System

Abstract

To provide a system according to an embodiment that accurately estimates the details of an utterance given by a person to be cared and establishes smooth communication with a care staff member.SOLUTION: A system according to an embodiment comprises an imaging unit, an image analysis unit, a voice analysis unit, an estimation unit, and a presentation unit. The imaging unit picks up an image of the mouth of a person to be cared. The image analysis unit reads the movement of the mouth of the person to be cared on the basis of the image picked up by the imaging unit. The voice analysis unit analyzes the characteristics of a voice uttered by the person to be cared. The estimation unit estimates the details of the utterance given by the person to be cared on the basis of the information obtained by the image analysis unit and the voice analysis unit. The presentation unit presents a result of the estimation made by the estimation unit to a care staff member.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, it was difficult to accurately understand what the care recipient was saying in the care setting, making it difficult to communicate smoothly.

[0005] The system according to the embodiment aims to accurately estimate the content of the comments made by the care recipient and facilitate smooth communication between the care recipient and the care staff. [Means for solving the problem]

[0006] The system according to the embodiment includes an imaging unit, an image analysis unit, a voice analysis unit, an estimation unit, and a presentation unit. The imaging unit captures an image of the mouth of the care recipient. The image analysis unit reads the movement of the care recipient's mouth based on the image captured by the imaging unit. The voice analysis unit analyzes characteristics of the voice uttered by the care recipient. The estimation unit estimates the content of the words spoken by the care recipient based on information obtained by the image analysis unit and the voice analysis unit. The presentation unit presents the estimation result by the estimation unit to the care staff. Effect of the Invention

[0007] The system according to the embodiment can accurately estimate the content of the comments made by the care recipient and facilitate smooth communication between the care recipient and the care staff. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The care support system according to the embodiment of the present invention is a system for accurately understanding the contents of the remarks of the care recipient. This care support system observes the movement of the mouth using a camera that captures the mouth of the care recipient. Next, the captured image is analyzed to read the movement of the mouth. Furthermore, the characteristics of the voice emitted by the care recipient are analyzed to obtain information such as tone, wavelength, tone, and strength. The contents of the remarks of the care recipient are estimated by combining these pieces of information. The estimated remarks are presented to the care staff. For example, the care support system is a system that includes an imaging unit that captures the mouth of the care recipient, an image analysis unit that reads the movement of the mouth of the care recipient based on the image captured by the imaging unit, a voice analysis unit that analyzes the characteristics of the voice emitted by the care recipient, an estimation unit that estimates the contents of the remarks of the care recipient based on the information obtained by the image analysis unit and the voice analysis unit, and a presentation unit that presents the estimation result by the estimation unit to the care staff. Furthermore, the estimation unit combines and analyzes the movement of the mouth and the characteristics of the voice to identify the contents of the remarks of the care recipient. The estimation unit can also estimate the contents of the remarks of the care recipient by further using the past movements and voice characteristics of the care recipient. The imaging unit further includes a face analysis unit that captures the entire face of the care recipient and analyzes changes in facial expression, and the estimation unit estimates the emotional state of the care recipient based on the changes in facial expression and can present the emotional state to the care worker along with the content of the remarks. The system further includes a health monitoring unit that analyzes the content of the remarks of the care recipient and monitors the health condition of the care recipient in real time, and the presentation unit can notify medical staff when an abnormality in the health condition is detected by the health monitoring unit. The estimation unit has a function of analyzing the content of the remarks of the care recipient and distinguishing between everyday conversation and emergency matters, and the presentation unit can immediately notify the care worker when an emergency matter is detected by the estimation unit. This allows the care support system to accurately understand the content of the remarks of the care recipient and facilitate communication with the care worker.

[0029] The care support system according to the embodiment includes an imaging unit, an image analysis unit, a voice analysis unit, an estimation unit, and a presentation unit. The imaging unit images the mouth of the care recipient. The mouth of the care recipient includes, for example, lip movement and opening and closing of the mouth, but is not limited to such examples. For example, the imaging unit images the mouth of the care recipient with a high-resolution camera and stores the image data. The imaging unit can also image the entire face of the care recipient and analyze changes in facial expression. For example, the imaging unit images the entire face of the care recipient and analyzes changes in facial expression such as smiling, anger, and surprise. The image analysis unit reads the movement of the mouth of the care recipient based on the image captured by the imaging unit. The image analysis unit analyzes the movement of the lips and the opening and closing of the mouth, for example, using AI. For example, the image analysis unit analyzes the movement of the lips and estimates the content of the statement. The image analysis unit can also analyze the opening and closing of the mouth and estimate the content of the statement. The voice analysis unit analyzes the characteristics of the voice emitted by the care recipient. The voice analysis unit analyzes voice characteristics such as volume, pitch, and tone using, for example, AI. For example, the voice analysis unit analyzes the volume and estimates the spoken content. The voice analysis unit can also analyze the pitch and estimate the spoken content. The estimation unit estimates the spoken content of the care recipient based on the information obtained by the image analysis unit and the voice analysis unit. The estimation unit uses, for example, AI to analyze a combination of mouth movement and voice characteristics and estimate the spoken content. For example, the estimation unit analyzes a combination of mouth movement and voice characteristics to identify the spoken content. The estimation unit can also estimate the spoken content by further using the past movements and voice characteristics of the care recipient. For example, the estimation unit estimates the spoken content by using data of the past mouth movement of the care recipient and voice characteristics. The presentation unit presents the estimation result by the estimation unit to the care staff. The presentation unit displays the estimation result using, for example, AI. For example, the presentation unit displays the estimation result on a screen. The presentation unit can also notify the estimation result by voice. As a result, the care support system according to the embodiment can accurately understand what the care recipient says and facilitate communication with the care staff.

[0030] The imaging unit captures the mouth of the care recipient. The mouth of the care recipient includes, for example, lip movement, opening and closing of the mouth, and the like, but is not limited to such examples. For example, the imaging unit captures the mouth of the care recipient with a high-resolution camera and saves the image data. Specifically, the imaging unit can capture minute movements and changes of the mouth of the care recipient in detail using the high-resolution camera. This makes it possible to accurately record minute changes in lip movement and opening and closing of the mouth. In addition, the imaging unit can capture the entire face of the care recipient and analyze changes in facial expression. For example, the imaging unit captures the entire face of the care recipient and analyzes changes in facial expression such as smile, anger, and surprise. This makes it possible to grasp the emotional and psychological state of the care recipient, and provide important information for the care worker to take appropriate action. Furthermore, the imaging unit can track the facial movement of the care recipient in real time and analyze the movement pattern. This makes it possible to quickly detect changes in the condition of the care recipient and immediately take necessary care measures. The imaging unit may use multiple cameras to capture the facial movement of the care recipient with high accuracy. For example, by capturing images from different angles, it is possible to obtain three-dimensional image data and perform more detailed analysis. This allows the movement of the mouth and entire face of the person receiving care to be captured from multiple angles, resulting in highly accurate analysis results.

[0031] The image analysis unit reads the movement of the mouth of the care recipient based on the image captured by the imaging unit. The image analysis unit, for example, uses AI to analyze the movement of the lips and the opening and closing of the mouth. Specifically, the image analysis unit uses deep learning technology to analyze the movement of the lips and the opening and closing of the mouth of the care recipient with high accuracy. For example, the image analysis unit analyzes the movement of the lips to estimate the content of the speech. The image analysis unit can also analyze the opening and closing of the mouth to estimate the content of the speech. The AI ​​is trained using a huge data set and learns the pattern of the movement of the mouth of the care recipient. This allows the image analysis unit to estimate the content of the speech from the movement of the mouth of the care recipient with high accuracy. Furthermore, the image analysis unit can also analyze the change in the facial expression of the entire face of the care recipient. For example, it is possible to analyze the change in facial expression such as smile, anger, surprise, etc., and grasp the emotional state of the care recipient. This allows the care worker to take appropriate measures according to the emotional state of the care recipient. The image analysis unit can also analyze the pattern of the facial movement of the care recipient and detect abnormal movements. For example, abnormal mouth movements or changes in facial expressions can be detected and abnormalities can be detected early, allowing caregivers to respond quickly to changes in the condition of the person being cared for and provide appropriate care.

[0032] The voice analysis unit analyzes the characteristics of the voice emitted by the care recipient. The voice analysis unit analyzes the characteristics of the voice, such as the volume, pitch, and tone, using, for example, AI. Specifically, the voice analysis unit can analyze the waveform data of the voice of the care recipient and capture the changes in the volume, pitch, and tone in detail. For example, the voice analysis unit analyzes the volume and estimates the contents of the speech. The voice analysis unit can also analyze the pitch and estimate the contents of the speech. The AI ​​uses voice recognition technology to analyze the characteristics of the voice of the care recipient with high accuracy. As a result, the voice analysis unit can estimate the contents of the speech from the characteristics of the voice of the care recipient with high accuracy. Furthermore, the voice analysis unit can also analyze the emotional state of the voice of the care recipient. For example, the voice tone and pitch changes can be analyzed to grasp the emotional state of the care recipient. As a result, the care worker can take appropriate measures according to the emotional state of the care recipient. The voice analysis unit can also analyze the voice pattern of the care recipient and detect abnormal changes in the voice. For example, it can detect changes in the tone and pitch of the voice that are different from normal and detect abnormalities early. This enables care staff to respond quickly to changes in the condition of the person being cared for and provide appropriate care.

