System

Abstract

An object of a system according to an embodiment is to generate an appropriate response in communication with a senior.SOLUTION: A system includes an emotion analysis unit, a response generation unit, and a provision unit. The emotion analysis unit analyzes the speech of the senior. The response generation unit generates an appropriate response on the basis of the result analyzed by the emotion analysis unit. The providing unit provides the senior with the response generated by the response generating 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 making it difficult to generate appropriate responses when communicating with seniors.

[0005] The system according to the embodiment aims to generate appropriate responses in communication with seniors. [Means for solving the problem]

[0006] The system according to the embodiment includes a sentiment analysis unit, a response generation unit, and a provision unit. The sentiment analysis unit analyzes the senior's comments. The response generation unit generates an appropriate response based on the analysis results obtained by the sentiment analysis unit. The provision unit provides the senior with the response generated by the response generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can generate appropriate responses in communication with seniors. [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 communication system according to an embodiment of the present invention analyzes a senior's utterances and generates and provides an appropriate response. The communication system analyzes the senior's utterances, and a generation AI generates an appropriate response and provides it to the senior, thereby enabling natural conversation with the senior. For example, the communication system analyzes the content of the senior's utterance, and the generation AI generates a response based on that content. The generation AI can also generate a response taking the senior's emotions and intentions into consideration. For example, if a senior says, "The weather is nice today," the generation AI generates a response such as, "Yes, it's very nice today. Would you like to go for a walk?" If a senior says, "I've been feeling a little lonely lately," the generation AI generates a response such as, "That sounds lonely. Shall we think of something fun together?" Furthermore, the generation AI can learn the senior's past utterances and behavioral history to generate more personalized responses. For example, if a senior previously said, "I'm looking forward to my grandchildren coming to visit," the generation AI generates a response such as, "I'm looking forward to your grandchildren coming to visit. When are you planning on coming next?" This allows the communication system to allow seniors to enjoy natural conversations with the robot, contributing to reducing feelings of loneliness and maintaining cognitive function. The communication system can then analyze what the senior says and generate and provide appropriate responses, enabling natural conversations with seniors. For example, if seniors converse with a robot on a daily basis, this will increase opportunities for conversation and help maintain cognitive function. Furthermore, if the robot can understand the senior's emotions and intentions and generate appropriate responses, it will reduce the senior's feelings of loneliness. This is expected to improve the quality of life for seniors.

[0029] A communication system according to an embodiment includes an emotion analysis unit, a response generation unit, and a providing unit. The emotion analysis unit analyzes the senior's utterances. The senior's utterances include, but are not limited to, everyday conversations, questions, and impressions. The emotion analysis unit analyzes the senior's utterances using natural language processing technology. The emotion analysis unit can analyze not only the senior's utterance content but also their emotions and intentions. For example, the emotion analysis unit can analyze the senior's tone and facial expressions to infer their emotions. The response generation unit generates an appropriate response based on the analysis results by the emotion analysis unit. The response generation unit generates a response based on the senior's utterance content using, for example, a generation AI. The response generation unit can also generate a response based on the senior's health status and daily routine. For example, the response generation unit generates a response taking into account the senior's vital signs and daily activities. Furthermore, the response generation unit can learn the senior's past utterances and behavioral history to generate personalized responses. For example, the response generation unit generates a response on a related topic based on the senior's past utterances. The providing unit provides the response generated by the response generating unit to the senior. The providing unit provides the response audibly, for example, using an audio output device. The providing unit can also display the response in text using a display. Furthermore, the providing unit can estimate the senior's emotions and adjust the way the response is provided based on the estimated senior's emotions. For example, if the senior is sad, the providing unit provides the response in a gentle tone. In this way, the communication system according to the embodiment can realize a natural conversation with the senior by analyzing the senior's utterances and generating and providing an appropriate response.

[0030] The emotion analysis unit can analyze not only the content of the senior's speech but also their emotions and intentions. The emotion analysis unit, for example, analyzes the content of the senior's speech using natural language processing technology. For example, the emotion analysis unit analyzes the tone and facial expressions of the senior's speech to estimate their emotions. The emotion analysis unit can also analyze emotions by taking into account background information of the senior's speech. For example, if the senior is outdoors, the emotion analysis unit analyzes environmental sounds and background noise and reflects this in the estimation of their emotions. Furthermore, if the senior is speaking during a specific event, the emotion analysis unit can analyze their emotions by taking into account the content of the event. This allows for the generation of a more appropriate response by analyzing the senior's emotions and intentions. Some or all of the above-described processing in the emotion analysis unit may be performed using, or without, a generation AI. For example, the emotion analysis unit can input the content of the senior's speech into a generation AI and have the generation AI analyze their emotions and intentions.

[0031] The response generation unit can generate a response based on the senior's health condition and daily routine. The response generation unit can generate a response by taking into account, for example, the senior's vital signs and daily activities. For example, the response generation unit can analyze the senior's heart rate and blood pressure to generate a response based on the senior's health condition. The response generation unit can also generate a response by taking into account the senior's daily routine. For example, the response generation unit can generate a response at an appropriate time based on the senior's daily schedule. Furthermore, the response generation unit can adjust the content of the response based on the senior's health condition and daily routine. For example, if the senior is in good health, the response generation unit can generate a response suggesting active activities. This allows for the provision of a more personalized response by generating a response based on the senior's health condition and daily routine. Some or all of the above-described processing in the response generation unit can be performed using, or without, a generation AI. For example, the response generation unit can input the senior's health data into the generation AI and have the generation AI generate a response.

[0032] The response generation unit can learn the senior's past utterances and behavioral history and generate personalized responses. The response generation unit, for example, generates a response on a related topic based on the senior's past utterances. For example, the response generation unit learns what the senior has previously said and generates a response on a related topic. The response generation unit can also learn the senior's past behavioral history and generate personalized responses. For example, the response generation unit generates a response that suggests an appropriate activity based on the senior's past behavioral history. Furthermore, the response generation unit can comprehensively analyze the senior's past utterances and behavioral history and generate personalized responses. For example, the response generation unit generates a response based on the senior's past utterances and behavioral history. In this way, by learning the senior's past utterances and behavioral history, it is possible to provide more personalized responses. Some or all of the above-described processing in the response generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the response generation unit can input the senior's past utterances and behavioral history into the generation AI and cause the generation AI to generate a personalized response.

[0033] The providing unit can provide the generated response to the senior. The providing unit can provide the response audibly using, for example, an audio output device. For example, the providing unit can provide the generated response audibly to the senior using a speaker. The providing unit can also display the response in text using a display. For example, the providing unit can display the generated response in text on a display and provide it to the senior. The providing unit can also estimate the senior's emotions and adjust the way the response is provided based on the estimated senior's emotions. For example, if the senior is sad, the providing unit can provide a response in a gentle tone. This makes it possible to provide the generated response to the senior and realize a natural conversation with the senior. Some or all of the above-described processing in the providing unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the providing unit can input the generated response to the generation AI and cause the generation AI to adjust the way the response is provided.

