System

Abstract

To provide a system according to an embodiment that compensates a communication shortage of a living alone elderly and prevents a fall in a brain function.SOLUTION: A system according to an embodiment comprises: a learning unit; a generation unit; a voice generation unit; and a report unit. The learning unit is configured to learn individual information on a family, and a habit of a conversation. The generation unit is configured to generate a reply on the basis of the information learned by the learning unit. The voice generation unit is configured to reproduce the replay generated by the generation unit by a voice of a person himself using a voice generation technology. The report unit is configured to summarize a content of a daily conversation and report the summary to the family.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not adequately provide means to prevent the decline in brain function and progression of dementia caused by lack of communication among elderly people living alone, and there is room for improvement.

[0005] The system according to the embodiment aims to compensate for the lack of communication among elderly people living alone and to prevent a decline in brain function. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, a generating unit, a voice generating unit, and a reporting unit. The learning unit learns personal information and conversational habits of family members. The generating unit generates a response based on the information learned by the learning unit. The voice generating unit reproduces the response generated by the generating unit in the person's own voice using voice generation technology. The reporting unit summarizes the contents of daily conversations and reports them to the family members. Effect of the Invention

[0007] The system according to the embodiment can compensate for the lack of communication among elderly people living alone and prevent the decline in brain function. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A communication support system according to an embodiment of the present invention is a system for compensating for the lack of communication of elderly people living alone. This communication support system is a system that learns personal information and conversation habits of family members and generates a response. The system reproduces the person's voice using voice generation technology and conducts daily conversations. Furthermore, the contents of the daily conversation are summarized and reported to the family. First, the system learns personal information and conversation habits of family members. Next, a response is generated based on the learned information and reproduced in the person's voice using voice generation technology. Furthermore, the contents of the daily conversation are summarized and reported to the family. This system allows elderly people living alone to maintain daily communication and prevent a decline in brain function. In addition, it becomes easier for families to understand the condition of elderly people living alone, and a reduction in the burden of care can be expected. For example, the system collects information such as the names, hobbies, and past events of family members and analyzes conversation patterns. Next, a response is generated based on the learned information and reproduced in the person's voice using voice generation technology. Furthermore, the contents of the daily conversation are summarized and reported to the family via email or an app. This allows elderly people living alone to maintain daily communication and prevent a decline in brain function. In addition, it will be easier for family members to keep track of the condition of elderly people living alone, which is expected to reduce the burden of caregiving. As a result, the communication support system can compensate for the lack of communication among elderly people living alone and prevent the decline of brain function.

[0029] The communication support system according to the embodiment includes a learning unit, a generation unit, a voice generation unit, and a report unit. The learning unit learns personal information and conversation habits of family members. The personal information of family members includes, for example, names, ages, addresses, hobbies, etc., but is not limited to such examples. The learning unit collects, for example, information on family members' names, hobbies, and past events, and analyzes conversation patterns. For example, the learning unit collects information on family members' names, hobbies, and past events, and analyzes conversation patterns. The generation unit generates a response based on the information learned by the learning unit. The response is generated using, for example, natural language generation technology or template-based generation technology, but is not limited to such examples. For example, the generation unit generates a response using natural language generation technology. The generation unit can also generate a response using template-based generation technology. The voice generation unit reproduces the response generated by the generation unit in the person's voice using voice generation technology. The voice generation technology includes, for example, voice synthesis technology and deep learning-based voice generation technology, but is not limited to such examples. For example, the voice generation unit reproduces the person's voice using voice synthesis technology. The voice generating unit can also reproduce the person's voice using deep learning-based voice generating technology. The report unit summarizes the contents of daily conversations and reports them to the family. The report is provided to the family through, for example, email or an app, but is not limited to such examples. For example, the report unit summarizes the contents of daily conversations and reports them to the family through email. The report unit can also summarize the contents of daily conversations and report them to the family through an app. In this way, the communication support system according to the embodiment can compensate for the lack of communication in single elderly people and prevent a decline in brain function. A part or all of the above-mentioned processing in the report unit may be performed, for example, using AI, or may be performed without using AI. For example, the report unit can summarize the contents of daily conversations and generate a report using an AI model.

[0030] The learning unit learns personal information and conversation habits of family members. Personal information of family members includes, for example, names, ages, addresses, hobbies, etc., but is not limited to such examples. The learning unit, for example, collects information on family members' names, hobbies, past events, etc., and analyzes conversation patterns. Specifically, the learning unit collects information on family members' names, hobbies, past events, etc., and analyzes conversation patterns. As a result, the learning unit can grasp the individual characteristics and preferences of family members and realize more natural and friendly conversations. For example, the learning unit analyzes the conversation history of family members and learns frequently used phrases and reactions to specific topics. As a result, the learning unit can understand the conversation style and preferences of family members and lay the foundation for generating more appropriate responses. Furthermore, the learning unit can also analyze the emotional state and stress level of family members. For example, the learning unit detects changes in tone of voice and speaking style to infer the emotional state of family members. As a result, the learning unit can generate responses that are in line with the emotions of family members, and realize deeper communication. The learning unit can continuously update this information and respond to changes in the family. For example, when new hobbies or events occur, the information can be quickly incorporated and the content of the conversation can be kept up to date. This allows the learning module to generate appropriate responses based on the latest information about family members at all times, improving the quality of communication.

[0031] The generation unit generates a response based on the information learned by the learning unit. The response is generated using, for example, a natural language generation technique or a template-based generation technique, but is not limited to such examples. Specifically, the generation unit generates a response using a natural language generation technique. For example, the generation unit generates a response related to the names, hobbies, and past events of family members based on the information provided by the learning unit. This allows the generation unit to provide a friendly response to the family members. The generation unit can also generate a response using a template-based generation technique. For example, a template prepared in advance for a specific situation or topic is used to quickly generate an appropriate response. This allows the generation unit to provide an efficient and consistent response. Furthermore, the generation unit can generate a response taking into account the context of the conversation. For example, the content of the conversation before and after is analyzed, and an appropriate response is provided at an appropriate time. This allows the generation unit to realize a more natural and fluent conversation. The generation unit can provide a variety of appropriate responses to the family members by using these techniques in combination. For example, a combination of natural language generation technology and template-based generation technology allows flexible and efficient response generation to be realized. This enables the generation unit to facilitate smooth communication with family members and build deeper relationships.

