System

Abstract

To provide a system capable of early detecting an abnormality in care recipients in-home care and handling appropriately.SOLUTION: A system in an embodiment includes a calling unit, a response analysis unit, an abnormality determination unit, and a contacting unit. The calling unit periodically calls out the care recipients. The response analysis unit analyzes the response to a call made by a calling unit. The abnormality determination unit determines the abnormality based on the response content analyzed by the response analysis unit. The contacting unit contacts an expert when an abnormality is determined by the abnormality determination unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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] With conventional technology, there was a problem in that it was difficult to detect abnormalities in the care recipient at an early stage and respond appropriately when providing at-home care.

[0005] The system according to the embodiment aims to detect abnormalities in a care recipient at an early stage during home care and to respond appropriately. [Means for solving the problem]

[0006] The system according to the embodiment includes a calling unit, a response analysis unit, an abnormality determination unit, and a communication unit. The calling unit periodically calls out to the care recipient. The response analysis unit analyzes a response to the calling made by the calling unit. The abnormality determination unit determines an abnormality based on the response content analyzed by the response analysis unit. The communication unit contacts an expert when an abnormality is determined by the abnormality determination unit. Effect of the Invention

[0007] The system according to the embodiment can detect abnormalities in a care recipient at an early stage during home care and respond appropriately. [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 the 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) The home care support system according to the embodiment of the present invention is a system that periodically calls out to the care recipient, records the response, and contacts the caregiver or doctor if there is an abnormality. This system provides a mechanism for periodically calling out to the care recipient, recording the response, and contacting the caregiver or doctor if there is an abnormality. For example, the system periodically calls out to the care recipient. This calling out is performed using a voice message generated by AI. For example, a message such as "Good morning. How are you feeling today?" is included. Next, the AI ​​analyzes and records the response of the care recipient. The response content is converted into text data using voice recognition technology and stored in a database. Furthermore, the AI ​​analyzes the response content and determines whether there is an abnormality. For example, if the care recipient answers "I'm not feeling well," the system determines that there is an abnormality and contacts the caregiver or doctor. This contact is performed via email or SMS. The system can also analyze the response history of the care recipient and grasp long-term changes in health condition. This makes it possible to efficiently manage the health of the care recipient. This allows the home care support system to efficiently manage the health condition of the care recipient and quickly respond to any abnormality.

[0029] The home care support system according to the embodiment includes a calling unit, a response analysis unit, an abnormality determination unit, and a contact unit. The calling unit calls the care recipient periodically. The calling unit calls the care recipient using, for example, a voice message generated by AI. For example, the calling unit can generate a message such as "Good morning. How are you feeling today?". The response analysis unit analyzes the care recipient's response to the calling made by the calling unit. The response analysis unit converts the response content into text data using, for example, a voice recognition technology, and stores the text data in a database. For example, the response analysis unit can analyze the response of the care recipient using a voice recognition technology and convert it into text data. The abnormality determination unit determines an abnormality based on the response content analyzed by the response analysis unit. For example, the abnormality determination unit determines an abnormality when the care recipient answers "I'm not feeling well". For example, the abnormality determination unit can analyze the response content and determine whether there is an abnormality. The contact unit contacts a caregiver or a doctor when an abnormality is determined by the abnormality determination unit. The communication unit communicates, for example, via email or SMS. For example, when an abnormality is detected, the communication unit can send an email or SMS to a caregiver or doctor. This allows the home care support system according to the embodiment to automate the recording of calls to and responses from the care recipient, and can quickly respond to abnormalities.

[0030] The voice calling unit periodically calls out to the care recipient. For example, the voice calling unit calls out to the care recipient using a voice message generated by AI. Specifically, the AI ​​learns the past response data and daily behavior patterns of the care recipient and generates an optimal message for each care recipient. For example, the AI ​​can generate a personalized message such as "Good morning, Tanaka-san. How are you feeling today?" by taking into account the name and preferences of the care recipient. Furthermore, the voice calling unit can call out to the care recipient at an appropriate time according to the schedule and health condition of the care recipient. For example, the voice calling unit can call out to the care recipient according to the time of waking up in the morning and meal times to support the daily rhythm of the care recipient. Furthermore, the voice calling unit can convey messages to the care recipient in multiple ways, such as not only voice messages but also screen displays and vibration notifications. This makes it possible to accommodate care recipients with hearing impairments. Furthermore, the voice calling unit can monitor the responses and reactions of the care recipient in real time and adjust the content and timing of the message as necessary. This makes it possible for the voice calling unit to provide effective and flexible support to the care recipient.

[0031] The response analysis unit analyzes the response of the care recipient to the call made by the call unit. The response analysis unit converts the response content into text data using, for example, voice recognition technology and stores it in a database. Specifically, the voice recognition technology analyzes the speech of the care recipient with high accuracy and converts it into text data. For example, if the care recipient answers, "I'm not feeling well today," the content is accurately recorded as text data. Furthermore, the response analysis unit can analyze the meaning of the response content using not only voice recognition technology but also natural language processing technology. For example, it can read the emotions and intentions from the speech content of the care recipient and grasp the psychological state and health state behind the response. Furthermore, the response analysis unit can detect abnormal patterns and changes by comparing with past response data. For example, if a care recipient who is usually healthy suddenly answers, "I'm not feeling well," it can quickly detect the change and suggest the possibility of an abnormality. Furthermore, the response analysis unit can store the analysis result in a database and monitor the long-term health condition and behavioral patterns of the care recipient. This enables the response analysis unit to analyze the responses of the care recipient with high accuracy, contributing to early detection of abnormalities and long-term health management.

[0032] The abnormality determination unit determines an abnormality based on the response content analyzed by the response analysis unit. For example, the abnormality determination unit determines an abnormality when the care recipient answers "I'm not feeling well". Specifically, the abnormality determination unit analyzes the text data provided by the response analysis unit and compares it with a preset abnormality determination criterion. For example, if the text data contains keywords such as "I'm not feeling well", "I'm in pain", or "I feel dizzy", the abnormality determination unit determines an abnormality. The abnormality determination unit can also consider not only the response content but also changes in the tone of voice and manner of speech of the care recipient. For example, if a tone of voice or manner of speech that is different from usual is detected, the abnormality determination unit determines that this is also an abnormality. Furthermore, the abnormality determination unit can analyze abnormal patterns and trends by comparing with past response data and health data. For example, if the frequency of answers of "I'm not feeling well" has increased over the past few days, the abnormality determination unit can determine that this is a sign of abnormality. The abnormality determination unit can comprehensively analyze this information and determine the presence or absence of an abnormality with high accuracy. As a result, the abnormality determination unit can monitor the health condition of the care recipient in real time and respond quickly when an abnormality occurs.

[0033] The communication unit contacts the caregiver or doctor when the abnormality determination unit determines that an abnormality has occurred. The communication unit makes the contact via, for example, email or SMS. Specifically, when an abnormality has been determined, the communication unit automatically sends a notification to the contact information of the caregiver or doctor registered in advance. For example, if the care recipient answers that he or she is "not feeling well," the communication unit can send a detailed report including the content of the response via email or SMS. Furthermore, the communication unit can select different means of communication depending on the level of urgency. For example, if the level of urgency is high, the communication unit can directly contact the caregiver or doctor via telephone or voice call. Furthermore, the communication unit can record the content of the communication so that it can be confirmed later. For example, the content of the email or SMS sent can be saved in a database so that the caregiver or doctor can confirm it later. Furthermore, the communication unit can also send a notification to the family or emergency contact of the care recipient. This makes it possible to respond quickly and appropriately when an abnormality occurs in the care recipient. Through these functions, the communication unit can quickly convey the abnormality of the care recipient to the relevant parties and encourage them to respond appropriately. This allows the communication unit to play an important role in protecting the safety and health of the care recipient.

[0034] The home care support system includes a setting unit that sets the content or frequency of the call. The setting unit cooperates with the calling unit to set the content and frequency of the call. For example, the setting unit can set the content of the call to "Good morning. How are you feeling today?". The setting unit can also set the frequency of the call to once a day, three times a week, etc. This allows the content and frequency of the call to be flexibly set. Some or all of the above-mentioned processing in the setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the setting unit can input the content and frequency of the call to AI, which can then suggest optimal content and frequency.

[0035] The home care support system includes a recording unit that records a response history. The recording unit cooperates with the response analysis unit to record the response history. For example, the recording unit can record the response content of the care recipient as voice data or text data. The recording unit can also record the date and time of the response. This makes it possible to grasp long-term changes in health condition by recording the response history. Some or all of the above-mentioned processing in the recording unit may be performed, for example, using AI, or may be performed without using AI. For example, the recording unit can input the response content to AI, which can automatically record the response history.

[0036] The home care support system includes an analysis unit that analyzes the response history. The analysis unit cooperates with the abnormality determination unit to analyze the response history. For example, the analysis unit can grasp the health condition of the care recipient in detail based on the response history. The analysis unit can analyze the response content using, for example, keyword extraction technology. The analysis unit can also analyze the emotions of the care recipient using emotion analysis technology. Furthermore, the analysis unit can statistically analyze the response history using statistical analysis technology. Thereby, the health condition of the care recipient can be grasped in detail by analyzing the response history. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the response history to AI, and the AI ​​can automatically analyze the response history.

[0037] The home care support system includes a selection unit that selects a contact method. The selection unit cooperates with the contact unit to select the contact method. For example, the selection unit can select a means for contacting a caregiver or a doctor. The selection unit can select a contact method such as a telephone call, an email, or a messaging app. This allows the optimal contact method to be used by selecting the contact method. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can input the contact method to an AI, which can then suggest the optimal contact method.