[0034] The emotion analysis unit can analyze the senior's past speech history and improve the emotion analysis algorithm. The emotion analysis unit, for example, analyzes the senior's past speech history and adjusts the emotion analysis algorithm. For example, the emotion analysis unit analyzes expressions and words frequently used by the senior in the past and adjusts the emotion analysis algorithm. The emotion analysis unit can also learn patterns of specific emotions from the senior's past speech history and optimize the algorithm. Furthermore, the emotion analysis unit can track changes in emotions based on the senior's past speech history and dynamically adjust the algorithm. By analyzing the senior's past speech history, the emotion analysis algorithm can be optimized and the analysis accuracy can be improved. Some or all of the above-described processing in the emotion analysis unit can be performed using, or without, a generation AI. For example, the emotion analysis unit can input the senior's past speech history into the generation AI and have the generation AI improve the emotion analysis algorithm.

[0035] The emotion analysis unit can analyze not only the content of a senior's speech but also their voice tone and facial expression to more accurately estimate their emotions. For example, the emotion analysis unit can analyze the content of a senior's speech and their voice tone to estimate the intensity of their emotions. For example, the emotion analysis unit can analyze the content of a senior's speech and their voice tone to estimate the intensity of their emotions. The emotion analysis unit can also analyze the content of a senior's speech and their facial expression to identify the type of emotion. Furthermore, the emotion analysis unit can comprehensively analyze the content of a senior's speech, voice tone, and facial expression to estimate their detailed emotional state. This allows for more accurate emotion estimation by analyzing not only the content of a senior's speech but also their voice tone and facial expression. Some or all of the above-described processing in the emotion analysis unit can be performed using, or without, a generation AI. For example, the emotion analysis unit can input the senior's voice data and facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0036] The emotion analysis unit can analyze emotions based on background information of the senior's utterances. The emotion analysis unit, for example, analyzes emotions by taking into account the background information of the senior's utterances. For example, if the senior is outdoors, the emotion analysis unit analyzes environmental sounds and background noise and reflects this in estimating the senior's emotion. Furthermore, if the senior is uttering during a specific event, the emotion analysis unit can also analyze emotions by taking into account the content of the event. Furthermore, if the senior is uttering during a specific time period, the emotion analysis unit can also analyze emotions by taking into account the general emotional trends of that time period. This enables more accurate emotion analysis by taking into account the background information of the senior's utterances. Some or all of the above-described processing in the emotion analysis unit may be performed using, or without, a generation AI. For example, the emotion analysis unit can input background information of the senior's utterances into the generation AI and have the generation AI perform emotion analysis.

[0037] The emotion analysis unit can infer emotions by analyzing not only the content of what the senior says but also their body movements and posture. For example, the emotion analysis unit can analyze the content of what the senior says and their body movements to infer the intensity of their emotions. For example, the emotion analysis unit can analyze the content of what the senior says and their body movements to infer the intensity of their emotions. The emotion analysis unit can also identify the type of emotion by analyzing the content of what the senior says and their posture. Furthermore, the emotion analysis unit can comprehensively analyze the content of what the senior says, their body movements, and their posture to infer their detailed emotional state. This allows for more accurate emotion estimation by analyzing their body movements and posture in addition to the content of what the senior says. Some or all of the above-described processing in the emotion analysis unit may be performed using, or without, a generation AI. For example, the emotion analysis unit can input data on the body movements and posture of the senior into the generation AI and have the generation AI perform emotion estimation.

[0038] The emotion analysis unit can analyze emotions based on the content of a senior's comments by referring to related past comments and actions. For example, the emotion analysis unit compares the content of a senior's comments with past comments and analyzes changes in emotions. For example, the emotion analysis unit compares the content of a senior's comments with past comments and analyzes changes in emotions. The emotion analysis unit can also analyze emotional trends by referring to the content of a senior's comments and past actions. Furthermore, the emotion analysis unit can comprehensively analyze the content of a senior's comments and past comments and actions to estimate a detailed emotional state. This enables more accurate emotion analysis by referring to related past comments and actions based on the content of a senior's comments. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, or without, a generation AI. For example, the emotion analysis unit can input data on the senior's past comments and actions into the generation AI and have the generation AI perform emotion analysis.

[0039] The emotion analysis unit can analyze the senior's health data in addition to the content of the senior's remarks to infer their emotions. The emotion analysis unit, for example, analyzes the senior's remarks and heart rate to infer the intensity of their emotions. For example, the emotion analysis unit analyzes the senior's remarks and heart rate to infer the intensity of their emotions. The emotion analysis unit can also analyze the senior's remarks and blood pressure to identify the type of emotion. Furthermore, the emotion analysis unit can comprehensively analyze the senior's remarks, heart rate, and blood pressure to infer their detailed emotional state. This allows for more accurate emotion estimation by analyzing the senior's health data in addition to the content of the senior's remarks. Some or all of the above-described processing in the emotion analysis unit may be performed using, or without, a generation AI. For example, the emotion analysis unit can input the senior's health data into the generation AI and have the generation AI perform emotion estimation.

[0040] When generating a response, the response generation unit can adjust the content of the response based on the senior's health condition and daily routine. The response generation unit adjusts the content of the response based on, for example, the senior's health condition and daily routine. For example, if the senior is in good health, the response generation unit generates a response suggesting active activity. Also, if the senior is in poor health, the response generation unit can generate a response suggesting rest. Furthermore, the response generation unit can generate a response at an appropriate time based on the senior's daily routine. This makes it possible to provide a more appropriate response by adjusting the content of the response based on the senior's health condition and daily routine. Some or all of the above-described processing in the response generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the response generation unit can input the senior's health data and daily routine data into the generation AI and have the generation AI adjust the content of the response.

[0041] When generating a response, the response generation unit can generate a personalized response by referring to the senior's past utterances and behavioral history. The response generation unit, for example, generates a response on a related topic based on the senior's past utterances. For example, the response generation unit generates a response on a related topic based on what the senior has said in the past. The response generation unit can also generate a personalized response by referring to the senior's past behavioral history. For example, the response generation unit generates a response that suggests an appropriate activity based on the senior's past behavioral history. Furthermore, the response generation unit can generate a personalized response by comprehensively analyzing the senior's past utterances and behavioral history. For example, the response generation unit generates a response based on the senior's past utterances and behavioral history based on the senior's past utterances and behavioral history. In this way, by referring to the senior's past utterances and behavioral history, a more personalized response can be provided. Some or all of the above-described processing in the response generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the response generation unit can input the senior's past utterances and behavioral history into the generation AI and cause the generation AI to generate a personalized response.

[0042] When generating a response, the response generation unit can adjust the content of the response based on the senior's current environment and situation. The response generation unit generates a response, for example, taking into account the senior's current environment and situation. For example, if the senior is outdoors, the response generation unit generates a response appropriate to that environment. Also, if the senior is attending a specific event, the response generation unit can generate a response related to that event. Furthermore, if the senior is in a specific time period, the response generation unit can generate a response appropriate to that time period. This makes it possible to provide a more appropriate response by taking into account the senior's current environment and situation. Some or all of the above-described processing in the response generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the response generation unit may input data on the senior's current environment and situation into the generation AI and have the generation AI adjust the content of the response.

