System

Abstract

An object of the system according to the embodiment is to efficiently convert a speech of a user into a text, generate an appropriate response based on the text, and cooperate with an external service.SOLUTION: A system according to an embodiment includes a speech recognition unit, a response generation unit, and a coordination unit. The speech recognition unit converts the speech of the user into text by a speech recognition technique. The response generation unit generates a response based on the text converted by the speech recognition unit. The cooperation unit cooperates with the external service based on the response generated by the response generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of not being able to efficiently convert user utterances into text, generate appropriate responses based on that text, and integrate with external services.

[0005] The system according to the embodiment aims to efficiently convert user utterances into text, generate appropriate responses based on the text, and cooperate with external services. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech recognition unit, a response generation unit, and a linking unit. The speech recognition unit converts a user's utterance into text using speech recognition technology. The response generation unit generates a response based on the text converted by the speech recognition unit. The linking unit links with an external service based on the response generated by the response generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently convert user utterances into text, generate appropriate responses based on the text, and link with external services. [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 care system according to an embodiment of the present invention provides mental and physical care for people busy with childcare, work, and housework. The care system provides support through conversations with characters selected by the user. Specifically, the system utilizes natural language processing and speech recognition technology by a generative AI to understand the user's utterances and generate appropriate responses. The system also connects with various external services via an API to provide support tailored to the user's needs. For example, if a user says, "I'm tired today," the generative AI generates a response such as, "Thank you for your hard work. What happened today?" Furthermore, the care system connects with services that play relaxing music and provide weather information to provide users with a relaxing environment and the latest weather information. This allows people busy with childcare, work, and housework to care for their mind and body without putting themselves off. For example, the care system allows users to feel comforted and encouraged by conversations with their favorite characters. Furthermore, by connecting with various external services, users can receive support tailored to their needs. This will enable us to aim for a society in which women can play more active and vibrant roles.

[0029] The care system according to the embodiment includes a speech recognition unit, a response generation unit, and a linking unit. The speech recognition unit converts a user's speech into text using speech recognition technology. Examples of speech recognition technology include, but are not limited to, deep learning-based speech recognition and HMM (Hidden Markov Model). For example, the speech recognition unit converts the user's speech into text in real time. The speech recognition unit can also improve the accuracy of speech recognition by removing background noise using noise reduction technology. The response generation unit uses a generation AI to generate a response based on the text converted by the speech recognition unit. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's speech and generates an appropriate response. For example, if the user says, "I'm tired today," the response generation unit generates a response such as, "Thank you for your hard work. What happened today?" The response generation unit can also analyze the user's emotions and generate a response according to the emotions. The linking unit links with an external service based on the response generated by the response generation unit. Examples of external services include, but are not limited to, a service that plays relaxing music and a service that provides weather information. For example, when a user says, "I want to relax," the linking unit links with a service that plays relaxing music to provide the user with a relaxing environment. Also, when a user asks, "What's the weather like today?" the linking unit links with a service that provides weather information to provide the latest weather information. As a result, the care system according to the embodiment can recognize the user's speech, generate an appropriate response, and link with external services to provide support according to the user's needs.

[0030] The link unit includes a music playback unit that plays relaxing music. The music playback unit plays relaxing music. Examples of relaxing music include, but are not limited to, classical music, nature sounds, and healing music. For example, the music playback unit plays classical music when the user feels like relaxing. The music playback unit can also play nature sounds when the user is feeling stressed. Furthermore, the music playback unit can play healing music when the user wants to concentrate. In this way, the music playback unit can support the user's relaxation by playing relaxing music. Some or all of the above-described processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input user emotion data into a generation AI, which can select and play optimal music based on the user's emotions.

[0031] The linking unit includes a weather information providing unit that provides weather information. The weather information providing unit provides the latest weather information. Weather information includes, but is not limited to, temperature, probability of precipitation, and wind speed. For example, when a user asks, "What's the weather like today?", the weather information providing unit provides the latest temperature and probability of precipitation. Furthermore, when a user asks, "What's the weather like tomorrow?", the weather information providing unit can provide the wind speed and temperature for the next day. Furthermore, when a user asks, "What's the weather like this weekend?", the weather information providing unit can provide a weekend weather forecast. In this way, the weather information providing unit can provide information that meets the user's needs by providing weather information. Some or all of the above-described processing in the weather information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the weather information providing unit can input weather data to a generation AI, which can generate and provide optimal weather information based on the user's needs.

[0032] The voice recognition unit can analyze background sounds of the user's speech and remove noise during voice recognition. For example, if the user is in a noisy place such as a cafe, the voice recognition unit can analyze the background sounds and remove noise. Furthermore, if the user is talking while watching TV at home, the voice recognition unit can also remove the sound of the TV as noise. Furthermore, if the user is out and there is wind noise, the voice recognition unit can also remove the wind noise as noise. This allows for improved voice recognition accuracy by analyzing background sounds and removing noise. Some or all of the above-described processing in the voice recognition unit may be performed using, or without, AI, for example. For example, the voice recognition unit can input the user's voice data to a generation AI, which can then analyze the background sounds and remove noise.

[0033] During speech recognition, the speech recognition unit analyzes the speed and tone of a user's speech to more accurately understand the intent of the speech. For example, if a user speaks at a fast speed, the speech recognition unit analyzes the speed to understand the intent. Furthermore, if a user speaks in a low tone, the speech recognition unit can analyze the tone to understand the intent. Furthermore, if a user speaks in a high tone, the speech recognition unit can analyze the tone to understand the intent. In this way, by analyzing the speech speed and tone, the intent of the speech can be accurately understood. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit inputs the user's speech data to a generation AI, which can analyze the speech speed and tone to understand the intent.

[0034] During speech recognition, the speech recognition unit can improve recognition accuracy by referring to the user's past utterance history. The speech recognition unit can improve recognition accuracy by, for example, referring to phrases frequently used by the user in the past. The speech recognition unit can also improve recognition accuracy by referring to utterances that the user has previously misrecognized. Furthermore, the speech recognition unit can also improve recognition accuracy by referring to utterances that the user has previously spoken with a particular accent. In this way, the accuracy of speech recognition can be improved by referring to the past utterance history. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can input the user's past utterance data into a generation AI, which can then improve recognition accuracy by referring to the past utterance history.

[0035] During speech recognition, the speech recognition unit can recognize regional words and accents by taking into account the user's geographical location information. For example, if the user is in the Kansai region, the speech recognition unit can recognize the Kansai dialect. Also, if the user is in the Tohoku region, the speech recognition unit can recognize the Tohoku dialect. Furthermore, if the user is overseas, the speech recognition unit can recognize the regional words and accents. This allows for accurate recognition of regional words and accents by taking geographical location information into account. Some or all of the above-described processing in the speech recognition unit may be performed using, or without, AI, for example. For example, the speech recognition unit can input the user's geographical location data into a generation AI, which can then recognize regional words and accents.

[0036] During voice recognition, the voice recognition unit can analyze the user's social media activity and prioritize recognition of relevant comments. For example, the voice recognition unit can prioritize recognition of phrases frequently used by the user on social media. The voice recognition unit can also prioritize recognition of topics that the user is talking about on social media. Furthermore, the voice recognition unit can also prioritize recognition of comments made by people the user follows on social media. In this way, by analyzing social media activity, relevant comments can be prioritized. Some or all of the above-described processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice recognition unit can input the user's social media data into a generation AI, which can then prioritize recognition of relevant comments.

[0037] The speech recognition unit can customize the recognition method by reflecting the user's past feedback during speech recognition. The speech recognition unit can improve the accuracy of speech recognition based on, for example, feedback provided by the user in the past. The speech recognition unit can also improve the recognition method by reflecting recognition errors pointed out by the user in the past. Furthermore, the speech recognition unit can also customize based on the recognition method that the user previously preferred. In this way, by reflecting past feedback, the recognition method can be customized and accuracy can be improved. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can input user feedback data to a generation AI, and the generation AI can customize the recognition method based on the feedback.

[0038] When generating a response, the response generation unit can adjust the level of detail of the response based on the importance of the user's utterance. For example, the response generation unit generates a detailed response when the user asks an important question. The response generation unit can also generate a concise response when the user provides a light topic. Furthermore, the response generation unit can also generate a quick and detailed response when the user conveys an urgent requirement. This makes it possible to generate an appropriate response by adjusting the level of detail of the response based on the importance of the utterance. Some or all of the above-mentioned processing in the response generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the response generation unit can input user utterance data into a generation AI, which can adjust the level of detail of the response based on the importance of the utterance.