[0032] The voice generation unit reproduces the response generated by the generation unit in the person's voice using a voice generation technology. The voice generation technology includes, for example, a voice synthesis technology and a deep learning-based voice generation technology, but is not limited to such examples. Specifically, the voice generation unit reproduces the person's voice using a voice synthesis technology. For example, the generated response is reproduced in a natural voice using a voice synthesis technology, providing familiar voice communication to family members. The voice generation unit can also reproduce the person's voice using a deep learning-based voice generation technology. For example, a deep learning model is used to learn the characteristics of the person's voice and generate a more realistic voice. This allows the voice generation unit to provide more natural and realistic voice communication to family members. Furthermore, the voice generation unit can adjust the tone and emotion of the voice. For example, by changing the tone and emotion of the voice according to the emotional state of the family members, more emotional communication is realized. This allows the voice generation unit to provide voice communication that is in line with the emotions of the family members. The voice generation unit can provide diverse and appropriate voice communication to family members by using these technologies in combination. For example, by combining speech synthesis technology with deep learning-based speech generation technology, flexible and efficient speech generation can be realized, allowing the speech generation unit to facilitate smooth communication with family members and build deeper relationships.

[0033] The report unit summarizes the contents of the daily conversation and reports it to the family. The report is provided to the family through, for example, email or an app, but is not limited to such examples. Specifically, the report unit summarizes the contents of the daily conversation and reports it to the family through email. For example, the report unit analyzes the contents of the daily conversation and creates a summary by extracting important information and topics. This allows the report unit to briefly convey the contents of the daily conversation to the family. The report unit can also summarize the contents of the daily conversation and report it to the family through an app. For example, the report unit provides the family with a summary of the daily conversation in real time through a dedicated app. This allows the report unit to enable the family to check the contents of the daily conversation at any time. Furthermore, the report unit can analyze the contents of the conversation and generate a report according to the interests and preferences of the family. For example, the report unit focuses on summarizing information related to a specific topic and provides it to the family. This allows the report unit to provide more valuable information to the family. The report unit can provide a variety of appropriate reports to the family by using these technologies in combination. For example, a flexible and efficient report provision can be achieved by combining email and an app. This allows the reporting department to communicate more smoothly with families and build deeper relationships.

[0034] The communication support system includes an information collection unit that collects information on family members' names or hobbies, and past events, and analyzes conversation patterns. The information collection unit collects information on family members' names, hobbies, and past events, and analyzes conversation patterns. For example, the information collection unit collects information on family members' names, hobbies, and past events, and analyzes conversation patterns. Specific methods and standards for analyzing conversation patterns include, but are not limited to, extraction of frequent phrases and analysis of conversation flow. For example, the information collection unit extracts frequent phrases and analyzes conversation patterns. The information collection unit can also analyze the conversation flow and analyze conversation patterns. This makes it possible to learn personal information and conversation habits of family members in detail. Part or all of the above-mentioned processing in the information collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the information collection unit can input information on family members' names, hobbies, past events, and the like into an AI model, and have the AI ​​execute analysis of conversation patterns.

[0035] The learning unit can analyze the past conversation history of the family and select an appropriate learning method. For example, the learning unit identifies frequently discussed topics from the past conversation history of the family and prioritizes learning of the topics. The learning unit can also analyze the conversation history of the family and learn topics that are discussed during a specific time period. The learning unit can also learn the flow and patterns of conversation based on the conversation history of the family and generate natural responses. This makes it possible to select an optimal learning method based on the past conversation history. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the past conversation history of the family into an AI model and cause the AI ​​to select an appropriate learning method.

[0036] The learning unit can perform filtering based on the family's living conditions and areas of interest during learning. The learning unit, for example, prioritizes learning of current interests based on the family's living conditions. The learning unit can also filter and learn related information taking into account the family's hobbies and interests. The learning unit can also perform learning at an appropriate time in accordance with the family's life rhythm. This makes it possible to filter learning content based on the family's living conditions and areas of interest. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data on the family's living conditions and areas of interest into an AI model and have the AI ​​perform filtering.

[0037] During learning, the learning unit can prioritize learning of highly relevant information based on the geographical location information of the family. For example, the learning unit prioritizes learning of information related to the location where the family is currently located. The learning unit can also learn information related to places that the family frequently visits. The learning unit can also learn local events and news based on the geographical location information of the family. This allows for preferential learning of highly relevant information based on the geographical location information of the family. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the geographical location information of the family into an AI model and cause the AI ​​to learn highly relevant information.

[0038] The learning unit can analyze the family's social media activities during learning and learn related information. For example, the learning unit learns related topics based on information shared by the family on social media. The learning unit can also analyze the content of the family's social media posts and learn topics of interest. The learning unit can also learn related information by referring to the content of posts by the family's social media followers and friends. This makes it possible to learn related information based on the family's social media activities. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the family's social media activity data into an AI model and cause the AI ​​to learn related information.

[0039] The generation unit can adjust the level of detail of the response based on the importance of the conversation when generating the response. For example, in the case of an important conversation, the generation unit generates a detailed response. In addition, in the case of an everyday conversation, the generation unit can also generate a concise response. In addition, in the case of a topic in which the user is particularly interested, the generation unit can also generate a response including detailed information. This makes it possible to adjust the level of detail of the response according to the importance of the conversation. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or may be performed without using AI. For example, the generation unit can input the importance data of the conversation into an AI model and cause the AI ​​to adjust the level of detail of the response.

[0040] The generation unit can apply different generation algorithms depending on the category of the conversation when generating a reply. For example, in the case of a conversation about the family's health, the generation unit generates a reply including specialized information. In addition, in the case of a conversation about the family's hobbies, the generation unit can also generate a reply including related information. In addition, in the case of a conversation about past events of the family, the generation unit can also generate a reply that shares memories. This makes it possible to apply an appropriate generation algorithm depending on the category of the conversation. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the category data of the conversation into an AI model and cause the AI ​​to apply an appropriate generation algorithm.

[0041] The generation unit can determine the priority of replies based on the submission time of the conversation when generating replies. For example, the generation unit generates replies with priority to the most recent conversation. The generation unit can also generate replies at an appropriate timing for past conversations. The generation unit can also generate replies with priority to conversations that took place in a specific time period. This makes it possible to determine the priority of replies based on the submission time of the conversation. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input conversation submission time data into an AI model and cause AI to determine the priority of replies.

[0042] The generation unit can adjust the order of replies based on the relevance of the conversation when generating replies. For example, the generation unit generates replies preferentially for conversations with high relevance. The generation unit can also generate replies in an appropriate order even for conversations with low relevance. The generation unit can also generate replies in a natural order, taking into account the flow of the conversation. This makes it possible to adjust the order of replies based on the relevance of the conversation. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input conversation relevance data into an AI model and cause AI to adjust the order of replies.