[0043] When generating a response, the response generation unit can provide related information based on the content of the senior's utterance. The response generation unit provides related information based on, for example, the content of the senior's utterance. For example, if the senior is talking about a specific topic, the response generation unit provides information related to that topic. Furthermore, if the senior asks a question, the response generation unit can provide detailed information in response to the question. Furthermore, the response generation unit can provide additional information about a topic in which the senior is interested. This makes it possible to provide a more appropriate response by providing related information based on the content of the senior's utterance. Some or all of the above-described processing in the response generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the response generation unit can input the content of the senior's utterance into the generation AI and cause the generation AI to provide related information.

[0044] When generating a response, the response generation unit can suggest the next conversation topic based on the content of the senior's utterance. The response generation unit, for example, suggests the next conversation topic based on the content of the senior's utterance. For example, if the senior is talking about a specific topic, the response generation unit can suggest the next topic related to that topic. Also, if the senior asks a question, the response generation unit can suggest the next topic related to the question. Furthermore, the response generation unit can suggest the next conversation topic for a topic in which the senior has shown interest. In this way, by suggesting the next conversation topic based on the content of the senior's utterance, the conversation can flow smoothly. Some or all of the above-mentioned processing in the response generation unit may be performed using, or without, a generation AI. For example, the response generation unit can input the content of the senior's utterance into the generation AI and cause the generation AI to suggest the next conversation topic.

[0045] When generating a response, the response generation unit can suggest an appropriate action based on the content of the senior's utterance. The response generation unit suggests an appropriate action based on, for example, the content of the senior's utterance. For example, if the senior says that they want to listen to music, the response generation unit can suggest appropriate music. Also, if the senior talks about the brightness of the room, the response generation unit can suggest adjusting the lighting. Furthermore, if the senior talks about a specific activity, the response generation unit can suggest an action related to that activity. In this way, by suggesting an appropriate action based on the content of the senior's utterance, it is possible to support the senior's life. Some or all of the above-mentioned processing in the response generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the response generation unit can input the content of the senior's utterance into the generation AI and have the generation AI execute the suggestion of an appropriate action.

[0046] When providing a response, the providing unit can select an appropriate delivery method by referring to the senior's past response history. The providing unit, for example, selects an appropriate delivery method by referring to the senior's past response history. For example, the providing unit selects the optimal delivery method based on the senior's preferred response methods in the past. The providing unit can also select a delivery method appropriate for a specific situation from the senior's past response history. Furthermore, the providing unit can comprehensively analyze the senior's past response history and select the optimal delivery method. In this way, by referring to the senior's past response history, the optimal delivery method can be selected and the quality of the response can be improved. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the providing unit can input the senior's past response history into the generation AI and cause the generation AI to select an appropriate delivery method.

[0047] When providing a response, the providing unit can customize the content to be provided according to the senior's current activity and situation. The providing unit customizes the content to be provided according to, for example, the senior's current activity and situation. For example, if the senior is outdoors, the providing unit can provide a response appropriate to the environment. Furthermore, if the senior is attending a specific event, the providing unit can provide a response related to the event. Furthermore, if the senior is attending a specific time period, the providing unit can provide a response appropriate to that time period. In this way, by customizing the content to be provided according to the senior's current activity and situation, a more appropriate response can be provided. Some or all of the above-described processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input data on the senior's current activity and situation into the generation AI and cause the generation AI to customize the content to be provided.

[0048] The providing unit can improve the response delivery method by reflecting the senior's feedback when providing a response. The providing unit, for example, improves the response delivery method by reflecting the senior's feedback. For example, if the senior provides positive feedback on the response, the providing unit continues the response delivery method. In addition, if the senior provides negative feedback on the response, the providing unit can change the response delivery method. Furthermore, the providing unit can comprehensively analyze the senior's feedback and find the optimal response delivery method. In this way, by reflecting the senior's feedback, the response delivery method can be improved and the quality of the response can be improved. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the providing unit can input the senior's feedback data into the generation AI and cause the generation AI to improve the response delivery method.

[0049] When providing a response, the providing unit can select the optimal delivery method by taking into account the senior's device information. The providing unit selects the optimal delivery method by taking into account, for example, the senior's device information. For example, if the senior is using a smartphone, the providing unit can provide a response optimized for that device. Furthermore, if the senior is using a tablet, the providing unit can provide a response optimized for a large screen. Furthermore, if the senior is using a smartwatch, the providing unit can provide a concise and highly visible response. This makes it possible to select the optimal delivery method by taking into account the senior's device information and improve the quality of the response. Some or all of the above-described processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input the senior's device information into the generation AI and cause the generation AI to select the optimal delivery method.

[0050] When providing a response, the providing unit can make the provided content multilingual according to the senior's language setting. The providing unit, for example, makes the provided content multilingual according to the senior's language setting. For example, the providing unit provides a response in a language based on the language setting of the senior's device. The providing unit can also provide a language switching function if the senior speaks multiple languages. Furthermore, if the senior selects a specific language, the providing unit can provide a response in that language. This makes it possible to provide a more appropriate response by making the provided content multilingual according to the senior's language setting. Some or all of the above-described processing by the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the senior's language setting data into the generation AI and cause the generation AI to execute the multilingual provided content.

[0051] When providing a response, the providing unit can adjust the response method according to the senior's visual or hearing condition. The providing unit adjusts the response method according to, for example, the senior's visual or hearing condition. For example, if the senior has visual problems, the providing unit provides a response by voice. Also, if the senior has hearing problems, the providing unit can provide a response by text. Furthermore, the providing unit can select the optimal response method by comprehensively considering the senior's visual or hearing condition. This makes it possible to provide a more appropriate response by adjusting the response method according to the senior's visual or hearing condition. Some or all of the above-mentioned processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input data on the senior's visual or hearing condition into the generation AI and have the generation AI adjust the response method.

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

[0053] The communication system can further include a topic suggestion unit that suggests conversation topics based on the senior's hobbies and interests. For example, if the senior is interested in gardening, the topic suggestion unit can suggest topics about seasonal flowers and how to grow plants. If the senior likes music, the topic suggestion unit can suggest topics about the latest music news or the senior's favorite artists. Furthermore, if the senior is interested in traveling, the topic suggestion unit can suggest topics about recommended travel spots and travel plans. This allows for richer communication with seniors by providing conversations based on the senior's hobbies and interests.

[0054] The communication system can further include a health monitoring unit that monitors the senior's health data and issues an alert if an abnormality is detected. For example, if the senior's heart rate suddenly rises, the health monitoring unit can issue an alert and encourage the senior to rest. If the senior's blood pressure is abnormally high, the health monitoring unit can also suggest contacting a medical institution. Furthermore, if the senior's activity level is extremely low, the health monitoring unit can issue an alert encouraging them to exercise. This makes it possible to monitor the senior's health status in real time and encourage appropriate measures.

[0055] The communication system may further include a contact support unit to support communication between the senior and family and friends. For example, if the senior wants to contact their family, the contact support unit may provide a function to easily start a video call. If the senior wants to send a message to a friend, the contact support unit may allow the senior to create and send the message using voice input. Furthermore, if the senior wants to attend a specific event, the contact support unit may provide details of the event and assist with the participation procedure. This makes it easier for the senior to maintain connections with family and friends.