[0033] The estimation unit estimates the contents of the remarks of the care recipient based on the information obtained by the image analysis unit and the voice analysis unit. The estimation unit, for example, uses AI to combine and analyze the mouth movement and voice characteristics to estimate the contents of the remarks. Specifically, the estimation unit uses deep learning technology to comprehensively analyze the mouth movement and voice characteristics to estimate the contents of the remarks with high accuracy. For example, the estimation unit combines and analyzes the mouth movement and voice characteristics to identify the contents of the remarks. The estimation unit can also estimate the contents of the remarks by further using the past movements and voice characteristics of the care recipient. For example, the estimation unit estimates the contents of the remarks by using data on the past mouth movement and voice characteristics of the care recipient. This allows the estimation unit to estimate the contents of the remarks of the care recipient with high accuracy and provide them to the care staff. Furthermore, the estimation unit can estimate the contents of the remarks of the care recipient in real time and quickly provide them to the care staff. This allows the care staff to quickly grasp the contents of the remarks of the care recipient and take appropriate measures. In addition, the estimation unit can continuously learn the contents of the remarks of the care recipient and improve the accuracy. For example, the estimation unit can continuously learn the utterances of the care recipient and build an estimation model optimized for each care recipient. This allows the estimation unit to estimate the utterances of the care recipient with high accuracy and facilitate smooth communication with the care staff.

[0034] The presentation unit presents the estimation result by the estimation unit to the care worker. The presentation unit displays the estimation result using, for example, AI. Specifically, the presentation unit displays the estimation result on a screen. For example, the presentation unit displays the estimation result on a screen in real time so that the care worker can quickly check it. The presentation unit can also notify the estimation result by voice. For example, the presentation unit notifies the estimation result by voice so that the care worker can quickly grasp the information even if the care worker cannot visually check it. Furthermore, the presentation unit can also transmit the estimation result as a text message. For example, the presentation unit transmits the estimation result as a text message to the smartphone of the care worker so that the care worker can check it anytime and anywhere. As a result, the presentation unit can quickly and reliably provide the estimation result to the care worker and accurately understand the contents of the statement of the care recipient. Furthermore, the presentation unit can record the estimation result so that it can be referred to later. For example, the presentation unit saves the estimation result in a database so that the care worker can refer to past estimation results. As a result, the care worker can check the history of the contents of the statement of the care recipient and take appropriate measures. The presentation unit can also visually display the estimation result as a graph or chart. For example, the presentation unit displays the estimation result as a graph or chart so that the care worker can understand the information at a glance. This allows the presentation unit to effectively provide information to the care worker and facilitate communication with the care recipient.

[0035] The estimation unit can identify the contents of the utterance of the care recipient by analyzing the combination of the mouth movement and the voice characteristics. The estimation unit, for example, analyzes the combination of the mouth movement and the voice characteristics. For example, the estimation unit analyzes the combination of the lip movement and the volume to identify the contents of the utterance. The estimation unit can also analyze the opening and closing of the mouth and the pitch to identify the contents of the utterance. As a result, the combination of the mouth movement and the voice characteristics improves the accuracy of identifying the contents of the utterance. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can identify the contents of the utterance by using an AI model that inputs the mouth movement and the voice characteristics and outputs the contents of the utterance.

[0036] The estimation unit can further use the past movements and voice characteristics of the care recipient to identify the contents of the remarks of the care recipient. The estimation unit performs analysis using, for example, the past movements and voice characteristics of the care recipient. For example, the estimation unit analyzes past mouth movement data and volume in combination to identify the contents of the remarks. The estimation unit can also analyze past facial expression changes and pitch in combination to identify the contents of the remarks. As a result, the estimation accuracy of the contents of the remarks is improved by using the past movements and voice characteristics. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can identify the contents of the remarks using an AI model that inputs past movements and voice characteristics and outputs the contents of the remarks.

[0037] The imaging unit may further include a face analysis unit that images the entire face of the care recipient and analyzes changes in facial expression. The imaging unit, for example, images the entire face of the care recipient and analyzes changes in facial expression. For example, the imaging unit analyzes changes in facial expression such as smile, anger, and surprise. In this way, the emotional state of the care recipient can be understood by analyzing changes in facial expression. Estimation of emotions 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 imaging unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the imaging unit may input image data of the entire face to the generation AI and cause the generation AI to execute analysis of changes in facial expression.

[0038] The estimation unit can identify the emotional state of the care recipient based on changes in facial expression, and present the emotional state together with the remarks to the care staff. The estimation unit, for example, identifies the emotional state based on changes in facial expression. For example, the estimation unit analyzes changes in facial expression, such as smile, anger, and surprise, and identifies the emotional state. The estimation unit can also present the emotional state together with the remarks to the care staff. In this way, by estimating and presenting the emotional state, the care staff can more accurately understand the condition of the care recipient. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input data of the facial expression changes to the generation AI and cause the generation AI to execute the identification of the emotional state.

[0039] The system may include a health monitoring unit that analyzes the remarks of the care recipient and monitors the health condition of the care recipient in real time. The health monitoring unit, for example, analyzes the remarks of the care recipient and monitors the health condition. For example, the health monitoring unit estimates health indicators such as body temperature, blood pressure, and heart rate from the remarks. The health monitoring unit can also detect abnormalities in the health condition and notify medical staff. This allows the health condition to be monitored in real time, making it possible to detect abnormalities early. Some or all of the above-mentioned processing in the health monitoring unit may be performed, for example, using AI or may be performed without using AI. For example, the health monitoring unit can input data on the remarks to the generation AI and cause the generation AI to monitor the health condition.

[0040] The estimation unit can analyze the content of the speech of the care recipient and distinguish between everyday conversation and emergency requirements. For example, the estimation unit distinguishes between everyday conversation, such as greetings and chatting, and emergency requirements, such as speech requesting help or warning of danger. In addition, when an emergency requirement is detected, the estimation unit can immediately notify the care staff. This enables appropriate response by distinguishing between everyday conversation and emergency requirements. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI or may be performed without using AI. For example, the estimation unit can input data of the speech content to the generation AI and cause the generation AI to distinguish between everyday conversation and emergency requirements.

[0041] The presentation unit can report to medical staff when an abnormality in the health condition is detected by the health monitoring unit. For example, the presentation unit detects abnormalities such as an abnormal rise in body temperature or a sudden change in blood pressure, and reports the abnormality to the medical staff. In addition, the presentation unit can immediately notify the medical staff when an abnormality is detected. This allows for a rapid response by detecting an abnormality in the health condition and notifying the medical staff. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input abnormal data on the health condition to the generation AI, and cause the generation AI to detect and notify the abnormality.

[0042] The imaging unit can analyze the past imaging data of the care recipient and select an appropriate imaging angle and distance. For example, the imaging unit selects an angle at which the entire face of the care recipient can be seen best from the past data. The imaging unit can also set a distance at which the mouth of the care recipient can be seen most clearly based on the past data. Furthermore, the imaging unit can analyze the past data and select an angle at which the facial expression of the care recipient looks most natural. In this way, optimal imaging conditions can be selected by analyzing the past data. A part or all of the above-mentioned processing in the imaging unit may be performed, for example, using AI or may be performed without using AI. For example, the imaging unit can input past imaging data to the generation AI and cause the generation AI to select optimal imaging angles and distances.

[0043] The imaging unit can automatically adjust the imaging conditions during imaging, taking into account the current ambient light and background of the care recipient. For example, when the ambient light is strong, the imaging unit automatically adjusts the exposure of the camera. Also, when the background is complex, the imaging unit can blur the background to emphasize the face of the care recipient. Furthermore, when the ambient light is weak, the imaging unit can automatically increase the sensitivity of the camera. This allows a clearer image to be obtained by taking into account the ambient light and background. Some or all of the above-mentioned processing in the imaging unit may be performed, for example, using AI, or may be performed without using AI. For example, the imaging unit can input data on the ambient light and background to the generation AI, and cause the generation AI to automatically adjust the imaging conditions.

[0044] The imaging unit can take the geographical location information of the care recipient into consideration when capturing images and preferentially acquire highly relevant imaging data. For example, when the care recipient is at home, the imaging unit preferentially captures images of the daily life of the care recipient. Also, when the care recipient is in a hospital, the imaging unit can preferentially capture images of interactions with medical staff. Furthermore, when the care recipient is out, the imaging unit can capture images of the surrounding environment and the state of the care recipient. This allows highly relevant data to be acquired by taking the geographical location information into consideration. A part or all of the above-mentioned processing in the imaging unit may be performed, for example, using AI or may be performed without using AI. For example, the imaging unit can input data of geographical location information to the generation AI and cause the generation AI to acquire highly relevant imaging data.

[0045] The imaging unit can analyze the social media activity of the care recipient at the time of imaging and acquire related imaging data. The imaging unit determines the timing of imaging based on, for example, a location shared by the care recipient on social media. The imaging unit can also set the imaging angle and distance with reference to photos and videos shared by the care recipient on social media. Furthermore, the imaging unit can identify places and events of interest from the social media activity of the care recipient and perform imaging. As a result, related data can be acquired by analyzing the social media activity. A part or all of the above-mentioned processing in the imaging unit may be performed using, for example, AI, or may be performed without using AI. For example, the imaging unit can input data of social media activity to the generation AI and cause the generation AI to acquire related imaging data.

[0046] The image analysis unit can adjust the accuracy of the analysis based on the importance of the mouth movement of the care recipient during image analysis. For example, when the mouth movement is clear, the image analysis unit performs a detailed analysis. Also, when the mouth movement is unclear, the image analysis unit can perform a simplified analysis. Furthermore, when the mouth movement is fast, the image analysis unit can perform the analysis by increasing the frame rate. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the mouth movement. A part or all of the above-mentioned processing in the image analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the image analysis unit can input data on the mouth movement to the generation AI and cause the generation AI to adjust the accuracy of the analysis.

[0047] The image analysis unit can apply different analysis algorithms depending on the type of mouth movement of the care recipient during image analysis. For example, when the mouth movement is at the word level, the image analysis unit applies a word recognition algorithm. Furthermore, when the mouth movement is at the sentence level, the image analysis unit can apply a sentence recognition algorithm. Furthermore, when the mouth movement is at the phoneme level, the image analysis unit can apply a phoneme recognition algorithm. This improves the analysis accuracy by applying different analysis algorithms depending on the category of mouth movement. Part or all of the above-mentioned processing in the image analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the image analysis unit can input data of mouth movement to the generation AI and cause the generation AI to apply an appropriate analysis algorithm.

