AI to transmit information in a calm voice. Furthermore, if the user is relaxed, the bone conduction unit can also use the generation AI to transmit information in a cheerful voice. Furthermore, if the user is in a hurry, the bone conduction unit can also use the generation AI to transmit information in a quick and concise voice. This allows for more appropriate voice transmission by adjusting the voice transmission method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the bone conduction unit may be performed using AI, or without AI. For example, the bone conduction unit can input the user's emotion data into the generation AI and have the generation AI adjust the voice transmission method.

[0087] When transmitting voice, the bone conduction unit can select a transmission method by referring to the user's past voice reception history. For example, the bone conduction unit uses a generation AI to analyze the user's preferred voice reception format in the past and select the optimal transmission method. The bone conduction unit can also use the generation AI to select the most effective transmission method from the user's past voice reception history. The bone conduction unit can also use the generation AI to optimize the timing of voice transmission based on the user's past voice reception history. This improves the accuracy of voice transmission by selecting the optimal transmission method based on the user's past voice reception history. Some or all of the above-described processing in the bone conduction unit may be performed using, for example, AI, or may be performed without using AI. For example, the bone conduction unit can input past voice reception history data into the generation AI and have the generation AI select the transmission method.

[0088] The bone conduction unit can improve the accuracy of voice transmission based on the user's current situation or environment. For example, the bone conduction unit acquires information about the user's current environment using a generation AI and reflects this information in the voice transmission. The bone conduction unit can also use the generation AI to select an appropriate transmission method taking the user's current situation into consideration. The bone conduction unit can also use the generation AI to improve the transmission accuracy based on the user's current environment. This enables more appropriate voice transmission by improving the transmission accuracy based on the user's current situation and environment. Some or all of the above-described processing in the bone conduction unit may be performed using, for example, AI, or may be performed without using AI. For example, the bone conduction unit can input data about the user's current situation and environment into the generation AI and have the generation AI improve the transmission accuracy.

[0089] The bone conduction unit can estimate the user's emotions and determine the priority of the audio to be transmitted based on the estimated user's emotions. For example, when the user is stressed, the bone conduction unit uses a generation AI to prioritize important audio. Furthermore, when the user is relaxed, the bone conduction unit can also use a generation AI to transmit all audio evenly. Furthermore, when the user is in a hurry, the bone conduction unit can also use a generation AI to prioritize audio that is immediately needed. This allows important audio to be transmitted preferentially by determining audio priorities 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 bone conduction unit may be performed using, for example, an AI, or without an AI. For example, the bone conduction unit can input the user's emotion data into the generation AI and have the generation AI determine the audio priorities.

[0090] When transmitting voice, the bone conduction unit can prioritize relevant voice based on the user's geographical location information. For example, when the user is in a specific area, the bone conduction unit uses a generation AI to prioritize voice related to that area. Furthermore, when the user is traveling, the bone conduction unit can also use a generation AI to prioritize voice related to the user's travel destination. Furthermore, when the user is at home, the bone conduction unit can also use a generation AI to prioritize voice related to daily life. This prioritizes the transmission of relevant voice based on the user's geographical location information, thereby improving the accuracy of voice transmission. Some or all of the above-described processing in the bone conduction unit may be performed using AI, for example, or without AI. For example, the bone conduction unit can input the user's geographical location information data into the generation AI and have the generation AI transmit relevant voice.