[0056] The communication system can also be equipped with a rhythm management unit to support the senior's daily rhythm. For example, it can set a reminder for the senior to wake up at the same time every day. It can also set a reminder for the senior to eat meals regularly. It can also set a reminder for the senior to go to bed at an appropriate time. This helps to regulate the senior's daily rhythm and support a healthy lifestyle.

[0057] The communication system can also be equipped with a safety monitoring unit to ensure the safety of seniors. For example, if a senior falls, the safety monitoring unit will automatically issue an alert and notify emergency contacts. If the senior remains motionless for a long period of time, the safety monitoring unit can issue an alert to check the senior's condition. It can also suggest safe routes for seniors when they go out. This ensures the safety of seniors and provides an environment where they can live with peace of mind.

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

[0059] Step 1: The emotion analysis unit analyzes the senior's comments. These include everyday conversations, questions, and impressions. The emotion analysis unit uses natural language processing technology to analyze the content of the comments, and further analyzes the tone and facial expressions of the comments to infer emotions and intentions. Step 2: The response generation unit generates an appropriate response based on the results of the analysis by the sentiment analysis unit. The response generation unit uses generative AI to generate a response based on the senior's comments, taking into account the senior's health condition, daily routine, past comments and behavioral history to generate a personalized response. Step 3: The providing unit provides the response generated by the response generating unit to the senior. The providing unit can provide the response by voice using the audio output device or by text using the display. The providing unit also estimates the senior's emotions and adjusts the way the response is provided based on the estimated emotions.

[0060] (Example 2) A communication system according to an embodiment of the present invention analyzes a senior's utterances and generates and provides an appropriate response. The communication system analyzes the senior's utterances, and a generation AI generates an appropriate response and provides it to the senior, thereby enabling natural conversation with the senior. For example, the communication system analyzes the content of the senior's utterance, and the generation AI generates a response based on that content. The generation AI can also generate a response taking the senior's emotions and intentions into consideration. For example, if a senior says, "The weather is nice today," the generation AI generates a response such as, "Yes, it's very nice today. Would you like to go for a walk?" If a senior says, "I've been feeling a little lonely lately," the generation AI generates a response such as, "That sounds lonely. Shall we think of something fun together?" Furthermore, the generation AI can learn the senior's past utterances and behavioral history to generate more personalized responses. For example, if a senior previously said, "I'm looking forward to my grandchildren coming to visit," the generation AI generates a response such as, "I'm looking forward to your grandchildren coming to visit. When are you planning on coming next?" This allows the communication system to allow seniors to enjoy natural conversations with the robot, contributing to reducing feelings of loneliness and maintaining cognitive function. The communication system can then analyze what the senior says and generate and provide appropriate responses, enabling natural conversations with seniors. For example, if seniors converse with a robot on a daily basis, this will increase opportunities for conversation and help maintain cognitive function. Furthermore, if the robot can understand the senior's emotions and intentions and generate appropriate responses, it will reduce the senior's feelings of loneliness. This is expected to improve the quality of life for seniors.

[0061] A communication system according to an embodiment includes an emotion analysis unit, a response generation unit, and a providing unit. The emotion analysis unit analyzes the senior's utterances. The senior's utterances include, but are not limited to, everyday conversations, questions, and impressions. The emotion analysis unit analyzes the senior's utterances using natural language processing technology. The emotion analysis unit can analyze not only the senior's utterance content but also their emotions and intentions. For example, the emotion analysis unit can analyze the senior's tone and facial expressions to infer their emotions. The response generation unit generates an appropriate response based on the analysis results by the emotion analysis unit. The response generation unit generates a response based on the senior's utterance content using, for example, a generation AI. The response generation unit can also generate a response based on the senior's health status and daily routine. For example, the response generation unit generates a response taking into account the senior's vital signs and daily activities. Furthermore, the response generation unit can learn the senior's past utterances and behavioral history to generate personalized responses. For example, the response generation unit generates a response on a related topic based on the senior's past utterances. The providing unit provides the response generated by the response generating unit to the senior. The providing unit provides the response audibly, for example, using an audio output device. The providing unit can also display the response in text using a display. Furthermore, the providing unit can estimate the senior's emotions and adjust the way the response is provided based on the estimated senior's emotions. For example, if the senior is sad, the providing unit provides the response in a gentle tone. In this way, the communication system according to the embodiment can realize a natural conversation with the senior by analyzing the senior's utterances and generating and providing an appropriate response.

[0062] The emotion analysis unit can analyze not only the content of the senior's speech but also their emotions and intentions. The emotion analysis unit, for example, analyzes the content of the senior's speech using natural language processing technology. For example, the emotion analysis unit analyzes the tone and facial expressions of the senior's speech to estimate their emotions. The emotion analysis unit can also analyze emotions by taking into account background information of the senior's speech. For example, if the senior is outdoors, the emotion analysis unit analyzes environmental sounds and background noise and reflects this in the estimation of their emotions. Furthermore, if the senior is speaking during a specific event, the emotion analysis unit can analyze their emotions by taking into account the content of the event. This allows for the generation of a more appropriate response by analyzing the senior's emotions and intentions. Some or all of the above-described processing in the emotion analysis unit may be performed using, or without, a generation AI. For example, the emotion analysis unit can input the content of the senior's speech into a generation AI and have the generation AI analyze their emotions and intentions.

[0063] The response generation unit can generate a response based on the senior's health condition and daily routine. The response generation unit can generate a response by taking into account, for example, the senior's vital signs and daily activities. For example, the response generation unit can analyze the senior's heart rate and blood pressure to generate a response based on the senior's health condition. The response generation unit can also generate a response by taking into account the senior's daily routine. For example, the response generation unit can generate a response at an appropriate time based on the senior's daily schedule. Furthermore, the response generation unit can adjust the content of the response based on the senior's health condition and daily routine. For example, if the senior is in good health, the response generation unit can generate a response suggesting active activities. This allows for the provision of a more personalized response by generating a response based on the senior's health condition and daily routine. Some or all of the above-described processing in the response generation unit can be performed using, or without, a generation AI. For example, the response generation unit can input the senior's health data into the generation AI and have the generation AI generate a response.

[0064] The response generation unit can learn the senior's past utterances and behavioral history and generate personalized responses. The response generation unit, for example, generates a response on a related topic based on the senior's past utterances. For example, the response generation unit learns what the senior has previously said and generates a response on a related topic. The response generation unit can also learn the senior's past behavioral history and generate personalized responses. For example, the response generation unit generates a response that suggests an appropriate activity based on the senior's past behavioral history. Furthermore, the response generation unit can comprehensively analyze the senior's past utterances and behavioral history and generate personalized responses. For example, the response generation unit generates a response based on the senior's past utterances and behavioral history. In this way, by learning the senior's past utterances and behavioral history, it is possible to provide more personalized responses. Some or all of the above-described processing in the response generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the response generation unit can input the senior's past utterances and behavioral history into the generation AI and cause the generation AI to generate a personalized response.