[0048] The image analysis unit can determine the importance of the analysis based on the time of imaging of the care recipient during image analysis. For example, the image analysis unit prioritizes analysis of the latest imaging data. Also, the image analysis unit can prioritize analysis of important data by referring to past imaging data. Furthermore, the image analysis unit can perform simplified analysis of data captured at older times. As a result, important data can be analyzed preferentially by determining the priority of analysis based on the time of imaging. A part or all of the above-mentioned processing in the image analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the image analysis unit can input data of the time of imaging to the generation AI and cause the generation AI to determine the priority of analysis.

[0049] The image analysis unit can adjust the order of analysis based on the relevance of the care recipient during image analysis. For example, the image analysis unit preferentially analyzes data related to the content of the care recipient's remarks. The image analysis unit can also preferentially analyze data related to the health condition of the care recipient. Furthermore, the image analysis unit can also preferentially analyze data related to the emotional state of the care recipient. This allows for efficient analysis by adjusting the order of analysis based on relevance. A part or all of the above-mentioned processing in the image analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the image analysis unit can input relevance data to the generation AI and cause the generation AI to adjust the order of analysis.

[0050] The voice analysis unit can improve the accuracy of the analysis by considering the interrelationships of the voices of the care recipient during the voice analysis. The voice analysis unit, for example, analyzes the interrelationships between the tone and pitch of the voice. The voice analysis unit can also analyze the interrelationships between the strength and rhythm of the voice. Furthermore, the voice analysis unit can analyze the interrelationships between the wavelength and frequency of the voice. As a result, the accuracy of the analysis is improved by considering the interrelationships of the voices. A part or all of the above-mentioned processing in the voice analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice analysis unit can input data on the interrelationships of the voices to the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0051] The voice analysis unit can perform the analysis while taking into consideration the characteristic information of the person who submits the voice of the care recipient during the voice analysis. The voice analysis unit analyzes the characteristics of the voice based on, for example, the age of the care recipient. The voice analysis unit can also analyze the characteristics of the voice based on the gender of the care recipient. Furthermore, the voice analysis unit can analyze the characteristics of the voice based on the health condition of the care recipient. This improves the accuracy of the analysis by taking into consideration the attribute information of the submitter. A part or all of the above-mentioned processing in the voice analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the voice analysis unit can input data of the characteristic information of the submitter to the generation AI and cause the generation AI to perform the analysis.

[0052] The voice analysis unit can perform the analysis while taking into consideration the geographical location of the care recipient during the voice analysis. The voice analysis unit performs the analysis while taking into consideration, for example, the dialect and accent of the area where the care recipient lives. The voice analysis unit can also perform the analysis while taking into consideration the characteristics of the voice of the area to which the care recipient has moved. Furthermore, the voice analysis unit can perform the analysis while taking into consideration the characteristics of the voice of the area to which the care recipient has visited. This improves the accuracy of the analysis by taking into consideration the geographical distribution. A part or all of the above-mentioned processing in the voice analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice analysis unit can input data of the geographical location to the generation AI and cause the generation AI to execute the analysis.

[0053] The voice analysis unit can improve the accuracy of the analysis by referring to related literature on the care recipient during the voice analysis. The voice analysis unit performs the analysis by referring to, for example, research papers on the characteristics of the voice of the care recipient. The voice analysis unit can also perform the analysis by referring to a database on the characteristics of the voice of the care recipient. Furthermore, the voice analysis unit can perform the analysis by referring to past data on the characteristics of the voice of the care recipient. As a result, the accuracy of the analysis is improved by referring to the related literature. A part or all of the above-mentioned processing in the voice analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the voice analysis unit can input data of related literature to the generation AI and have the generation AI perform the analysis.

[0054] The estimation unit can adjust the estimation algorithm by referring to the past utterances of the care recipient at the time of estimation. The estimation unit can also analyze the past utterance patterns of the care recipient and optimize the estimation algorithm. Furthermore, the estimation unit can compare the past utterances of the care recipient with the current utterances and improve the estimation algorithm. As a result, the accuracy of the estimation algorithm is improved by referring to the past utterances. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI or may be performed without using AI. For example, the estimation unit can input data of the past utterances to the generation AI and cause the generation AI to adjust the estimation algorithm.

[0055] The estimation unit can adjust the estimation means based on the current living situation of the care recipient at the time of estimation. For example, when the care recipient is in a hospital, the estimation unit can preferentially estimate medical-related utterance contents. Furthermore, when the care recipient is at home, the estimation unit can preferentially estimate utterance contents related to daily life. Furthermore, when the care recipient is out, the estimation unit can preferentially estimate utterance contents related to the destination. This allows more appropriate utterance contents to be estimated by customizing the estimation means based on the current living situation. Part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI or may be performed without using AI. For example, the estimation unit can input data of the current living situation to the generation AI and cause the generation AI to adjust the estimation means.

[0056] The estimation unit can select an appropriate estimation method in consideration of the geographical location information of the care recipient at the time of estimation. For example, when the care recipient is in a hospital, the estimation unit can preferentially estimate medical-related utterance content. Also, when the care recipient is at home, the estimation unit can preferentially estimate utterance content related to daily life. Furthermore, when the care recipient is out, the estimation unit can preferentially estimate utterance content related to the destination. As a result, more appropriate utterance content can be estimated by considering the geographical location information. Part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI or may be performed without using AI. For example, the estimation unit can input data of geographical location information to the generation AI and cause the generation AI to select the estimation method.

[0057] At the time of estimation, the estimation unit can provide a means of estimation by analyzing the social media activity of the care recipient. For example, the estimation unit estimates the content of the comment based on the information shared by the care recipient on social media. In addition, the estimation unit can estimate the topic of interest from the social media activity of the care recipient. Furthermore, the estimation unit can analyze the comment pattern of the care recipient on social media and optimize the estimation algorithm. As a result, more appropriate comment content can be estimated by analyzing the social media activity. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input data of the social media activity to the generation AI and cause the generation AI to provide the means of estimation.

[0058] The presentation unit can select an appropriate display method by referring to the past operation history of the care recipient at the time of presentation and display. For example, the presentation unit preferentially provides a display method that the care recipient has used in the past. The presentation unit can also select a display method with the highest visibility from the past operation history of the care recipient. Furthermore, the presentation unit can analyze the past operation history of the care recipient and suggest an optimal display method. As a result, the optimal display method can be provided by referring to the past operation history. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input data of the past operation history to the generation AI and cause the generation AI to select the display method.

[0059] The presentation unit can select an appropriate display method in consideration of the device information of the care recipient when presenting and displaying. For example, when the care recipient uses a smartphone, the presentation unit provides a display method that matches the screen size. In addition, when the care recipient uses a tablet, the presentation unit can provide a display method optimized for a large screen. Furthermore, when the care recipient uses a smartwatch, the presentation unit can provide a simple and highly visible display method. This makes it possible to provide an optimal display method by considering the device information. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input data of the device information to the generation AI and cause the generation AI to select the display method.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The care support system may further include a motion detection unit that detects the motion of the care recipient. The motion detection unit detects the hand motion and body motion of the care recipient and analyzes these motions. For example, the motion detection unit may detect the motion of the care recipient raising their hand and determine that the motion is a sign of asking for help. The motion detection unit may also detect the motion of the care recipient shaking their body and determine that the motion indicates anxiety or tension. Furthermore, the motion detection unit may learn the motion patterns of the care recipient and detect abnormal motions. In this way, by analyzing the motion of the care recipient, understanding of the content of what is being said can be supplemented, enabling more accurate care support.

[0062] The care support system may further include an environmental sound analysis unit that analyzes the environmental sounds of the care recipient. The environmental sound analysis unit detects sounds around the care recipient and analyzes these sounds. For example, the environmental sound analysis unit may detect sounds and voices occurring around the care recipient and determine whether these sounds affect the contents of the care recipient's speech. The environmental sound analysis unit may also learn the sound environment around the care recipient and detect abnormal sounds. Furthermore, the environmental sound analysis unit may analyze the association between the contents of the care recipient's speech and environmental sounds to complement the understanding of the contents of the speech. In this way, the contents of the care recipient's speech can be more accurately understood by analyzing the environmental sounds.

[0063] The care support system may further include a biometric information acquisition unit that acquires biometric information of the care recipient. The biometric information acquisition unit acquires biometric information such as the heart rate, blood pressure, and body temperature of the care recipient, and analyzes this information. For example, the biometric information acquisition unit may detect fluctuations in the heart rate of the care recipient and determine that the fluctuations indicate tension or excitement. The biometric information acquisition unit may also detect an increase in the body temperature of the care recipient and determine that the increase indicates poor health. Furthermore, the biometric information acquisition unit may learn the fluctuation patterns of the biometric information of the care recipient and detect abnormal fluctuations. This allows for more accurate care support by analyzing the biometric information, which complements the understanding of the content of the care recipient's statements.

[0064] The care support system may further include a life rhythm analysis unit that analyzes the life rhythm of the care recipient. The life rhythm analysis unit analyzes the sleep pattern, meal timing, activity time period, etc. of the care recipient, and grasps the life rhythm based on this information. For example, the life rhythm analysis unit may analyze the sleep pattern of the care recipient and suggest appropriate wake-up times and bedtimes. The life rhythm analysis unit may also analyze the meal timing of the care recipient and suggest appropriate meal times. Furthermore, the life rhythm analysis unit may analyze the activity time period of the care recipient and suggest appropriate exercise and rest timings. In this way, by analyzing the life rhythm, the health condition of the care recipient can be maintained and a better life can be supported.