[0091] The bone conduction unit can analyze the user's social media activities and transmit related audio when transmitting audio. For example, the bone conduction unit can analyze information shared by the user on social media using a generation AI and transmit related audio. The bone conduction unit can also transmit information about accounts the user follows on social media using a generation AI. The bone conduction unit can also analyze the user's social media activity history using a generation AI and transmit related audio. This allows for appropriate transmission of related audio by analyzing the user's social media activities. Some or all of the above-described processing in the bone conduction unit can be performed using, for example, AI, or without AI. For example, the bone conduction unit can input the user's social media activity data into a generation AI and have the generation AI transmit related audio. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, understanding unit, generation unit, and provision unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14 and analyzes a user's input. The understanding unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and understands the context and intention based on the analyzed input. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates information based on the understood context and intention. The provision unit is realized, for example, by the control unit 46A of the smart device 14 and provides the generated information to the user via bone conduction earphones. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, understanding unit, generation unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 and analyzes a user's input. The understanding unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and understands a context and intention based on the analyzed input. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates information based on the understood context and intention. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214 and provides the generated information to the user through bone conduction earphones. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, understanding unit, generation 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 analysis unit is realized by the processor 46 of the headset type terminal 314 and analyzes a user's input. The understanding unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and understands the context and intention based on the analyzed input. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates information based on the understood context and intention. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314 and provides the generated information to the user via bone conduction earphones. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, understanding unit, generation unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 and analyzes the user's input. The understanding unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and understands the context and intention based on the analyzed input. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates information based on the understood context and intention. The provision unit is realized, for example, by the control unit 46A of the robot 414 and provides the generated information to the user via bone conduction earphones.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The analysis unit can take the user's health condition data into account when analyzing the user's input. For example, if the user is tired, the analysis unit can use the generation AI to tolerate input errors and perform flexible analysis. If the user is healthy, the analysis unit can also use the generation AI to perform a detailed analysis and improve accuracy. Furthermore, if the user is ill, the analysis unit can use the generation AI to perform a quick analysis and provide immediate feedback. This allows for more appropriate analysis by adjusting the accuracy of input analysis according to the user's health condition.

[0094] The analysis unit can estimate the user's emotions and adjust the feedback method for the analyzed input based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI can be used to provide feedback in a gentle tone. If the user is relaxed, the generation AI can be used to provide detailed feedback. Furthermore, if the user is in a hurry, the generation AI can be used to provide quick feedback. This allows for more appropriate feedback by adjusting the feedback method according to the user's emotions.

[0095] The analysis unit can analyze the user's past input history and take the user's learning style into consideration when selecting an analysis method. For example, if the user is a visual learner, it can use a generation AI to provide visual feedback. If the user is an auditory learner, it can also use a generation AI to provide audio feedback. Furthermore, if the user is an experiential learner, it can also use a generation AI to provide interactive feedback. This improves the accuracy of analysis by selecting an analysis method according to the user's learning style.

[0096] When analyzing input, the analysis unit can filter the input based on the user's current activity level. For example, if the user is exercising, the generation AI can be used to remove noise and analyze the input. If the user is resting, the generation AI can be used to perform a detailed analysis to improve accuracy. Furthermore, if the user is working, the generation AI can be used to perform a quick analysis and provide immediate feedback. This improves the accuracy of the analysis by filtering according to the user's current activity level.

[0097] The analysis unit can estimate the user's emotions and adjust the format of the input to be analyzed based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI can be used to provide a concise input format. Alternatively, if the user is relaxed, the generation AI can be used to provide a detailed input format. Furthermore, if the user is in a hurry, the generation AI can be used to provide a quick input format. This allows for more appropriate analysis by adjusting the input format according to the user's emotions.

[0098] During input analysis, the analysis unit can take the user's cultural background into consideration when prioritizing analysis of highly relevant information based on the user's geographical location information. For example, if the user belongs to a specific cultural sphere, the generation AI can be used to prioritize analysis of information related to that culture. Also, if the user has a multicultural background, the generation AI can be used to prioritize analysis of multicultural information. Furthermore, if the user is interested in different cultures, the generation AI can be used to prioritize analysis of information related to different cultures. This improves the accuracy of analysis by prioritizing analysis of highly relevant information based on the user's cultural background.

[0099] When analyzing input, the analysis unit can analyze the user's social media activity and take into account the influence of the user's social network when analyzing related information. For example, if the user has influential followers, the generation AI can be used to prioritize analysis of information related to those followers. Also, if the user belongs to a specific community, the generation AI can be used to prioritize analysis of information related to that community. Furthermore, if the user is active on social media, the generation AI can be used to prioritize analysis of information related to that activity. This allows related information to be appropriately analyzed based on the influence of the user's social network.