[0043] The voice generation unit can select an optimal voice generation method by referring to past voice data when generating voice. The voice generation unit, for example, identifies a tone and speed preferred by the user based on the past voice data and generates voice. The voice generation unit can also analyze past voice data and reproduce natural pronunciation and intonation. The voice generation unit can also generate voice that is easy for the user to understand by referring to past voice data. This makes it possible to select an optimal voice generation method based on past voice data. A part or all of the above-mentioned processing in the voice generation unit may be performed, for example, using AI or may be performed without using AI. For example, the voice generation unit can input past voice data into an AI model and cause AI to select an optimal voice generation method.

[0044] The voice generation unit can apply different voice generation algorithms depending on the content of the conversation when generating the voice. For example, in the case of a conversation about the health of the family, the voice generation unit generates a voice including specialized information. In addition, in the case of a conversation about the hobbies of the family, the voice generation unit can also generate a voice including related information. In addition, in the case of a conversation about past events of the family, the voice generation unit can also generate a voice that shares memories. This makes it possible to apply an appropriate voice generation algorithm depending on the content of the conversation. A part or all of the above-mentioned processing in the voice generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice generation unit can input the content data of the conversation into an AI model and cause the AI ​​to apply an appropriate voice generation algorithm.

[0045] The voice generation unit can determine the priority of voices based on the submission time of the conversation when generating the voice. For example, the voice generation unit generates voice preferentially for the most recent conversation. The voice generation unit can also generate voice at an appropriate timing for past conversations. The voice generation unit can also generate voice preferentially for conversations that took place in a specific time period. This allows the priority of voices to be determined based on the submission time of the conversation. A part or all of the above-mentioned processing in the voice generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice generation unit can input conversation submission time data into an AI model and cause AI to determine the priority of voices.

[0046] The voice generation unit can adjust the order of the voices based on the relevance of the conversations when generating the voices. For example, the voice generation unit generates voices preferentially for conversations with high relevance. The voice generation unit can also generate voices in an appropriate order even for conversations with low relevance. The voice generation unit can also generate voices in a natural order, taking into account the flow of the conversation. This makes it possible to adjust the order of the voices based on the relevance of the conversations. A part or all of the above-mentioned processing in the voice generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice generation unit can input conversation relevance data into an AI model and cause the AI ​​to adjust the order of the voices.

[0047] When generating a report, the report unit can select an optimal report generation method by referring to past report data. The report unit, for example, identifies a report format preferred by the user based on past report data and generates a report. The report unit can also analyze past report data and reproduce natural expressions and configurations. The report unit can also generate a report that is easy for the user to understand by referring to past report data. This makes it possible to select an optimal report generation method based on past report data. A part or all of the above-mentioned processing in the report unit may be performed, for example, using AI or may be performed without using AI. For example, the report unit can input past report data into an AI model and cause AI to select an optimal report generation method.

[0048] The report unit can apply different report generation algorithms depending on the category of the conversation when generating a report. For example, in the case of a conversation about the health of a family member, the report unit generates a report including specialized information. In addition, in the case of a conversation about a family member's hobbies, the report unit can also generate a report including related information. In addition, in the case of a conversation about a past event of a family member, the report unit can also generate a report that shares memories. This makes it possible to apply an appropriate report generation algorithm depending on the category of the conversation. A part or all of the above-mentioned processing in the report unit may be performed, for example, using AI or may be performed without using AI. For example, the report unit can input the category data of the conversation into an AI model and cause the AI ​​to apply an appropriate report generation algorithm.

[0049] The report unit can determine the priority of the report based on the submission time of the conversation when generating the report. For example, the report unit generates a report with priority for the most recent conversation. The report unit can also generate a report at an appropriate timing for a past conversation. The report unit can also generate a report with priority for a conversation that took place in a specific time period. This allows the priority of the report to be determined based on the submission time of the conversation. A part or all of the above-mentioned processing in the report unit may be performed using, for example, AI, or may be performed without using AI. For example, the report unit can input the submission time data of the conversation into an AI model and cause the AI ​​to determine the priority of the report.

[0050] The report unit can adjust the order of reports based on the relevance of the conversations when generating reports. For example, the report unit generates reports preferentially for conversations with high relevance. The report unit can also generate reports in an appropriate order for conversations with low relevance. The report unit can also generate reports in a natural order, taking into account the flow of the conversation. This makes it possible to adjust the order of reports based on the relevance of the conversations. A part or all of the above-mentioned processing in the report unit may be performed using, for example, AI, or may be performed without using AI. For example, the report unit can input conversation relevance data into an AI model and cause AI to adjust the order of reports.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The communication support system may further include a health monitoring unit that monitors the user's health condition. The health monitoring unit may, for example, periodically measure the user's vital signs, such as heart rate, blood pressure, and body temperature, and issue an alert if an abnormality is detected. The health monitoring unit may also record the user's amount of exercise and sleep patterns, and analyze trends in the user's health condition. Furthermore, the health monitoring unit may record the user's diet and provide advice on nutritional balance. This allows the user's health condition to be managed comprehensively, and abnormalities to be detected early.

[0053] The communication support system may further include a recommendation unit that makes recommendations based on the user's hobbies and interests. The recommendation unit may, for example, suggest movies, music, books, etc. that the user is interested in. The recommendation unit may also analyze the user's past activity history and make suggestions for discovering new hobbies and interests. Furthermore, the recommendation unit may also suggest relaxing activities and stress relief methods based on the user's current mood and emotions. This may improve the user's quality of life.

[0054] The communication support system may further include a schedule management unit that manages the user's schedule. The schedule management unit, for example, automatically organizes the user's plans and reminds the user of important events and tasks. The schedule management unit may also analyze the user's past schedule history and suggest efficient time management methods. Furthermore, the schedule management unit may adjust the schedule according to the user's emotions and physical condition. This allows the user to manage their life in a more planned manner and reduce stress.

[0055] The communication support system may further include a learning support unit that supports the user's learning. For example, the learning support unit provides learning content in areas in which the user is interested and manages the progress of the learning. The learning support unit may also suggest the most suitable learning method according to the user's learning style. Furthermore, the learning support unit may also adjust the timing of the learning according to the user's emotions and concentration. This maximizes the user's learning effect and supports continuous learning.

[0056] The process flow of the first embodiment will be briefly described below.

