system

Abstract

The system according to this embodiment aims to efficiently monitor the movements of infants and the elderly, and to quickly detect and notify of any abnormalities. [Solution] The system according to the embodiment comprises an image analysis unit, a detection unit, a notification unit, a natural language processing unit, and an analysis unit. The image analysis unit monitors the movements of infants and elderly people. The detection unit detects abnormalities based on the movements monitored by the image analysis unit. The notification unit notifies the guardian or caregiver of the abnormality detected by the detection unit. The natural language processing unit interacts with the infant or elderly person. The analysis unit analyzes the content of the interaction conducted by the natural language processing unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, the movements of infants and the elderly are not sufficiently monitored efficiently, and abnormalities are not quickly detected and notified, leaving room for improvement.

[0005] The system according to the embodiment aims to efficiently monitor the movements of infants and the elderly and quickly detect and notify abnormalities.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an image analysis unit, a detection unit, a notification unit, a natural language processing unit, and an analysis unit. The image analysis unit monitors the movements of infants and elderly people. The detection unit detects abnormalities based on the movements monitored by the image analysis unit. The notification unit notifies guardians or caregivers of the abnormalities detected by the detection unit. The natural language processing unit interacts with infants and elderly people. The analysis unit analyzes the content of the interaction conducted by the natural language processing unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently monitor the movements of infants and the elderly, and quickly detect and notify of any abnormalities. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 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". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0025] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The rescue robot system according to an embodiment of the present invention aims to develop a rescue robot that uses an AI agent to monitor children and the elderly, anticipating a sharp increase in the double care of childcare and elderly care due to the declining birthrate, aging population, later marriages, and later childbirths, and in order to create an environment in which working people can work flexibly. The rescue robot system is equipped with an image analysis function for monitoring infants and the elderly. The AI ​​agent monitors the movements of infants and the elderly in real time through a camera and notifies parents or caregivers if an abnormality is detected. For example, immediate action is possible if an infant approaches a dangerous place or if an elderly person falls. Next, the rescue robot system is equipped with a natural language processing function to act as a conversation partner for infants and the elderly. The AI ​​agent can converse with infants and the elderly to alleviate feelings of loneliness. For example, the rescue robot system can respond if an infant asks for a playmate or if an elderly person needs someone to talk to. Furthermore, the rescue robot system is equipped with an automatic analysis processing function for contacting parents or caregivers. The AI ​​agent analyzes the condition of infants and the elderly and notifies parents or caregivers as needed. For example, a quick response is possible if an infant becomes ill or an elderly person complains of feeling unwell. Thus, the rescue robot system is equipped with image analysis, natural language processing, and automatic analysis functions for monitoring infants and the elderly, creating an environment where parents and caregivers do not need to be constantly present. This provides a flexible work environment for employees and reduces the burden of childcare and elder care. In this way, the rescue robot system can reduce the burden of childcare and elder care by monitoring the movements of infants and the elderly, detecting and notifying of abnormalities, engaging in dialogue, and performing analysis.

[0029] The rescue robot system according to this embodiment comprises an image analysis unit, a detection unit, a notification unit, a natural language processing unit, and an analysis unit. The image analysis unit monitors the movements of infants and elderly people. The image analysis unit monitors the movements of infants and elderly people in real time, for example, through a camera. The image analysis unit can monitor, for example, how infants walk or how elderly people stand up from a seated position. The image analysis unit can also detect abnormalities when infants or elderly people remain still for a long period of time. The detection unit detects abnormalities based on the movements monitored by the image analysis unit. The detection unit detects abnormalities, for example, when infants approach a dangerous place or when elderly people fall. The detection unit can detect abnormalities, for example, when infants approach stairs or when elderly people try to go out onto the road. The detection unit can also detect abnormalities when infants are near a fire or when elderly people remain still for a long period of time. The notification unit notifies guardians or caregivers of abnormalities detected by the detection unit. The notification unit can inform guardians or caregivers of abnormalities, for example, by emitting an alert sound. Furthermore, the notification unit can also notify parents or caregivers of abnormalities by sending messages. In addition, the notification unit can also notify parents or caregivers of abnormalities by making phone calls. The natural language processing unit interacts with infants and the elderly. For example, the natural language processing unit can interact when an infant is seeking a playmate. It can also interact when an elderly person needs someone to talk to. Furthermore, the natural language processing unit can interact when infants or the elderly are feeling lonely. The analysis unit analyzes the content of the conversation conducted by the natural language processing unit. For example, the analysis unit can analyze the emotions of infants and the elderly. It can also analyze the behavior of infants and the elderly. Furthermore, the analysis unit can analyze the health status of infants and the elderly. As a result, the rescue robot system according to this embodiment can reduce the burden of childcare and caregiving by monitoring the movements of infants and the elderly, detecting and notifying of abnormalities, interacting with them, and analyzing the data.