[0038] The setting unit can cooperate with the calling unit to set the content and frequency of the call. For example, the setting unit can cooperate with the calling unit to set the content of the call to "Good morning. How are you feeling today?". The setting unit can also set the frequency of the call to once a day, three times a week, etc. This allows for more effective calling by cooperating with the calling unit. Some or all of the above-mentioned processing in the setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the setting unit can input the content and frequency of the call to AI, which can then suggest optimal content and frequency.

[0039] The recording unit can cooperate with the response analysis unit to record the response history. The recording unit can cooperate with the response analysis unit to record the response content of the care recipient as voice data or text data. The recording unit can also record the date and time of the response. This allows for accurate recording of the response history by cooperating with the response analysis unit. Some or all of the above-mentioned processing in the recording unit can be performed using, for example, AI, or can be performed without using AI. For example, the recording unit can input the response content to AI, which can automatically record the response history.

[0040] The analysis unit can cooperate with the abnormality determination unit to analyze the response history. The analysis unit can cooperate with the abnormality determination unit to grasp the health condition of the care recipient in detail based on the response history. The analysis unit can analyze the response content using, for example, keyword extraction technology. The analysis unit can also analyze the emotions of the care recipient using emotion analysis technology. Furthermore, the analysis unit can statistically analyze the response history using statistical analysis technology. This enables early detection of abnormalities by cooperating with the abnormality determination unit. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the response history to AI, and the AI ​​can automatically analyze the response history.

[0041] The selection unit can cooperate with the contact unit to select a contact method. The selection unit can cooperate with the contact unit to select a means for contacting a caregiver or a doctor. The selection unit can select a contact method such as a telephone call, an email, or a message app. In this way, by cooperating with the contact unit, the optimal contact method can be selected. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can input the contact method to an AI, which can then suggest the optimal contact method.

[0042] The calling unit can analyze the past response history of the care recipient and select the optimal timing to call out to the care recipient. The calling unit can select the optimal timing to call out to the care recipient, for example, based on the time period in which the care recipient responded in the past. The calling unit can also call out to the care recipient on a specific day of the week or time period based on the care recipient's past response history. Furthermore, the calling unit can analyze the response history of the care recipient and call out to the care recipient at the timing when the care recipient responded best. This allows the care recipient to call out at the optimal timing based on the past response history. A part or all of the above-mentioned processing in the calling unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the calling unit can input the response history data of the care recipient to the generation AI and cause the generation AI to select the optimal timing to call out to the care recipient.

[0043] The voice-calling unit can customize the contents of the voice-call based on the current activity status of the care recipient when calling out to the care recipient. For example, when the care recipient is eating, the voice-calling unit can call out to the care recipient about the meal. Furthermore, when the care recipient is taking a break, the voice-calling unit can call out to the care recipient in a way that helps the care recipient relax. Furthermore, when the care recipient is exercising, the voice-calling unit can call out to encourage the care recipient to exercise. This makes it possible to call out to the care recipient according to the activity status of the care recipient. A part or all of the above-mentioned processing in the voice-calling unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice-calling unit can input activity status data of the care recipient to the generation AI and have the generation AI customize the contents of the voice-call.

[0044] When speaking to the care recipient, the voice-calling unit can give priority to speaking to highly relevant content in consideration of the geographical location information of the care recipient. For example, when the care recipient is at home, the voice-calling unit can give voice to the care recipient about activities at home. Also, when the care recipient is out, the voice-calling unit can give voice to the care recipient about precautions to take when out. Furthermore, when the care recipient is in a specific facility, the voice-calling unit can give voice to the care recipient about the facility. This makes it possible to give appropriate voice-calls based on the geographical location information. A part or all of the above-mentioned processing in the voice-calling unit may be performed, for example, using AI or may be performed without using AI. For example, the voice-calling unit can input the geographical location information of the care recipient to the generation AI and cause the generation AI to give priority to speaking to highly relevant content.

[0045] The voice-calling unit can analyze the social media activity of the care recipient and voice out relevant content when calling out to the care recipient. The voice-calling unit can, for example, call out based on content shared by the care recipient on social media. The voice-calling unit can also call out based on content in which the care recipient has shown interest on social media. Furthermore, the voice-calling unit can call out content related to accounts that the care recipient follows on social media. This makes it possible to call out based on social media activity. A part or all of the above-mentioned processing in the voice-calling unit may be performed, for example, using AI or may be performed without using AI. For example, the voice-calling unit can input social media activity data of the care recipient to the generation AI and have the generation AI voice out relevant content.

[0046] The response analysis unit can adjust the level of detail of the analysis based on the importance of the response content during response analysis. For example, the response analysis unit can perform a detailed analysis in the case of important response content. Also, the response analysis unit can perform a simplified analysis in the case of general response content. Furthermore, the response analysis unit can adjust the level of detail of the analysis in stages according to the importance of the response content. This enables analysis according to the importance of the response content. A part or all of the above-mentioned processing in the response analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the response analysis unit can input importance data of the response content to the generation AI and have the generation AI adjust the level of detail of the analysis.

[0047] The response analysis unit can apply different analysis algorithms depending on the category of the response during response analysis. For example, in the case of a response related to health, the response analysis unit can apply a health-related analysis algorithm. In addition, in the case of a response related to emotion, the response analysis unit can apply an emotion analysis algorithm. In addition, in the case of a response related to daily life, the response analysis unit can apply a daily life-related analysis algorithm. This enables analysis according to the category of the response. Some or all of the above-mentioned processing in the response analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the response analysis unit can input response category data to the generation AI and apply different analysis algorithms to the generation AI.

[0048] The response analysis unit can determine the analysis priority based on the submission time of the response when analyzing the response. The response analysis unit can, for example, prioritize the analysis of the latest response. The response analysis unit can also sequentially analyze past responses. Furthermore, the response analysis unit can gradually adjust the analysis priority according to the submission time of the response. This enables analysis based on the submission time of the response. A part or all of the above-mentioned processing in the response analysis unit can be performed, for example, using AI or can be performed without using AI. For example, the response analysis unit can input response submission time data to the generation AI and have the generation AI determine the analysis priority.

[0049] The response analysis unit can adjust the order of analysis based on the relevance of the responses during response analysis. The response analysis unit can, for example, prioritize analysis of highly relevant responses. The response analysis unit can also postpone less relevant responses. Furthermore, the response analysis unit can adjust the order of analysis stepwise according to the relevance of the responses. This enables analysis based on the relevance of the responses. A part or all of the above-mentioned processing in the response analysis unit can be performed, for example, using AI or can be performed without using AI. For example, the response analysis unit can input response relevance data to the generation AI and have the generation AI adjust the order of analysis.

[0050] The anomaly determination unit can improve the accuracy of the determination by considering the interrelationship of the response contents when determining an anomaly. The anomaly determination unit can, for example, analyze the interrelationship of the response contents and improve the accuracy of the determination of an anomaly. In addition, the anomaly determination unit can determine an anomaly by considering the relevance of the response contents. Furthermore, the anomaly determination unit can adjust the criteria for determining an anomaly based on the interrelationship of the response contents. As a result, the accuracy of the anomaly determination is improved by considering the interrelationship of the response contents. A part or all of the above-mentioned processing in the anomaly determination unit may be performed, for example, using AI or may be performed without using AI. For example, the anomaly determination unit can input the interrelationship data of the response contents to the generation AI and improve the accuracy of the determination in the generation AI.

[0051] The abnormality determination unit can make a determination taking into consideration attribute information of the care recipient when determining an abnormality. The abnormality determination unit can make a determination taking into consideration, for example, the age of the care recipient. The abnormality determination unit can also make a determination taking into consideration the gender of the care recipient. Furthermore, the abnormality determination unit can make a determination taking into consideration the health condition of the care recipient. This makes it possible to make an abnormality determination based on the attribute information of the care recipient. A part or all of the above-mentioned processing in the abnormality determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the abnormality determination unit can input attribute information data of the care recipient to the generation AI and have the generation AI make a determination.

[0052] The anomaly determination unit can make a determination taking into consideration the geographic distribution of the response when determining an anomaly. The anomaly determination unit can, for example, analyze the geographic distribution of the response to improve the accuracy of determining an anomaly. The anomaly determination unit can also make a determination of an anomaly taking into consideration the geographic distribution of the response. Furthermore, the anomaly determination unit can adjust the anomaly determination criteria based on the geographic distribution of the response. This enables an anomaly determination based on the geographic distribution of the response. A part or all of the above-mentioned processing in the anomaly determination unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the anomaly determination unit can input the geographic distribution data of the response to the generation AI and have the generation AI make a determination.

[0053] The anomaly determination unit can improve the accuracy of the determination by referring to the related literature when determining an anomaly. The anomaly determination unit can improve the accuracy of the determination of an anomaly, for example, by referring to the related literature. In addition, the anomaly determination unit can determine an anomaly based on information of the related literature. Furthermore, the anomaly determination unit can adjust the criteria for determining an anomaly based on the related literature. As a result, the accuracy of the anomaly determination is improved by referring to the related literature. A part or all of the above-mentioned processing in the anomaly determination unit may be performed, for example, using AI, or may be performed without using AI. For example, the anomaly determination unit can input related literature data to the generation AI to improve the accuracy of the determination in the generation AI.

[0054] The contact unit can select the optimal contact method by referring to the past contact history of the care recipient at the time of contact. For example, the contact unit can preferentially select a contact method that the care recipient has used in the past. The contact unit can also suggest the optimal contact means from the past contact history of the care recipient. Furthermore, the contact unit can analyze the contact history of the care recipient and select the most effective contact method. This enables the optimal contact method based on the past contact history. A part or all of the above-mentioned processing in the contact unit may be performed, for example, using AI or may be performed without using AI. For example, the contact unit can input the contact history data of the care recipient to the generation AI and have the generation AI select the optimal contact method.