[0057] Step 1: The learning module learns the personal information and conversational habits of family members. Personal information of family members includes names, ages, addresses, hobbies, etc. The learning module collects information such as family members' names, hobbies, and past events, and analyzes conversation patterns. Step 2: The generator generates a response based on the information learned by the trainer. The response is generated using natural language generation technology or template-based generation technology. Step 3: The voice generator reproduces the response generated by the generator in the person's own voice using voice generation technology, which includes voice synthesis technology and deep learning-based voice generation technology. Step 4: The reporting department summarizes the content of daily conversations and reports them to the family. The reports are provided to the family via email or app.

[0058] (Example 2) A communication support system according to an embodiment of the present invention is a system for compensating for the lack of communication of elderly people living alone. This communication support system is a system that learns personal information and conversation habits of family members and generates a response. The system reproduces the person's voice using voice generation technology and conducts daily conversations. Furthermore, the contents of the daily conversation are summarized and reported to the family. First, the system learns personal information and conversation habits of family members. Next, a response is generated based on the learned information and reproduced in the person's voice using voice generation technology. Furthermore, the contents of the daily conversation are summarized and reported to the family. This system allows elderly people living alone to maintain daily communication and prevent a decline in brain function. In addition, it becomes easier for families to understand the condition of elderly people living alone, and a reduction in the burden of care can be expected. For example, the system collects information such as the names, hobbies, and past events of family members and analyzes conversation patterns. Next, a response is generated based on the learned information and reproduced in the person's voice using voice generation technology. Furthermore, the contents of the daily conversation are summarized and reported to the family via email or an app. This allows elderly people living alone to maintain daily communication and prevent a decline in brain function. In addition, it will be easier for family members to keep track of the condition of elderly people living alone, which is expected to reduce the burden of caregiving. As a result, the communication support system can compensate for the lack of communication among elderly people living alone and prevent the decline of brain function.

[0059] The communication support system according to the embodiment includes a learning unit, a generation unit, a voice generation unit, and a report unit. The learning unit learns personal information and conversation habits of family members. The personal information of family members includes, for example, names, ages, addresses, hobbies, etc., but is not limited to such examples. The learning unit collects, for example, information on family members' names, hobbies, and past events, and analyzes conversation patterns. For example, the learning unit collects information on family members' names, hobbies, and past events, and analyzes conversation patterns. The generation unit generates a response based on the information learned by the learning unit. The response is generated using, for example, natural language generation technology or template-based generation technology, but is not limited to such examples. For example, the generation unit generates a response using natural language generation technology. The generation unit can also generate a response using template-based generation technology. The voice generation unit reproduces the response generated by the generation unit in the person's voice using voice generation technology. The voice generation technology includes, for example, voice synthesis technology and deep learning-based voice generation technology, but is not limited to such examples. For example, the voice generation unit reproduces the person's voice using voice synthesis technology. The voice generating unit can also reproduce the person's voice using deep learning-based voice generating technology. The report unit summarizes the contents of daily conversations and reports them to the family. The report is provided to the family through, for example, email or an app, but is not limited to such examples. For example, the report unit summarizes the contents of daily conversations and reports them to the family through email. The report unit can also summarize the contents of daily conversations and report them to the family through an app. In this way, the communication support system according to the embodiment can compensate for the lack of communication in single elderly people and prevent a decline in brain function. A part or all of the above-mentioned processing in the report unit may be performed, for example, using AI, or may be performed without using AI. For example, the report unit can summarize the contents of daily conversations and generate a report using an AI model.

[0060] The learning unit learns personal information and conversation habits of family members. Personal information of family members includes, for example, names, ages, addresses, hobbies, etc., but is not limited to such examples. The learning unit, for example, collects information on family members' names, hobbies, past events, etc., and analyzes conversation patterns. Specifically, the learning unit collects information on family members' names, hobbies, past events, etc., and analyzes conversation patterns. As a result, the learning unit can grasp the individual characteristics and preferences of family members and realize more natural and friendly conversations. For example, the learning unit analyzes the conversation history of family members and learns frequently used phrases and reactions to specific topics. As a result, the learning unit can understand the conversation style and preferences of family members and lay the foundation for generating more appropriate responses. Furthermore, the learning unit can also analyze the emotional state and stress level of family members. For example, the learning unit detects changes in tone of voice and speaking style to infer the emotional state of family members. As a result, the learning unit can generate responses that are in line with the emotions of family members, and realize deeper communication. The learning unit can continuously update this information and respond to changes in the family. For example, when new hobbies or events occur, the information can be quickly incorporated and the content of the conversation can be kept up to date. This allows the learning module to generate appropriate responses based on the latest information about family members at all times, improving the quality of communication.

[0061] The generation unit generates a response based on the information learned by the learning unit. The response is generated using, for example, a natural language generation technique or a template-based generation technique, but is not limited to such examples. Specifically, the generation unit generates a response using a natural language generation technique. For example, the generation unit generates a response related to the names, hobbies, and past events of family members based on the information provided by the learning unit. This allows the generation unit to provide a friendly response to the family members. The generation unit can also generate a response using a template-based generation technique. For example, a template prepared in advance for a specific situation or topic is used to quickly generate an appropriate response. This allows the generation unit to provide an efficient and consistent response. Furthermore, the generation unit can generate a response taking into account the context of the conversation. For example, the content of the conversation before and after is analyzed, and an appropriate response is provided at an appropriate time. This allows the generation unit to realize a more natural and fluent conversation. The generation unit can provide a variety of appropriate responses to the family members by using these techniques in combination. For example, a combination of natural language generation technology and template-based generation technology allows flexible and efficient response generation to be realized. This enables the generation unit to facilitate smooth communication with family members and build deeper relationships.

[0062] The voice generation unit reproduces the response generated by the generation unit in the person's voice using a voice generation technology. The voice generation technology includes, for example, a voice synthesis technology and a deep learning-based voice generation technology, but is not limited to such examples. Specifically, the voice generation unit reproduces the person's voice using a voice synthesis technology. For example, the generated response is reproduced in a natural voice using a voice synthesis technology, providing familiar voice communication to family members. The voice generation unit can also reproduce the person's voice using a deep learning-based voice generation technology. For example, a deep learning model is used to learn the characteristics of the person's voice and generate a more realistic voice. This allows the voice generation unit to provide more natural and realistic voice communication to family members. Furthermore, the voice generation unit can adjust the tone and emotion of the voice. For example, by changing the tone and emotion of the voice according to the emotional state of the family members, more emotional communication is realized. This allows the voice generation unit to provide voice communication that is in line with the emotions of the family members. The voice generation unit can provide diverse and appropriate voice communication to family members by using these technologies in combination. For example, by combining speech synthesis technology with deep learning-based speech generation technology, flexible and efficient speech generation can be realized, allowing the speech generation unit to facilitate smooth communication with family members and build deeper relationships.