[0039] When generating a response, the response generation unit can apply different response algorithms depending on the category of the user's utterance. For example, when the user asks a technical question, the response generation unit can apply a specialized response algorithm. Furthermore, when the user provides an emotional topic, the response generation unit can also apply a response algorithm that takes emotions into consideration. Furthermore, when the user provides an everyday topic, the response generation unit can also apply a general response algorithm. In this way, an appropriate response can be generated by applying a response algorithm depending on the category of the utterance. Some or all of the above-mentioned processing in the response generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the response generation unit can input the user's utterance data into a generation AI, which can then apply different response algorithms depending on the category of the utterance.

[0040] When generating a response, the response generation unit can improve the accuracy of the response by referring to the user's past response history. The response generation unit generates a response by referring to, for example, a response style that the user has previously preferred. The response generation unit can also generate a response so as to avoid responses that the user has previously dissatisfied with. Furthermore, the response generation unit can improve the accuracy of the response based on feedback provided by the user in the past. In this way, the accuracy of the response can be improved by referring to the past response history. Some or all of the above-mentioned processing in the response generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the response generation unit can input the user's response history data into the generation AI, and the generation AI can improve the accuracy of the response by referring to the past response history.

[0041] When generating a response, the response generation unit can determine the priority of the response based on the time when the user submitted the utterance. For example, if the user communicates an urgent requirement, the response generation unit generates the response with priority. Also, if the user asks a normal question, the response generation unit can generate a response with normal priority. Furthermore, the response generation unit can adjust the priority based on questions previously submitted by the user. In this way, an appropriate response can be generated by determining the priority of the response based on the time when the utterance was submitted. Some or all of the above-mentioned processing in the response generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the response generation unit can input the user's utterance data into a generation AI, and the generation AI can determine the priority of the response based on the time when the utterance was submitted.

[0042] When generating a response, the response generation unit can adjust the order of responses based on the relevance of the user's utterances. For example, if a user asks related questions consecutively, the response generation unit generates responses in order of increasing relevance. Furthermore, if a user provides different topics, the response generation unit can also generate responses in order of decreasing relevance. Furthermore, if a user provides an important topic, the response generation unit can also generate responses in order of decreasing relevance. In this way, by adjusting the order of responses based on the relevance of the utterances, an appropriate response can be generated. Some or all of the above-described processing in the response generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the response generation unit can input user utterance data to a generation AI, which can adjust the order of responses based on the relevance of the utterances.

[0043] When generating a response, the response generation unit can adjust the use of technical terminology in the response depending on the user's level of expertise. For example, if the user is an expert, the response generation unit generates a response that uses a lot of technical terminology. Furthermore, if the user is a beginner, the response generation unit can also generate a response that avoids technical terminology. Furthermore, if the user is an intermediate user, the response generation unit can generate a response that uses technical terminology appropriately. In this way, an appropriate response can be generated by adjusting the use of technical terminology depending on the level of expertise. Some or all of the above-mentioned processing in the response generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the response generation unit can input the user's expertise data into a generation AI, which can adjust the use of technical terminology in the response depending on the level of expertise.

[0044] At the time of collaboration, the collaboration unit can select the optimal external service by referring to the user's past collaboration history. The collaboration unit selects the optimal external service, for example, based on services the user has used in the past. The collaboration unit can also preferentially select services that the user has been satisfied with in the past. Furthermore, the collaboration unit can also select services that avoid services that the user has been dissatisfied with in the past. In this way, the optimal external service can be selected by referring to the past collaboration history. Some or all of the above-described processing in the collaboration unit may be performed using, for example, AI, or may be performed without using AI. For example, the collaboration unit can input the user's collaboration history data into the generation AI, and the generation AI can select the optimal external service by referring to the past collaboration history.

[0045] The linking unit can customize the linking method based on the user's current needs when linking. For example, if the user wants to relax, the linking unit can link with a service that plays relaxing music. If the user wants information, the linking unit can also link with a news service. Furthermore, if the user wants to exercise, the linking unit can also link with a fitness service. In this way, by customizing the linking method based on the user's current needs, appropriate support can be provided. Some or all of the above-described processing in the linking unit may be performed using, for example, AI, or may be performed without using AI. For example, the linking unit can input the user's needs data into the generation AI, which can then customize the linking method based on the user's current needs.

[0046] The collaboration unit can improve the collaboration method by reflecting user feedback during collaboration. The collaboration unit can improve the collaboration method, for example, based on feedback provided by the user in the past. The collaboration unit can also preferentially adopt collaboration methods that the user is satisfied with. Furthermore, the collaboration unit can also avoid and improve collaboration methods that the user is dissatisfied with. In this way, by reflecting feedback, the collaboration method can be improved and appropriate support can be provided. Some or all of the above-mentioned processing in the collaboration unit can be performed, for example, using AI or without using AI. For example, the collaboration unit can input user feedback data into the generation AI, and the generation AI can improve the collaboration method based on the feedback.

[0047] At the time of linking, the linking unit can select the optimal external service by taking into account the user's geographical location information. For example, when the user is in a specific area, the linking unit links with a service that provides weather information for that area. Furthermore, when the user is traveling, the linking unit can also link with a service that provides tourist spot information. Furthermore, when the user is at home, the linking unit can also link with a service that provides nearby restaurant information. In this way, the optimal external service can be selected by taking into account the geographical location information. Some or all of the above-described processing in the linking unit may be performed using, for example, AI, or may be performed without using AI. For example, the linking unit can input the user's geographical location data into the generation AI, and the generation AI can select the optimal external service by taking into account the geographical location information.

[0048] At the time of linking, the linking unit can analyze the user's social media activity and suggest external services to link with. For example, the linking unit can suggest services related to topics the user is talking about on social media. The linking unit can also suggest services used by people the user follows on social media. Furthermore, the linking unit can also suggest services related to places the user has checked in to on social media. In this way, related external services can be suggested by analyzing social media activity. Some or all of the above-mentioned processing in the linking unit may be performed using, for example, AI, or may be performed without using AI. For example, the linking unit can input the user's social media data into a generation AI, which can analyze the social media activity and suggest external services to link with.

[0049] The collaboration unit can customize the collaboration method by reflecting the user's past feedback during collaboration. The collaboration unit customizes the collaboration method based on, for example, feedback provided by the user in the past. The collaboration unit can also preferentially adopt collaboration methods that the user is satisfied with. Furthermore, the collaboration unit can customize the collaboration method by avoiding collaboration methods that the user is dissatisfied with. In this way, by reflecting past feedback, the collaboration method can be customized and appropriate support can be provided. Some or all of the above-described processing in the collaboration unit may be performed using, for example, AI, or may be performed without using AI. For example, the collaboration unit can input user feedback data into a generation AI, which can customize the collaboration method based on the feedback.

[0050] During emotion analysis, the emotion analysis unit can analyze background sounds of the user's speech and detect changes in emotion. For example, when the user is in a noisy place, the emotion analysis unit can analyze background sounds to detect changes in emotion. The emotion analysis unit can also analyze background sounds to detect changes in emotion when the user is in a quiet place. Furthermore, when the user is listening to music, the emotion analysis unit can analyze background sounds to detect changes in emotion. In this way, changes in emotion can be detected by analyzing background sounds. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the user's voice data to a generation AI, which can then analyze background sounds to detect changes in emotion.

[0051] During emotion analysis, the emotion analysis unit analyzes the speed and tone of the user's speech to more accurately understand the emotional intent. For example, if the user speaks quickly, the emotion analysis unit analyzes the speed to understand the emotional intent. Furthermore, if the user speaks in a low tone, the emotion analysis unit can analyze the tone to understand the emotional intent. Furthermore, if the user speaks in a high tone, the emotion analysis unit can analyze the tone to understand the emotional intent. In this way, by analyzing the speech speed and tone, the emotional intent can be accurately understood. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit inputs the user's voice data into a generation AI, which can analyze the speech speed and tone to understand the emotional intent.

[0052] During emotion analysis, the emotion analysis unit can improve the accuracy of the analysis by referring to the user's past emotion history. The emotion analysis unit can improve the analysis accuracy by, for example, referring to emotions the user has felt in the past. The emotion analysis unit can also improve the analysis accuracy based on feedback the user has provided in the past. Furthermore, the emotion analysis unit can improve the analysis accuracy by referring to events the user has experienced in the past. In this way, the analysis accuracy can be improved by referring to the past emotion history. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the user's emotion history data into the generation AI, and the generation AI can improve the analysis accuracy by referring to the past emotion history.

[0053] During emotion analysis, the emotion analysis unit can analyze region-specific emotional expressions by taking into account the user's geographical location information. For example, if the user is in the Kansai region, the emotion analysis unit analyzes Kansai-specific emotional expressions. Also, if the user is in the Tohoku region, the emotion analysis unit can analyze Tohoku-specific emotional expressions. Furthermore, if the user is overseas, the emotion analysis unit can analyze region-specific emotional expressions. This allows for accurate analysis of region-specific emotional expressions by taking geographical location information into account. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the user's geographical location data into the generation AI, which can then analyze region-specific emotional expressions.