[0065] The process flow of the first embodiment will be briefly described below.

[0066] Step 1: The imaging unit captures the mouth of the care recipient. The mouth of the care recipient includes lip movement and opening and closing of the mouth. The imaging unit captures these movements using a high-resolution camera and saves them as image data. The imaging unit also captures the entire face of the care recipient, and can analyze facial expressions such as smiling, anger, and surprise. Step 2: The image analysis unit reads the movement of the care recipient's mouth based on the image captured by the imaging unit. Using AI, the image analysis unit analyzes the movement of the lips and the opening and closing of the mouth to estimate the content of what was said. Step 3: The voice analysis unit analyzes the characteristics of the voice emitted by the care recipient. The voice analysis unit uses AI to analyze voice characteristics such as volume, pitch, and tone, and estimates the content of what is being said. Step 4: The estimation unit estimates the content of the care recipient's speech based on the information obtained by the image analysis unit and the voice analysis unit. The estimation unit uses AI to analyze a combination of mouth movements and voice characteristics to identify the content of speech. The estimation unit can also estimate the content of speech using the care recipient's past movements and voice characteristics. Step 5: The presentation unit presents the estimation result by the estimation unit to the care worker. The presentation unit uses AI to display the estimation result on a screen or notify the care worker by voice.

[0067] (Example 2) The care support system according to the embodiment of the present invention is a system for accurately understanding the contents of the remarks of the care recipient. This care support system observes the movement of the mouth using a camera that captures the mouth of the care recipient. Next, the captured image is analyzed to read the movement of the mouth. Furthermore, the characteristics of the voice emitted by the care recipient are analyzed to obtain information such as tone, wavelength, tone, and strength. The contents of the remarks of the care recipient are estimated by combining these pieces of information. The estimated remarks are presented to the care staff. For example, the care support system is a system that includes an imaging unit that captures the mouth of the care recipient, an image analysis unit that reads the movement of the mouth of the care recipient based on the image captured by the imaging unit, a voice analysis unit that analyzes the characteristics of the voice emitted by the care recipient, an estimation unit that estimates the contents of the remarks of the care recipient based on the information obtained by the image analysis unit and the voice analysis unit, and a presentation unit that presents the estimation result by the estimation unit to the care staff. Furthermore, the estimation unit combines and analyzes the movement of the mouth and the characteristics of the voice to identify the contents of the remarks of the care recipient. The estimation unit can also estimate the contents of the remarks of the care recipient by further using the past movements and voice characteristics of the care recipient. The imaging unit further includes a face analysis unit that captures the entire face of the care recipient and analyzes changes in facial expression, and the estimation unit estimates the emotional state of the care recipient based on the changes in facial expression and can present the emotional state to the care worker along with the content of the remarks. The system further includes a health monitoring unit that analyzes the content of the remarks of the care recipient and monitors the health condition of the care recipient in real time, and the presentation unit can notify medical staff when an abnormality in the health condition is detected by the health monitoring unit. The estimation unit has a function of analyzing the content of the remarks of the care recipient and distinguishing between everyday conversation and emergency matters, and the presentation unit can immediately notify the care worker when an emergency matter is detected by the estimation unit. This allows the care support system to accurately understand the content of the remarks of the care recipient and facilitate communication with the care worker.

[0068] The care support system according to the embodiment includes an imaging unit, an image analysis unit, a voice analysis unit, an estimation unit, and a presentation unit. The imaging unit images the mouth of the care recipient. The mouth of the care recipient includes, for example, lip movement and opening and closing of the mouth, but is not limited to such examples. For example, the imaging unit images the mouth of the care recipient with a high-resolution camera and stores the image data. The imaging unit can also image the entire face of the care recipient and analyze changes in facial expression. For example, the imaging unit images the entire face of the care recipient and analyzes changes in facial expression such as smiling, anger, and surprise. The image analysis unit reads the movement of the mouth of the care recipient based on the image captured by the imaging unit. The image analysis unit analyzes the movement of the lips and the opening and closing of the mouth, for example, using AI. For example, the image analysis unit analyzes the movement of the lips and estimates the content of the statement. The image analysis unit can also analyze the opening and closing of the mouth and estimate the content of the statement. The voice analysis unit analyzes the characteristics of the voice emitted by the care recipient. The voice analysis unit analyzes voice characteristics such as volume, pitch, and tone using, for example, AI. For example, the voice analysis unit analyzes the volume and estimates the spoken content. The voice analysis unit can also analyze the pitch and estimate the spoken content. The estimation unit estimates the spoken content of the care recipient based on the information obtained by the image analysis unit and the voice analysis unit. The estimation unit uses, for example, AI to analyze a combination of mouth movement and voice characteristics and estimate the spoken content. For example, the estimation unit analyzes a combination of mouth movement and voice characteristics to identify the spoken content. The estimation unit can also estimate the spoken content by further using the past movements and voice characteristics of the care recipient. For example, the estimation unit estimates the spoken content by using data of the past mouth movement of the care recipient and voice characteristics. The presentation unit presents the estimation result by the estimation unit to the care staff. The presentation unit displays the estimation result using, for example, AI. For example, the presentation unit displays the estimation result on a screen. The presentation unit can also notify the estimation result by voice. As a result, the care support system according to the embodiment can accurately understand what the care recipient says and facilitate communication with the care staff.

[0069] The imaging unit captures the mouth of the care recipient. The mouth of the care recipient includes, for example, lip movement, opening and closing of the mouth, and the like, but is not limited to such examples. For example, the imaging unit captures the mouth of the care recipient with a high-resolution camera and saves the image data. Specifically, the imaging unit can capture minute movements and changes of the mouth of the care recipient in detail using the high-resolution camera. This makes it possible to accurately record minute changes in lip movement and opening and closing of the mouth. In addition, the imaging unit can capture the entire face of the care recipient and analyze changes in facial expression. For example, the imaging unit captures the entire face of the care recipient and analyzes changes in facial expression such as smile, anger, and surprise. This makes it possible to grasp the emotional and psychological state of the care recipient, and provide important information for the care worker to take appropriate action. Furthermore, the imaging unit can track the facial movement of the care recipient in real time and analyze the movement pattern. This makes it possible to quickly detect changes in the condition of the care recipient and immediately take necessary care measures. The imaging unit may use multiple cameras to capture the facial movement of the care recipient with high accuracy. For example, by capturing images from different angles, it is possible to obtain three-dimensional image data and perform more detailed analysis. This allows the movement of the mouth and entire face of the person receiving care to be captured from multiple angles, resulting in highly accurate analysis results.

[0070] The image analysis unit reads the movement of the mouth of the care recipient based on the image captured by the imaging unit. The image analysis unit, for example, uses AI to analyze the movement of the lips and the opening and closing of the mouth. Specifically, the image analysis unit uses deep learning technology to analyze the movement of the lips and the opening and closing of the mouth of the care recipient with high accuracy. For example, the image analysis unit analyzes the movement of the lips to estimate the content of the speech. The image analysis unit can also analyze the opening and closing of the mouth to estimate the content of the speech. The AI ​​is trained using a huge data set and learns the pattern of the movement of the mouth of the care recipient. This allows the image analysis unit to estimate the content of the speech from the movement of the mouth of the care recipient with high accuracy. Furthermore, the image analysis unit can also analyze the change in the facial expression of the entire face of the care recipient. For example, it is possible to analyze the change in facial expression such as smile, anger, surprise, etc., and grasp the emotional state of the care recipient. This allows the care worker to take appropriate measures according to the emotional state of the care recipient. The image analysis unit can also analyze the pattern of the facial movement of the care recipient and detect abnormal movements. For example, abnormal mouth movements or changes in facial expressions can be detected and abnormalities can be detected early, allowing caregivers to respond quickly to changes in the condition of the person being cared for and provide appropriate care.

[0071] The voice analysis unit analyzes the characteristics of the voice emitted by the care recipient. The voice analysis unit analyzes the characteristics of the voice, such as the volume, pitch, and tone, using, for example, AI. Specifically, the voice analysis unit can analyze the waveform data of the voice of the care recipient and capture the changes in the volume, pitch, and tone in detail. For example, the voice analysis unit analyzes the volume and estimates the contents of the speech. The voice analysis unit can also analyze the pitch and estimate the contents of the speech. The AI ​​uses voice recognition technology to analyze the characteristics of the voice of the care recipient with high accuracy. As a result, the voice analysis unit can estimate the contents of the speech from the characteristics of the voice of the care recipient with high accuracy. Furthermore, the voice analysis unit can also analyze the emotional state of the voice of the care recipient. For example, the voice tone and pitch changes can be analyzed to grasp the emotional state of the care recipient. As a result, the care worker can take appropriate measures according to the emotional state of the care recipient. The voice analysis unit can also analyze the voice pattern of the care recipient and detect abnormal changes in the voice. For example, it can detect changes in the tone and pitch of the voice that are different from normal and detect abnormalities early. This enables care staff to respond quickly to changes in the condition of the person being cared for and provide appropriate care.

[0072] The estimation unit estimates the contents of the remarks of the care recipient based on the information obtained by the image analysis unit and the voice analysis unit. The estimation unit, for example, uses AI to combine and analyze the mouth movement and voice characteristics to estimate the contents of the remarks. Specifically, the estimation unit uses deep learning technology to comprehensively analyze the mouth movement and voice characteristics to estimate the contents of the remarks with high accuracy. For example, the estimation unit combines and analyzes the mouth movement and voice characteristics to identify the contents of the remarks. The estimation unit can also estimate the contents of the remarks by further using the past movements and voice characteristics of the care recipient. For example, the estimation unit estimates the contents of the remarks by using data on the past mouth movement and voice characteristics of the care recipient. This allows the estimation unit to estimate the contents of the remarks of the care recipient with high accuracy and provide them to the care staff. Furthermore, the estimation unit can estimate the contents of the remarks of the care recipient in real time and quickly provide them to the care staff. This allows the care staff to quickly grasp the contents of the remarks of the care recipient and take appropriate measures. In addition, the estimation unit can continuously learn the contents of the remarks of the care recipient and improve the accuracy. For example, the estimation unit can continuously learn the utterances of the care recipient and build an estimation model optimized for each care recipient. This allows the estimation unit to estimate the utterances of the care recipient with high accuracy and facilitate smooth communication with the care staff.