[0063] The report unit summarizes the contents of the daily conversation and reports it to the family. The report is provided to the family through, for example, email or an app, but is not limited to such examples. Specifically, the report unit summarizes the contents of the daily conversation and reports it to the family through email. For example, the report unit analyzes the contents of the daily conversation and creates a summary by extracting important information and topics. This allows the report unit to briefly convey the contents of the daily conversation to the family. The report unit can also summarize the contents of the daily conversation and report it to the family through an app. For example, the report unit provides the family with a summary of the daily conversation in real time through a dedicated app. This allows the report unit to enable the family to check the contents of the daily conversation at any time. Furthermore, the report unit can analyze the contents of the conversation and generate a report according to the interests and preferences of the family. For example, the report unit focuses on summarizing information related to a specific topic and provides it to the family. This allows the report unit to provide more valuable information to the family. The report unit can provide a variety of appropriate reports to the family by using these technologies in combination. For example, a flexible and efficient report provision can be achieved by combining email and an app. This allows the reporting department to communicate more smoothly with families and build deeper relationships.

[0064] The communication support system includes an information collection unit that collects information on family members' names or hobbies, and past events, and analyzes conversation patterns. The information collection unit collects information on family members' names, hobbies, and past events, and analyzes conversation patterns. For example, the information collection unit collects information on family members' names, hobbies, and past events, and analyzes conversation patterns. Specific methods and standards for analyzing conversation patterns include, but are not limited to, extraction of frequent phrases and analysis of conversation flow. For example, the information collection unit extracts frequent phrases and analyzes conversation patterns. The information collection unit can also analyze the conversation flow and analyze conversation patterns. This makes it possible to learn personal information and conversation habits of family members in detail. Part or all of the above-mentioned processing in the information collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the information collection unit can input information on family members' names, hobbies, past events, and the like into an AI model, and have the AI ​​execute analysis of conversation patterns.

[0065] The learning unit can estimate the user's emotions and determine the priority of information to be learned based on the estimated user's emotions. For example, when the user is stressed, the learning unit preferentially learns topics that can relax the user. Also, when the user is excited, the learning unit can preferentially learn topics that attract the user's interest. Also, when the user is tired, the learning unit can preferentially learn topics that are simple and easy to understand. This allows the priority of information to be learned to be adjusted according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of information to be learned.

[0066] The learning unit can analyze the past conversation history of the family and select an appropriate learning method. For example, the learning unit identifies frequently discussed topics from the past conversation history of the family and prioritizes learning of the topics. The learning unit can also analyze the conversation history of the family and learn topics that are discussed during a specific time period. The learning unit can also learn the flow and patterns of conversation based on the conversation history of the family and generate natural responses. This makes it possible to select an optimal learning method based on the past conversation history. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the past conversation history of the family into an AI model and cause the AI ​​to select an appropriate learning method.

[0067] The learning unit can perform filtering based on the family's living conditions and areas of interest during learning. The learning unit, for example, prioritizes learning of current interests based on the family's living conditions. The learning unit can also filter and learn related information taking into account the family's hobbies and interests. The learning unit can also perform learning at an appropriate time in accordance with the family's life rhythm. This makes it possible to filter learning content based on the family's living conditions and areas of interest. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data on the family's living conditions and areas of interest into an AI model and have the AI ​​perform filtering.

[0068] The learning unit can estimate the user's emotion and adjust the timing of acquiring the information to be learned based on the estimated emotion of the user. For example, when the user is relaxed, the learning unit delays the acquisition of the information to be learned. Also, when the user is excited, the learning unit can also accelerate the acquisition of the information to be learned. Also, when the user is tired, the learning unit can temporarily stop the acquisition of the information to be learned. This makes it possible to adjust the timing of acquiring the information to be learned according to the emotion of the user. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the timing of acquiring the information to be learned.

[0069] During learning, the learning unit can prioritize learning of highly relevant information based on the geographical location information of the family. For example, the learning unit prioritizes learning of information related to the location where the family is currently located. The learning unit can also learn information related to places that the family frequently visits. The learning unit can also learn local events and news based on the geographical location information of the family. This allows for preferential learning of highly relevant information based on the geographical location information of the family. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the geographical location information of the family into an AI model and cause the AI ​​to learn highly relevant information.

[0070] The learning unit can analyze the family's social media activities during learning and learn related information. For example, the learning unit learns related topics based on information shared by the family on social media. The learning unit can also analyze the content of the family's social media posts and learn topics of interest. The learning unit can also learn related information by referring to the content of posts by the family's social media followers and friends. This makes it possible to learn related information based on the family's social media activities. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the family's social media activity data into an AI model and cause the AI ​​to learn related information.

[0071] The generation unit can estimate the user's emotion and adjust the way of expressing the reply based on the estimated emotion of the user. For example, when the user is relaxed, the generation unit generates a reply in a calm expression method. Also, when the user is excited, the generation unit can generate a reply in a lively expression method. Also, when the user is tired, the generation unit can generate a reply in a simple and easy-to-understand expression method. This allows the way of expressing the reply to be adjusted according to the emotion of the user. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the way of expressing the reply.

[0072] The generation unit can adjust the level of detail of the response based on the importance of the conversation when generating the response. For example, in the case of an important conversation, the generation unit generates a detailed response. In addition, in the case of an everyday conversation, the generation unit can also generate a concise response. In addition, in the case of a topic in which the user is particularly interested, the generation unit can also generate a response including detailed information. This makes it possible to adjust the level of detail of the response according to the importance of the conversation. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or may be performed without using AI. For example, the generation unit can input the importance data of the conversation into an AI model and cause the AI ​​to adjust the level of detail of the response.

[0073] The generation unit can apply different generation algorithms depending on the category of the conversation when generating a reply. For example, in the case of a conversation about the family's health, the generation unit generates a reply including specialized information. In addition, in the case of a conversation about the family's hobbies, the generation unit can also generate a reply including related information. In addition, in the case of a conversation about past events of the family, the generation unit can also generate a reply that shares memories. This makes it possible to apply an appropriate generation algorithm depending on the category of the conversation. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the category data of the conversation into an AI model and cause the AI ​​to apply an appropriate generation algorithm.