[0065] The providing unit can provide the generated response to the senior. The providing unit can provide the response audibly using, for example, an audio output device. For example, the providing unit can provide the generated response audibly to the senior using a speaker. The providing unit can also display the response in text using a display. For example, the providing unit can display the generated response in text on a display and provide it to the senior. The providing unit can also estimate the senior's emotions and adjust the way the response is provided based on the estimated senior's emotions. For example, if the senior is sad, the providing unit can provide a response in a gentle tone. This makes it possible to provide the generated response to the senior and realize a natural conversation with the senior. Some or all of the above-described processing in the providing unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the providing unit can input the generated response to the generation AI and cause the generation AI to adjust the way the response is provided.

[0066] The emotion analysis unit can estimate the senior's emotions and adjust the analysis accuracy of the utterances based on the estimated emotions. The emotion analysis unit, for example, estimates the senior's emotions and adjusts the analysis accuracy of the utterances based on the estimated emotions. For example, if the senior is sad, the emotion analysis unit analyzes the tone and content of the utterances more carefully. Furthermore, if the senior is excited, the emotion analysis unit can adjust the analysis accuracy by taking into account the speed and emphasis of the utterances. Furthermore, if the senior is tired, the emotion analysis unit can adjust the analysis accuracy by emphasizing the conciseness and clarity of the utterances. This enables more accurate analysis by adjusting the analysis accuracy of the utterances based on the senior's emotions. Some or all of the above-described processing in the emotion analysis unit may be performed using, or without, a generation AI. For example, the emotion analysis unit can input the senior's emotion data into the generation AI and have the generation AI adjust the analysis accuracy of the utterances.

[0067] The emotion analysis unit can analyze the senior's past speech history and improve the emotion analysis algorithm. The emotion analysis unit, for example, analyzes the senior's past speech history and adjusts the emotion analysis algorithm. For example, the emotion analysis unit analyzes expressions and words frequently used by the senior in the past and adjusts the emotion analysis algorithm. The emotion analysis unit can also learn patterns of specific emotions from the senior's past speech history and optimize the algorithm. Furthermore, the emotion analysis unit can track changes in emotions based on the senior's past speech history and dynamically adjust the algorithm. By analyzing the senior's past speech history, the emotion analysis algorithm can be optimized and the analysis accuracy can be improved. Some or all of the above-described processing in the emotion analysis unit can be performed using, or without, a generation AI. For example, the emotion analysis unit can input the senior's past speech history into the generation AI and have the generation AI improve the emotion analysis algorithm.

[0068] The emotion analysis unit can analyze not only the content of a senior's speech but also their voice tone and facial expression to more accurately estimate their emotions. For example, the emotion analysis unit can analyze the content of a senior's speech and their voice tone to estimate the intensity of their emotions. For example, the emotion analysis unit can analyze the content of a senior's speech and their voice tone to estimate the intensity of their emotions. The emotion analysis unit can also analyze the content of a senior's speech and their facial expression to identify the type of emotion. Furthermore, the emotion analysis unit can comprehensively analyze the content of a senior's speech, voice tone, and facial expression to estimate their detailed emotional state. This allows for more accurate emotion estimation by analyzing not only the content of a senior's speech but also their voice tone and facial expression. Some or all of the above-described processing in the emotion analysis unit can be performed using, or without, a generation AI. For example, the emotion analysis unit can input the senior's voice data and facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0069] The emotion analysis unit can analyze emotions based on background information of the senior's utterances. The emotion analysis unit, for example, analyzes emotions by taking into account the background information of the senior's utterances. For example, if the senior is outdoors, the emotion analysis unit analyzes environmental sounds and background noise and reflects this in estimating the senior's emotion. Furthermore, if the senior is uttering during a specific event, the emotion analysis unit can also analyze emotions by taking into account the content of the event. Furthermore, if the senior is uttering during a specific time period, the emotion analysis unit can also analyze emotions by taking into account the general emotional trends of that time period. This enables more accurate emotion analysis by taking into account the background information of the senior's utterances. Some or all of the above-described processing in the emotion analysis unit may be performed using, or without, a generation AI. For example, the emotion analysis unit can input background information of the senior's utterances into the generation AI and have the generation AI perform emotion analysis.

[0070] The emotion analysis unit can estimate the emotions of seniors and prioritize the analysis results based on the estimated emotions of seniors. The emotion analysis unit, for example, estimates the emotions of seniors and prioritizes the analysis results based on the estimated emotions of seniors. For example, if a senior expresses a strong emotion, the emotion analysis unit prioritizes analysis of utterances related to that emotion. Furthermore, if a senior expresses multiple emotions, the emotion analysis unit can also prioritize analysis results based on the strongest emotion. Furthermore, if a senior expresses a specific emotion, the emotion analysis unit can prioritize analysis of past utterances related to that emotion. Thus, by prioritizing the analysis results based on the emotions of seniors, important analysis results can be processed preferentially. Some or all of the above-described processing in the emotion analysis unit may be performed using, or without, a generation AI. For example, the emotion analysis unit can input the emotion data of seniors into the generation AI and have the generation AI determine the priority of the analysis results.

[0071] The emotion analysis unit can infer emotions by analyzing not only the content of what the senior says but also their body movements and posture. For example, the emotion analysis unit can analyze the content of what the senior says and their body movements to infer the intensity of their emotions. For example, the emotion analysis unit can analyze the content of what the senior says and their body movements to infer the intensity of their emotions. The emotion analysis unit can also identify the type of emotion by analyzing the content of what the senior says and their posture. Furthermore, the emotion analysis unit can comprehensively analyze the content of what the senior says, their body movements, and their posture to infer their detailed emotional state. This allows for more accurate emotion estimation by analyzing their body movements and posture in addition to the content of what the senior says. Some or all of the above-described processing in the emotion analysis unit may be performed using, or without, a generation AI. For example, the emotion analysis unit can input data on the body movements and posture of the senior into the generation AI and have the generation AI perform emotion estimation.

[0072] The emotion analysis unit can analyze emotions based on the content of a senior's comments by referring to related past comments and actions. For example, the emotion analysis unit compares the content of a senior's comments with past comments and analyzes changes in emotions. For example, the emotion analysis unit compares the content of a senior's comments with past comments and analyzes changes in emotions. The emotion analysis unit can also analyze emotional trends by referring to the content of a senior's comments and past actions. Furthermore, the emotion analysis unit can comprehensively analyze the content of a senior's comments and past comments and actions to estimate a detailed emotional state. This enables more accurate emotion analysis by referring to related past comments and actions based on the content of a senior's comments. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, or without, a generation AI. For example, the emotion analysis unit can input data on the senior's past comments and actions into the generation AI and have the generation AI perform emotion analysis.