[0054] During emotion analysis, the emotion analysis unit can analyze the user's social media activity and prioritize analysis of related emotions. For example, the emotion analysis unit can prioritize analysis of emotional expressions frequently used by the user on social media. The emotion analysis unit can also prioritize analysis of emotions related to topics the user is talking about on social media. Furthermore, the emotion analysis unit can also prioritize analysis of emotional expressions of people the user follows on social media. In this way, by analyzing social media activity, related emotions can be prioritized. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the user's social media data into a generation AI, which can analyze the social media activity and prioritize analysis of related emotions.

[0055] The emotion analysis unit can customize the analysis method by reflecting the user's past feedback during emotion analysis. The emotion analysis unit customizes the analysis method, for example, based on feedback provided by the user in the past. The emotion analysis unit can also preferentially adopt analysis methods that the user is satisfied with. Furthermore, the emotion analysis unit can also customize the analysis method by avoiding analysis methods that the user is dissatisfied with. In this way, by reflecting past feedback, the analysis method can be customized and accuracy can be improved. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input user feedback data into a generation AI, which can customize the analysis method based on the feedback.

[0056] When playing music, the music playback unit can select optimal music by referring to the user's past music playback history. The music playback unit selects optimal music, for example, based on music that the user liked to listen to in the past. The music playback unit can also select optimal music based on music that the user found relaxing in the past. Furthermore, the music playback unit can also select optimal music based on music that the user found uplifting in the past. In this way, optimal music can be selected by referring to the past music playback history. Some or all of the above-described processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input the user's music playback history data to a generation AI, which can then select optimal music by referring to the past music playback history.

[0057] The music playback unit can customize the playback method based on the user's current mood when playing music. For example, if the user wants to relax, the music playback unit can play relaxing music. Furthermore, if the user wants to cheer up, the music playback unit can play up-tempo music. Furthermore, if the user wants to concentrate, the music playback unit can play music that helps improve concentration. In this way, by customizing the playback method based on the user's current mood, appropriate music can be played. Some or all of the above-described processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input the user's mood data into the generation AI, and the generation AI can customize the playback method based on the user's current mood.

[0058] The music playback unit can improve the playback method by reflecting user feedback when playing music. The music playback unit can improve the playback method, for example, based on feedback provided by the user in the past. The music playback unit can also preferentially adopt playback methods that the user is satisfied with. Furthermore, the music playback unit can also improve by avoiding playback methods that the user is dissatisfied with. In this way, by reflecting feedback, the playback method can be improved and appropriate music can be played. Some or all of the above-mentioned processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input user feedback data into a generation AI, which can then improve the playback method based on the feedback.

[0059] When playing music, the music playback unit can select optimal music by taking into account the user's geographical location information. For example, if the user is in a specific area, the music playback unit selects music for that area. Furthermore, if the user is traveling, the music playback unit can also select music for the travel destination. Furthermore, if the user is at home, the music playback unit can also select relaxing music. In this way, optimal music can be selected by taking into account the geographical location information. Some or all of the above-described processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input the user's geographical location data into a generation AI, which can select optimal music by taking into account the geographical location information.

[0060] When playing music, the music playback unit can analyze the user's social media activity and suggest music to play. For example, the music playback unit can suggest music that the user is talking about on social media. The music playback unit can also suggest music by artists the user follows on social media. Furthermore, the music playback unit can also suggest music related to places the user has checked in to on social media. In this way, related music can be suggested by analyzing social media activity. Some or all of the above-described processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input the user's social media data into a generation AI, which can analyze the social media activity and suggest music to play.

[0061] The music playback unit can customize the playback method by reflecting the user's past feedback when playing music. The music playback unit customizes the playback method based on, for example, feedback provided by the user in the past. The music playback unit can also preferentially adopt playback methods that the user is satisfied with. Furthermore, the music playback unit can also customize the playback method by avoiding playback methods that the user is dissatisfied with. In this way, by reflecting past feedback, the playback method can be customized and appropriate music can be played. Some or all of the above-described processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input user feedback data to a generation AI, which can then customize the playback method based on the feedback.

[0062] When providing weather information, the weather information providing unit can select the optimal providing method by referring to the user's past weather information usage history. The weather information providing unit selects the optimal providing method, for example, based on the user's past preferred providing method. The weather information providing unit can also preferentially select a providing method that the user has been satisfied with in the past. Furthermore, the weather information providing unit can select a providing method that avoids a providing method that the user has been dissatisfied with in the past. In this way, the optimal providing method can be selected by referring to the past weather information usage history. Some or all of the above-mentioned processing in the weather information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the weather information providing unit can input the user's weather information usage history data to a generation AI, which can then select the optimal providing method by referring to the past weather information usage history.

[0063] When providing weather information, the weather information providing unit can customize the provided content based on the user's current needs. For example, if the user plans to go out, the weather information providing unit can provide weather information suitable for going out. Furthermore, if the user plans to travel, the weather information providing unit can also provide weather information for the travel destination. Furthermore, if the user plans to spend time indoors, the weather information providing unit can also provide weather information that will affect the indoor environment. In this way, by customizing the provided content based on the current needs, appropriate information can be provided. Some or all of the above-mentioned processing in the weather information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the weather information providing unit can input the user's needs data into the generation AI, and the generation AI can customize the provided content based on the current needs.

[0064] The weather information providing unit can improve the weather information providing method by reflecting user feedback when providing weather information. The weather information providing unit can improve the weather information providing method, for example, based on feedback provided by the user in the past. The weather information providing unit can also preferentially adopt a providing method that the user is satisfied with. Furthermore, the weather information providing unit can also avoid and improve a providing method that the user is dissatisfied with. In this way, by reflecting feedback, the providing method can be improved and appropriate information can be provided. Some or all of the above-mentioned processing in the weather information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the weather information providing unit can input user feedback data into a generation AI, which can improve the providing method based on the feedback.

[0065] When providing weather information, the weather information providing unit can provide optimal weather information by taking into account the user's geographical location information. For example, if the user is in a specific area, the weather information providing unit can provide weather information for that area. Furthermore, if the user is traveling, the weather information providing unit can also provide weather information for the user's travel destination. Furthermore, if the user is at home, the weather information providing unit can also provide weather information for the user's neighborhood. In this way, optimal weather information can be provided by taking into account the geographical location information. Some or all of the above-described processing in the weather information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the weather information providing unit can input the user's geographical location data into a generation AI, which can then provide optimal weather information by taking into account the geographical location information.

[0066] When providing weather information, the weather information providing unit can analyze the user's social media activity and provide related weather information. The weather information providing unit can provide, for example, weather information for a region that the user is talking about on social media. The weather information providing unit can also provide weather information for a region where people the user follows on social media are located. Furthermore, the weather information providing unit can also provide weather information for locations where the user has checked in on social media. In this way, related weather information can be provided by analyzing social media activity. Some or all of the above-described processing in the weather information providing unit can be performed, for example, using AI or without AI. For example, the weather information providing unit can input the user's social media data into a generation AI, which can analyze the social media activity and provide related weather information.

[0067] When providing weather information, the weather information providing unit can customize the providing method by reflecting the user's past feedback. The weather information providing unit customizes the providing method, for example, based on feedback provided by the user in the past. The weather information providing unit can also preferentially adopt a providing method that the user is satisfied with. Furthermore, the weather information providing unit can also customize the providing method by avoiding a providing method that the user is dissatisfied with. In this way, by reflecting past feedback, the providing method can be customized and appropriate information can be provided. Some or all of the above-mentioned processing in the weather information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the weather information providing unit can input user feedback data to a generation AI, which can customize the providing method based on the feedback.

[0068] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0069] The care system may also include a health monitoring unit that monitors the user's health condition. The health monitoring unit measures the user's vital signs, such as heart rate, blood pressure, and body temperature, in real time and can issue an alert if an abnormality is detected. For example, if the user's heart rate suddenly increases, the health monitoring unit can issue an alert and encourage the user to rest. In addition, if the user's blood pressure is high, the health monitoring unit can instruct the linking unit to play relaxing music. Furthermore, if the user's body temperature is high, a message can be generated encouraging the user to drink more water. This allows the care system to constantly monitor the user's health condition and provide appropriate support.

[0070] The care system can also include a diet management unit that supports the user's dietary management. The diet management unit can record the user's dietary content and analyze nutritional balance. For example, it can automatically calculate the calories and nutrients of the foods the user eats and point out any excess or deficiency. The diet management unit can also propose a meal plan based on the user's goals. Furthermore, if the user has consumed too much of a particular nutrient, it can provide advice on how to balance the intake in the next meal. In this way, the care system can support the user's healthy eating habits.