[0074] The generation unit can estimate the user's emotion and adjust the length of the reply based on the estimated user's emotion. For example, the generation unit generates a longer reply when the user is relaxed. Also, the generation unit can generate a shorter reply when the user is in a hurry. Also, the generation unit can generate a reply of an appropriate length when the user is excited. This allows the length of the reply to be adjusted according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the reply.

[0075] The generation unit can determine the priority of replies based on the submission time of the conversation when generating replies. For example, the generation unit generates replies with priority to the most recent conversation. The generation unit can also generate replies at an appropriate timing for past conversations. The generation unit can also generate replies with priority to conversations that took place in a specific time period. This makes it possible to determine the priority of replies based on the submission time of the conversation. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input conversation submission time data into an AI model and cause AI to determine the priority of replies.

[0076] The generation unit can adjust the order of replies based on the relevance of the conversation when generating replies. For example, the generation unit generates replies preferentially for conversations with high relevance. The generation unit can also generate replies in an appropriate order even for conversations with low relevance. The generation unit can also generate replies in a natural order, taking into account the flow of the conversation. This makes it possible to adjust the order of replies based on the relevance of the conversation. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input conversation relevance data into an AI model and cause AI to adjust the order of replies.

[0077] The voice generation unit can estimate the user's emotion and adjust the tone and speed of the voice based on the estimated emotion of the user. For example, when the user is relaxed, the voice generation unit generates voice at a gentle tone and a slow speed. Also, when the user is excited, the voice generation unit can generate voice at a lively tone and a faster speed. Also, when the user is tired, the voice generation unit can generate voice at a calm tone and a moderate speed. This allows the tone and speed of the voice to be adjusted according to the emotion of the user. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the voice generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the voice generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the tone and speed of the voice.

[0078] The voice generation unit can select an optimal voice generation method by referring to past voice data when generating voice. The voice generation unit, for example, identifies a tone and speed preferred by the user based on the past voice data and generates voice. The voice generation unit can also analyze past voice data and reproduce natural pronunciation and intonation. The voice generation unit can also generate voice that is easy for the user to understand by referring to past voice data. This makes it possible to select an optimal voice generation method based on past voice data. A part or all of the above-mentioned processing in the voice generation unit may be performed, for example, using AI or may be performed without using AI. For example, the voice generation unit can input past voice data into an AI model and cause AI to select an optimal voice generation method.

[0079] The voice generation unit can apply different voice generation algorithms depending on the content of the conversation when generating the voice. For example, in the case of a conversation about the health of the family, the voice generation unit generates a voice including specialized information. In addition, in the case of a conversation about the hobbies of the family, the voice generation unit can also generate a voice including related information. In addition, in the case of a conversation about past events of the family, the voice generation unit can also generate a voice that shares memories. This makes it possible to apply an appropriate voice generation algorithm depending on the content of the conversation. A part or all of the above-mentioned processing in the voice generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice generation unit can input the content data of the conversation into an AI model and cause the AI ​​to apply an appropriate voice generation algorithm.

[0080] The voice generation unit can estimate the user's emotion and adjust the volume of the voice based on the estimated user's emotion. For example, when the user is relaxed, the voice generation unit generates the voice at a moderate volume. Also, when the user is excited, the voice generation unit can generate the voice at a slightly louder volume. Also, when the user is tired, the voice generation unit can generate the voice at a slightly lower volume. This allows the volume of the voice to be adjusted according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the voice generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the voice generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the volume of the voice.

[0081] The voice generation unit can determine the priority of voices based on the submission time of the conversation when generating the voice. For example, the voice generation unit generates voice preferentially for the most recent conversation. The voice generation unit can also generate voice at an appropriate timing for past conversations. The voice generation unit can also generate voice preferentially for conversations that took place in a specific time period. This allows the priority of voices to be determined based on the submission time of the conversation. A part or all of the above-mentioned processing in the voice generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice generation unit can input conversation submission time data into an AI model and cause AI to determine the priority of voices.

[0082] The voice generation unit can adjust the order of the voices based on the relevance of the conversations when generating the voices. For example, the voice generation unit generates voices preferentially for conversations with high relevance. The voice generation unit can also generate voices in an appropriate order even for conversations with low relevance. The voice generation unit can also generate voices in a natural order, taking into account the flow of the conversation. This makes it possible to adjust the order of the voices based on the relevance of the conversations. A part or all of the above-mentioned processing in the voice generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice generation unit can input conversation relevance data into an AI model and cause the AI ​​to adjust the order of the voices.

[0083] The report unit can estimate the user's emotion and adjust the contents of the report based on the estimated user's emotion. For example, when the user is relaxed, the report unit generates a detailed report. Also, when the user is excited, the report unit can generate a report that focuses on the main points. Also, when the user is tired, the report unit can generate a concise report. This allows the contents of the report to be adjusted according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the report unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the report unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the contents of the report.

[0084] When generating a report, the report unit can select an optimal report generation method by referring to past report data. The report unit, for example, identifies a report format preferred by the user based on past report data and generates a report. The report unit can also analyze past report data and reproduce natural expressions and configurations. The report unit can also generate a report that is easy for the user to understand by referring to past report data. This makes it possible to select an optimal report generation method based on past report data. A part or all of the above-mentioned processing in the report unit may be performed, for example, using AI or may be performed without using AI. For example, the report unit can input past report data into an AI model and cause AI to select an optimal report generation method.

[0085] The report unit can apply different report generation algorithms depending on the category of the conversation when generating a report. For example, in the case of a conversation about the health of a family member, the report unit generates a report including specialized information. In addition, in the case of a conversation about a family member's hobbies, the report unit can also generate a report including related information. In addition, in the case of a conversation about a past event of a family member, the report unit can also generate a report that shares memories. This makes it possible to apply an appropriate report generation algorithm depending on the category of the conversation. A part or all of the above-mentioned processing in the report unit may be performed, for example, using AI or may be performed without using AI. For example, the report unit can input the category data of the conversation into an AI model and cause the AI ​​to apply an appropriate report generation algorithm.

[0086] The report unit can estimate the user's emotion and adjust the length of the report based on the estimated user's emotion. For example, the report unit generates a longer report when the user is relaxed. Also, the report unit can generate a shorter report when the user is in a hurry. Also, the report unit can generate a report of an appropriate length when the user is excited. This allows the length of the report to be adjusted according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the report unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the report unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the report.