[0073] The emotion analysis unit can analyze the senior's health data in addition to the content of the senior's remarks to infer their emotions. The emotion analysis unit, for example, analyzes the senior's remarks and heart rate to infer the intensity of their emotions. For example, the emotion analysis unit analyzes the senior's remarks and heart rate to infer the intensity of their emotions. The emotion analysis unit can also analyze the senior's remarks and blood pressure to identify the type of emotion. Furthermore, the emotion analysis unit can comprehensively analyze the senior's remarks, heart rate, and blood pressure to infer their detailed emotional state. This allows for more accurate emotion estimation by analyzing the senior's health data in addition to the content of the senior's remarks. Some or all of the above-described processing in the emotion analysis unit may be performed using, or without, a generation AI. For example, the emotion analysis unit can input the senior's health data into the generation AI and have the generation AI perform emotion estimation.

[0074] The response generation unit can estimate the senior's emotions and adjust the way a response is expressed based on the estimated senior's emotions. The response generation unit, for example, estimates the senior's emotions and adjusts the way a response is expressed based on the estimated senior's emotions. For example, if the senior is sad, the response generation unit can generate a response in a gentle tone. If the senior is excited, the response generation unit can also generate a response in a lively tone. Furthermore, if the senior is tired, the response generation unit can also generate a response in a calm tone. This allows a more appropriate response to be provided by adjusting the way a response is expressed based on the senior's emotions. Some or all of the above-described processing in the response generation unit may be performed using, or without, a generation AI. For example, the response generation unit can input the senior's emotion data into the generation AI and cause the generation AI to adjust the way a response is expressed.

[0075] When generating a response, the response generation unit can adjust the content of the response based on the senior's health condition and daily routine. The response generation unit adjusts the content of the response based on, for example, the senior's health condition and daily routine. For example, if the senior is in good health, the response generation unit generates a response suggesting active activity. Also, if the senior is in poor health, the response generation unit can generate a response suggesting rest. Furthermore, the response generation unit can generate a response at an appropriate time based on the senior's daily routine. This makes it possible to provide a more appropriate response by adjusting the content of the response based on the senior's health condition and daily routine. Some or all of the above-described processing in the response generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the response generation unit can input the senior's health data and daily routine data into the generation AI and have the generation AI adjust the content of the response.

[0076] When generating a response, the response generation unit can generate a personalized response by referring to the senior's past utterances and behavioral history. The response generation unit, for example, generates a response on a related topic based on the senior's past utterances. For example, the response generation unit generates a response on a related topic based on what the senior has said in the past. The response generation unit can also generate a personalized response by referring to the senior's past behavioral history. For example, the response generation unit generates a response that suggests an appropriate activity based on the senior's past behavioral history. Furthermore, the response generation unit can generate a personalized response by comprehensively analyzing the senior's past utterances and behavioral history. For example, the response generation unit generates a response based on the senior's past utterances and behavioral history based on the senior's past utterances and behavioral history. In this way, by referring to the senior's past utterances and behavioral history, a more personalized response can be provided. Some or all of the above-described processing in the response generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the response generation unit can input the senior's past utterances and behavioral history into the generation AI and cause the generation AI to generate a personalized response.

[0077] When generating a response, the response generation unit can adjust the content of the response based on the senior's current environment and situation. The response generation unit generates a response, for example, taking into account the senior's current environment and situation. For example, if the senior is outdoors, the response generation unit generates a response appropriate to that environment. Also, if the senior is attending a specific event, the response generation unit can generate a response related to that event. Furthermore, if the senior is in a specific time period, the response generation unit can generate a response appropriate to that time period. This makes it possible to provide a more appropriate response by taking into account the senior's current environment and situation. Some or all of the above-described processing in the response generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the response generation unit may input data on the senior's current environment and situation into the generation AI and have the generation AI adjust the content of the response.

[0078] The response generation unit can estimate the senior's emotions and adjust the length of the response based on the estimated senior's emotions. The response generation unit, for example, estimates the senior's emotions and adjusts the length of the response based on the estimated senior's emotions. For example, if the senior is in a hurry, the response generation unit generates a short, to-the-point response. Also, if the senior is relaxed, the response generation unit can generate a longer response including detailed explanations. Furthermore, if the senior is excited, the response generation unit can generate a response with a visually stimulating effect. This allows for a more appropriate response to be provided by adjusting the length of the response based on the senior's emotions. Some or all of the above-described processing in the response generation unit may be performed using, or without, a generation AI. For example, the response generation unit can input the senior's emotion data into the generation AI and have the generation AI adjust the length of the response.

[0079] When generating a response, the response generation unit can provide related information based on the content of the senior's utterance. The response generation unit provides related information based on, for example, the content of the senior's utterance. For example, if the senior is talking about a specific topic, the response generation unit provides information related to that topic. Furthermore, if the senior asks a question, the response generation unit can provide detailed information in response to the question. Furthermore, the response generation unit can provide additional information about a topic in which the senior is interested. This makes it possible to provide a more appropriate response by providing related information based on the content of the senior's utterance. Some or all of the above-described processing in the response generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the response generation unit can input the content of the senior's utterance into the generation AI and cause the generation AI to provide related information.

[0080] When generating a response, the response generation unit can suggest the next conversation topic based on the content of the senior's utterance. The response generation unit, for example, suggests the next conversation topic based on the content of the senior's utterance. For example, if the senior is talking about a specific topic, the response generation unit can suggest the next topic related to that topic. Also, if the senior asks a question, the response generation unit can suggest the next topic related to the question. Furthermore, the response generation unit can suggest the next conversation topic for a topic in which the senior has shown interest. In this way, by suggesting the next conversation topic based on the content of the senior's utterance, the conversation can flow smoothly. Some or all of the above-mentioned processing in the response generation unit may be performed using, or without, a generation AI. For example, the response generation unit can input the content of the senior's utterance into the generation AI and cause the generation AI to suggest the next conversation topic.

[0081] When generating a response, the response generation unit can suggest an appropriate action based on the content of the senior's utterance. The response generation unit suggests an appropriate action based on, for example, the content of the senior's utterance. For example, if the senior says that they want to listen to music, the response generation unit can suggest appropriate music. Also, if the senior talks about the brightness of the room, the response generation unit can suggest adjusting the lighting. Furthermore, if the senior talks about a specific activity, the response generation unit can suggest an action related to that activity. In this way, by suggesting an appropriate action based on the content of the senior's utterance, it is possible to support the senior's life. Some or all of the above-mentioned processing in the response generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the response generation unit can input the content of the senior's utterance into the generation AI and have the generation AI execute the suggestion of an appropriate action.

[0082] The providing unit can estimate the senior's emotions and adjust the response provision method based on the estimated senior's emotions. The providing unit, for example, estimates the senior's emotions and adjusts the response provision method based on the estimated senior's emotions. For example, if the senior is sad, the providing unit can provide a response in a gentle tone. Also, if the senior is excited, the providing unit can provide a response in a lively tone. Furthermore, if the senior is tired, the providing unit can provide a response in a calm tone. In this way, by adjusting the response provision method based on the senior's emotions, a more appropriate response can be provided. Some or all of the above-described processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input the senior's emotion data into the generation AI and cause the generation AI to adjust the response provision method.