[0055] The contact unit can customize the means of contact based on the current situation of the care recipient at the time of contact. For example, when the care recipient is out, the contact unit can use a mobile phone to make the contact. Also, when the care recipient is at home, the contact unit can use a landline to make the contact. Furthermore, when the care recipient is in a specific facility, the contact unit can use the contact means of the facility. This enables the means of contact according to the situation of the care recipient. A part or all of the above-mentioned processing in the contact unit may be performed using, for example, AI, or may be performed without using AI. For example, the contact unit can input the current situation data of the care recipient to the generation AI and have the generation AI customize the means of contact.

[0056] The contact unit can select the optimal contact method in consideration of the geographical location information of the care recipient at the time of contact. For example, when the care recipient is at home, the contact unit can use the home's contact means. Also, when the care recipient is out, the contact unit can use a mobile phone to make the contact. Furthermore, when the care recipient is at a specific facility, the contact unit can use the facility's contact means. This enables the optimal contact method based on the geographical location information. A part or all of the above-mentioned processing in the contact unit may be performed using, for example, AI, or may be performed without using AI. For example, the contact unit can input the geographical location information data of the care recipient to the generation AI and cause the generation AI to select the optimal contact method.

[0057] The contact unit can analyze the social media activity of the care recipient at the time of contact and suggest a means of contact. The contact unit can, for example, suggest a means of contact that the care recipient frequently uses on social media. The contact unit can also select the optimal means of contact from the social media activity of the care recipient. Furthermore, the contact unit can suggest a means of contact related to an account that the care recipient follows on social media. This enables a means of contact based on social media activity. A part or all of the above-mentioned processing in the contact unit may be performed, for example, using AI or may be performed without using AI. For example, the contact unit can input social media activity data of the care recipient to the generation AI and have the generation AI suggest a means of contact.

[0058] The setting unit can set optimal settings by referring to the past response history of the care recipient at the time of setting. For example, the setting unit can preferentially set the call contents that the care recipient liked in the past. The setting unit can also set the optimal call frequency from the past response history of the care recipient. Furthermore, the setting unit can analyze the response history of the care recipient and set the most effective call contents. This enables optimal settings based on the past response history. A part or all of the above-mentioned processing in the setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the setting unit can input the response history data of the care recipient to the generation AI and cause the generation AI to perform optimal settings.

[0059] The setting unit can perform optimal settings in consideration of the geographical location information of the care recipient at the time of setting. For example, when the care recipient is at home, the setting unit can perform settings suitable for the home. Also, when the care recipient is out, the setting unit can perform settings suitable for the destination. Furthermore, when the care recipient is in a specific facility, the setting unit can perform settings suitable for the facility. This enables optimal settings based on geographical location information. A part or all of the above-mentioned processing in the setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the setting unit can input geographical location information data of the care recipient to the generation AI and cause the generation AI to perform optimal settings.

[0060] The recording unit can adjust the level of detail of the recording based on the importance of the response content during recording. For example, the recording unit can perform detailed recording in the case of important response content. Also, the recording unit can perform simple recording in the case of general response content. Furthermore, the recording unit can adjust the level of detail of the recording stepwise according to the importance of the response content. This enables recording according to the importance of the response content. A part or all of the above-mentioned processing in the recording unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the recording unit can input importance data of the response content to the generation AI and cause the generation AI to adjust the level of detail of the recording.

[0061] The recording unit can adjust the order of recording based on the submission time of the response during recording. The recording unit can, for example, preferentially record the latest response. Also, the recording unit can sequentially record past responses. Furthermore, the recording unit can gradually adjust the order of recording according to the submission time of the response. This enables recording based on the submission time of the response. A part or all of the above-mentioned processing in the recording unit can be performed, for example, using AI or can be performed without using AI. For example, the recording unit can input response submission time data to the generation AI and have the generation AI adjust the order of recording.

[0062] The analysis unit can adjust the level of detail of the analysis based on the importance of the response content during the analysis. For example, the analysis unit can perform a detailed analysis in the case of important response content. Also, the analysis unit can perform a simplified analysis in the case of general response content. Furthermore, the analysis unit can adjust the level of detail of the analysis in stages according to the importance of the response content. This enables analysis according to the importance of the response content. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input importance data of the response content to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0063] During analysis, the analysis unit can adjust the order of analysis based on the submission time of the response. The analysis unit can, for example, prioritize the analysis of the latest response. Also, the analysis unit can sequentially analyze past responses. Furthermore, the analysis unit can gradually adjust the order of analysis according to the submission time of the response. This enables analysis based on the submission time of the response. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input response submission time data to the generation AI and have the generation AI adjust the order of analysis.

[0064] At the time of selection, the selection unit can select the optimal contact method by referring to the past contact history of the care recipient. For example, the selection unit can preferentially select a contact method that the care recipient has used in the past. The selection unit can also suggest the optimal contact means from the past contact history of the care recipient. Furthermore, the selection unit can analyze the contact history of the care recipient and select the most effective contact method. This makes it possible to select the optimal contact method based on the past contact history. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the contact history data of the care recipient to the generation AI and have the generation AI select the optimal contact method.

[0065] The selection unit can select the optimal contact method in consideration of the geographical location information of the care recipient at the time of selection. For example, when the care recipient is at home, the selection unit can use the home contact means. Also, when the care recipient is out, the selection unit can contact using a mobile phone. Furthermore, when the care recipient is at a specific facility, the selection unit can use the facility's contact means. This enables the optimal contact method based on the geographical location information. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the geographical location information data of the care recipient to the generation AI and have the generation AI select the optimal contact method.

[0066] At the time of selection, the selection unit can analyze the social media activity of the care recipient and suggest a means of contact. For example, the selection unit can suggest a means of contact that the care recipient frequently uses on social media. The selection unit can also select the optimal means of contact from the social media activity of the care recipient. Furthermore, the selection unit can suggest a means of contact related to an account that the care recipient follows on social media. This enables a means of contact based on social media activity. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI or may be performed without using AI. For example, the selection unit can input social media activity data of the care recipient to the generation AI and have the generation AI suggest a means of contact.

[0067] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0068] The home care support system can learn the daily rhythm of the person receiving care and automatically adjust the optimal timing for speaking to them. For example, it can identify the time of day after breakfast when the person is most relaxed and speak to them at that time. Also, if the person tends to feel anxious at night, it can increase the frequency of speaking to them at night. It can also learn the activity patterns of the person receiving care on weekends and provide different speaking content on weekends. This makes it possible to speak to the person receiving care flexibly according to their daily rhythm.

[0069] The home care support system can record the dietary content of the care recipient and analyze the nutritional balance. For example, the care recipient can take a photo of the meal and upload it to the system, which can analyze the dietary content. It can also evaluate the nutritional balance based on the dietary content and make dietary suggestions to supplement missing nutrients. It can also analyze the dietary records over the long term to find areas for improvement in the dietary habits. This allows for more comprehensive health management of the care recipient.

[0070] The home care support system can record the exercise history of the care recipient and detect lack of exercise. For example, it can record the type and frequency of exercise that the care recipient does daily and evaluate the amount of exercise. If lack of exercise is detected, an appropriate exercise program can be suggested. Furthermore, it can analyze exercise history over the long term and identify areas for improvement in exercise habits. This can support the exercise habits of the care recipient and contribute to maintaining their health.

[0071] The home care support system can record the sleep patterns of the care recipient and evaluate the quality of their sleep. For example, the care recipient can record the time they go to bed and the time they wake up, and measure the amount of sleep they get. It can also evaluate the quality of their sleep and suggest areas for improvement. It can also analyze sleep patterns over the long term and detect early signs of sleep disorders. This can improve the quality of sleep of the care recipient and improve their overall health.

[0072] The home care support system can record the social activities of the care recipient and provide support to reduce feelings of isolation. For example, it can record the frequency of social events and interactions that the care recipient has participated in and evaluate the level of social activity. If feelings of isolation are detected, it can suggest opportunities for local community activities and online interactions. Furthermore, it can analyze the social activity history over the long term and find specific support measures to reduce feelings of isolation. This can strengthen the social connections of the care recipient and support their mental health.

[0073] The process flow of the first embodiment will be briefly described below.

[0074] Step 1: The voice message module periodically speaks to the care recipient. For example, it generates a message such as "Good morning. How are you feeling today?" using a voice message generated by AI. Step 2: The response analysis unit analyzes the response of the care recipient to the call made by the call unit. For example, the response content is converted into text data using a voice recognition technology, and stored in a database. Step 3: The abnormality determination unit determines an abnormality based on the response content analyzed by the response analysis unit. For example, if the care recipient answers "I'm not feeling well," it is determined to be abnormal. Step 4: If the abnormality determination unit determines that an abnormality has occurred, the communication unit contacts a caregiver or a doctor. For example, the communication is performed via email or SMS.

[0075] (Example 2) The home care support system according to the embodiment of the present invention is a system that periodically calls out to the care recipient, records the response, and contacts the caregiver or doctor if there is an abnormality. This system provides a mechanism for periodically calling out to the care recipient, recording the response, and contacting the caregiver or doctor if there is an abnormality. For example, the system periodically calls out to the care recipient. This calling out is performed using a voice message generated by AI. For example, a message such as "Good morning. How are you feeling today?" is included. Next, the AI ​​analyzes and records the response of the care recipient. The response content is converted into text data using voice recognition technology and stored in a database. Furthermore, the AI ​​analyzes the response content and determines whether there is an abnormality. For example, if the care recipient answers "I'm not feeling well," the system determines that there is an abnormality and contacts the caregiver or doctor. This contact is performed via email or SMS. The system can also analyze the response history of the care recipient and grasp long-term changes in health condition. This makes it possible to efficiently manage the health of the care recipient. This allows the home care support system to efficiently manage the health condition of the care recipient and quickly respond to any abnormality.