[0030] The image analysis unit monitors the movements of infants and the elderly. For example, the image analysis unit monitors the movements of infants and the elderly in real time through cameras. Specifically, the cameras acquire high-resolution video and use image analysis algorithms to detect movement. It can monitor infants walking or elderly people standing up from a seated position. The image analysis unit can also detect abnormalities if infants or the elderly remain still for extended periods. For example, if an infant does not move for a certain period of time or an elderly person remains in the same posture for a long time, this is detected as an abnormality. The image analysis unit analyzes these movements in real time and immediately notifies the detection unit when an abnormality occurs. Furthermore, the image analysis unit can achieve wide-area monitoring by linking multiple cameras. For example, cameras can be installed in multiple locations such as each room in the house or the garden, and the video obtained from each camera can be integrated and analyzed. This allows for accurate monitoring of the movements of infants and the elderly no matter where they are. In addition, the image analysis unit can use infrared cameras and low-light cameras to detect movement even at night or in dark places. This ensures the safety of infants and the elderly at all times, day and night.

[0031] The detection unit detects anomalies based on movements monitored by the image analysis unit. For example, the detection unit detects anomalies when a child approaches a dangerous area or when an elderly person falls. Specifically, the detection unit analyzes data sent from the image analysis unit to identify abnormal movements and locations. For example, it can detect anomalies when a child approaches stairs or when an elderly person tries to go out onto the road. The detection unit can also detect anomalies when a child is near a fire or when an elderly person remains stationary for a long time. The detection unit detects these anomalies in real time and immediately notifies the notification unit. Furthermore, the detection unit can select an appropriate response depending on the type and urgency of the anomaly. For example, if a child is near a fire, it will immediately issue an alert and notify the guardian. Also, if an elderly person falls, it will quickly contact the caregiver as emergency response is required. By quickly and accurately detecting these anomalies, the detection unit can ensure the safety of children and the elderly. Furthermore, the detection unit can learn anomaly patterns based on past data and perform more accurate detection. This allows the detection unit to provide highly accurate anomaly detection based on the latest information at all times, supporting a quick and appropriate response.

[0032] The notification unit notifies parents or caregivers of anomalies detected by the detection unit. For example, the notification unit can alert parents or caregivers of an anomaly by emitting an alert sound. Specifically, when an anomaly is detected, the notification unit immediately emits an alert sound to draw the attention of those nearby. The notification unit can also notify parents or caregivers of an anomaly by sending a message. For example, it can send a notification to a smartphone or tablet providing detailed information about the anomaly. Furthermore, the notification unit can also notify parents or caregivers of an anomaly by making a phone call. This allows parents or caregivers to respond immediately. By combining these notification methods, the notification unit can reliably communicate anomalies and encourage a rapid response. Moreover, the notification unit can flexibly change the notification content and method depending on the type and urgency of the anomaly. For example, for minor anomalies, only a message notification is sent, while for serious anomalies, both an alert sound and a phone call are used. The notification unit can also improve the notification content and method based on feedback from parents and caregivers, resulting in more effective notifications. This allows the notification unit to quickly and reliably inform parents and caregivers of any abnormalities, ensuring the safety of infants and the elderly.