[0087] The report unit can determine the priority of the report based on the submission time of the conversation when generating the report. For example, the report unit generates a report with priority for the most recent conversation. The report unit can also generate a report at an appropriate timing for a past conversation. The report unit can also generate a report with priority for a conversation that took place in a specific time period. This allows the priority of the report to be determined based on the submission time of the conversation. A part or all of the above-mentioned processing in the report unit may be performed using, for example, AI, or may be performed without using AI. For example, the report unit can input the submission time data of the conversation into an AI model and cause the AI ​​to determine the priority of the report.

[0088] The report unit can adjust the order of reports based on the relevance of the conversations when generating reports. For example, the report unit generates reports preferentially for conversations with high relevance. The report unit can also generate reports in an appropriate order for conversations with low relevance. The report unit can also generate reports in a natural order, taking into account the flow of the conversation. This makes it possible to adjust the order of reports based on the relevance of the conversations. A part or all of the above-mentioned processing in the report unit may be performed using, for example, AI, or may be performed without using AI. For example, the report unit can input conversation relevance data into an AI model and cause AI to adjust the order of reports.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The communication support system may further include a health monitoring unit that monitors the user's health condition. The health monitoring unit may, for example, periodically measure the user's vital signs, such as heart rate, blood pressure, and body temperature, and issue an alert if an abnormality is detected. The health monitoring unit may also record the user's amount of exercise and sleep patterns, and analyze trends in the user's health condition. Furthermore, the health monitoring unit may record the user's diet and provide advice on nutritional balance. This allows the user's health condition to be managed comprehensively, and abnormalities to be detected early.

[0091] The communication support system may further include a recommendation unit that makes recommendations based on the user's hobbies and interests. The recommendation unit may, for example, suggest movies, music, books, etc. that the user is interested in. The recommendation unit may also analyze the user's past activity history and make suggestions for discovering new hobbies and interests. Furthermore, the recommendation unit may also suggest relaxing activities and stress relief methods based on the user's current mood and emotions. This may improve the user's quality of life.

[0092] The communication support system may further include a music player that estimates the user's emotion and plays appropriate music based on the estimated emotion. For example, the music player plays calm music when the user is relaxed and plays lively music when the user is excited. The music player may also play comforting music when the user is sad. Furthermore, the music player may analyze the user's past music playback history and suggest music that the user likes. This allows a music experience that corresponds to the user's emotion to be provided.

[0093] The communication support system may further include an exercise suggestion unit that estimates the user's emotions and suggests appropriate exercises based on the estimated emotions. For example, the exercise suggestion unit suggests relaxing yoga or stretching when the user is feeling stressed, and suggests jogging or dancing when the user is energetic. The exercise suggestion unit may also suggest light walking when the user is tired. Furthermore, the exercise suggestion unit may analyze the user's past exercise history and create an appropriate exercise plan. This makes it possible to support the user's exercise habits according to their emotions.

[0094] The communication support system may further include a relaxation suggestion unit that estimates the user's emotions and suggests an appropriate relaxation method based on the estimated emotions. For example, the relaxation suggestion unit suggests deep breathing or meditation when the user feels stressed, and suggests aromatherapy or massage when the user is relaxed. The relaxation suggestion unit may also suggest a warm bath or light reading when the user is tired. Furthermore, the relaxation suggestion unit may analyze the user's past relaxation history and suggest an effective relaxation method. This makes it possible to provide a relaxation experience that corresponds to the user's emotions.

[0095] The communication support system may further include a schedule management unit that manages the user's schedule. The schedule management unit, for example, automatically organizes the user's plans and reminds the user of important events and tasks. The schedule management unit may also analyze the user's past schedule history and suggest efficient time management methods. Furthermore, the schedule management unit may adjust the schedule according to the user's emotions and physical condition. This allows the user to manage their life in a more planned manner and reduce stress.

[0096] The communication support system may further include a learning support unit that supports the user's learning. For example, the learning support unit provides learning content in areas in which the user is interested and manages the progress of the learning. The learning support unit may also suggest the most suitable learning method according to the user's learning style. Furthermore, the learning support unit may also adjust the timing of the learning according to the user's emotions and concentration. This maximizes the user's learning effect and supports continuous learning.

[0097] The communication support system may further include a meal suggestion unit that estimates the user's emotions and suggests an appropriate meal based on the estimated emotions. For example, the meal suggestion unit suggests a relaxing meal when the user is stressed, and suggests a nutritious meal when the user is energetic. The meal suggestion unit may also suggest an easy-to-digest meal when the user is tired. Furthermore, the meal suggestion unit may analyze the user's past meal history and create a balanced meal plan. This makes it possible to support the user's eating habits according to their emotions.

[0098] The communication support system may further include a travel suggestion unit that estimates the user's emotions and suggests an appropriate travel destination based on the estimated emotions. For example, the travel suggestion unit may suggest a quiet resort if the user wants to relax, or suggest an active travel destination if the user is looking for adventure. The travel suggestion unit may also suggest a historical tourist spot if the user is looking for a cultural experience. Furthermore, the travel suggestion unit may analyze the user's past travel history and create a travel plan that matches the user's preferences. This makes it possible to provide a travel experience that matches the user's emotions.

[0099] The communication support system may further include a reading suggestion unit that estimates the user's emotions and suggests appropriate reading based on the estimated emotions. For example, the reading suggestion unit may suggest a calm story if the user wants to relax, and a thrilling novel if the user wants to be stimulated. The reading suggestion unit may also suggest educational books if the user wants to learn. Furthermore, the reading suggestion unit may analyze the user's past reading history and create a reading plan that matches the user's preferences. This makes it possible to provide a reading experience that matches the user's emotions.

[0100] The process flow of the second embodiment will be briefly described below.

[0101] Step 1: The learning module learns the personal information and conversational habits of family members. Personal information of family members includes names, ages, addresses, hobbies, etc. The learning module collects information such as family members' names, hobbies, and past events, and analyzes conversation patterns. Step 2: The generator generates a response based on the information learned by the trainer. The response is generated using natural language generation technology or template-based generation technology. Step 3: The voice generator reproduces the response generated by the generator in the person's own voice using voice generation technology, which includes voice synthesis technology and deep learning-based voice generation technology. Step 4: The reporting department summarizes the content of daily conversations and reports them to the family. The reports are provided to the family via email or app.