[0076] The home care support system according to the embodiment includes a calling unit, a response analysis unit, an abnormality determination unit, and a contact unit. The calling unit calls the care recipient periodically. The calling unit calls the care recipient using, for example, a voice message generated by AI. For example, the calling unit can generate a message such as "Good morning. How are you feeling today?". The response analysis unit analyzes the care recipient's response to the calling made by the calling unit. The response analysis unit converts the response content into text data using, for example, a voice recognition technology, and stores the text data in a database. For example, the response analysis unit can analyze the response of the care recipient using a voice recognition technology and convert it into text data. The abnormality determination unit determines an abnormality based on the response content analyzed by the response analysis unit. For example, the abnormality determination unit determines an abnormality when the care recipient answers "I'm not feeling well". For example, the abnormality determination unit can analyze the response content and determine whether there is an abnormality. The contact unit contacts a caregiver or a doctor when an abnormality is determined by the abnormality determination unit. The communication unit communicates, for example, via email or SMS. For example, when an abnormality is detected, the communication unit can send an email or SMS to a caregiver or doctor. This allows the home care support system according to the embodiment to automate the recording of calls to and responses from the care recipient, and can quickly respond to abnormalities.

[0077] The voice calling unit periodically calls out to the care recipient. For example, the voice calling unit calls out to the care recipient using a voice message generated by AI. Specifically, the AI ​​learns the past response data and daily behavior patterns of the care recipient and generates an optimal message for each care recipient. For example, the AI ​​can generate a personalized message such as "Good morning, Tanaka-san. How are you feeling today?" by taking into account the name and preferences of the care recipient. Furthermore, the voice calling unit can call out to the care recipient at an appropriate time according to the schedule and health condition of the care recipient. For example, the voice calling unit can call out to the care recipient according to the time of waking up in the morning and meal times to support the daily rhythm of the care recipient. Furthermore, the voice calling unit can convey messages to the care recipient in multiple ways, such as not only voice messages but also screen displays and vibration notifications. This makes it possible to accommodate care recipients with hearing impairments. Furthermore, the voice calling unit can monitor the responses and reactions of the care recipient in real time and adjust the content and timing of the message as necessary. This makes it possible for the voice calling unit to provide effective and flexible support to the care recipient.

[0078] The response analysis unit analyzes the response of the care recipient to the call made by the call unit. The response analysis unit converts the response content into text data using, for example, voice recognition technology and stores it in a database. Specifically, the voice recognition technology analyzes the speech of the care recipient with high accuracy and converts it into text data. For example, if the care recipient answers, "I'm not feeling well today," the content is accurately recorded as text data. Furthermore, the response analysis unit can analyze the meaning of the response content using not only voice recognition technology but also natural language processing technology. For example, it can read the emotions and intentions from the speech content of the care recipient and grasp the psychological state and health state behind the response. Furthermore, the response analysis unit can detect abnormal patterns and changes by comparing with past response data. For example, if a care recipient who is usually healthy suddenly answers, "I'm not feeling well," it can quickly detect the change and suggest the possibility of an abnormality. Furthermore, the response analysis unit can store the analysis result in a database and monitor the long-term health condition and behavioral patterns of the care recipient. This enables the response analysis unit to analyze the responses of the care recipient with high accuracy, contributing to early detection of abnormalities and long-term health management.

[0079] The abnormality determination unit determines an abnormality based on the response content analyzed by the response analysis unit. For example, the abnormality determination unit determines an abnormality when the care recipient answers "I'm not feeling well". Specifically, the abnormality determination unit analyzes the text data provided by the response analysis unit and compares it with a preset abnormality determination criterion. For example, if the text data contains keywords such as "I'm not feeling well", "I'm in pain", or "I feel dizzy", the abnormality determination unit determines an abnormality. The abnormality determination unit can also consider not only the response content but also changes in the tone of voice and manner of speech of the care recipient. For example, if a tone of voice or manner of speech that is different from usual is detected, the abnormality determination unit determines that this is also an abnormality. Furthermore, the abnormality determination unit can analyze abnormal patterns and trends by comparing with past response data and health data. For example, if the frequency of answers of "I'm not feeling well" has increased over the past few days, the abnormality determination unit can determine that this is a sign of abnormality. The abnormality determination unit can comprehensively analyze this information and determine the presence or absence of an abnormality with high accuracy. As a result, the abnormality determination unit can monitor the health condition of the care recipient in real time and respond quickly when an abnormality occurs.

[0080] The communication unit contacts the caregiver or doctor when the abnormality determination unit determines that an abnormality has occurred. The communication unit makes the contact via, for example, email or SMS. Specifically, when an abnormality has been determined, the communication unit automatically sends a notification to the contact information of the caregiver or doctor registered in advance. For example, if the care recipient answers that he or she is "not feeling well," the communication unit can send a detailed report including the content of the response via email or SMS. Furthermore, the communication unit can select different means of communication depending on the level of urgency. For example, if the level of urgency is high, the communication unit can directly contact the caregiver or doctor via telephone or voice call. Furthermore, the communication unit can record the content of the communication so that it can be confirmed later. For example, the content of the email or SMS sent can be saved in a database so that the caregiver or doctor can confirm it later. Furthermore, the communication unit can also send a notification to the family or emergency contact of the care recipient. This makes it possible to respond quickly and appropriately when an abnormality occurs in the care recipient. Through these functions, the communication unit can quickly convey the abnormality of the care recipient to the relevant parties and encourage them to respond appropriately. This allows the communication unit to play an important role in protecting the safety and health of the care recipient.

[0081] The home care support system includes a setting unit that sets the content or frequency of the call. The setting unit cooperates with the calling unit to set the content and frequency of the call. For example, the setting unit can set the content of the call to "Good morning. How are you feeling today?". The setting unit can also set the frequency of the call to once a day, three times a week, etc. This allows the content and frequency of the call to be flexibly set. Some or all of the above-mentioned processing in the setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the setting unit can input the content and frequency of the call to AI, which can then suggest optimal content and frequency.

[0082] The home care support system includes a recording unit that records a response history. The recording unit cooperates with the response analysis unit to record the response history. For example, the recording unit can record the response content of the care recipient as voice data or text data. The recording unit can also record the date and time of the response. This makes it possible to grasp long-term changes in health condition by recording the response history. Some or all of the above-mentioned processing in the recording unit may be performed, for example, using AI, or may be performed without using AI. For example, the recording unit can input the response content to AI, which can automatically record the response history.

[0083] The home care support system includes an analysis unit that analyzes the response history. The analysis unit cooperates with the abnormality determination unit to analyze the response history. For example, the analysis unit can grasp the health condition of the care recipient in detail based on the response history. The analysis unit can analyze the response content using, for example, keyword extraction technology. The analysis unit can also analyze the emotions of the care recipient using emotion analysis technology. Furthermore, the analysis unit can statistically analyze the response history using statistical analysis technology. Thereby, the health condition of the care recipient can be grasped in detail by analyzing the response history. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the response history to AI, and the AI ​​can automatically analyze the response history.

[0084] The home care support system includes a selection unit that selects a contact method. The selection unit cooperates with the contact unit to select the contact method. For example, the selection unit can select a means for contacting a caregiver or a doctor. The selection unit can select a contact method such as a telephone call, an email, or a messaging app. This allows the optimal contact method to be used by selecting the contact method. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can input the contact method to an AI, which can then suggest the optimal contact method.

[0085] The setting unit can cooperate with the calling unit to set the content and frequency of the call. For example, the setting unit can cooperate with the calling unit to set the content of the call to "Good morning. How are you feeling today?". The setting unit can also set the frequency of the call to once a day, three times a week, etc. This allows for more effective calling by cooperating with the calling unit. Some or all of the above-mentioned processing in the setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the setting unit can input the content and frequency of the call to AI, which can then suggest optimal content and frequency.

[0086] The recording unit can cooperate with the response analysis unit to record the response history. The recording unit can cooperate with the response analysis unit to record the response content of the care recipient as voice data or text data. The recording unit can also record the date and time of the response. This allows for accurate recording of the response history by cooperating with the response analysis unit. Some or all of the above-mentioned processing in the recording unit can be performed using, for example, AI, or can be performed without using AI. For example, the recording unit can input the response content to AI, which can automatically record the response history.

[0087] The analysis unit can cooperate with the abnormality determination unit to analyze the response history. The analysis unit can cooperate with the abnormality determination unit to grasp the health condition of the care recipient in detail based on the response history. The analysis unit can analyze the response content using, for example, keyword extraction technology. The analysis unit can also analyze the emotions of the care recipient using emotion analysis technology. Furthermore, the analysis unit can statistically analyze the response history using statistical analysis technology. This enables early detection of abnormalities by cooperating with the abnormality determination unit. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the response history to AI, and the AI ​​can automatically analyze the response history.

[0088] The selection unit can cooperate with the contact unit to select a contact method. The selection unit can cooperate with the contact unit to select a means for contacting a caregiver or a doctor. The selection unit can select a contact method such as a telephone call, an email, or a message app. In this way, by cooperating with the contact unit, the optimal contact method can be selected. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can input the contact method to an AI, which can then suggest the optimal contact method.

[0089] The voice-calling unit can estimate the emotion of the care recipient and adjust the content of the voice-call based on the estimated emotion. For example, when the care recipient is stressed, the voice-calling unit can speak to the care recipient in a gentle manner to relax the care recipient. Furthermore, when the care recipient is in good spirits, the voice-calling unit can speak to the care recipient in an active manner. Furthermore, when the care recipient is anxious, the voice-calling unit can speak to the care recipient in a manner that gives the care recipient a sense of security. This makes it possible to voice the care recipient according to his / her emotion. The emotion estimation is realized by 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-calling unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the voice-calling unit can input emotion data of the care recipient to the generation AI and cause the generation AI to execute emotion estimation.