[0033] The natural language processing unit (NLP) interacts with infants and the elderly. For example, it can interact with infants when they are seeking a playmate. Specifically, it recognizes the infant's speech and generates an appropriate response. For instance, if an infant says, "Let's play together," the NLP will respond, "What would you like to play?" The NLP can also interact with elderly individuals when they need someone to talk to. For example, if an elderly person says, "The weather is nice today," the NLP will respond, "It really is nice weather. Shall we go for a walk?" Furthermore, the NLP can interact with infants and the elderly when they are feeling lonely. For example, if an infant says, "I'm lonely," the NLP will respond, "Let's talk together," and if an elderly person says, "There's no one here," the NLP will respond, "I'm here." Through these interactions, the NLP can provide psychological support to infants and the elderly. In addition, the NLP can record the content of the interactions and provide it to the analysis unit, providing data to understand the state of the infants and the elderly. This allows the natural language processing unit to provide psychological support to infants and the elderly through dialogue, ensuring their safety and security.

[0034] The analysis unit analyzes the content of conversations conducted by the natural language processing unit. For example, the analysis unit can analyze the emotions of infants and elderly people. Specifically, the analysis unit analyzes the content of the conversation, tone of voice, facial expressions, etc., to understand the emotional state of infants and elderly people. For example, if an infant is speaking happily, it will be analyzed as "joy," and if an elderly person is speaking in a depressed voice, it will be analyzed as "sadness." The analysis unit can also analyze the behavior of infants and elderly people. For example, if an infant frequently walks around in the same place, it will be analyzed as "excitement," and if an elderly person stays in the same place for a long time, it will be analyzed as "fatigue." Furthermore, the analysis unit can also analyze the health status of infants and elderly people. For example, based on the content of the conversation and behavioral patterns, it will analyze the possibility that an infant has a cold or that an elderly person is unwell. Based on these analysis results, the analysis unit can provide appropriate advice to parents and caregivers. For example, if there is a possibility that an infant has a cold, it will notify them that "we recommend that you see a doctor," and if there is a possibility that an elderly person is unwell, it will notify them that "we recommend that you get some rest." This allows the analysis unit to analyze the emotions, behaviors, and health status of infants and the elderly, and to provide appropriate advice to parents and caregivers, thereby supporting their safety and health.

[0035] The image analysis unit can monitor the movements of infants and the elderly in real time via a camera. For example, the image analysis unit can monitor in real time the movements of infants walking or the movements of elderly people standing up from a seated position via a camera. For example, the image analysis unit can immediately detect abnormalities if an infant approaches a dangerous place or if an elderly person falls. The image analysis unit can also detect abnormalities if infants or elderly people remain still for a long period of time. In this way, abnormalities can be detected immediately by monitoring movements in real time via a camera. Real-time monitoring is performed with a delay of, for example, seconds. Some or all of the above processing in the image analysis unit may be performed using, for example, AI, or without AI. For example, the image analysis unit can input video data acquired by the camera into a generating AI and have the generating AI perform motion analysis from the video data.

[0036] The detection unit can detect anomalies, such as when a child approaches a dangerous place or when an elderly person falls. For example, the detection unit can detect anomalies when a child approaches stairs or when an elderly person tries to go out onto the road. The detection unit can also detect anomalies, such as when a child is near a fire or when an elderly person remains stationary for a long time. This allows for a quick response by detecting dangerous places and falls. Dangerous places include, but are not limited to, stairs, roads, and areas near fire. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input motion data acquired by the image analysis unit into a generating AI and have the generating AI perform anomaly detection.

[0037] The notification unit can notify parents or caregivers when it detects an anomaly. For example, the notification unit can notify parents or caregivers of an anomaly by emitting an alert sound. The notification unit can also notify parents or caregivers of an anomaly by sending a message. Furthermore, the notification unit can notify parents or caregivers of an anomaly by making a telephone notification. This allows for appropriate action to be taken by promptly notifying when an anomaly is detected. Notification methods include, but are not limited to, alert sounds, messages, and telephone notifications. Some or all of the above-described processes in the notification unit may be performed using, for example, AI, or not using AI. For example, the notification unit can input data on anomalies detected by the detection unit into a generation AI and have the generation AI generate notifications.