[0071] The care system may also include an exercise management unit that supports the user's exercise habits. The exercise management unit can record the user's exercise history and analyze the effects of the exercise. For example, it can record the type and duration of the exercise performed by the user and calculate the calories burned. The exercise management unit can also suggest an exercise plan based on the user's goals. Furthermore, if the user has neglected to exercise, it can send a reminder to encourage the user to exercise. In this way, the care system can support the user's healthy exercise habits.

[0072] The care system may also include a sleep management unit that monitors the user's sleep state. The sleep management unit can record the user's sleep patterns and provide advice to promote high-quality sleep. For example, the sleep management unit can analyze the user's sleep time and the percentage of deep sleep and point out areas for improvement. The sleep management unit can also play relaxing music before bed to help the user relax and fall asleep. Furthermore, if the user wakes up in the middle of the night, the sleep management unit can provide advice to help the user fall asleep again. In this way, the care system can support the user's high-quality sleep.

[0073] The processing flow of the first embodiment will be briefly explained below.

[0074] Step 1: The speech recognition unit converts the user's speech into text using speech recognition technology, which includes deep learning-based speech recognition and HMM (Hidden Markov Model). The speech recognition unit converts the user's speech into text in real time and improves the accuracy of speech recognition by removing background noise using noise reduction technology. Step 2: The response generation unit uses a generation AI to generate a response based on the text converted by the speech recognition unit. The generation AI includes text generation AI (e.g., LLM) and multimodal generation AI, which analyzes the user's utterances and generates an appropriate response. For example, if the user says, "I'm tired today," the response generation unit generates a response such as, "Thank you for your hard work. What happened today?" The response generation unit can also analyze the user's emotions and generate a response that corresponds to those emotions. Step 3: The linking unit links with external services based on the response generated by the response generation unit. External services include services that play relaxing music and services that provide weather information. For example, if the user says, "I want to relax," the linking unit links with a service that plays relaxing music to provide the user with a relaxing environment. Also, if the user asks, "What's the weather like today?" the linking unit links with a service that provides weather information to provide the latest weather information.

[0075] (Example 2) A care system according to an embodiment of the present invention provides mental and physical care for people busy with childcare, work, and housework. The care system provides support through conversations with characters selected by the user. Specifically, the system utilizes natural language processing and speech recognition technology by a generative AI to understand the user's utterances and generate appropriate responses. The system also connects with various external services via an API to provide support tailored to the user's needs. For example, if a user says, "I'm tired today," the generative AI generates a response such as, "Thank you for your hard work. What happened today?" Furthermore, the care system connects with services that play relaxing music and provide weather information to provide users with a relaxing environment and the latest weather information. This allows people busy with childcare, work, and housework to care for their mind and body without putting themselves off. For example, the care system allows users to feel comforted and encouraged by conversations with their favorite characters. Furthermore, by connecting with various external services, users can receive support tailored to their needs. This will enable us to aim for a society in which women can play more active and vibrant roles.

[0076] The care system according to the embodiment includes a speech recognition unit, a response generation unit, and a linking unit. The speech recognition unit converts a user's speech into text using speech recognition technology. Examples of speech recognition technology include, but are not limited to, deep learning-based speech recognition and HMM (Hidden Markov Model). For example, the speech recognition unit converts the user's speech into text in real time. The speech recognition unit can also improve the accuracy of speech recognition by removing background noise using noise reduction technology. The response generation unit uses a generation AI to generate a response based on the text converted by the speech recognition unit. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's speech and generates an appropriate response. For example, if the user says, "I'm tired today," the response generation unit generates a response such as, "Thank you for your hard work. What happened today?" The response generation unit can also analyze the user's emotions and generate a response according to the emotions. The linking unit links with an external service based on the response generated by the response generation unit. Examples of external services include, but are not limited to, a service that plays relaxing music and a service that provides weather information. For example, when a user says, "I want to relax," the linking unit links with a service that plays relaxing music to provide the user with a relaxing environment. Also, when a user asks, "What's the weather like today?" the linking unit links with a service that provides weather information to provide the latest weather information. As a result, the care system according to the embodiment can recognize the user's speech, generate an appropriate response, and link with external services to provide support according to the user's needs.

[0077] The response generation unit includes an emotion analysis unit that analyzes the user's emotions. The emotion analysis unit analyzes the user's utterances and infers the emotions. Emotion analysis includes, but is not limited to, text analysis, voice analysis, and facial expression analysis. For example, the emotion analysis unit analyzes the content of the user's utterances and infers the emotions. The emotion analysis unit can also analyze the tone and speed of the user's voice to infer the emotions. Furthermore, the emotion analysis unit can capture the user's facial expressions with a camera and infer the emotions using facial expression analysis technology. This allows the emotion analysis unit to analyze the user's emotions in detail, and the response generation unit to generate a more appropriate response. 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. This allows a more appropriate response to be generated by analyzing the user's emotions.

[0078] The link unit includes a music playback unit that plays relaxing music. The music playback unit plays relaxing music. Examples of relaxing music include, but are not limited to, classical music, nature sounds, and healing music. For example, the music playback unit plays classical music when the user feels like relaxing. The music playback unit can also play nature sounds when the user is feeling stressed. Furthermore, the music playback unit can play healing music when the user wants to concentrate. In this way, the music playback unit can support the user's relaxation by playing relaxing music. Some or all of the above-described processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input user emotion data into a generation AI, which can select and play optimal music based on the user's emotions.

[0079] The linking unit includes a weather information providing unit that provides weather information. The weather information providing unit provides the latest weather information. Weather information includes, but is not limited to, temperature, probability of precipitation, and wind speed. For example, when a user asks, "What's the weather like today?", the weather information providing unit provides the latest temperature and probability of precipitation. Furthermore, when a user asks, "What's the weather like tomorrow?", the weather information providing unit can provide the wind speed and temperature for the next day. Furthermore, when a user asks, "What's the weather like this weekend?", the weather information providing unit can provide a weekend weather forecast. In this way, the weather information providing unit can provide information that meets the user's needs by providing weather information. Some or all of the above-described processing in the weather information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the weather information providing unit can input weather data to a generation AI, which can generate and provide optimal weather information based on the user's needs.

[0080] The speech recognition unit can estimate a user's emotions and dynamically adjust the accuracy of speech recognition based on the estimated user emotions. For example, when the user is stressed, the speech recognition unit can increase the accuracy of speech recognition to reduce misrecognition. Furthermore, when the user is relaxed, the speech recognition unit can return the accuracy of speech recognition to normal and maintain natural conversation. Furthermore, when the user is excited, the speech recognition unit can increase the accuracy of speech recognition to accommodate faster speech rates. This allows for reducing misrecognition by adjusting the accuracy of speech recognition 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, 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 speech recognition unit may be performed using AI, or may be performed without AI. For example, the speech recognition unit can input the user's voice data into a generation AI, which can dynamically adjust the accuracy of speech recognition based on the user's emotions.

[0081] The voice recognition unit can analyze background sounds of the user's speech and remove noise during voice recognition. For example, if the user is in a noisy place such as a cafe, the voice recognition unit can analyze the background sounds and remove noise. Furthermore, if the user is talking while watching TV at home, the voice recognition unit can also remove the sound of the TV as noise. Furthermore, if the user is out and there is wind noise, the voice recognition unit can also remove the wind noise as noise. This allows for improved voice recognition accuracy by analyzing background sounds and removing noise. Some or all of the above-described processing in the voice recognition unit may be performed using, or without, AI, for example. For example, the voice recognition unit can input the user's voice data to a generation AI, which can then analyze the background sounds and remove noise.

[0082] During speech recognition, the speech recognition unit analyzes the speed and tone of a user's speech to more accurately understand the intent of the speech. For example, if a user speaks at a fast speed, the speech recognition unit analyzes the speed to understand the intent. Furthermore, if a user speaks in a low tone, the speech recognition unit can analyze the tone to understand the intent. Furthermore, if a user speaks in a high tone, the speech recognition unit can analyze the tone to understand the intent. In this way, by analyzing the speech speed and tone, the intent of the speech can be accurately understood. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit inputs the user's speech data to a generation AI, which can analyze the speech speed and tone to understand the intent.

[0083] During speech recognition, the speech recognition unit can improve recognition accuracy by referring to the user's past utterance history. The speech recognition unit can improve recognition accuracy by, for example, referring to phrases frequently used by the user in the past. The speech recognition unit can also improve recognition accuracy by referring to utterances that the user has previously misrecognized. Furthermore, the speech recognition unit can also improve recognition accuracy by referring to utterances that the user has previously spoken with a particular accent. In this way, the accuracy of speech recognition can be improved by referring to the past utterance history. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can input the user's past utterance data into a generation AI, which can then improve recognition accuracy by referring to the past utterance history.