[0102] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0104] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0105] Each of the multiple elements including the learning unit, the generation unit, the voice generation unit, and the report unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart device 14, and learns personal information and conversation habits of family members. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a response based on the learned information. The voice generation unit is realized, for example, by the control unit 46A of the smart device 14, and reproduces the generated response in the person's voice using voice generation technology. The report unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes the contents of daily conversations and reports them to family members. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] 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.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0113] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] 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.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0121] Each of the multiple elements including the learning unit, the generation unit, the voice generation unit, and the report 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 learning unit is realized by the control unit 46A of the smart glasses 214, and learns personal information and conversation habits of family members. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a response based on the learned information. The voice generation unit is realized, for example, by the control unit 46A of the smart glasses 214, and reproduces the generated response in the person's voice using voice generation technology. The report unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes the contents of daily conversations and reports them to family members. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] 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.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] 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.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0132] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0134] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0137] Each of the multiple elements including the learning unit, the generation unit, the voice generation unit, and the report unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the headset type terminal 314, and learns personal information and conversation habits of family members. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a response based on the learned information. The voice generation unit is realized, for example, by the control unit 46A of the headset type terminal 314, and reproduces the generated response in the person's voice using voice generation technology. The report unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes the contents of daily conversations and reports them to the family. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 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.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] 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.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0145] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0146] 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.

[0147] 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.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0149] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0151] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0153] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] Each of the multiple elements including the learning unit, the generation unit, the voice generation unit, and the report unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the robot 414, and learns personal information and conversation habits of family members. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a response based on the learned information. The voice generation unit is realized, for example, by the control unit 46A of the robot 414, and reproduces the generated response in the person's voice using voice generation technology. The report unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes the contents of daily conversations and reports them to the family. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0155] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0156] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0157] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0158] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0159] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0160] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0161] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0162] 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.

[0163] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0164] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0165] 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.

[0166] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0167] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0168] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0169] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0170] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0171] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0172] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0173] (Appendix 1) A learning section that learns personal information and conversation habits of family members; a generation unit that generates a response based on the information learned by the learning unit; a voice generation unit that reproduces the response generated by the generation unit in the user's voice using a voice generation technique; A report section that summarizes the contents of daily conversations and reports them to family members. A system characterized by: (Appendix 2) Equipped with an information collection section that collects information such as family names, hobbies, and past events, and analyzes conversation patterns 2. The system of claim 1, (Appendix 3) The learning unit is Estimate user emotions and prioritize information to be learned based on the estimated user emotions. 2. The system of claim 1, (Appendix 4) The learning unit is Analyze past conversation history of family members and select appropriate learning methods 2. The system of claim 1, (Appendix 5) The learning unit is Filter your learning based on your family situation and interests 2. The system of claim 1, (Appendix 6) The learning unit is The system estimates the user's emotions and adjusts the timing of acquiring information to be learned based on the estimated user's emotions. 2. The system of claim 1, (Appendix 7) The learning unit is When studying, prioritize the most relevant information based on your family's geographic location 2. The system of claim 1, (Appendix 8) The learning unit is Analyze your family's social media activity and learn relevant information while studying 2. The system of claim 1, (Appendix 9) The generation unit is Infer the user's emotions and adjust the way the reply is expressed based on the estimated user's emotions 2. The system of claim 1, (Appendix 10) The generation unit is When generating responses, adjust the detail of the response based on the importance of the conversation 2. The system of claim 1, (Appendix 11) The generation unit is When generating replies, different generation algorithms are applied depending on the conversation category. 2. The system of claim 1, (Appendix 12) The generation unit is Infer user sentiment and adjust the length of responses based on the estimated sentiment 2. The system of claim 1, (Appendix 13) The generation unit is During response generation, prioritize responses based on when they were submitted in the conversation 2. The system of claim 1, (Appendix 14) The generation unit is When generating replies, adjust the order of replies based on conversation relevance 2. The system of claim 1, (Appendix 15) The voice generating unit is Infer user emotion and adjust speech tone and speed based on the estimated user emotion 2. The system of claim 1, (Appendix 16) The voice generating unit is When generating speech, past speech data is referenced to select the optimal speech generation method. 2. The system of claim 1, (Appendix 17) The voice generating unit is When generating speech, different speech generation algorithms are applied depending on the content of the conversation. 2. The system of claim 1, (Appendix 18) The voice generating unit is Estimate user emotion and adjust the volume of the audio based on the estimated user emotion 2. The system of claim 1, (Appendix 19) The voice generating unit is During speech generation, prioritize speech based on when it was submitted 2. The system of claim 1, (Appendix 20) The voice generating unit is During speech generation, adjust the order of speech based on conversational relevance 2. The system of claim 1, (Appendix 21) The report unit includes: Infer user sentiment and adjust report content based on the inferred user sentiment 2. The system of claim 1, (Appendix 22) The report unit includes: When generating a report, refer to past report data to select the optimal report generation method 2. The system of claim 1, (Appendix 23) The report unit includes: When generating reports, apply different report generation algorithms depending on the conversation category 2. The system of claim 1, (Appendix 24) The report unit includes: Infer user sentiment and adjust report length based on estimated user sentiment 2. The system of claim 1, (Appendix 25) The report unit includes: When generating reports, prioritize reports based on when the conversation was submitted 2. The system of claim 1, (Appendix 26) The report unit includes: When generating reports, adjust the order of reports based on conversation relevance 2. The system of claim 1, [Explanation of symbols]

[0174] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A learning section that learns personal information and conversation habits of family members; a generation unit that generates a response based on the information learned by the learning unit; a voice generation unit that reproduces the response generated by the generation unit in the user's voice using a voice generation technique; A report section that summarizes the contents of daily conversations and reports them to family members. A system characterized by:

2. Equipped with an information collection section that collects information such as family names, hobbies, and past events, and analyzes conversation patterns 2. The system of claim 1 .

3. The learning unit is Estimate user emotions and prioritize information to be learned based on the estimated user emotions.

2. The system of claim 1 .

4. The learning unit is Analyze past conversation history of family members and select appropriate learning methods 2. The system of claim 1 .

5. The learning unit is Filter your learning based on your family situation and interests 2. The system of claim 1 .

6. The learning unit is The system estimates the user's emotions and adjusts the timing of acquiring information to be learned based on the estimated user's emotions.

2. The system of claim 1 .

7. The learning unit is When studying, prioritize the most relevant information based on your family's geographic location 2. The system of claim 1 .

8. The learning unit is Analyze your family's social media activity and learn relevant information while studying 2. The system of claim 1 .

9. The generation unit is Infer the user's emotions and adjust the way the reply is expressed based on the estimated user's emotions 2. The system of claim 1 .

Images