[0073] The presentation unit presents the estimation result by the estimation unit to the care worker. The presentation unit displays the estimation result using, for example, AI. Specifically, the presentation unit displays the estimation result on a screen. For example, the presentation unit displays the estimation result on a screen in real time so that the care worker can quickly check it. The presentation unit can also notify the estimation result by voice. For example, the presentation unit notifies the estimation result by voice so that the care worker can quickly grasp the information even if the care worker cannot visually check it. Furthermore, the presentation unit can also transmit the estimation result as a text message. For example, the presentation unit transmits the estimation result as a text message to the smartphone of the care worker so that the care worker can check it anytime and anywhere. As a result, the presentation unit can quickly and reliably provide the estimation result to the care worker and accurately understand the contents of the statement of the care recipient. Furthermore, the presentation unit can record the estimation result so that it can be referred to later. For example, the presentation unit saves the estimation result in a database so that the care worker can refer to past estimation results. As a result, the care worker can check the history of the contents of the statement of the care recipient and take appropriate measures. The presentation unit can also visually display the estimation result as a graph or chart. For example, the presentation unit displays the estimation result as a graph or chart so that the care worker can understand the information at a glance. This allows the presentation unit to effectively provide information to the care worker and facilitate communication with the care recipient.

[0074] The estimation unit can identify the contents of the utterance of the care recipient by analyzing the combination of the mouth movement and the voice characteristics. The estimation unit, for example, analyzes the combination of the mouth movement and the voice characteristics. For example, the estimation unit analyzes the combination of the lip movement and the volume to identify the contents of the utterance. The estimation unit can also analyze the opening and closing of the mouth and the pitch to identify the contents of the utterance. As a result, the combination of the mouth movement and the voice characteristics improves the accuracy of identifying the contents of the utterance. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can identify the contents of the utterance by using an AI model that inputs the mouth movement and the voice characteristics and outputs the contents of the utterance.

[0075] The estimation unit can further use the past movements and voice characteristics of the care recipient to identify the contents of the remarks of the care recipient. The estimation unit performs analysis using, for example, the past movements and voice characteristics of the care recipient. For example, the estimation unit analyzes past mouth movement data and volume in combination to identify the contents of the remarks. The estimation unit can also analyze past facial expression changes and pitch in combination to identify the contents of the remarks. As a result, the estimation accuracy of the contents of the remarks is improved by using the past movements and voice characteristics. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can identify the contents of the remarks using an AI model that inputs past movements and voice characteristics and outputs the contents of the remarks.

[0076] The imaging unit may further include a face analysis unit that images the entire face of the care recipient and analyzes changes in facial expression. The imaging unit, for example, images the entire face of the care recipient and analyzes changes in facial expression. For example, the imaging unit analyzes changes in facial expression such as smile, anger, and surprise. In this way, the emotional state of the care recipient can be understood by analyzing changes in facial expression. Estimation of emotions 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 imaging unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the imaging unit may input image data of the entire face to the generation AI and cause the generation AI to execute analysis of changes in facial expression.

[0077] The estimation unit can identify the emotional state of the care recipient based on changes in facial expression, and present the emotional state together with the remarks to the care staff. The estimation unit, for example, identifies the emotional state based on changes in facial expression. For example, the estimation unit analyzes changes in facial expression, such as smile, anger, and surprise, and identifies the emotional state. The estimation unit can also present the emotional state together with the remarks to the care staff. In this way, by estimating and presenting the emotional state, the care staff can more accurately understand the condition of the care recipient. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input data of the facial expression changes to the generation AI and cause the generation AI to execute the identification of the emotional state.

[0078] The system may include a health monitoring unit that analyzes the remarks of the care recipient and monitors the health condition of the care recipient in real time. The health monitoring unit, for example, analyzes the remarks of the care recipient and monitors the health condition. For example, the health monitoring unit estimates health indicators such as body temperature, blood pressure, and heart rate from the remarks. The health monitoring unit can also detect abnormalities in the health condition and notify medical staff. This allows the health condition to be monitored in real time, making it possible to detect abnormalities early. Some or all of the above-mentioned processing in the health monitoring unit may be performed, for example, using AI or may be performed without using AI. For example, the health monitoring unit can input data on the remarks to the generation AI and cause the generation AI to monitor the health condition.

[0079] The estimation unit can analyze the content of the speech of the care recipient and distinguish between everyday conversation and emergency requirements. For example, the estimation unit distinguishes between everyday conversation, such as greetings and chatting, and emergency requirements, such as speech requesting help or warning of danger. In addition, when an emergency requirement is detected, the estimation unit can immediately notify the care staff. This enables appropriate response by distinguishing between everyday conversation and emergency requirements. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI or may be performed without using AI. For example, the estimation unit can input data of the speech content to the generation AI and cause the generation AI to distinguish between everyday conversation and emergency requirements.

[0080] The presentation unit can report to medical staff when an abnormality in the health condition is detected by the health monitoring unit. For example, the presentation unit detects abnormalities such as an abnormal rise in body temperature or a sudden change in blood pressure, and reports the abnormality to the medical staff. In addition, the presentation unit can immediately notify the medical staff when an abnormality is detected. This allows for a rapid response by detecting an abnormality in the health condition and notifying the medical staff. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input abnormal data on the health condition to the generation AI, and cause the generation AI to detect and notify the abnormality.

[0081] The estimation unit can determine the importance of the utterance contents based on the emotional state of the care recipient. For example, the estimation unit can analyze the emotional state such as joy, sadness, and anger, and determine the importance of the utterance contents. The estimation unit can also determine the priority of the utterance contents based on the emotional state. This allows important utterances to be preferentially processed by determining the priority of the utterance contents based on the emotional state. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is 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 estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input data of the emotional state to the generation AI and cause the generation AI to determine the importance of the utterance contents.

[0082] The imaging unit can estimate the emotion of the care recipient and adjust the timing of imaging based on the estimated emotion of the care recipient. For example, when the care recipient is relaxed, the imaging unit captures images at regular intervals. Also, when the care recipient is nervous, the imaging unit can refrain from imaging until the emotion stabilizes. Furthermore, when the care recipient is excited, the imaging unit can capture images frequently and collect detailed data. As a result, more appropriate data can be obtained by adjusting the timing of imaging based on the emotion. 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 imaging unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the imaging unit can input data of the emotional state to the generation AI and cause the generation AI to adjust the timing of imaging.

[0083] The imaging unit can analyze the past imaging data of the care recipient and select an appropriate imaging angle and distance. For example, the imaging unit selects an angle at which the entire face of the care recipient can be seen best from the past data. The imaging unit can also set a distance at which the mouth of the care recipient can be seen most clearly based on the past data. Furthermore, the imaging unit can analyze the past data and select an angle at which the facial expression of the care recipient looks most natural. In this way, optimal imaging conditions can be selected by analyzing the past data. A part or all of the above-mentioned processing in the imaging unit may be performed, for example, using AI or may be performed without using AI. For example, the imaging unit can input past imaging data to the generation AI and cause the generation AI to select optimal imaging angles and distances.

[0084] The imaging unit can automatically adjust the imaging conditions during imaging, taking into account the current ambient light and background of the care recipient. For example, when the ambient light is strong, the imaging unit automatically adjusts the exposure of the camera. Also, when the background is complex, the imaging unit can blur the background to emphasize the face of the care recipient. Furthermore, when the ambient light is weak, the imaging unit can automatically increase the sensitivity of the camera. This allows a clearer image to be obtained by taking into account the ambient light and background. Some or all of the above-mentioned processing in the imaging unit may be performed, for example, using AI, or may be performed without using AI. For example, the imaging unit can input data on the ambient light and background to the generation AI, and cause the generation AI to automatically adjust the imaging conditions.

[0085] The imaging unit can estimate the emotion of the care recipient and determine the priority of imaging based on the estimated emotion of the care recipient. For example, when the care recipient feels anxious, the imaging unit prioritizes imaging and collects data. Also, when the care recipient is relaxed, the imaging unit can reduce the frequency of imaging. Furthermore, when the care recipient is excited, the imaging unit can frequently capture images and collect detailed data. As a result, important data can be preferentially acquired by determining the priority of imaging based on emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the imaging unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the imaging unit can input data of the emotional state to the generation AI and cause the generation AI to execute the determination of the priority of imaging.

[0086] The imaging unit can take the geographical location information of the care recipient into consideration when capturing images and preferentially acquire highly relevant imaging data. For example, when the care recipient is at home, the imaging unit preferentially captures images of the daily life of the care recipient. Also, when the care recipient is in a hospital, the imaging unit can preferentially capture images of interactions with medical staff. Furthermore, when the care recipient is out, the imaging unit can capture images of the surrounding environment and the state of the care recipient. This allows highly relevant data to be acquired by taking the geographical location information into consideration. A part or all of the above-mentioned processing in the imaging unit may be performed, for example, using AI or may be performed without using AI. For example, the imaging unit can input data of geographical location information to the generation AI and cause the generation AI to acquire highly relevant imaging data.

[0087] The imaging unit can analyze the social media activity of the care recipient at the time of imaging and acquire related imaging data. The imaging unit determines the timing of imaging based on, for example, a location shared by the care recipient on social media. The imaging unit can also set the imaging angle and distance with reference to photos and videos shared by the care recipient on social media. Furthermore, the imaging unit can identify places and events of interest from the social media activity of the care recipient and perform imaging. As a result, related data can be acquired by analyzing the social media activity. A part or all of the above-mentioned processing in the imaging unit may be performed using, for example, AI, or may be performed without using AI. For example, the imaging unit can input data of social media activity to the generation AI and cause the generation AI to acquire related imaging data.