[0083] When providing a response, the providing unit can select an appropriate delivery method by referring to the senior's past response history. The providing unit, for example, selects an appropriate delivery method by referring to the senior's past response history. For example, the providing unit selects the optimal delivery method based on the senior's preferred response methods in the past. The providing unit can also select a delivery method appropriate for a specific situation from the senior's past response history. Furthermore, the providing unit can comprehensively analyze the senior's past response history and select the optimal delivery method. In this way, by referring to the senior's past response history, the optimal delivery method can be selected and the quality of the response can be improved. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the providing unit can input the senior's past response history into the generation AI and cause the generation AI to select an appropriate delivery method.

[0084] When providing a response, the providing unit can customize the content to be provided according to the senior's current activity and situation. The providing unit customizes the content to be provided according to, for example, the senior's current activity and situation. For example, if the senior is outdoors, the providing unit can provide a response appropriate to the environment. Furthermore, if the senior is attending a specific event, the providing unit can provide a response related to the event. Furthermore, if the senior is attending a specific time period, the providing unit can provide a response appropriate to that time period. In this way, by customizing the content to be provided according to the senior's current activity and situation, a more appropriate response can be provided. Some or all of the above-described processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input data on the senior's current activity and situation into the generation AI and cause the generation AI to customize the content to be provided.

[0085] The providing unit can improve the response delivery method by reflecting the senior's feedback when providing a response. The providing unit, for example, improves the response delivery method by reflecting the senior's feedback. For example, if the senior provides positive feedback on the response, the providing unit continues the response delivery method. In addition, if the senior provides negative feedback on the response, the providing unit can change the response delivery method. Furthermore, the providing unit can comprehensively analyze the senior's feedback and find the optimal response delivery method. In this way, by reflecting the senior's feedback, the response delivery method can be improved and the quality of the response can be improved. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the providing unit can input the senior's feedback data into the generation AI and cause the generation AI to improve the response delivery method.

[0086] The providing unit can estimate the senior's emotions and adjust the timing of providing a response based on the estimated senior's emotions. The providing unit, for example, estimates the senior's emotions and adjusts the timing of providing a response based on the estimated senior's emotions. For example, if the senior is sad, the providing unit can provide a response at an appropriate time. Furthermore, if the senior is excited, the providing unit can also provide a response quickly. Furthermore, if the senior is tired, the providing unit can also provide a response at a time when the senior is calm. In this way, by adjusting the timing of providing a response based on the senior's emotions, it is possible to provide a response at a more appropriate time. Some or all of the above-described processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the senior's emotion data into the generation AI and cause the generation AI to adjust the timing of providing a response.

[0087] When providing a response, the providing unit can select the optimal delivery method by taking into account the senior's device information. The providing unit selects the optimal delivery method by taking into account, for example, the senior's device information. For example, if the senior is using a smartphone, the providing unit can provide a response optimized for that device. Furthermore, if the senior is using a tablet, the providing unit can provide a response optimized for a large screen. Furthermore, if the senior is using a smartwatch, the providing unit can provide a concise and highly visible response. This makes it possible to select the optimal delivery method by taking into account the senior's device information and improve the quality of the response. Some or all of the above-described processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input the senior's device information into the generation AI and cause the generation AI to select the optimal delivery method.

[0088] When providing a response, the providing unit can make the provided content multilingual according to the senior's language setting. The providing unit, for example, makes the provided content multilingual according to the senior's language setting. For example, the providing unit provides a response in a language based on the language setting of the senior's device. The providing unit can also provide a language switching function if the senior speaks multiple languages. Furthermore, if the senior selects a specific language, the providing unit can provide a response in that language. This makes it possible to provide a more appropriate response by making the provided content multilingual according to the senior's language setting. Some or all of the above-described processing by the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the senior's language setting data into the generation AI and cause the generation AI to execute the multilingual provided content.

[0089] When providing a response, the providing unit can adjust the response method according to the senior's visual or hearing condition. The providing unit adjusts the response method according to, for example, the senior's visual or hearing condition. For example, if the senior has visual problems, the providing unit provides a response by voice. Also, if the senior has hearing problems, the providing unit can provide a response by text. Furthermore, the providing unit can select the optimal response method by comprehensively considering the senior's visual or hearing condition. This makes it possible to provide a more appropriate response by adjusting the response method according to the senior's visual or hearing condition. Some or all of the above-mentioned processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input data on the senior's visual or hearing condition into the generation AI and have the generation AI adjust the response method. === Hard Collateral 1-1 === Each of the above-described elements, including the emotion analysis unit, response generation unit, and provision unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the emotion analysis unit can detect the senior's utterances and facial expressions using the camera 42 and microphone 38B of the smart device 14 and analyze the senior's emotions using the control unit 46A. The emotion analysis unit can also be implemented by the specific processing unit 290 of the data processing device 12 and can analyze the senior's utterances using natural language processing technology. The response generation unit can also be implemented by the control unit 46A of the smart device 14 and can generate a response based on the senior's utterances using a generation AI. The response generation unit can also be implemented by the specific processing unit 290 of the data processing device 12 and can generate a response based on the senior's health status and daily routine. The provision unit can provide a response by voice using the output device 40 of the smart device 14. The provision unit can also be implemented by the specific processing unit 290 of the data processing device 12 and can display the response in text using the display 40A. === Hard Collateral 1-2 === Each of the multiple elements, including the emotion analysis unit, response generation unit, and provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the emotion analysis unit can detect the senior's utterances and facial expressions using the camera 42 and microphone 238 of the smart glasses 214 and analyze the senior's emotions using the control unit 46A. The emotion analysis unit can also be realized by the specific processing unit 290 of the data processing device 12 and can analyze the senior's utterances using natural language processing technology. The response generation unit can also be realized by the control unit 46A of the smart glasses 214 and can generate a response based on the senior's utterances using a generation AI. The response generation unit can also be realized by the specific processing unit 290 of the data processing device 12 and can generate a response based on the senior's health condition and daily routine. The provision unit can provide a response by voice using, for example, the speaker 240 of the smart glasses 214. The provision unit can also be realized by the specific processing unit 290 of the data processing device 12 and can display a response in text using a display. === Hard Collateral 1-3 === Each of the multiple elements, including the emotion analysis unit, response generation unit, and provision unit, described above, is implemented, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the emotion analysis unit can detect the senior's utterances and facial expressions using the camera 42 and microphone 238 of the headset terminal 314 and analyze the senior's emotions using the control unit 46A. The emotion analysis unit can also be implemented by the specific processing unit 290 of the data processing device 12 and can analyze the senior's utterances using natural language processing technology. The response generation unit can also be implemented by the control unit 46A of the headset terminal 314 and can generate a response based on the senior's utterances using a generation AI. The response generation unit can also be implemented by the specific processing unit 290 of the data processing device 12 and can generate a response based on the senior's health condition and daily routine. The provision unit can provide a response by voice using, for example, the speaker 240 of the headset terminal 314. The provision unit can also be implemented by the specific processing unit 290 of the data processing device 12 and can display a response in text using the display 343. === Hard Collateral 1-4 === Each of the multiple elements, including the emotion analysis unit, response generation unit, and provision unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the emotion analysis unit can detect the senior's utterances and facial expressions using the camera 42 and microphone 238 of the robot 414 and analyze the senior's emotions using the control unit 46A. The emotion analysis unit can also be realized by the specific processing unit 290 of the data processing device 12 and can analyze the senior's utterances using natural language processing technology. The response generation unit can also be realized by the control unit 46A of the robot 414 and can generate a response based on the senior's utterances using a generation AI. The response generation unit can also be realized by the specific processing unit 290 of the data processing device 12 and can generate a response based on the senior's health condition and daily routine. The provision unit can provide a response by voice using, for example, the speaker 240 of the robot 414. The provision unit can also be realized by the specific processing unit 290 of the data processing device 12 and can display the response in text using a display.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The communication system can further include a topic suggestion unit that suggests conversation topics based on the senior's hobbies and interests. For example, if the senior is interested in gardening, the topic suggestion unit can suggest topics about seasonal flowers and how to grow plants. If the senior likes music, the topic suggestion unit can suggest topics about the latest music news or the senior's favorite artists. Furthermore, if the senior is interested in traveling, the topic suggestion unit can suggest topics about recommended travel spots and travel plans. This allows for richer communication with seniors by providing conversations based on the senior's hobbies and interests.