[0038] The natural language processing unit can interact with infants and the elderly to alleviate feelings of loneliness. For example, the natural language processing unit can engage in dialogue when an infant is seeking a playmate. It can also engage in dialogue when an elderly person needs someone to talk to. Furthermore, the natural language processing unit can engage in dialogue when infants or the elderly are feeling lonely. This allows for the alleviation of loneliness and the provision of emotional support through dialogue. The content of the dialogue includes, but is not limited to, voice dialogue, text dialogue, and dialogue topics. Some or all of the processing described above in the natural language processing unit may be performed using, for example, AI, or not using AI. For example, the natural language processing unit can input dialogue data with infants or the elderly into a generating AI, and have the generating AI perform the generation of dialogues.

[0039] The analysis unit can analyze the condition of infants and the elderly and notify parents or caregivers as needed. For example, the analysis unit can analyze the emotions of infants and the elderly. The analysis unit can also analyze the behavior of infants and the elderly. Furthermore, the analysis unit can analyze the health status of infants and the elderly. This allows for appropriate responses by analyzing the condition and notifying as needed. Conditions include, but are not limited to, health status, emotional status, and behavioral status. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input dialogue data acquired by the natural language processing unit into a generating AI and have the generating AI perform the condition analysis.

[0040] The image analysis unit can improve the accuracy of anomaly prediction by referring to the past behavioral patterns of infants and the elderly during image analysis. For example, if an infant has engaged in dangerous behavior during a specific time period in the past, the image analysis unit will pay particular attention to that time period. For example, the image analysis unit will record the locations where an elderly person has fallen in the past and strengthen monitoring at those locations. For example, if an infant has repeated a specific behavior in the past, the image analysis unit will predict the likelihood of that behavior recurring and strengthen monitoring. This improves the accuracy of anomaly prediction by referring to past behavioral patterns. Past behavioral patterns include, but are not limited to, behavioral history data and behavioral frequency. Some or all of the above processing in the image analysis unit may be performed using, for example, AI, or not using AI. For example, the image analysis unit can input past behavioral data into a generating AI and have the generating AI perform anomaly prediction.

[0041] The image analysis unit can adjust the monitoring frequency during image analysis, taking into account the health status of infants and the elderly. For example, if an infant is unwell, the image analysis unit increases the monitoring frequency to detect abnormalities early. For example, if an elderly person is in good health, the image analysis unit decreases the monitoring frequency and allocates resources to other important tasks. For example, if an infant's health is deteriorating, the image analysis unit increases the monitoring frequency to detect abnormalities early. This allows for more appropriate monitoring by adjusting the monitoring frequency based on health status. Health status includes, but is not limited to, medical history, current health status, and medical data. Some or all of the above processing in the image analysis unit may be performed using, for example, AI, or not using AI. For example, the image analysis unit can input health status data into a generating AI and have the generating AI adjust the monitoring frequency.

[0042] The image analysis unit can adjust the monitoring range during image analysis, taking into account the living environment of infants and the elderly. For example, if an infant approaches a dangerous area, the AI ​​will monitor that area with particular attention. For example, the image analysis unit can record places where the elderly are prone to falling and strengthen monitoring in those areas. For example, if an infant is likely to engage in dangerous behavior in a particular area, the image analysis unit will strengthen monitoring in that area. This allows for more appropriate monitoring by adjusting the monitoring range based on the living environment. The living environment includes, but is not limited to, the structure of the residence, the surrounding environment, and lifestyle habits. Some or all of the above processing in the image analysis unit may be performed using, for example, AI, or not using AI. For example, the image analysis unit can input living environment data into a generating AI and have the generating AI adjust the monitoring range.

[0043] The image analysis unit can improve the accuracy of monitoring by referring to the activity history of infants and the elderly during image analysis. For example, if an infant has engaged in dangerous behavior during a specific time period in the past, the image analysis unit will pay particular attention to that time period. For example, the image analysis unit will record the location where an elderly person has fallen in the past and strengthen monitoring at that location. For example, if an infant has repeated a specific behavior in the past, the image analysis unit will predict the likelihood of that behavior recurring and strengthen monitoring. In this way, the accuracy of monitoring is improved by referring to the activity history. The activity history includes, but is not limited to, daily behavior patterns and exercise levels. Some or all of the above processing in the image analysis unit may be performed using, for example, AI, or not using AI. For example, the image analysis unit can input activity history data into a generating AI and have the generating AI perform the improvement of monitoring accuracy.