[0088] The image analysis unit can estimate the emotion of the care recipient and adjust the display method of the image analysis based on the estimated emotion of the care recipient. For example, the image analysis unit displays a detailed analysis result when the care recipient is relaxed. Furthermore, the image analysis unit can display a simple analysis result when the care recipient is tense. Furthermore, the image analysis unit can display a visually stimulating analysis result when the care recipient is excited. This allows a more appropriate analysis result to be provided by adjusting the expression method based on the emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the image analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the image analysis unit can input data of the emotional state to the generation AI and cause the generation AI to adjust the display method.

[0089] The image analysis unit can adjust the accuracy of the analysis based on the importance of the mouth movement of the care recipient during image analysis. For example, when the mouth movement is clear, the image analysis unit performs a detailed analysis. Also, when the mouth movement is unclear, the image analysis unit can perform a simplified analysis. Furthermore, when the mouth movement is fast, the image analysis unit can perform the analysis by increasing the frame rate. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the mouth movement. A part or all of the above-mentioned processing in the image analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the image analysis unit can input data on the mouth movement to the generation AI and cause the generation AI to adjust the accuracy of the analysis.

[0090] The image analysis unit can apply different analysis algorithms depending on the type of mouth movement of the care recipient during image analysis. For example, when the mouth movement is at the word level, the image analysis unit applies a word recognition algorithm. Furthermore, when the mouth movement is at the sentence level, the image analysis unit can apply a sentence recognition algorithm. Furthermore, when the mouth movement is at the phoneme level, the image analysis unit can apply a phoneme recognition algorithm. This improves the analysis accuracy by applying different analysis algorithms depending on the category of mouth movement. Part or all of the above-mentioned processing in the image analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the image analysis unit can input data of mouth movement to the generation AI and cause the generation AI to apply an appropriate analysis algorithm.

[0091] The image analysis unit can estimate the emotion of the care recipient and adjust the time of image analysis based on the estimated emotion of the care recipient. For example, the image analysis unit performs a long analysis when the care recipient is relaxed. Also, the image analysis unit can perform a short analysis when the care recipient is tense. Furthermore, the image analysis unit can perform a detailed analysis when the care recipient is excited. This allows efficient analysis by adjusting the length of analysis based on the emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the image analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the image analysis unit can input data of the emotional state to the generation AI and cause the generation AI to adjust the analysis time.

[0092] The image analysis unit can determine the importance of the analysis based on the time of imaging of the care recipient during image analysis. For example, the image analysis unit prioritizes analysis of the latest imaging data. Also, the image analysis unit can prioritize analysis of important data by referring to past imaging data. Furthermore, the image analysis unit can perform simplified analysis of data captured at older times. As a result, important data can be analyzed preferentially by determining the priority of analysis based on the time of imaging. A part or all of the above-mentioned processing in the image analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the image analysis unit can input data of the time of imaging to the generation AI and cause the generation AI to determine the priority of analysis.

[0093] The image analysis unit can adjust the order of analysis based on the relevance of the care recipient during image analysis. For example, the image analysis unit preferentially analyzes data related to the content of the care recipient's remarks. The image analysis unit can also preferentially analyze data related to the health condition of the care recipient. Furthermore, the image analysis unit can also preferentially analyze data related to the emotional state of the care recipient. This allows for efficient analysis by adjusting the order of analysis based on relevance. A part or all of the above-mentioned processing in the image analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the image analysis unit can input relevance data to the generation AI and cause the generation AI to adjust the order of analysis.

[0094] The voice analysis unit can estimate the emotion of the care recipient and set the voice analysis standard based on the estimated emotion of the care recipient. For example, the voice analysis unit performs detailed voice analysis when the care recipient is relaxed. Furthermore, the voice analysis unit can perform simplified voice analysis when the care recipient is nervous. Furthermore, the voice analysis unit can perform analysis that emphasizes the strength of the voice when the care recipient is excited. This allows a more appropriate analysis result to be provided by adjusting the voice analysis standard based on the emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the voice analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the voice analysis unit can input data of the emotional state to the generation AI and cause the generation AI to adjust the voice analysis standard.

[0095] The voice analysis unit can improve the accuracy of the analysis by considering the interrelationships of the voices of the care recipient during the voice analysis. The voice analysis unit, for example, analyzes the interrelationships between the tone and pitch of the voice. The voice analysis unit can also analyze the interrelationships between the strength and rhythm of the voice. Furthermore, the voice analysis unit can analyze the interrelationships between the wavelength and frequency of the voice. As a result, the accuracy of the analysis is improved by considering the interrelationships of the voices. A part or all of the above-mentioned processing in the voice analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice analysis unit can input data on the interrelationships of the voices to the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0096] The voice analysis unit can perform the analysis while taking into consideration the characteristic information of the person who submits the voice of the care recipient during the voice analysis. The voice analysis unit analyzes the characteristics of the voice based on, for example, the age of the care recipient. The voice analysis unit can also analyze the characteristics of the voice based on the gender of the care recipient. Furthermore, the voice analysis unit can analyze the characteristics of the voice based on the health condition of the care recipient. This improves the accuracy of the analysis by taking into consideration the attribute information of the submitter. A part or all of the above-mentioned processing in the voice analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the voice analysis unit can input data of the characteristic information of the submitter to the generation AI and cause the generation AI to perform the analysis.

[0097] The voice analysis unit can estimate the emotion of the care recipient and set the order of displaying the voice analysis results based on the estimated emotion of the care recipient. For example, when the care recipient is relaxed, the voice analysis unit can preferentially display detailed analysis results. Also, when the care recipient is nervous, the voice analysis unit can preferentially display simplified analysis results. Furthermore, when the care recipient is excited, the voice analysis unit can preferentially display analysis results that emphasize the strength and weakness of the voice. As a result, important analysis results can be preferentially displayed by adjusting the display order based on the emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the voice analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the voice analysis unit can input data of the emotional state to the generation AI and cause the generation AI to adjust the display order.

[0098] The voice analysis unit can perform the analysis while taking into consideration the geographical location of the care recipient during the voice analysis. The voice analysis unit performs the analysis while taking into consideration, for example, the dialect and accent of the area where the care recipient lives. The voice analysis unit can also perform the analysis while taking into consideration the characteristics of the voice of the area to which the care recipient has moved. Furthermore, the voice analysis unit can perform the analysis while taking into consideration the characteristics of the voice of the area to which the care recipient has visited. This improves the accuracy of the analysis by taking into consideration the geographical distribution. A part or all of the above-mentioned processing in the voice analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice analysis unit can input data of the geographical location to the generation AI and cause the generation AI to execute the analysis.

[0099] The voice analysis unit can improve the accuracy of the analysis by referring to related literature on the care recipient during the voice analysis. The voice analysis unit performs the analysis by referring to, for example, research papers on the characteristics of the voice of the care recipient. The voice analysis unit can also perform the analysis by referring to a database on the characteristics of the voice of the care recipient. Furthermore, the voice analysis unit can perform the analysis by referring to past data on the characteristics of the voice of the care recipient. As a result, the accuracy of the analysis is improved by referring to the related literature. A part or all of the above-mentioned processing in the voice analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the voice analysis unit can input data of related literature to the generation AI and have the generation AI perform the analysis.

[0100] The estimation unit can estimate the emotion of the care recipient and adjust the identification method of the utterance content based on the estimated emotion of the care recipient. For example, when the care recipient is relaxed, the estimation unit estimates the detailed utterance content. Furthermore, when the care recipient is nervous, the estimation unit can estimate the simplified utterance content. Furthermore, when the care recipient is excited, the estimation unit can estimate the utterance content with emphasis on the emotion. As a result, by adjusting the estimation method based on the emotion, more appropriate utterance content can be estimated. The estimation of the emotion 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 estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input data of the emotional state to the generation AI and cause the generation AI to adjust the estimation method of the utterance content.

[0101] The estimation unit can adjust the estimation algorithm by referring to the past utterances of the care recipient at the time of estimation. The estimation unit can also analyze the past utterance patterns of the care recipient and optimize the estimation algorithm. Furthermore, the estimation unit can compare the past utterances of the care recipient with the current utterances and improve the estimation algorithm. As a result, the accuracy of the estimation algorithm is improved by referring to the past utterances. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI or may be performed without using AI. For example, the estimation unit can input data of the past utterances to the generation AI and cause the generation AI to adjust the estimation algorithm.

[0102] The estimation unit can adjust the estimation means based on the current living situation of the care recipient at the time of estimation. For example, when the care recipient is in a hospital, the estimation unit can preferentially estimate medical-related utterance contents. Furthermore, when the care recipient is at home, the estimation unit can preferentially estimate utterance contents related to daily life. Furthermore, when the care recipient is out, the estimation unit can preferentially estimate utterance contents related to the destination. This allows more appropriate utterance contents to be estimated by customizing the estimation means based on the current living situation. Part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI or may be performed without using AI. For example, the estimation unit can input data of the current living situation to the generation AI and cause the generation AI to adjust the estimation means.

[0103] The estimation unit can select an appropriate estimation method in consideration of the geographical location information of the care recipient at the time of estimation. For example, when the care recipient is in a hospital, the estimation unit can preferentially estimate medical-related utterance content. Also, when the care recipient is at home, the estimation unit can preferentially estimate utterance content related to daily life. Furthermore, when the care recipient is out, the estimation unit can preferentially estimate utterance content related to the destination. As a result, more appropriate utterance content can be estimated by considering the geographical location information. Part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI or may be performed without using AI. For example, the estimation unit can input data of geographical location information to the generation AI and cause the generation AI to select the estimation method.