[0084] The speech recognition unit can estimate the user's emotion and adjust the start timing of speech recognition based on the estimated user emotion. For example, if the user is nervous, the speech recognition unit can delay the start timing of speech recognition to relax the user. Furthermore, if the user is relaxed, the speech recognition unit can also return the start timing of speech recognition to normal. Furthermore, if the user is in a hurry, the speech recognition unit can also advance the start timing of speech recognition to respond quickly. By adjusting the start timing of speech recognition according to the user's emotion, speech recognition can be started at a more appropriate time. Emotion estimation is realized 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 speech recognition unit may be performed using, for example, AI, or without AI. For example, the speech recognition unit can input user emotion data into the generation AI, and the generation AI can adjust the start timing of speech recognition based on the emotion.

[0085] During speech recognition, the speech recognition unit can recognize regional words and accents by taking into account the user's geographical location information. For example, if the user is in the Kansai region, the speech recognition unit can recognize the Kansai dialect. Also, if the user is in the Tohoku region, the speech recognition unit can recognize the Tohoku dialect. Furthermore, if the user is overseas, the speech recognition unit can recognize the regional words and accents. This allows for accurate recognition of regional words and accents by taking geographical location information into account. Some or all of the above-described processing in the speech recognition unit may be performed using, or without, AI, for example. For example, the speech recognition unit can input the user's geographical location data into a generation AI, which can then recognize regional words and accents.

[0086] During voice recognition, the voice recognition unit can analyze the user's social media activity and prioritize recognition of relevant comments. For example, the voice recognition unit can prioritize recognition of phrases frequently used by the user on social media. The voice recognition unit can also prioritize recognition of topics that the user is talking about on social media. Furthermore, the voice recognition unit can also prioritize recognition of comments made by people the user follows on social media. In this way, by analyzing social media activity, relevant comments can be prioritized. Some or all of the above-described processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice recognition unit can input the user's social media data into a generation AI, which can then prioritize recognition of relevant comments.

[0087] The speech recognition unit can customize the recognition method by reflecting the user's past feedback during speech recognition. The speech recognition unit can improve the accuracy of speech recognition based on, for example, feedback provided by the user in the past. The speech recognition unit can also improve the recognition method by reflecting recognition errors pointed out by the user in the past. Furthermore, the speech recognition unit can also customize based on the recognition method that the user previously preferred. In this way, by reflecting past feedback, the recognition method can be customized and accuracy can be improved. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can input user feedback data to a generation AI, and the generation AI can customize the recognition method based on the feedback.

[0088] The response generation unit can estimate the user's emotions and adjust the way a response is expressed based on the estimated user's emotions. For example, if the user is sad, the response generation unit can respond with kind words. Furthermore, if the user is happy, the response generation unit can respond with cheerful words. Furthermore, if the user is angry, the response generation unit can respond with calm words. This allows for adjusting the way a response is expressed based on the user's emotions, thereby generating a more appropriate response. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may 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 response generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the response generation unit can input the user's emotion data into the generation AI, which can then adjust the way a response is expressed based on the emotion.

[0089] When generating a response, the response generation unit can adjust the level of detail of the response based on the importance of the user's utterance. For example, the response generation unit generates a detailed response when the user asks an important question. The response generation unit can also generate a concise response when the user provides a light topic. Furthermore, the response generation unit can also generate a quick and detailed response when the user conveys an urgent requirement. This makes it possible to generate an appropriate response by adjusting the level of detail of the response based on the importance of the utterance. Some or all of the above-mentioned processing in the response generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the response generation unit can input user utterance data into a generation AI, which can adjust the level of detail of the response based on the importance of the utterance.

[0090] When generating a response, the response generation unit can apply different response algorithms depending on the category of the user's utterance. For example, when the user asks a technical question, the response generation unit can apply a specialized response algorithm. Furthermore, when the user provides an emotional topic, the response generation unit can also apply a response algorithm that takes emotions into consideration. Furthermore, when the user provides an everyday topic, the response generation unit can also apply a general response algorithm. In this way, an appropriate response can be generated by applying a response algorithm depending on the category of the utterance. Some or all of the above-mentioned processing in the response generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the response generation unit can input the user's utterance data into a generation AI, which can then apply different response algorithms depending on the category of the utterance.

[0091] When generating a response, the response generation unit can improve the accuracy of the response by referring to the user's past response history. The response generation unit generates a response by referring to, for example, a response style that the user has previously preferred. The response generation unit can also generate a response so as to avoid responses that the user has previously dissatisfied with. Furthermore, the response generation unit can improve the accuracy of the response based on feedback provided by the user in the past. In this way, the accuracy of the response can be improved by referring to the past response history. Some or all of the above-mentioned processing in the response generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the response generation unit can input the user's response history data into the generation AI, and the generation AI can improve the accuracy of the response by referring to the past response history.

[0092] The response generation unit can estimate the user's emotions and adjust the length of the response based on the estimated user's emotions. For example, the response generation unit can generate a short response when the user is in a hurry. The response generation unit can also generate a longer response when the user is relaxed. Furthermore, the response generation unit can generate a long and detailed response when the user is seeking detailed information. This allows an appropriate response to be generated by adjusting the length of the response 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 response generation unit can be performed using, for example, AI, or without AI. For example, the response generation unit can input the user's emotion data into the generation AI, which can then adjust the length of the response based on the emotion.

[0093] When generating a response, the response generation unit can determine the priority of the response based on the time when the user submitted the utterance. For example, if the user communicates an urgent requirement, the response generation unit generates the response with priority. Also, if the user asks a normal question, the response generation unit can generate a response with normal priority. Furthermore, the response generation unit can adjust the priority based on questions previously submitted by the user. In this way, an appropriate response can be generated by determining the priority of the response based on the time when the utterance was submitted. Some or all of the above-mentioned processing in the response generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the response generation unit can input the user's utterance data into a generation AI, and the generation AI can determine the priority of the response based on the time when the utterance was submitted.

[0094] When generating a response, the response generation unit can adjust the order of responses based on the relevance of the user's utterances. For example, if a user asks related questions consecutively, the response generation unit generates responses in order of increasing relevance. Furthermore, if a user provides different topics, the response generation unit can also generate responses in order of decreasing relevance. Furthermore, if a user provides an important topic, the response generation unit can also generate responses in order of decreasing relevance. In this way, by adjusting the order of responses based on the relevance of the utterances, an appropriate response can be generated. Some or all of the above-described processing in the response generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the response generation unit can input user utterance data to a generation AI, which can adjust the order of responses based on the relevance of the utterances.

[0095] When generating a response, the response generation unit can adjust the use of technical terminology in the response depending on the user's level of expertise. For example, if the user is an expert, the response generation unit generates a response that uses a lot of technical terminology. Furthermore, if the user is a beginner, the response generation unit can also generate a response that avoids technical terminology. Furthermore, if the user is an intermediate user, the response generation unit can generate a response that uses technical terminology appropriately. In this way, an appropriate response can be generated by adjusting the use of technical terminology depending on the level of expertise. Some or all of the above-mentioned processing in the response generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the response generation unit can input the user's expertise data into a generation AI, which can adjust the use of technical terminology in the response depending on the level of expertise.

[0096] The linking unit can estimate the user's emotions and select an external service to link with based on the estimated user's emotions. For example, if the user wants to relax, the linking unit can link with a service that plays relaxing music. If the user wants information, the linking unit can also link with a news service. If the user wants to exercise, the linking unit can also link with a fitness service. This makes it possible to select an external service based on the user's emotions and provide appropriate support. Emotion estimation is achieved using an emotion estimation function, for example, using 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 these examples. Some or all of the above-mentioned processing in the linking unit can be performed using, for example, AI, or without AI. For example, the linking unit can input the user's emotion data into the generation AI, and the generation AI can select an external service to link with based on the emotion.

[0097] At the time of collaboration, the collaboration unit can select the optimal external service by referring to the user's past collaboration history. The collaboration unit selects the optimal external service, for example, based on services the user has used in the past. The collaboration unit can also preferentially select services that the user has been satisfied with in the past. Furthermore, the collaboration unit can also select services that avoid services that the user has been dissatisfied with in the past. In this way, the optimal external service can be selected by referring to the past collaboration history. Some or all of the above-described processing in the collaboration unit may be performed using, for example, AI, or may be performed without using AI. For example, the collaboration unit can input the user's collaboration history data into the generation AI, and the generation AI can select the optimal external service by referring to the past collaboration history.

[0098] The linking unit can customize the linking method based on the user's current needs when linking. For example, if the user wants to relax, the linking unit can link with a service that plays relaxing music. If the user wants information, the linking unit can also link with a news service. Furthermore, if the user wants to exercise, the linking unit can also link with a fitness service. In this way, by customizing the linking method based on the user's current needs, appropriate support can be provided. Some or all of the above-described processing in the linking unit may be performed using, for example, AI, or may be performed without using AI. For example, the linking unit can input the user's needs data into the generation AI, which can then customize the linking method based on the user's current needs.