[0090] The calling unit can analyze the past response history of the care recipient and select the optimal timing to call out to the care recipient. The calling unit can select the optimal timing to call out to the care recipient, for example, based on the time period in which the care recipient responded in the past. The calling unit can also call out to the care recipient on a specific day of the week or time period based on the care recipient's past response history. Furthermore, the calling unit can analyze the response history of the care recipient and call out to the care recipient at the timing when the care recipient responded best. This allows the care recipient to call out at the optimal timing based on the past response history. A part or all of the above-mentioned processing in the calling unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the calling unit can input the response history data of the care recipient to the generation AI and cause the generation AI to select the optimal timing to call out to the care recipient.

[0091] The voice-calling unit can customize the contents of the voice-call based on the current activity status of the care recipient when calling out to the care recipient. For example, when the care recipient is eating, the voice-calling unit can call out to the care recipient about the meal. Furthermore, when the care recipient is taking a break, the voice-calling unit can call out to the care recipient in a way that helps the care recipient relax. Furthermore, when the care recipient is exercising, the voice-calling unit can call out to encourage the care recipient to exercise. This makes it possible to call out to the care recipient according to the activity status of the care recipient. A part or all of the above-mentioned processing in the voice-calling unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice-calling unit can input activity status data of the care recipient to the generation AI and have the generation AI customize the contents of the voice-call.

[0092] The calling unit can estimate the emotion of the care recipient and adjust the frequency of calling based on the estimated emotion. For example, the calling unit can reduce the frequency of calling when the care recipient is stressed. Also, the calling unit can increase the frequency of calling when the care recipient is in good spirits. Furthermore, the calling unit can call the care recipient at an appropriate frequency when the care recipient is anxious. This allows calling at a frequency according to the emotion of the care recipient. 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 calling unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the calling unit can input emotion data of the care recipient to the generation AI and have the generation AI adjust the frequency of calling.

[0093] When speaking to the care recipient, the voice-calling unit can give priority to speaking to highly relevant content in consideration of the geographical location information of the care recipient. For example, when the care recipient is at home, the voice-calling unit can give voice to the care recipient about activities at home. Also, when the care recipient is out, the voice-calling unit can give voice to the care recipient about precautions to take when out. Furthermore, when the care recipient is in a specific facility, the voice-calling unit can give voice to the care recipient about the facility. This makes it possible to give appropriate voice-calls based on the geographical location information. A part or all of the above-mentioned processing in the voice-calling unit may be performed, for example, using AI or may be performed without using AI. For example, the voice-calling unit can input the geographical location information of the care recipient to the generation AI and cause the generation AI to give priority to speaking to highly relevant content.

[0094] The voice-calling unit can analyze the social media activity of the care recipient and voice out relevant content when calling out to the care recipient. The voice-calling unit can, for example, call out based on content shared by the care recipient on social media. The voice-calling unit can also call out based on content in which the care recipient has shown interest on social media. Furthermore, the voice-calling unit can call out content related to accounts that the care recipient follows on social media. This makes it possible to call out based on social media activity. A part or all of the above-mentioned processing in the voice-calling unit may be performed, for example, using AI or may be performed without using AI. For example, the voice-calling unit can input social media activity data of the care recipient to the generation AI and have the generation AI voice out relevant content.

[0095] The response analysis unit can estimate the emotion of the care recipient and adjust the response analysis method based on the estimated emotion. For example, the response analysis unit can simplify the response analysis when the care recipient is stressed. In addition, the response analysis unit can perform a detailed analysis when the care recipient is in good spirits. Furthermore, the response analysis unit can perform an analysis that gives a sense of security when the care recipient is anxious. This enables an analysis method according to the emotion of the care recipient. 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 response analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the response analysis unit can input emotion data of the care recipient to the generation AI and cause the generation AI to adjust the response analysis method.

[0096] The response analysis unit can adjust the level of detail of the analysis based on the importance of the response content during response analysis. For example, the response analysis unit can perform a detailed analysis in the case of important response content. Also, the response analysis unit can perform a simplified analysis in the case of general response content. Furthermore, the response analysis unit can adjust the level of detail of the analysis in stages according to the importance of the response content. This enables analysis according to the importance of the response content. A part or all of the above-mentioned processing in the response analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the response analysis unit can input importance data of the response content to the generation AI and have the generation AI adjust the level of detail of the analysis.

[0097] The response analysis unit can apply different analysis algorithms depending on the category of the response during response analysis. For example, in the case of a response related to health, the response analysis unit can apply a health-related analysis algorithm. In addition, in the case of a response related to emotion, the response analysis unit can apply an emotion analysis algorithm. In addition, in the case of a response related to daily life, the response analysis unit can apply a daily life-related analysis algorithm. This enables analysis according to the category of the response. Some or all of the above-mentioned processing in the response analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the response analysis unit can input response category data to the generation AI and apply different analysis algorithms to the generation AI.

[0098] The response analysis unit can estimate the emotion of the care recipient and adjust the analysis order of the responses based on the estimated emotion. For example, when the care recipient is stressed, the response analysis unit can prioritize analysis of important responses. Furthermore, when the care recipient is in good spirits, the response analysis unit can analyze all responses evenly. Furthermore, when the care recipient is anxious, the response analysis unit can prioritize analysis of responses that give a sense of security. This enables the analysis order according to the emotion of the care recipient. 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 response analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the response analysis unit can input emotion data of the care recipient to the generation AI and have the generation AI adjust the analysis order of the responses.

[0099] The response analysis unit can determine the analysis priority based on the submission time of the response when analyzing the response. The response analysis unit can, for example, prioritize the analysis of the latest response. The response analysis unit can also sequentially analyze past responses. Furthermore, the response analysis unit can gradually adjust the analysis priority according to the submission time of the response. This enables analysis based on the submission time of the response. A part or all of the above-mentioned processing in the response analysis unit can be performed, for example, using AI or can be performed without using AI. For example, the response analysis unit can input response submission time data to the generation AI and have the generation AI determine the analysis priority.

[0100] The response analysis unit can adjust the order of analysis based on the relevance of the responses during response analysis. The response analysis unit can, for example, prioritize analysis of highly relevant responses. The response analysis unit can also postpone less relevant responses. Furthermore, the response analysis unit can adjust the order of analysis stepwise according to the relevance of the responses. This enables analysis based on the relevance of the responses. A part or all of the above-mentioned processing in the response analysis unit can be performed, for example, using AI or can be performed without using AI. For example, the response analysis unit can input response relevance data to the generation AI and have the generation AI adjust the order of analysis.

[0101] The abnormality determination unit can estimate the emotion of the care recipient and adjust the abnormality determination criteria based on the estimated emotion. For example, when the care recipient is stressed, the abnormality determination unit can relax the abnormality determination criteria. Also, when the care recipient is in good spirits, the abnormality determination unit can tighten the abnormality determination criteria. Furthermore, when the care recipient is anxious, the abnormality determination unit can apply a determination criterion that gives a sense of security. This enables abnormality determination according to the emotion of the care recipient. 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 abnormality determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the abnormality determination unit can input emotion data of the care recipient to the generation AI and cause the generation AI to adjust the abnormality determination criteria.

[0102] The anomaly determination unit can improve the accuracy of the determination by considering the interrelationship of the response contents when determining an anomaly. The anomaly determination unit can, for example, analyze the interrelationship of the response contents and improve the accuracy of the determination of an anomaly. In addition, the anomaly determination unit can determine an anomaly by considering the relevance of the response contents. Furthermore, the anomaly determination unit can adjust the criteria for determining an anomaly based on the interrelationship of the response contents. As a result, the accuracy of the anomaly determination is improved by considering the interrelationship of the response contents. A part or all of the above-mentioned processing in the anomaly determination unit may be performed, for example, using AI or may be performed without using AI. For example, the anomaly determination unit can input the interrelationship data of the response contents to the generation AI and improve the accuracy of the determination in the generation AI.

[0103] The abnormality determination unit can make a determination taking into consideration attribute information of the care recipient when determining an abnormality. The abnormality determination unit can make a determination taking into consideration, for example, the age of the care recipient. The abnormality determination unit can also make a determination taking into consideration the gender of the care recipient. Furthermore, the abnormality determination unit can make a determination taking into consideration the health condition of the care recipient. This makes it possible to make an abnormality determination based on the attribute information of the care recipient. A part or all of the above-mentioned processing in the abnormality determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the abnormality determination unit can input attribute information data of the care recipient to the generation AI and have the generation AI make a determination.

[0104] The abnormality determination unit can estimate the emotion of the care recipient and adjust the order of displaying the abnormality determination results based on the estimated emotion. For example, when the care recipient is stressed, the abnormality determination unit can preferentially display important abnormalities. Furthermore, when the care recipient is in good health, the abnormality determination unit can display all abnormalities evenly. Furthermore, when the care recipient is anxious, the abnormality determination unit can preferentially display abnormalities that give a sense of security. This makes it possible to display the abnormality determination results according to the emotion of the care recipient. 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 abnormality determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the abnormality determination unit can input emotion data of the care recipient to the generation AI and cause the generation AI to adjust the display order of the abnormality determination results.

[0105] The anomaly determination unit can make a determination taking into consideration the geographic distribution of the response when determining an anomaly. The anomaly determination unit can, for example, analyze the geographic distribution of the response to improve the accuracy of determining an anomaly. The anomaly determination unit can also make a determination of an anomaly taking into consideration the geographic distribution of the response. Furthermore, the anomaly determination unit can adjust the anomaly determination criteria based on the geographic distribution of the response. This enables an anomaly determination based on the geographic distribution of the response. A part or all of the above-mentioned processing in the anomaly determination unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the anomaly determination unit can input the geographic distribution data of the response to the generation AI and have the generation AI make a determination.