[0104] At the time of estimation, the estimation unit can provide a means of estimation by analyzing the social media activity of the care recipient. For example, the estimation unit estimates the content of the comment based on the information shared by the care recipient on social media. In addition, the estimation unit can estimate the topic of interest from the social media activity of the care recipient. Furthermore, the estimation unit can analyze the comment pattern of the care recipient on social media and optimize the estimation algorithm. As a result, more appropriate comment content can be estimated by analyzing the social media activity. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input data of the social media activity to the generation AI and cause the generation AI to provide the means of estimation.

[0105] The presentation unit can estimate the emotion of the care recipient and set the display method of presentation based on the estimated emotion of the care recipient. The presentation unit, for example, estimates the emotion of the care recipient and adjusts the display method of presentation based on the estimated emotion. For example, when the care recipient is relaxed, the presentation unit provides a display method including detailed information. Furthermore, when the care recipient is tense, the presentation unit can provide a display method that is simple and highly visible. Furthermore, when the care recipient is excited, the presentation unit can provide a visually stimulating display method. This allows more appropriate information to be provided by adjusting the display method based on the emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the presentation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the presentation unit can input data of the emotional state to the generation AI and cause the generation AI to adjust the display method.

[0106] The presentation unit can select an appropriate display method by referring to the past operation history of the care recipient at the time of presentation and display. For example, the presentation unit preferentially provides a display method that the care recipient has used in the past. The presentation unit can also select a display method with the highest visibility from the past operation history of the care recipient. Furthermore, the presentation unit can analyze the past operation history of the care recipient and suggest an optimal display method. As a result, the optimal display method can be provided by referring to the past operation history. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input data of the past operation history to the generation AI and cause the generation AI to select the display method.

[0107] The presentation unit can estimate the emotion of the care recipient and set the presented operation procedure based on the estimated emotion of the care recipient. For example, when the care recipient is relaxed, the presentation unit can provide detailed operation procedures. Furthermore, when the care recipient is nervous, the presentation unit can provide simplified operation procedures. Furthermore, when the care recipient is excited, the presentation unit can provide visually stimulating operation procedures. In this way, by adjusting the operation procedures based on the emotion, more appropriate operation procedures can be provided. 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 presentation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the presentation unit can input data of the emotional state to the generation AI and cause the generation AI to adjust the operation procedure.

[0108] The presentation unit can select an appropriate display method in consideration of the device information of the care recipient when presenting and displaying. For example, when the care recipient uses a smartphone, the presentation unit provides a display method that matches the screen size. In addition, when the care recipient uses a tablet, the presentation unit can provide a display method optimized for a large screen. Furthermore, when the care recipient uses a smartwatch, the presentation unit can provide a simple and highly visible display method. This makes it possible to provide an optimal display method by considering the device information. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input data of the device information to the generation AI and cause the generation AI to select the display method.

[0109] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0110] The care support system may further include a motion detection unit that detects the motion of the care recipient. The motion detection unit detects the hand motion and body motion of the care recipient and analyzes these motions. For example, the motion detection unit may detect the motion of the care recipient raising their hand and determine that the motion is a sign of asking for help. The motion detection unit may also detect the motion of the care recipient shaking their body and determine that the motion indicates anxiety or tension. Furthermore, the motion detection unit may learn the motion patterns of the care recipient and detect abnormal motions. In this way, by analyzing the motion of the care recipient, understanding of the content of what is being said can be supplemented, enabling more accurate care support.

[0111] The care support system may further include an environmental sound analysis unit that analyzes the environmental sounds of the care recipient. The environmental sound analysis unit detects sounds around the care recipient and analyzes these sounds. For example, the environmental sound analysis unit may detect sounds and voices occurring around the care recipient and determine whether these sounds affect the contents of the care recipient's speech. The environmental sound analysis unit may also learn the sound environment around the care recipient and detect abnormal sounds. Furthermore, the environmental sound analysis unit may analyze the association between the contents of the care recipient's speech and environmental sounds to complement the understanding of the contents of the speech. In this way, the contents of the care recipient's speech can be more accurately understood by analyzing the environmental sounds.

[0112] The care support system may further include a biometric information acquisition unit that acquires biometric information of the care recipient. The biometric information acquisition unit acquires biometric information such as the heart rate, blood pressure, and body temperature of the care recipient, and analyzes this information. For example, the biometric information acquisition unit may detect fluctuations in the heart rate of the care recipient and determine that the fluctuations indicate tension or excitement. The biometric information acquisition unit may also detect an increase in the body temperature of the care recipient and determine that the increase indicates poor health. Furthermore, the biometric information acquisition unit may learn the fluctuation patterns of the biometric information of the care recipient and detect abnormal fluctuations. This allows for more accurate care support by analyzing the biometric information, which complements the understanding of the content of the care recipient's statements.

[0113] The care support system may further include an instruction generating unit that estimates the emotion of the care recipient and generates an instruction for the care staff based on the estimated emotion. The instruction generating unit analyzes the emotional state of the care recipient and instructs the care staff on an appropriate response method according to the emotion. For example, when the care recipient feels anxious, the instruction generating unit can instruct the care staff to speak to the care recipient to reassure the care recipient. When the care recipient feels angry, the instruction generating unit can also instruct the care staff to respond calmly. Furthermore, when the care recipient feels happy, the instruction generating unit can instruct the care staff to share the joy. In this way, by generating appropriate instructions based on the emotion, the care staff can respond more appropriately to the care recipient.

[0114] The care support system may further include an entertainment providing unit that estimates the emotion of the care recipient and provides music and images based on the estimated emotion. The entertainment providing unit analyzes the emotional state of the care recipient and provides music and images according to the emotion. For example, if the care recipient is relaxed, the entertainment providing unit may provide music with a relaxing effect. Also, if the care recipient is excited, the entertainment providing unit may provide images to calm the excitement. Furthermore, if the care recipient is sad, the entertainment providing unit may provide music and images to brighten the mood. In this way, the emotional state of the care recipient can be improved by providing appropriate entertainment based on the emotion.

[0115] The care support system may further include an environment adjustment unit that estimates the emotion of the care recipient and adjusts the lighting and temperature based on the estimated emotion. The environment adjustment unit analyzes the emotional state of the care recipient and adjusts the lighting and temperature according to the emotion. For example, when the care recipient is relaxed, the environment adjustment unit can provide lighting with a relaxing effect. When the care recipient is excited, the environment adjustment unit can also adjust the temperature to calm the excitement. Furthermore, when the care recipient feels anxious, the environment adjustment unit can provide lighting and temperature to give a sense of security. In this way, the emotional state of the care recipient can be improved by providing an appropriate environment based on the emotion.

[0116] The care support system may further include a meal suggestion unit that estimates the emotion of the care recipient and suggests a meal menu based on the estimated emotion. The meal suggestion unit analyzes the emotional state of the care recipient and suggests a meal menu according to the emotion. For example, if the care recipient is relaxed, the meal suggestion unit may suggest a menu using ingredients that have a relaxing effect. Also, if the care recipient is excited, the meal suggestion unit may suggest a menu using ingredients to calm the excitement. Furthermore, if the care recipient is sad, the meal suggestion unit may suggest a menu using ingredients to brighten the mood. In this way, the emotional state of the care recipient can be improved by suggesting an appropriate meal menu based on the emotion.

[0117] The care support system may further include an exercise suggestion unit that estimates the emotion of the care recipient and suggests an exercise program based on the estimated emotion. The exercise suggestion unit analyzes the emotional state of the care recipient and suggests an exercise program according to the emotion. For example, if the care recipient is relaxed, the exercise suggestion unit may suggest stretching that has a relaxing effect. Also, if the care recipient is excited, the exercise suggestion unit may suggest yoga to calm the excitement. Furthermore, if the care recipient is feeling anxious, the exercise suggestion unit may suggest light exercise to give a sense of security. In this way, the emotional state of the care recipient can be improved by suggesting an appropriate exercise program based on the emotion.

[0118] The care support system may further include a communication suggestion unit that estimates the emotion of the care recipient and suggests a communication method based on the estimated emotion. The communication suggestion unit analyzes the emotional state of the care recipient and suggests a communication method according to the emotion. For example, if the care recipient is relaxed, the communication suggestion unit may suggest a topic that has a relaxing effect. Also, if the care recipient is excited, the communication suggestion unit may suggest a gentle way of speaking to calm the excitement. Furthermore, if the care recipient is feeling anxious, the communication suggestion unit may suggest gentle words to give a sense of security. In this way, the emotional state of the care recipient can be improved by suggesting an appropriate communication method based on the emotion.

[0119] The care support system may further include a life rhythm analysis unit that analyzes the life rhythm of the care recipient. The life rhythm analysis unit analyzes the sleep pattern, meal timing, activity time period, etc. of the care recipient, and grasps the life rhythm based on this information. For example, the life rhythm analysis unit may analyze the sleep pattern of the care recipient and suggest appropriate wake-up times and bedtimes. The life rhythm analysis unit may also analyze the meal timing of the care recipient and suggest appropriate meal times. Furthermore, the life rhythm analysis unit may analyze the activity time period of the care recipient and suggest appropriate exercise and rest timings. In this way, by analyzing the life rhythm, the health condition of the care recipient can be maintained and a better life can be supported.

[0120] The process flow of the second embodiment will be briefly described below.