[0099] The collaboration unit can improve the collaboration method by reflecting user feedback during collaboration. The collaboration unit can improve the collaboration method, for example, based on feedback provided by the user in the past. The collaboration unit can also preferentially adopt collaboration methods that the user is satisfied with. Furthermore, the collaboration unit can also avoid and improve collaboration methods that the user is dissatisfied with. In this way, by reflecting feedback, the collaboration method can be improved and appropriate support can be provided. Some or all of the above-mentioned processing in the collaboration unit can be performed, for example, using AI or without using AI. For example, the collaboration unit can input user feedback data into the generation AI, and the generation AI can improve the collaboration method based on the feedback.

[0100] The linking unit can estimate the user's emotions and prioritize external services to be linked based on the estimated user's emotions. For example, if the user wants to relax, the linking unit can prioritize a service that plays relaxing music. Furthermore, if the user wants to get information, the linking unit can prioritize a news service. Furthermore, if the user wants to exercise, the linking unit can prioritize a fitness service. By prioritizing external services based on the user's emotions, appropriate support can be provided. The emotion estimation is realized 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 linking unit can be performed using, for example, AI, or without AI. For example, the linking unit can input the user's emotion data into the generation AI, which can then prioritize external services to be linked based on the emotion.

[0101] At the time of linking, the linking unit can select the optimal external service by taking into account the user's geographical location information. For example, when the user is in a specific area, the linking unit links with a service that provides weather information for that area. Furthermore, when the user is traveling, the linking unit can also link with a service that provides tourist spot information. Furthermore, when the user is at home, the linking unit can also link with a service that provides nearby restaurant information. In this way, the optimal external service can be selected by taking into account the geographical location information. Some or all of the above-described processing in the linking unit may be performed using, for example, AI, or may be performed without using AI. For example, the linking unit can input the user's geographical location data into the generation AI, and the generation AI can select the optimal external service by taking into account the geographical location information.

[0102] At the time of linking, the linking unit can analyze the user's social media activity and suggest external services to link with. For example, the linking unit can suggest services related to topics the user is talking about on social media. The linking unit can also suggest services used by people the user follows on social media. Furthermore, the linking unit can also suggest services related to places the user has checked in to on social media. In this way, related external services can be suggested by analyzing social media activity. Some or all of the above-mentioned processing in the linking unit may be performed using, for example, AI, or may be performed without using AI. For example, the linking unit can input the user's social media data into a generation AI, which can analyze the social media activity and suggest external services to link with.

[0103] The collaboration unit can customize the collaboration method by reflecting the user's past feedback during collaboration. The collaboration unit customizes the collaboration method based on, for example, feedback provided by the user in the past. The collaboration unit can also preferentially adopt collaboration methods that the user is satisfied with. Furthermore, the collaboration unit can customize the collaboration method by avoiding collaboration methods that the user is dissatisfied with. In this way, by reflecting past feedback, the collaboration method can be customized and appropriate support can be provided. Some or all of the above-described processing in the collaboration unit may be performed using, for example, AI, or may be performed without using AI. For example, the collaboration unit can input user feedback data into a generation AI, which can customize the collaboration method based on the feedback.

[0104] The emotion analysis unit can estimate the user's emotion and dynamically adjust the accuracy of the analysis based on the estimated user emotion. For example, if the user is stressed, the emotion analysis unit can increase the accuracy of the emotion analysis to perform a more detailed analysis. Furthermore, if the user is relaxed, the emotion analysis unit can also return the accuracy of the emotion analysis to normal. Furthermore, if the user is excited, the emotion analysis unit can increase the accuracy of the emotion analysis to perform a quicker analysis. This allows for a more detailed analysis by adjusting the accuracy of the analysis based on the user's emotion. The 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 emotion analysis unit can be performed using, for example, an AI, or without an AI. For example, the emotion analysis unit can input the user's emotion data into the generation AI, which can dynamically adjust the accuracy of the analysis based on the emotion.

[0105] During emotion analysis, the emotion analysis unit can analyze background sounds of the user's speech and detect changes in emotion. For example, when the user is in a noisy place, the emotion analysis unit can analyze background sounds to detect changes in emotion. The emotion analysis unit can also analyze background sounds to detect changes in emotion when the user is in a quiet place. Furthermore, when the user is listening to music, the emotion analysis unit can analyze background sounds to detect changes in emotion. In this way, changes in emotion can be detected by analyzing background sounds. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the user's voice data to a generation AI, which can then analyze background sounds to detect changes in emotion.

[0106] During emotion analysis, the emotion analysis unit analyzes the speed and tone of the user's speech to more accurately understand the emotional intent. For example, if the user speaks quickly, the emotion analysis unit analyzes the speed to understand the emotional intent. Furthermore, if the user speaks in a low tone, the emotion analysis unit can analyze the tone to understand the emotional intent. Furthermore, if the user speaks in a high tone, the emotion analysis unit can analyze the tone to understand the emotional intent. In this way, by analyzing the speech speed and tone, the emotional intent can be accurately understood. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit inputs the user's voice data into a generation AI, which can analyze the speech speed and tone to understand the emotional intent.

[0107] During emotion analysis, the emotion analysis unit can improve the accuracy of the analysis by referring to the user's past emotion history. The emotion analysis unit can improve the analysis accuracy by, for example, referring to emotions the user has felt in the past. The emotion analysis unit can also improve the analysis accuracy based on feedback the user has provided in the past. Furthermore, the emotion analysis unit can improve the analysis accuracy by referring to events the user has experienced in the past. In this way, the analysis accuracy can be improved by referring to the past emotion history. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the user's emotion history data into the generation AI, and the generation AI can improve the analysis accuracy by referring to the past emotion history.

[0108] The emotion analysis unit can estimate the user's emotion and adjust the start timing of the analysis based on the estimated user emotion. For example, if the user is nervous, the emotion analysis unit can delay the start timing of the analysis to relax the user. Furthermore, if the user is relaxed, the emotion analysis unit can also return the start timing of the analysis to normal. Furthermore, if the user is in a hurry, the emotion analysis unit can also advance the start timing of the analysis to respond quickly. By adjusting the start timing of the analysis based on the user's emotion, the analysis can be started at an appropriate time. The emotion estimation is realized 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 emotion analysis unit can be performed using, for example, an AI, or without an AI. For example, the emotion analysis unit can input the user's emotion data into the generation AI, which can then adjust the start timing of the analysis based on the emotion.

[0109] During emotion analysis, the emotion analysis unit can analyze region-specific emotional expressions by taking into account the user's geographical location information. For example, if the user is in the Kansai region, the emotion analysis unit analyzes Kansai-specific emotional expressions. Also, if the user is in the Tohoku region, the emotion analysis unit can analyze Tohoku-specific emotional expressions. Furthermore, if the user is overseas, the emotion analysis unit can analyze region-specific emotional expressions. This allows for accurate analysis of region-specific emotional expressions by taking geographical location information into account. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the user's geographical location data into the generation AI, which can then analyze region-specific emotional expressions.

[0110] During emotion analysis, the emotion analysis unit can analyze the user's social media activity and prioritize analysis of related emotions. For example, the emotion analysis unit can prioritize analysis of emotional expressions frequently used by the user on social media. The emotion analysis unit can also prioritize analysis of emotions related to topics the user is talking about on social media. Furthermore, the emotion analysis unit can also prioritize analysis of emotional expressions of people the user follows on social media. In this way, by analyzing social media activity, related emotions can be prioritized. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the user's social media data into a generation AI, which can analyze the social media activity and prioritize analysis of related emotions.

[0111] The emotion analysis unit can customize the analysis method by reflecting the user's past feedback during emotion analysis. The emotion analysis unit customizes the analysis method, for example, based on feedback provided by the user in the past. The emotion analysis unit can also preferentially adopt analysis methods that the user is satisfied with. Furthermore, the emotion analysis unit can also customize the analysis method by avoiding analysis methods that the user is dissatisfied with. In this way, by reflecting past feedback, the analysis method can be customized and accuracy can be improved. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input user feedback data into a generation AI, which can customize the analysis method based on the feedback.

[0112] The music playback unit can estimate the user's emotions and select music to play based on the estimated user's emotions. For example, if the user wants to relax, the music playback unit can select relaxing music. Furthermore, if the user wants to cheer up, the music playback unit can select music that will enhance concentration. By selecting music based on the user's emotions, appropriate music can be played. The emotion estimation is achieved using an emotion estimation function, such as 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 music playback unit can be performed using, for example, AI, or without AI. For example, the music playback unit can input the user's emotion data into the generation AI, and the generation AI can select music to play based on the emotion.

[0113] When playing music, the music playback unit can select optimal music by referring to the user's past music playback history. The music playback unit selects optimal music, for example, based on music that the user liked to listen to in the past. The music playback unit can also select optimal music based on music that the user found relaxing in the past. Furthermore, the music playback unit can also select optimal music based on music that the user found uplifting in the past. In this way, optimal music can be selected by referring to the past music playback history. Some or all of the above-described processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input the user's music playback history data to a generation AI, which can then select optimal music by referring to the past music playback history.