[0106] The anomaly determination unit can improve the accuracy of the determination by referring to the related literature when determining an anomaly. The anomaly determination unit can improve the accuracy of the determination of an anomaly, for example, by referring to the related literature. In addition, the anomaly determination unit can determine an anomaly based on information of the related literature. Furthermore, the anomaly determination unit can adjust the criteria for determining an anomaly based on the related literature. As a result, the accuracy of the anomaly determination is improved by referring to the related literature. A part or all of the above-mentioned processing in the anomaly determination unit may be performed, for example, using AI, or may be performed without using AI. For example, the anomaly determination unit can input related literature data to the generation AI to improve the accuracy of the determination in the generation AI.

[0107] The communication unit can estimate the emotion of the care recipient and adjust the method of contact based on the estimated emotion. For example, when the care recipient is stressed, the communication unit can contact the care recipient using gentle words. Furthermore, when the care recipient is in good spirits, the communication unit can contact the care recipient using active words. Furthermore, when the care recipient is anxious, the communication unit can contact the care recipient using words that give a sense of security. This enables a method of contact according to the emotion of the care recipient. 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 communication unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the communication unit can input emotion data of the care recipient to the generation AI and have the generation AI adjust the method of contact.

[0108] The contact unit can select the optimal contact method by referring to the past contact history of the care recipient at the time of contact. For example, the contact unit can preferentially select a contact method that the care recipient has used in the past. The contact unit can also suggest the optimal contact means from the past contact history of the care recipient. Furthermore, the contact unit can analyze the contact history of the care recipient and select the most effective contact method. This enables the optimal contact method based on the past contact history. A part or all of the above-mentioned processing in the contact unit may be performed, for example, using AI or may be performed without using AI. For example, the contact unit can input the contact history data of the care recipient to the generation AI and have the generation AI select the optimal contact method.

[0109] The contact unit can customize the means of contact based on the current situation of the care recipient at the time of contact. For example, when the care recipient is out, the contact unit can use a mobile phone to make the contact. Also, when the care recipient is at home, the contact unit can use a landline to make the contact. Furthermore, when the care recipient is in a specific facility, the contact unit can use the contact means of the facility. This enables the means of contact according to the situation of the care recipient. A part or all of the above-mentioned processing in the contact unit may be performed using, for example, AI, or may be performed without using AI. For example, the contact unit can input the current situation data of the care recipient to the generation AI and have the generation AI customize the means of contact.

[0110] The communication unit can estimate the emotion of the care recipient and determine the priority of communication based on the estimated emotion. For example, when the care recipient is stressed, the communication unit can prioritize important communication. Also, when the care recipient is in good spirits, the communication unit can make all communication equally. Furthermore, when the care recipient is anxious, the communication unit can prioritize communication that gives a sense of security. This enables the priority of communication according to the emotion of the care recipient. 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 communication unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the communication unit can input emotion data of the care recipient to the generation AI and have the generation AI determine the priority of communication.

[0111] The contact unit can select the optimal contact method in consideration of the geographical location information of the care recipient at the time of contact. For example, when the care recipient is at home, the contact unit can use the home's contact means. Also, when the care recipient is out, the contact unit can use a mobile phone to make the contact. Furthermore, when the care recipient is at a specific facility, the contact unit can use the facility's contact means. This enables the optimal contact method based on the geographical location information. A part or all of the above-mentioned processing in the contact unit may be performed using, for example, AI, or may be performed without using AI. For example, the contact unit can input the geographical location information data of the care recipient to the generation AI and cause the generation AI to select the optimal contact method.

[0112] The contact unit can analyze the social media activity of the care recipient at the time of contact and suggest a means of contact. The contact unit can, for example, suggest a means of contact that the care recipient frequently uses on social media. The contact unit can also select the optimal means of contact from the social media activity of the care recipient. Furthermore, the contact unit can suggest a means of contact related to an account that the care recipient follows on social media. This enables a means of contact based on social media activity. A part or all of the above-mentioned processing in the contact unit may be performed, for example, using AI or may be performed without using AI. For example, the contact unit can input social media activity data of the care recipient to the generation AI and have the generation AI suggest a means of contact.

[0113] The setting unit can estimate the emotion of the care recipient and set the content and frequency of the voice based on the estimated emotion. For example, when the care recipient is stressed, the setting unit can reduce the frequency of voices and make the content gentler. Also, when the care recipient is in good spirits, the setting unit can increase the frequency of voices and make the content more active. Furthermore, when the care recipient is anxious, the setting unit can set voices that give a sense of security. This makes it possible to set the content and frequency of voices according to the emotion of the care recipient. 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 setting unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the setting unit can input emotion data of the care recipient to the generation AI and set the content and frequency of voices in the generation AI.

[0114] The setting unit can set optimal settings by referring to the past response history of the care recipient at the time of setting. For example, the setting unit can preferentially set the call contents that the care recipient liked in the past. The setting unit can also set the optimal call frequency from the past response history of the care recipient. Furthermore, the setting unit can analyze the response history of the care recipient and set the most effective call contents. This enables optimal settings based on the past response history. A part or all of the above-mentioned processing in the setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the setting unit can input the response history data of the care recipient to the generation AI and cause the generation AI to perform optimal settings.

[0115] The setting unit can estimate the emotion of the care recipient and determine the priority of the settings based on the estimated emotion. For example, when the care recipient is stressed, the setting unit can prioritize important settings. Also, when the care recipient is in good spirits, the setting unit can perform all settings equally. Furthermore, when the care recipient is anxious, the setting unit can prioritize settings that give a sense of security. This enables the prioritization of settings according to the emotion of the care recipient. The estimation of 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 setting unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the setting unit can input emotion data of the care recipient to the generation AI and have the generation AI determine the priority of the settings.

[0116] The setting unit can perform optimal settings in consideration of the geographical location information of the care recipient at the time of setting. For example, when the care recipient is at home, the setting unit can perform settings suitable for the home. Also, when the care recipient is out, the setting unit can perform settings suitable for the destination. Furthermore, when the care recipient is in a specific facility, the setting unit can perform settings suitable for the facility. This enables optimal settings based on geographical location information. A part or all of the above-mentioned processing in the setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the setting unit can input geographical location information data of the care recipient to the generation AI and cause the generation AI to perform optimal settings.

[0117] The recording unit can estimate the emotion of the care recipient and adjust the recording method of the response history based on the estimated emotion. For example, when the care recipient is stressed, the recording unit can use a simple recording method. Furthermore, when the care recipient is in good spirits, the recording unit can use a detailed recording method. Furthermore, when the care recipient is anxious, the recording unit can use a recording method that gives a sense of security. This enables a recording method according to the emotion of the care recipient. 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 recording unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the recording unit can input emotion data of the care recipient to the generation AI and have the generation AI adjust the recording method.

[0118] The recording unit can adjust the level of detail of the recording based on the importance of the response content during recording. For example, the recording unit can perform detailed recording in the case of important response content. Also, the recording unit can perform simple recording in the case of general response content. Furthermore, the recording unit can adjust the level of detail of the recording stepwise according to the importance of the response content. This enables recording according to the importance of the response content. A part or all of the above-mentioned processing in the recording unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the recording unit can input importance data of the response content to the generation AI and cause the generation AI to adjust the level of detail of the recording.

[0119] The recording unit can estimate the emotion of the care recipient and determine the priority of recording based on the estimated emotion. For example, when the care recipient is stressed, the recording unit can preferentially record important responses. Moreover, when the care recipient is in good spirits, the recording unit can record all responses evenly. Furthermore, when the care recipient is anxious, the recording unit can preferentially record responses that give a sense of security. This enables the priority of recording according to the emotion of the care recipient. 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 recording unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the recording unit can input emotion data of the care recipient to the generation AI and have the generation AI determine the priority of recording.

[0120] The recording unit can adjust the order of recording based on the submission time of the response during recording. The recording unit can, for example, preferentially record the latest response. Also, the recording unit can sequentially record past responses. Furthermore, the recording unit can gradually adjust the order of recording according to the submission time of the response. This enables recording based on the submission time of the response. A part or all of the above-mentioned processing in the recording unit can be performed, for example, using AI or can be performed without using AI. For example, the recording unit can input response submission time data to the generation AI and have the generation AI adjust the order of recording.

[0121] The analysis unit can estimate the emotion of the care recipient and adjust the analysis method of the response history based on the estimated emotion. For example, when the care recipient is stressed, the analysis unit can use a simple analysis method. Furthermore, when the care recipient is in good spirits, the analysis unit can use a detailed analysis method. Furthermore, when the care recipient is anxious, the analysis unit can use an analysis method that gives a sense of security. This enables an analysis method according to the emotion of the care recipient. 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 analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input emotion data of the care recipient to the generation AI and have the generation AI adjust the analysis method.

[0122] The analysis unit can adjust the level of detail of the analysis based on the importance of the response content during the analysis. For example, the analysis unit can perform a detailed analysis in the case of important response content. Also, the analysis unit can perform a simplified analysis in the case of general response content. Furthermore, the analysis unit can adjust the level of detail of the analysis in stages according to the importance of the response content. This enables analysis according to the importance of the response content. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input importance data of the response content to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0123] The analysis unit can estimate the emotion of the care recipient and determine the priority of the analysis based on the estimated emotion. For example, when the care recipient is stressed, the analysis unit can prioritize the analysis of important responses. Furthermore, when the care recipient is in good spirits, the analysis unit can analyze all responses equally. Furthermore, when the care recipient is anxious, the analysis unit can prioritize the analysis of responses that give a sense of security. This enables the analysis priority to be determined according to the emotion of the care recipient. 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 analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input emotion data of the care recipient to the generation AI and have the generation AI determine the priority of the analysis.