[0100] The understanding unit can take the user's communication style into consideration when estimating the user's emotions and adjusting how the context and intent are understood based on the estimated user emotions. For example, if the user has a direct communication style, the generative AI can be used to perform a concise context understanding. Alternatively, if the user has an indirect communication style, the generative AI can be used to perform a detailed context understanding. Furthermore, if the user has a non-verbal communication style, the generative AI can be used to perform non-verbal context understanding. This allows for more appropriate understanding by adjusting how the context and intent are understood according to the user's communication style.

[0101] When understanding context and intent, the understanding unit can take the user's learning history into consideration when adjusting the understanding algorithm by referring to past understanding data. For example, the generation AI can be used to select the optimal algorithm based on what the user has learned in the past. The generation AI can also be used to improve understanding accuracy based on patterns the user has learned in the past. Furthermore, the generation AI can be used to optimize the method of understanding context and intent based on data the user has learned in the past. In this way, by referring to the user's learning history, the understanding algorithm can be optimized and understanding accuracy improved.

[0102] The understanding unit can take the user's psychological state into account when understanding context and intent, improving the accuracy of understanding based on the user's current situation or environment. For example, if the user is nervous, the generation AI can be used to provide a concise context understanding. Alternatively, if the user is relaxed, the generation AI can be used to provide a detailed context understanding. Furthermore, if the user is focused, the generation AI can be used to provide a quick context understanding. This allows for more appropriate understanding by improving the accuracy of understanding based on the user's psychological state.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The analysis unit analyzes the user's input. User input includes text input, voice input, gesture input, etc. The analysis unit analyzes these inputs using text analysis technology, voice analysis technology, and image analysis technology. For example, the analysis unit analyzes text input using natural language processing technology, converts voice input into text using voice recognition software, and analyzes the text. Furthermore, the analysis unit recognizes gestures using a camera and analyzes the gestures. Step 2: The understanding unit understands the context and intent based on the input analyzed by the analysis unit. The understanding unit uses machine learning algorithms and natural language processing technology to understand the context and intent. It can also understand the context and intent by referring to past data. For example, it uses machine learning algorithms to learn the patterns of the user's input and understands the context and intent based on those patterns. Step 3: The generator generates information based on the context and intent understood by the understander. The generator generates information using text generation technology, speech generation technology, and image generation technology. For example, natural language generation technology is used to generate text information, and speech synthesis software is used to convert the text information into speech. Furthermore, image editing software is used to generate visual information. Step 4: The providing unit provides the information generated by the generating unit through the bone conduction earphone. The providing unit transmits audio information to the user using bone conduction technology. The providing unit can also display visual information on a display or provide information using haptic feedback. For example, audio information is transmitted through the user's bones using bone conduction technology, visual information is displayed on a display, and haptic feedback is provided using a vibration motor.

[0105] 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.

[0106] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0107] 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.

[0108] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0109] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0110] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0123] 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.

[0124] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0125] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0139] 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.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0156] 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.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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."

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] [Explanation of symbols]

[0177] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes user input; an understanding unit that understands a context and intent based on the input analyzed by the analysis unit; a generation unit that generates information based on the context and intention understood by the understanding unit; a providing unit that provides the information generated by the generating unit through a bone conduction earphone; Equipped with A system characterized by:

2. The analysis unit Estimate the user's emotions and adjust the accuracy of input analysis based on the estimated user emotions.

2. The system of claim 1.

3. The analysis unit Analyze the user's past input history and select an analysis method 2. The system of claim 1.

4. The analysis unit When parsing input, filtering is performed based on the user's current situation or environment.

2. The system of claim 1.

5. The analysis unit Estimate the user's emotions and prioritize inputs to be analyzed based on the estimated user emotions.

2. The system of claim 1.

6. The analysis unit When analyzing input, prioritize relevant information based on the user's geographic location.

2. The system of claim 1.

7. The analysis unit When analyzing input, analyze the user's social media activity and analyze related information.

2. The system of claim 1.

8. The understanding unit Inferring user sentiment and adjusting context and intent understanding based on the inferred sentiment 2. The system of claim 1.

Images