[0092] The communication system can further include a health monitoring unit that monitors the senior's health data and issues an alert if an abnormality is detected. For example, if the senior's heart rate suddenly rises, the health monitoring unit can issue an alert and encourage the senior to rest. If the senior's blood pressure is abnormally high, the health monitoring unit can also suggest contacting a medical institution. Furthermore, if the senior's activity level is extremely low, the health monitoring unit can issue an alert encouraging them to exercise. This makes it possible to monitor the senior's health status in real time and encourage appropriate measures.

[0093] The communication system may further include a contact support unit to support communication between the senior and family and friends. For example, if the senior wants to contact their family, the contact support unit may provide a function to easily start a video call. If the senior wants to send a message to a friend, the contact support unit may allow the senior to create and send the message using voice input. Furthermore, if the senior wants to attend a specific event, the contact support unit may provide details of the event and assist with the participation procedure. This makes it easier for the senior to maintain connections with family and friends.

[0094] The communication system can also be equipped with a rhythm management unit to support the senior's daily rhythm. For example, it can set a reminder for the senior to wake up at the same time every day. It can also set a reminder for the senior to eat meals regularly. It can also set a reminder for the senior to go to bed at an appropriate time. This helps to regulate the senior's daily rhythm and support a healthy lifestyle.

[0095] The communication system can also be equipped with a safety monitoring unit to ensure the safety of seniors. For example, if a senior falls, the safety monitoring unit will automatically issue an alert and notify emergency contacts. If the senior remains motionless for a long period of time, the safety monitoring unit can issue an alert to check the senior's condition. It can also suggest safe routes for seniors when they go out. This ensures the safety of seniors and provides an environment where they can live with peace of mind.

[0096] The communication system can estimate the senior's emotions and provide entertainment to improve the senior's mood based on the estimated emotions. For example, if the senior is sad, the emotion analysis unit can play the senior's favorite music. If the senior is bored, the emotion analysis unit can suggest movies or TV shows that the senior will be interested in. Furthermore, if the senior is feeling lonely, the emotion analysis unit can suggest a video call with the senior's friends or family. In this way, appropriate entertainment can be provided based on the senior's emotions to improve the senior's mood.

[0097] The communication system can estimate the senior's emotions and suggest relaxation methods to reduce the senior's stress based on the estimated emotions. For example, if the senior is feeling stressed, the emotion analysis unit can suggest deep breathing or meditation. If the senior is feeling tense, the emotion analysis unit can play relaxing music. Furthermore, if the senior is feeling anxious, the emotion analysis unit can suggest activities related to the senior's favorite hobbies. In this way, appropriate relaxation methods can be provided based on the senior's emotions, reducing the senior's stress.

[0098] The communication system can estimate the emotions of seniors and support goal setting to improve their motivation based on the estimated emotions. For example, if a senior is feeling unmotivated, the emotion analysis unit can set small goals and support their achievement. If a senior is feeling anxious about achieving a goal, the emotion analysis unit can suggest goals broken down into stages. Furthermore, if a senior achieves a goal, the emotion analysis unit can praise the achievement and suggest the next goal. This makes it possible to support appropriate goal setting based on the senior's emotions and improve their motivation.

[0099] The communication system can estimate the senior's emotions and suggest events to strengthen the senior's social connections based on the estimated emotions. For example, if the senior feels lonely, the emotion analysis unit can suggest local community events. If the senior is bored, the emotion analysis unit can suggest online hobby groups. Furthermore, if the senior is looking for social activities, the emotion analysis unit can suggest get-togethers with friends. In this way, appropriate social events can be provided based on the senior's emotions, strengthening the senior's social connections.

[0100] The communication system can estimate the senior's emotions, record the senior's emotions based on the estimated emotions, and track long-term changes in emotions. For example, the emotion analysis unit records the senior's emotions daily and displays emotional changes in a graph. If the senior frequently displays a particular emotion, the system can identify the cause and suggest improvement measures. Furthermore, the senior's emotional changes can be shared with family members and medical professionals to provide appropriate support. This makes it possible to track the senior's emotional changes over the long term and take appropriate measures.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The emotion analysis unit analyzes the senior's comments. These include everyday conversations, questions, and impressions. The emotion analysis unit uses natural language processing technology to analyze the content of the comments, and further analyzes the tone and facial expressions of the comments to infer emotions and intentions. Step 2: The response generation unit generates an appropriate response based on the results of the analysis by the sentiment analysis unit. The response generation unit uses generative AI to generate a response based on the senior's comments, taking into account the senior's health condition, daily routine, past comments and behavioral history to generate a personalized response. Step 3: The providing unit provides the response generated by the response generating unit to the senior. The providing unit can provide the response by voice using the audio output device or by text using the display. The providing unit also estimates the senior's emotions and adjusts the way the response is provided based on the estimated emotions.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] 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.

[0122] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] 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.

[0138] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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."

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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, in order to avoid confusion and to 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.

[0173] 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.

[0174] [Explanation of symbols]

[0175] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. An emotion analysis unit that analyzes the senior's comments, a response generation unit that generates an appropriate response based on the result of the analysis by the emotion analysis unit; a providing unit that provides the response generated by the response generating unit to the senior; Equipped with A system characterized by:

2. The emotion analysis unit Analyze not only what seniors say, but also their emotions and intentions 2. The system of claim 1.

3. The response generation unit Generate responses based on the senior's health and daily routine 2. The system of claim 1.

4. The response generation unit Learns the senior's past statements and behavioral history to generate personalized responses 2. The system of claim 1.

5. The providing unit Providing the generated response to the senior 2. The system of claim 1.

6. The emotion analysis unit Estimate the emotions of seniors and adjust the accuracy of speech analysis based on the estimated emotions of seniors.

2. The system of claim 1.

7. The emotion analysis unit Analyzing senior citizens' past speech history and improving the sentiment analysis algorithm 2. The system of claim 1.

8. The emotion analysis unit In addition to the content of what the senior says, the system analyzes their tone of voice and facial expressions to estimate their emotions more accurately.

2. The system of claim 1.

Images