[0121] Step 1: The imaging unit captures the mouth of the care recipient. The mouth of the care recipient includes lip movement and opening and closing of the mouth. The imaging unit captures these movements using a high-resolution camera and saves them as image data. The imaging unit also captures the entire face of the care recipient, and can analyze facial expressions such as smiling, anger, and surprise. Step 2: The image analysis unit reads the movement of the care recipient's mouth based on the image captured by the imaging unit. Using AI, the image analysis unit analyzes the movement of the lips and the opening and closing of the mouth to estimate the content of what was said. Step 3: The voice analysis unit analyzes the characteristics of the voice emitted by the care recipient. The voice analysis unit uses AI to analyze voice characteristics such as volume, pitch, and tone, and estimates the content of what is being said. Step 4: The estimation unit estimates the content of the care recipient's speech based on the information obtained by the image analysis unit and the voice analysis unit. The estimation unit uses AI to analyze a combination of mouth movements and voice characteristics to identify the content of speech. The estimation unit can also estimate the content of speech using the care recipient's past movements and voice characteristics. Step 5: The presentation unit presents the estimation result by the estimation unit to the care worker. The presentation unit uses AI to display the estimation result on a screen or notify the care worker by voice.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] For example, the imaging unit is realized by the camera 42 of the smart device 14. For example, the image analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the voice analysis unit is realized by the microphone 38B and the control unit 46A of the smart device 14. For example, the estimation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the presentation unit is realized by the display 40A and the speaker 40B of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0126] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] For example, the imaging unit is realized by the camera 42 of the smart glasses 214. For example, the image analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the voice analysis unit is realized by the microphone 238 and the control unit 46A of the smart glasses 214. For example, the estimation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the presentation unit is realized by the speaker 240 of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0142] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0152] 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.

[0153] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 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.

[0154] 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 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.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. 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.

[0156] 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.

[0157] For example, the imaging unit is realized by the camera 42 of the headset type terminal 314. For example, the image analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the voice analysis unit is realized by the microphone 238 and the control unit 46A of the headset type terminal 314. For example, the estimation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the presentation unit is realized by the display 343 and the speaker 240 of the headset type terminal 314. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0158] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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).

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] For example, the imaging unit is realized by the camera 42 of the robot 414. For example, the image analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the voice analysis unit is realized by the microphone 238 and the control unit 46A of the robot 414. For example, the estimation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the presentation unit is realized by the speaker 240 and the control target 443 of the robot 414. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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 on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0179] 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.

[0180] 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."

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] (Appendix 1) An imaging unit that images the mouth of the care recipient; an image analysis unit that reads the movement of the mouth of the care recipient based on the image captured by the imaging unit; a voice analysis unit that analyzes characteristics of a voice uttered by the care recipient; an estimation unit that estimates the content of a statement made by the care recipient based on information obtained by the image analysis unit and the voice analysis unit; a presentation unit that presents the estimation result by the estimation unit to a care worker; A system characterized by: (Appendix 2) The estimation unit is The mouth movements and the voice characteristics are combined and analyzed to identify the contents of the speech of the care recipient. 2. The system of claim 1, (Appendix 3) The estimation unit is The past movements and voice characteristics of the care recipient are further used to identify the contents of the care recipient's speech. 2. The system of claim 1, (Appendix 4) The imaging unit includes: The apparatus further includes a face analysis unit that captures an image of the entire face of the care recipient and analyzes changes in facial expression. 2. The system of claim 1, (Appendix 5) The estimation unit is The emotional state of the care recipient is identified based on the change in facial expression, and the emotional state is presented to the care staff together with the content of the remarks. 2. The system of claim 1, (Appendix 6) A health monitoring unit is provided for analyzing the contents of the comments of the care recipient and for instantly monitoring the health condition of the care recipient. 2. The system of claim 1, (Appendix 7) The estimation unit is Analyze the speech of the care recipient and distinguish between everyday conversation and urgent matters 2. The system of claim 1, (Appendix 8) The presentation unit is If the health monitoring unit detects an abnormality in the health condition, the abnormality is reported to medical staff. 3. The system of claim 2, (Appendix 9) The estimation unit is Determining the importance of the comment content based on the emotional state of the care recipient 2. The system of claim 1, (Appendix 10) The imaging unit includes: The emotion of the care recipient is estimated, and the timing of imaging is adjusted based on the estimated emotion of the care recipient. 2. The system of claim 1, (Appendix 11) The imaging unit includes: Analyze the past image data of the care recipient and select the appropriate imaging angle and distance 2. The system of claim 1, (Appendix 12) The imaging unit includes: When capturing an image, the imaging conditions are automatically adjusted to take into account the current ambient light and background of the care recipient. 2. The system of claim 1, (Appendix 13) The imaging unit includes: The emotion of the care recipient is estimated, and the importance of imaging is determined based on the estimated emotion of the care recipient. 2. The system of claim 1, (Appendix 14) The imaging unit includes: When capturing images, the system takes into consideration the geographic location information of the care recipient and prioritizes obtaining image data with high relevance. 2. The system of claim 1, (Appendix 15) The imaging unit includes: At the time of imaging, the social media activity of the care recipient is analyzed and relevant imaging data is obtained. 2. The system of claim 1, (Appendix 16) The image analysis unit Estimating the emotion of the care recipient and adjusting the display method of image analysis based on the estimated emotion of the care recipient 2. The system of claim 1, (Appendix 17) The image analysis unit When analyzing images, the accuracy of the analysis is adjusted based on the importance of the mouth movements of the care recipient. 2. The system of claim 1, (Appendix 18) The image analysis unit When analyzing images, different analysis algorithms are applied depending on the type of mouth movement of the care recipient. 2. The system of claim 1, (Appendix 19) The image analysis unit Estimating the emotions of the care recipient and adjusting the time of image analysis based on the estimated emotions of the care recipient 2. The system of claim 1, (Appendix 20) The image analysis unit When analyzing images, the importance of the analysis is determined based on the time when the image of the care recipient was taken. 2. The system of claim 1, (Appendix 21) The image analysis unit When analyzing images, adjust the order of analysis based on the relevance to the care recipient 2. The system of claim 1, (Appendix 22) The voice analysis unit is To estimate the emotion of a care recipient and set a standard for voice analysis based on the estimated emotion of the care recipient. 2. The system of claim 1, (Appendix 23) The voice analysis unit is When analyzing voices, the accuracy of the analysis is improved by taking into account the correlation of the voices of the care recipients. 2. The system of claim 1, (Appendix 24) The voice analysis unit is When analyzing voices, the analysis is performed taking into account the characteristics of the person submitting the voice of the person receiving care. 2. The system of claim 1, (Appendix 25) The voice analysis unit is Estimating the emotion of the care recipient and setting an order for displaying the voice analysis results based on the estimated emotion of the care recipient 2. The system of claim 1, (Appendix 26) The voice analysis unit is When analyzing voices, the geographic location of the person receiving care is taken into account. 2. The system of claim 1, (Appendix 27) The voice analysis unit is When analyzing voice, reference literature related to the care recipient to improve the accuracy of the analysis. 2. The system of claim 1, (Appendix 28) The estimation unit is Estimate the emotions of the care recipient and adjust the method of identifying the utterance content based on the estimated emotions of the care recipient 2. The system of claim 1, (Appendix 29) The estimation unit is When making an estimation, the estimation algorithm is adjusted by referring to the care recipient's past statements. 2. The system of claim 1, (Appendix 30) The estimation unit is At the time of estimation, adjust the estimation measures based on the current living situation of the care recipient. 2. The system of claim 1, (Appendix 31) The estimation unit is When estimating, an appropriate estimation method is selected taking into account the geographic location information of the care recipient. 2. The system of claim 1, (Appendix 32) The estimation unit is At the time of estimation, the social media activity of the care recipient is analyzed to provide a means of estimation. 2. The system of claim 1, (Appendix 33) The presentation unit is Estimating the emotion of the care recipient and setting the display method based on the estimated emotion of the care recipient 2. The system of claim 1, (Appendix 34) The presentation unit is When presenting information, the system selects the appropriate display method by referring to the care recipient's past operation history. 2. The system of claim 1, (Appendix 35) The presentation unit is Estimating the emotions of the care recipient and setting the presented operation procedure based on the estimated emotions of the care recipient 2. The system of claim 1, (Appendix 36) The presentation unit is When presenting information, the system selects the appropriate display method taking into account the device information of the care recipient. 2. The system of claim 1, [Explanation of symbols]

[0194] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. An imaging unit that images the mouth of the care recipient; an image analysis unit that reads a movement of the mouth of the care recipient based on the image captured by the imaging unit; a voice analysis unit that analyzes characteristics of a voice uttered by the care recipient; an estimation unit that estimates a statement of the care recipient based on information obtained by the image analysis unit and the voice analysis unit; a presentation unit that presents the estimation result by the estimation unit to a care worker; A system characterized by:

2. The estimation unit is The mouth movement and the voice characteristics are combined and analyzed to identify the contents of the speech of the care recipient.

2. The system of claim 1 .

3. The estimation unit is The past movements and voice characteristics of the care recipient are further used to identify the contents of the speech of the care recipient.

2. The system of claim 1 .

4. The imaging unit includes: The apparatus further includes a face analysis unit that captures an image of the entire face of the care recipient and analyzes changes in facial expression.

2. The system of claim 1 .

5. The estimation unit is Identifying the emotional state of the care recipient based on the change in facial expression, and presenting the emotional state together with the content of the speech to a care worker.

2. The system of claim 1 .

6. A health monitoring unit is provided for analyzing the contents of the comments of the care recipient and for instantly monitoring the health condition of the care recipient.

2. The system of claim 1 .

7. The estimation unit is Analyze the speech of the care recipient and distinguish between everyday conversation and urgent matters 2. The system of claim 1 .

8. The presentation unit is If the health monitoring unit detects an abnormality in the health condition, the abnormality is reported to medical staff.

7. The system of claim 6.

9. The estimation unit is Determining the importance of the contents of the care recipient's comments based on the care recipient's emotional state 2. The system of claim 1 .

10. The imaging unit includes: The feeling of the care recipient is estimated, and the timing of imaging is adjusted based on the estimated feeling of the care recipient.

2. The system of claim 1 .

Images