[0114] The music playback unit can customize the playback method based on the user's current mood when playing music. For example, if the user wants to relax, the music playback unit can play relaxing music. Furthermore, if the user wants to cheer up, the music playback unit can play up-tempo music. Furthermore, if the user wants to concentrate, the music playback unit can play music that helps improve concentration. In this way, by customizing the playback method based on the user's current mood, appropriate music can be played. Some or all of the above-described processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input the user's mood data into the generation AI, and the generation AI can customize the playback method based on the user's current mood.

[0115] The music playback unit can improve the playback method by reflecting user feedback when playing music. The music playback unit can improve the playback method, for example, based on feedback provided by the user in the past. The music playback unit can also preferentially adopt playback methods that the user is satisfied with. Furthermore, the music playback unit can also improve by avoiding playback methods that the user is dissatisfied with. In this way, by reflecting feedback, the playback method can be improved and appropriate music can be played. Some or all of the above-mentioned processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input user feedback data into a generation AI, which can then improve the playback method based on the feedback.

[0116] The music playback unit can estimate the user's emotions and determine the priority of music to be played based on the estimated user's emotions. For example, if the user wants to relax, the music playback unit can prioritize playing relaxing music. Furthermore, if the user wants to cheer up, the music playback unit can prioritize playing up-tempo music. Furthermore, if the user wants to concentrate, the music playback unit can prioritize playing music that enhances concentration. Thus, by determining the priority of music based on the user's emotions, appropriate music can be played. 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 music playback unit can be performed using, for example, AI, or without AI. For example, the music playback unit can input the user's emotion data into the generation AI, which can then prioritize the music to be played based on the emotion.

[0117] When playing music, the music playback unit can select optimal music by taking into account the user's geographical location information. For example, if the user is in a specific area, the music playback unit selects music for that area. Furthermore, if the user is traveling, the music playback unit can also select music for the travel destination. Furthermore, if the user is at home, the music playback unit can also select relaxing music. In this way, optimal music can be selected by taking into account the geographical location information. Some or all of the above-described processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input the user's geographical location data into a generation AI, which can select optimal music by taking into account the geographical location information.

[0118] When playing music, the music playback unit can analyze the user's social media activity and suggest music to play. For example, the music playback unit can suggest music that the user is talking about on social media. The music playback unit can also suggest music by artists the user follows on social media. Furthermore, the music playback unit can also suggest music related to places the user has checked in to on social media. In this way, related music can be suggested by analyzing social media activity. Some or all of the above-described processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input the user's social media data into a generation AI, which can analyze the social media activity and suggest music to play.

[0119] The music playback unit can customize the playback method by reflecting the user's past feedback when playing music. The music playback unit customizes the playback method based on, for example, feedback provided by the user in the past. The music playback unit can also preferentially adopt playback methods that the user is satisfied with. Furthermore, the music playback unit can also customize the playback method by avoiding playback methods that the user is dissatisfied with. In this way, by reflecting past feedback, the playback method can be customized and appropriate music can be played. Some or all of the above-described processing in the music playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the music playback unit can input user feedback data to a generation AI, which can then customize the playback method based on the feedback.

[0120] The weather information providing unit can estimate the user's emotions and adjust the method of providing weather information based on the estimated user's emotions. For example, if the user is relaxed, the weather information providing unit can provide weather information in calm language. If the user is in a hurry, the weather information providing unit can also provide brief weather information. If the user is excited, the weather information providing unit can also provide detailed weather information. This allows appropriate information to be provided by adjusting the method of providing weather information based on 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-mentioned processing in the weather information providing unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the weather information providing unit can input the user's emotion data into the generation AI, and the generation AI can adjust the method of providing weather information based on the emotion.

[0121] When providing weather information, the weather information providing unit can select the optimal providing method by referring to the user's past weather information usage history. The weather information providing unit selects the optimal providing method, for example, based on the user's past preferred providing method. The weather information providing unit can also preferentially select a providing method that the user has been satisfied with in the past. Furthermore, the weather information providing unit can select a providing method that avoids a providing method that the user has been dissatisfied with in the past. In this way, the optimal providing method can be selected by referring to the past weather information usage history. Some or all of the above-mentioned processing in the weather information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the weather information providing unit can input the user's weather information usage history data to a generation AI, which can then select the optimal providing method by referring to the past weather information usage history.

[0122] When providing weather information, the weather information providing unit can customize the provided content based on the user's current needs. For example, if the user plans to go out, the weather information providing unit can provide weather information suitable for going out. Furthermore, if the user plans to travel, the weather information providing unit can also provide weather information for the travel destination. Furthermore, if the user plans to spend time indoors, the weather information providing unit can also provide weather information that will affect the indoor environment. In this way, by customizing the provided content based on the current needs, appropriate information can be provided. Some or all of the above-mentioned processing in the weather information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the weather information providing unit can input the user's needs data into the generation AI, and the generation AI can customize the provided content based on the current needs.

[0123] The weather information providing unit can improve the weather information providing method by reflecting user feedback when providing weather information. The weather information providing unit can improve the weather information providing method, for example, based on feedback provided by the user in the past. The weather information providing unit can also preferentially adopt a providing method that the user is satisfied with. Furthermore, the weather information providing unit can also avoid and improve a providing method that the user is dissatisfied with. In this way, by reflecting feedback, the providing method can be improved and appropriate information can be provided. Some or all of the above-mentioned processing in the weather information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the weather information providing unit can input user feedback data into a generation AI, which can improve the providing method based on the feedback.

[0124] The weather information providing unit can estimate the user's emotions and determine the priority of weather information based on the estimated user's emotions. For example, if the user is relaxed, the weather information providing unit can prioritize providing calm weather information. Furthermore, if the user is in a hurry, the weather information providing unit can prioritize providing important weather information. Furthermore, if the user is excited, the weather information providing unit can prioritize providing detailed weather information. This allows appropriate information to be provided by determining the priority of weather information based on 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-mentioned processing in the weather information providing unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the weather information providing unit can input the user's emotion data into the generation AI, which can then prioritize weather information based on the emotion.

[0125] When providing weather information, the weather information providing unit can provide optimal weather information by taking into account the user's geographical location information. For example, if the user is in a specific area, the weather information providing unit can provide weather information for that area. Furthermore, if the user is traveling, the weather information providing unit can also provide weather information for the user's travel destination. Furthermore, if the user is at home, the weather information providing unit can also provide weather information for the user's neighborhood. In this way, optimal weather information can be provided by taking into account the geographical location information. Some or all of the above-described processing in the weather information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the weather information providing unit can input the user's geographical location data into a generation AI, which can then provide optimal weather information by taking into account the geographical location information.

[0126] When providing weather information, the weather information providing unit can analyze the user's social media activity and provide related weather information. The weather information providing unit can provide, for example, weather information for a region that the user is talking about on social media. The weather information providing unit can also provide weather information for a region where people the user follows on social media are located. Furthermore, the weather information providing unit can also provide weather information for locations where the user has checked in on social media. In this way, related weather information can be provided by analyzing social media activity. Some or all of the above-described processing in the weather information providing unit can be performed, for example, using AI or without AI. For example, the weather information providing unit can input the user's social media data into a generation AI, which can analyze the social media activity and provide related weather information.