[0124] During analysis, the analysis unit can adjust the order of analysis based on the submission time of the response. The analysis unit can, for example, prioritize the analysis of the latest response. Also, the analysis unit can sequentially analyze past responses. Furthermore, the analysis unit can gradually adjust the order of analysis according to the submission time of the response. This enables analysis based on the submission time of the response. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input response submission time data to the generation AI and have the generation AI adjust the order of analysis.

[0125] The selection unit can estimate the emotion of the care recipient and adjust the selection of the contact method based on the estimated emotion. For example, when the care recipient is stressed, the selection unit can contact the care recipient using gentle words. Furthermore, when the care recipient is in good spirits, the selection unit can contact the care recipient using active words. Furthermore, when the care recipient is anxious, the selection unit can contact the care recipient using words that give a sense of security. This makes it possible to select a contact method according to the emotion of the care recipient. 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 selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can input emotion data of the care recipient to the generation AI and have the generation AI adjust the selection of the contact method.

[0126] At the time of selection, the selection unit can select the optimal contact method by referring to the past contact history of the care recipient. For example, the selection unit can preferentially select a contact method that the care recipient has used in the past. The selection unit can also suggest the optimal contact means from the past contact history of the care recipient. Furthermore, the selection unit can analyze the contact history of the care recipient and select the most effective contact method. This makes it possible to select the optimal contact method based on the past contact history. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the contact history data of the care recipient to the generation AI and have the generation AI select the optimal contact method.

[0127] The selection unit can estimate the emotion of the care recipient and determine the priority of the contact method based on the estimated emotion. For example, when the care recipient is stressed, the selection unit can prioritize important contact. Also, when the care recipient is in good spirits, the selection unit can make all contacts equally. Furthermore, when the care recipient is anxious, the selection unit can prioritize contacts that give a sense of security. This enables the priority of the contact method according to the emotion of the care recipient. 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 selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can input emotion data of the care recipient to the generation AI and have the generation AI determine the priority of the contact method.

[0128] The selection unit can select the optimal contact method in consideration of the geographical location information of the care recipient at the time of selection. For example, when the care recipient is at home, the selection unit can use the home contact means. Also, when the care recipient is out, the selection unit can contact using a mobile phone. Furthermore, when the care recipient is at a specific facility, the selection unit can use the facility's contact means. This enables the optimal contact method based on the geographical location information. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the geographical location information data of the care recipient to the generation AI and have the generation AI select the optimal contact method.

[0129] At the time of selection, the selection unit can analyze the social media activity of the care recipient and suggest a means of contact. For example, the selection unit can suggest a means of contact that the care recipient frequently uses on social media. The selection unit can also select the optimal means of contact from the social media activity of the care recipient. Furthermore, the selection unit can suggest a means of contact related to an account that the care recipient follows on social media. This enables a means of contact based on social media activity. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI or may be performed without using AI. For example, the selection unit can input social media activity data of the care recipient to the generation AI and have the generation AI suggest a means of contact.

[0130] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0131] The home care support system can learn the daily rhythm of the person receiving care and automatically adjust the optimal timing for speaking to them. For example, it can identify the time of day after breakfast when the person is most relaxed and speak to them at that time. Also, if the person tends to feel anxious at night, it can increase the frequency of speaking to them at night. It can also learn the activity patterns of the person receiving care on weekends and provide different speaking content on weekends. This makes it possible to speak to the person receiving care flexibly according to their daily rhythm.

[0132] The home care support system can record the dietary content of the care recipient and analyze the nutritional balance. For example, the care recipient can take a photo of the meal and upload it to the system, which can analyze the dietary content. It can also evaluate the nutritional balance based on the dietary content and make dietary suggestions to supplement missing nutrients. It can also analyze the dietary records over the long term to find areas for improvement in the dietary habits. This allows for more comprehensive health management of the care recipient.

[0133] The home care support system can record the exercise history of the care recipient and detect lack of exercise. For example, it can record the type and frequency of exercise that the care recipient does daily and evaluate the amount of exercise. If lack of exercise is detected, an appropriate exercise program can be suggested. Furthermore, it can analyze exercise history over the long term and identify areas for improvement in exercise habits. This can support the exercise habits of the care recipient and contribute to maintaining their health.

[0134] The home care support system can record the sleep patterns of the care recipient and evaluate the quality of their sleep. For example, the care recipient can record the time they go to bed and the time they wake up, and measure the amount of sleep they get. It can also evaluate the quality of their sleep and suggest areas for improvement. It can also analyze sleep patterns over the long term and detect early signs of sleep disorders. This can improve the quality of sleep of the care recipient and improve their overall health.

[0135] The home care support system can record the social activities of the care recipient and provide support to reduce feelings of isolation. For example, it can record the frequency of social events and interactions that the care recipient has participated in and evaluate the level of social activity. If feelings of isolation are detected, it can suggest opportunities for local community activities and online interactions. Furthermore, it can analyze the social activity history over the long term and find specific support measures to reduce feelings of isolation. This can strengthen the social connections of the care recipient and support their mental health.

[0136] The home care support system can estimate the emotions of the person receiving care and adjust the content of the messages based on the estimated emotions. For example, if the person receiving care is feeling stressed, the system can speak to them in a gentle manner to help them relax. If the person receiving care is feeling energetic, the system can speak to them in an active manner. If the person receiving care is feeling anxious, the system can speak to them in a way that gives them a sense of security. This makes it possible to speak to the person receiving care in accordance with their emotions.

[0137] The home care support system can estimate the emotions of the care recipient and adjust the response analysis method based on the estimated emotions. For example, if the care recipient is feeling stressed, the response analysis can be simplified. If the care recipient is feeling energetic, a detailed analysis can be performed. Furthermore, if the care recipient is feeling anxious, an analysis that gives a sense of security can be performed. This makes it possible to use an analysis method that corresponds to the emotions of the care recipient.

[0138] The home care support system can estimate the emotions of the care recipient and adjust the criteria for determining abnormalities based on the estimated emotions. For example, if the care recipient is feeling stressed, the criteria for determining abnormalities can be relaxed. If the care recipient is in good health, the criteria for determining abnormalities can be made stricter. Furthermore, if the care recipient is feeling anxious, criteria that give a sense of security can be applied. This makes it possible to determine abnormalities according to the emotions of the care recipient.

[0139] The home care support system can estimate the emotions of the person receiving care and adjust the method of contact based on the estimated emotions. For example, if the person receiving care is feeling stressed, it can contact them using kind words. If the person receiving care is feeling energetic, it can contact them using active words. If the person receiving care is feeling anxious, it can contact them using words that give a sense of security. This makes it possible to contact the person receiving care in a way that suits their emotions.

[0140] The home care support system can estimate the emotions of the person receiving care and determine the priority of recording based on the estimated emotions. For example, if the person receiving care is feeling stressed, important responses can be recorded with priority. If the person receiving care is in good spirits, all responses can be recorded equally. If the person receiving care is feeling anxious, responses that give a sense of security can be recorded with priority. This makes it possible to prioritize recording according to the emotions of the person receiving care.

[0141] The process flow of the second embodiment will be briefly described below.

[0142] Step 1: The voice message module periodically speaks to the care recipient. For example, it generates a message such as "Good morning. How are you feeling today?" using a voice message generated by AI. Step 2: The response analysis unit analyzes the response of the care recipient to the call made by the call unit. For example, the response content is converted into text data using a voice recognition technology, and stored in a database. Step 3: The abnormality determination unit determines an abnormality based on the response content analyzed by the response analysis unit. For example, if the care recipient answers "I'm not feeling well," it is determined to be abnormal. Step 4: If the abnormality determination unit determines that an abnormality has occurred, the communication unit contacts a caregiver or a doctor. For example, the communication is performed via email or SMS.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] Each of the multiple elements including the above-mentioned calling unit, response analysis unit, abnormality determination unit, contact unit, setting unit, recording unit, analysis unit, and selection unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the calling unit is realized by the control unit 46A of the smart device 14, and calls the care recipient using a voice message generated by AI. The response analysis unit is realized by the specific processing unit 290 of the data processing device 12, and converts the response content into text data using voice recognition technology and stores it in the database 24. The abnormality determination unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the response content to determine an abnormality. The contact unit is realized by the control unit 46A of the smart device 14, and sends an email or SMS to a caregiver or a doctor when an abnormality is determined. The setting unit is realized by the control unit 46A of the smart device 14, and sets the content and frequency of the calling. The recording unit is realized by the specific processing unit 290 of the data processing device 12, and records the response history. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the response history. The selection unit is realized by the control unit 46A of the smart device 14, and selects the contact method. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0147] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] Each of the multiple elements including the above-mentioned calling unit, response analysis unit, abnormality determination unit, contact unit, setting unit, recording unit, analysis unit, and selection unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the calling unit is realized by the control unit 46A of the smart glasses 214, and calls the care recipient using a voice message generated by AI. The response analysis unit is realized by the specific processing unit 290 of the data processing device 12, and converts the response content into text data using voice recognition technology and stores it in the database 24. The abnormality determination unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the response content to determine an abnormality. The contact unit is realized by the control unit 46A of the smart glasses 214, and sends an email or SMS to a caregiver or a doctor when an abnormality is determined. The setting unit is realized by the control unit 46A of the smart glasses 214, and sets the content and frequency of the call. The recording unit is realized by the specific processing unit 290 of the data processing device 12, and records the response history. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the response history. The selection unit is realized by the control unit 46A of the smart glasses 214, and selects the contact method. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0163] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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).

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] Each of the multiple elements including the above-mentioned calling unit, response analysis unit, abnormality determination unit, contact unit, setting unit, recording unit, analysis unit, and selection unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the calling unit is realized by the control unit 46A of the headset type terminal 314, and calls the care recipient using a voice message generated by AI. The response analysis unit is realized by the specific processing unit 290 of the data processing device 12, and converts the response content into text data using voice recognition technology and stores it in the database 24. The abnormality determination unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the response content to determine an abnormality. The contact unit is realized by the control unit 46A of the headset type terminal 314, and sends an email or SMS to the caregiver or doctor when an abnormality is determined. The setting unit is realized by the control unit 46A of the headset type terminal 314, and sets the content and frequency of the calling. The recording unit is realized by the specific processing unit 290 of the data processing device 12, and records the response history. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the response history. The selection unit is realized by the control unit 46A of the headset type terminal 314, and selects the contact method. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0179] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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).

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] Each of the multiple elements including the above-mentioned calling unit, response analysis unit, abnormality determination unit, contact unit, setting unit, recording unit, analysis unit, and selection unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the calling unit is realized by the control unit 46A of the robot 414, and calls out to the care recipient using a voice message generated by AI. The response analysis unit is realized by the specific processing unit 290 of the data processing device 12, and converts the response content into text data using voice recognition technology and stores it in the database 24. The abnormality determination unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the response content to determine an abnormality. The contact unit is realized by the control unit 46A of the robot 414, and sends an email or SMS to the caregiver or doctor when an abnormality is determined. The setting unit is realized by the control unit 46A of the robot 414, and sets the content and frequency of the calling. The recording unit is realized by the specific processing unit 290 of the data processing device 12, and records the response history. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the response history. The selection unit is realized by the control unit 46A of the robot 414, and selects the contact method. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0196] 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.

[0197] 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.

[0198] These emotions are distributed in the three 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.

[0199] 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).

[0200] 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.

[0201] 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."

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] (Appendix 1) The calling department regularly calls out to those receiving care; a response analysis unit that analyzes a response to the call made by the call unit; an anomaly determination unit that determines an anomaly based on the response content analyzed by the response analysis unit; A contact unit that contacts an expert when an abnormality is determined by the abnormality determination unit. A system characterized by: (Appendix 2) The system described in appendix 1, further comprising a setting unit for setting the content or frequency of the call. (Appendix 3) Equipped with a recording unit that records response history 2. The system of claim 1, (Appendix 4) Equipped with an analysis section that analyzes response history 2. The system of claim 1, (Appendix 5) A selection section for selecting a contact method is provided. 2. The system of claim 1, (Appendix 6) The setting unit is Work with the Communication Department to determine the content and frequency of communication. 3. The system of claim 2, (Appendix 7) The recording unit is Links with the response analysis unit to record response history 4. The system of claim 3. (Appendix 8) The analysis unit includes: Links with the anomaly determination unit to analyze response history 5. The system of claim 4. (Appendix 9) The selection unit is Work with the liaison department to select the method of contact 6. The system of claim 5, (Appendix 10) The voice-calling unit is Estimate the emotions of the person receiving care and adjust the content of conversations based on the estimated emotions 2. The system of claim 1, (Appendix 11) The voice-calling unit is Analyze the past response history of the care recipient and select the optimal timing to speak to them 2. The system of claim 1, (Appendix 12) The voice-calling unit is Customize conversations based on the care recipient's current activity status 2. The system of claim 1, (Appendix 13) The voice-calling unit is Estimate the emotions of the person receiving care and adjust the frequency of conversations based on the estimated emotions 2. The system of claim 1, (Appendix 14) The voice-calling unit is When communicating with a care recipient, the system takes into account their geographic location information and prioritizes messaging that is more relevant to them. 2. The system of claim 1, (Appendix 15) The voice-calling unit is When communicating with care recipients, analyze their social media activity and respond with relevant content 2. The system of claim 1, (Appendix 16) The response analysis unit Infer the emotions of the person receiving care and adjust the response analysis method based on the inferred emotions. 2. The system of claim 1, (Appendix 17) The response analysis unit When analyzing responses, adjust the level of detail based on the importance of the response content. 2. The system of claim 1, (Appendix 18) The response analysis unit During response analysis, apply different analysis algorithms depending on the category of the response 2. The system of claim 1, (Appendix 19) The response analysis unit Estimate the emotion of the care recipient and adjust the analysis order of the responses based on the estimated emotion. 2. The system of claim 1, (Appendix 20) The response analysis unit During response analysis, prioritize analysis based on when responses were submitted 2. The system of claim 1, (Appendix 21) The response analysis unit During response analysis, adjust the order of analysis based on response relevance 2. The system of claim 1, (Appendix 22) The abnormality determination unit is Estimating the emotions of the person receiving care and adjusting the criteria for determining abnormalities based on the estimated emotions 2. The system of claim 1, (Appendix 23) The abnormality determination unit is When determining an anomaly, the accuracy of the determination is improved by taking into account the correlation of response contents. 2. The system of claim 1, (Appendix 24) The abnormality determination unit is When determining abnormalities, the attribute information of the care recipient is taken into consideration. 2. The system of claim 1, (Appendix 25) The abnormality determination unit is Estimating the emotions of the care recipient and adjusting the order in which abnormality results are displayed based on the estimated emotions 2. The system of claim 1, (Appendix 26) The abnormality determination unit is When determining anomalies, the geographic distribution of responses is taken into account. 2. The system of claim 1, (Appendix 27) The abnormality determination unit is When determining anomalies, improve the accuracy of the determination by referring to related literature 2. The system of claim 1, (Appendix 28) The communication unit includes: Estimate the emotions of the person you care for and adjust the way you contact them based on those emotions 2. The system of claim 1, (Appendix 29) The communication unit includes: When contacting a care recipient, the most appropriate contact method is selected by referring to the care recipient's past contact history. 2. The system of claim 1, (Appendix 30) The communication unit includes: When contacting them, tailor your communication based on the current situation of the person you care for 2. The system of claim 1, (Appendix 31) The communication unit includes: Estimate the emotions of the person you care for and prioritize contact based on the estimated emotions 2. The system of claim 1, (Appendix 32) The communication unit includes: When contacting a care recipient, the most appropriate contact method is selected based on the recipient's geographic location. 2. The system of claim 1, (Appendix 33) The communication unit includes: When contacting someone, analyze their social media activity to suggest ways to contact them 2. The system of claim 1, (Appendix 34) The setting unit is Estimate the emotions of the person receiving care, and set the content and frequency of messages based on the estimated emotions 3. The system of claim 2, (Appendix 35) The setting unit is When setting up, the system will refer to the care recipient's past response history to determine the optimal settings 3. The system of claim 2, (Appendix 36) The setting unit is Estimate the emotions of the person receiving care and prioritize settings based on the estimated emotions 3. The system of claim 2, (Appendix 37) The setting unit is During setup, the geographic location of the care recipient is taken into account to optimize the settings 3. The system of claim 2, (Appendix 38) The recording unit is Estimate the emotions of the person receiving care and adjust the method of recording the response history based on the estimated emotions. 4. The system of claim 3. (Appendix 39) The recording unit is When recording, adjust the detail of the recording based on the importance of the response 4. The system of claim 3. (Appendix 40) The recording unit is Estimate the emotions of the person you care for and prioritize records based on the estimated emotions 4. The system of claim 3. (Appendix 41) The recording unit is When recording, adjust the order of records based on when responses were submitted 4. The system of claim 3. (Appendix 42) The analysis unit includes: Estimate the emotions of the person receiving care and adjust the analysis method of the response history based on the estimated emotions. 5. The system of claim 4. (Appendix 43) The analysis unit includes: During analysis, adjust the level of detail based on the importance of the responses 5. The system of claim 4. (Appendix 44) The analysis unit includes: Estimate the emotions of the person you care for and prioritize the analysis based on the estimated emotions. 5. The system of claim 4. (Appendix 45) The analysis unit includes: During analysis, adjust the order of analysis based on when responses were submitted 5. The system of claim 4. (Appendix 46) The selection unit is Estimate the emotions of the person you care for and adjust the contact method selection based on the estimated emotions 6. The system of claim 5, (Appendix 47) The selection unit is When selecting, the most appropriate contact method is selected by referring to the care recipient's past contact history. 6. The system of claim 5, (Appendix 48) The selection unit is Estimate the emotions of the person you care for and prioritize contact methods based on the estimated emotions 6. The system of claim 5, (Appendix 49) The selection unit is When selecting, the optimal contact method is chosen taking into account the geographic location of the care recipient. 6. The system of claim 5, (Appendix 50) The selection unit is At the time of selection, analyze the care recipient's social media activity to suggest ways to contact them 6. The system of claim 5, [Explanation of symbols]

[0215] 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. The calling department regularly calls out to those receiving care; a response analysis unit that analyzes a response to the call made by the call unit; an anomaly determination unit that determines an anomaly based on the response content analyzed by the response analysis unit; A contact unit that contacts an expert when an abnormality is determined by the abnormality determination unit. A system characterized by:

2. A setting unit is provided for setting the content or frequency of the call 2. The system of claim 1 .

3. Equipped with a recording unit that records response history 2. The system of claim 1 .

4. Equipped with an analysis section that analyzes response history 2. The system of claim 1 .

5. A selection section for selecting a contact method is provided.

2. The system of claim 1 .

6. The setting unit is Cooperating with the voice-calling unit, the content and frequency of voice-calling is set 3. The system of claim 2.

7. The recording unit is Linking with the response analysis unit to record response history 4. The system of claim 3.

8. The analysis unit includes: Analyzing the response history in cooperation with the abnormality determination unit 5. The system of claim 4.

9. The selection unit is Cooperate with the abovementioned contact department to select the contact method 6. The system of claim 5.

10. The voice-calling unit is Estimate the emotions of the person receiving care and adjust the content of conversations based on the estimated emotions 2. The system of claim 1 .

Images