[0127] When providing weather information, the weather information providing unit can customize the providing method by reflecting the user's past feedback. The weather information providing unit customizes the providing method, for example, based on feedback provided by the user in the past. The weather information providing unit can also preferentially adopt a providing method that the user is satisfied with. Furthermore, the weather information providing unit can also customize the providing method by avoiding a providing method that the user is dissatisfied with. In this way, by reflecting past feedback, the providing method can be customized and appropriate information can be provided. Some or all of the above-mentioned processing in the weather information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the weather information providing unit can input user feedback data to a generation AI, which can customize the providing method based on the feedback. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned voice recognition unit, response generation unit, linking unit, emotion analysis unit, music playback unit, and weather information provision unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the voice recognition unit is implemented by the microphone 38B and control unit 46A of the smart device 14 and converts a user's utterances into text in real time. The response generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates an appropriate response using a generative AI. The linking unit is implemented by the specific processing unit 290 of the data processing device 12 and links with external services to provide support tailored to the user's needs. The emotion analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the user's utterances and tone of voice to estimate their emotions. The music playback unit is implemented by the output device 40 of the smart device 14 and plays relaxing music. The weather information provision unit is implemented by the specific processing unit 290 of the data processing device 12 and provides the latest weather information. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned voice recognition unit, response generation unit, collaboration unit, emotion analysis unit, music playback unit, and weather information provision unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the voice recognition unit is realized by the microphone 238 and control unit 46A of the smart glasses 214 and converts a user's utterances into text in real time. The response generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an appropriate response using a generative AI. The collaboration unit is realized by the specific processing unit 290 of the data processing device 12 and collaborates with external services to provide support tailored to the user's needs. The emotion analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the user's utterances and tone of voice to estimate emotions. The music playback unit is realized by the speaker 240 of the smart glasses 214 and plays relaxing music. The weather information provision unit is realized by the specific processing unit 290 of the data processing device 12 and provides the latest weather information. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned voice recognition unit, response generation unit, linking unit, emotion analysis unit, music playback unit, and weather information provision unit, is implemented, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the voice recognition unit is implemented by the microphone 238 and control unit 46A of the headset-type terminal 314 and converts a user's utterances into text in real time. The response generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates an appropriate response using a generation AI. The linking unit is implemented by the specific processing unit 290 of the data processing device 12 and links with external services to provide support tailored to the user's needs. The emotion analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the user's utterances and tone of voice to estimate their emotions. The music playback unit is implemented by the speaker 240 of the headset-type terminal 314 and plays relaxing music. The weather information provision unit is implemented by the specific processing unit 290 of the data processing device 12 and provides the latest weather information. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned voice recognition unit, response generation unit, collaboration unit, emotion analysis unit, music playback unit, and weather information provision unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the voice recognition unit is realized by the microphone 238 and control unit 46A of the robot 414 and converts the user's utterances into text in real time. The response generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates appropriate responses using a generative AI. The collaboration unit is realized by the specific processing unit 290 of the data processing device 12 and collaborates with external services to provide support tailored to the user's needs. The emotion analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the user's utterances and tone of voice to infer emotions. The music playback unit is realized by the speaker 240 of the robot 414 and plays relaxing music. The weather information provision unit is realized by the specific processing unit 290 of the data processing device 12 and provides the latest weather information.

[0128] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0129] The care system may also include a health monitoring unit that monitors the user's health condition. The health monitoring unit measures the user's vital signs, such as heart rate, blood pressure, and body temperature, in real time and can issue an alert if an abnormality is detected. For example, if the user's heart rate suddenly increases, the health monitoring unit can issue an alert and encourage the user to rest. In addition, if the user's blood pressure is high, the health monitoring unit can instruct the linking unit to play relaxing music. Furthermore, if the user's body temperature is high, a message can be generated encouraging the user to drink more water. This allows the care system to constantly monitor the user's health condition and provide appropriate support.

[0130] The care system can also include a diet management unit that supports the user's dietary management. The diet management unit can record the user's dietary content and analyze nutritional balance. For example, it can automatically calculate the calories and nutrients of the foods the user eats and point out any excess or deficiency. The diet management unit can also propose a meal plan based on the user's goals. Furthermore, if the user has consumed too much of a particular nutrient, it can provide advice on how to balance the intake in the next meal. In this way, the care system can support the user's healthy eating habits.

[0131] The care system may also include an exercise management unit that supports the user's exercise habits. The exercise management unit can record the user's exercise history and analyze the effects of the exercise. For example, it can record the type and duration of the exercise performed by the user and calculate the calories burned. The exercise management unit can also suggest an exercise plan based on the user's goals. Furthermore, if the user has neglected to exercise, it can send a reminder to encourage the user to exercise. In this way, the care system can support the user's healthy exercise habits.

[0132] The care system may also include a sleep management unit that monitors the user's sleep state. The sleep management unit can record the user's sleep patterns and provide advice to promote high-quality sleep. For example, the sleep management unit can analyze the user's sleep time and the percentage of deep sleep and point out areas for improvement. The sleep management unit can also play relaxing music before bed to help the user relax and fall asleep. Furthermore, if the user wakes up in the middle of the night, the sleep management unit can provide advice to help the user fall asleep again. In this way, the care system can support the user's high-quality sleep.

[0133] The care system may also include a stress management unit that monitors the user's stress level. The stress management unit can analyze the user's heart rate and breathing pattern to estimate the stress level. For example, if the user's heart rate is high, the stress level is determined to be high and the linking unit is instructed to play relaxing music. The care system may also generate a message encouraging the user to take deep breaths. Furthermore, if the user is feeling stressed, the care system may provide advice on creating a relaxing environment. In this way, the care system can reduce the user's stress and support their mental health.

[0134] The care system can estimate the user's emotions and suggest appropriate exercises based on the estimated emotions. For example, if the user is feeling stressed, it can suggest relaxing yoga or deep breathing exercises. If the user wants to cheer up, it can suggest energetic dancing or jogging. Furthermore, if the user wants to concentrate, it can suggest meditation or mindfulness exercises. In this way, the care system can suggest exercises that correspond to the user's emotions and support the health of both mind and body.

[0135] The care system can estimate the user's emotions and suggest appropriate relaxation methods based on the estimated emotions. For example, if the user is tense, it can suggest playing relaxing music. If the user is sad, it can provide a positive message to lift the user's mood. Furthermore, if the user is tired, it can encourage the user to take a short break. In this way, the care system can suggest relaxation methods according to the user's emotions and support their mental health.

[0136] The care system can estimate the user's emotions and suggest appropriate meals based on the estimated emotions. For example, if the user is feeling stressed, it can suggest relaxing herbal tea or light meals. If the user wants to feel energized, it can suggest nutritious meals to replenish energy. Furthermore, if the user wants to concentrate, it can suggest meals to support brain function. In this way, the care system can suggest meals that correspond to the user's emotions and support the health of both mind and body.

[0137] The care system can estimate the user's emotions and suggest appropriate communication methods based on the estimated emotions. For example, if the user is angry, it can suggest taking a deep breath to calm down. If the user is sad, it can suggest talking to friends or family. Furthermore, if the user is happy, it can suggest ways to share that joy. In this way, the care system can suggest communication methods according to the user's emotions and support their mental health.

[0138] The care system can estimate the user's emotions and suggest appropriate hobbies and activities based on the estimated emotions. For example, if the user is feeling stressed, it can suggest relaxing reading or art. If the user wants to cheer up, it can suggest energetic sports or outdoor activities. Furthermore, if the user wants to concentrate, it can suggest activities that improve concentration, such as puzzles or arts and crafts. In this way, the care system can suggest hobbies and activities that correspond to the user's emotions and support their mental health.

[0139] The processing flow of the second embodiment will be briefly explained below.

[0140] Step 1: The speech recognition unit converts the user's speech into text using speech recognition technology, which includes deep learning-based speech recognition and HMM (Hidden Markov Model). The speech recognition unit converts the user's speech into text in real time and improves the accuracy of speech recognition by removing background noise using noise reduction technology. Step 2: The response generation unit uses a generation AI to generate a response based on the text converted by the speech recognition unit. The generation AI includes text generation AI (e.g., LLM) and multimodal generation AI, which analyzes the user's utterances and generates an appropriate response. For example, if the user says, "I'm tired today," the response generation unit generates a response such as, "Thank you for your hard work. What happened today?" The response generation unit can also analyze the user's emotions and generate a response that corresponds to those emotions. Step 3: The linking unit links with external services based on the response generated by the response generation unit. External services include services that play relaxing music and services that provide weather information. For example, if the user says, "I want to relax," the linking unit links with a service that plays relaxing music to provide the user with a relaxing environment. Also, if the user asks, "What's the weather like today?" the linking unit links with a service that provides weather information to provide the latest weather information.

[0141] 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.

[0142] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0143] 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.

[0144] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0145] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0159] 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.

[0160] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0161] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0171] In the 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.

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

[0173] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0175] The data processing system 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.

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

[0177] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0178] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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).

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0192] 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.

[0193] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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).

[0198] 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.

[0199] 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."

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] [Explanation of symbols]

[0213] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a speech recognition unit that converts user speech into text using speech recognition technology; a response generation unit that generates a response based on the text converted by the speech recognition unit; a linking unit that links with an external service based on the response generated by the response generating unit. A system characterized by:

2. The response generation unit Equipped with an emotion analysis unit that analyzes user emotions 2. The system of claim 1.

3. The linking unit is Equipped with a music playback unit that plays relaxing music 2. The system of claim 1.

4. The linking unit is A weather information providing unit is provided to provide weather information.

2. The system of claim 1.

5. The voice recognition unit Estimates user emotions and dynamically adjusts speech recognition accuracy based on the estimated user emotions.

2. The system of claim 1.

6. The voice recognition unit During speech recognition, background sounds of the user's speech are analyzed and noise is removed.

2. The system of claim 1.

7. The voice recognition unit During speech recognition, the speed and tone of the user's speech are analyzed to more accurately understand the intent of what is being said.

2. The system of claim 1.

8. The voice recognition unit During speech recognition, the accuracy of recognition is improved by referring to the user's past speech history.

2. The system of claim 1.

Images