[0044] The detection unit can improve detection accuracy by referring to the past abnormality history of infants and elderly individuals when detection occurs. For example, if an infant has shown abnormality during a specific time period in the past, the detection unit will pay particular attention to that time period. For example, the detection unit will record the locations where elderly individuals have fallen in the past and enhance detection at those locations. For example, if an infant has repeated a specific behavior in the past, the detection unit will predict the likelihood of that behavior recurring and enhance detection. In this way, detection accuracy is improved by referring to past abnormality history. Past abnormality history includes, but is not limited to, the frequency of abnormality occurrences and the type of abnormality. Some or all of the above processing in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input past abnormality data into a generating AI and have the generating AI perform the improvement of detection accuracy.

[0045] The detection unit can adjust the frequency of abnormality detection when detecting an abnormality, taking into account the health status of infants and the elderly. For example, if an infant is unwell, the detection unit increases the detection frequency to detect abnormalities earlier. For example, if an elderly person is in good health, the detection unit decreases the detection frequency to allocate resources to other important tasks. For example, if an infant's health is deteriorating, the detection unit increases the detection frequency to detect abnormalities earlier. This allows for more appropriate abnormality detection by adjusting the abnormality detection frequency based on health status. Health status includes, but is not limited to, medical history, current health status, and medical data. Some or all of the above processing in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input health status data into a generating AI and have the generating AI adjust the abnormality detection frequency.

[0046] The detection unit can adjust the detection range for anomalies when detecting an anomaly, taking into account the living environment of infants and the elderly. For example, if an infant approaches a dangerous place, the AI ​​will pay particular attention to detecting that place. For example, the detection unit can record places where the elderly are prone to falling and strengthen detection in those places. For example, if an infant is likely to engage in dangerous behavior in a particular place, the detection unit will strengthen detection in that place. This allows for more appropriate anomaly detection by adjusting the detection range for anomalies based on the living environment. The living environment includes, but is not limited to, the structure of the residence, the surrounding environment, and lifestyle habits. Some or all of the above processing in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input living environment data into a generating AI and have the generating AI perform the adjustment of the anomaly detection range.

[0047] The detection unit can improve the accuracy of anomaly detection by referring to the activity history of infants and elderly people when detecting anomalies. For example, if an infant has shown abnormalities during a specific time period in the past, the detection unit will pay particular attention to that time period. For example, the detection unit will record the locations where elderly people have fallen in the past and strengthen detection at those locations. For example, if an infant has repeated a specific behavior in the past, the detection unit will predict the likelihood of that behavior recurring and strengthen detection. In this way, the accuracy of anomaly detection is improved by referring to the activity history. The activity history includes, but is not limited to, daily behavior patterns and exercise levels. Some or all of the above processing in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input activity history data into a generating AI and have the generating AI perform the improvement of anomaly detection accuracy.

[0048] The notification unit can select the optimal notification method by referring to the past response history of the guardian or caregiver when issuing a notification. For example, the notification unit may prioritize suggesting notification methods (email, phone, etc.) that the guardian has used in the past. For example, the notification unit may select the optimal notification method based on the type of anomaly the guardian has responded to in the past. For example, the notification unit may select the optimal notification method based on the time period the guardian has responded in the past. In this way, the optimal notification method can be selected by referring to the past response history. The past response history includes, but is not limited to, the frequency and content of responses. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit may input past response data into a generating AI and have the generating AI select the optimal notification method.

[0049] The notification unit can adjust the urgency of the notification according to the type of anomaly. For example, the notification unit sends a high-urgency notification if a child approaches a dangerous place. For example, the notification unit sends a high-urgency notification if an elderly person falls. For example, the notification unit sends a high-urgency notification if a child is unwell. By adjusting the urgency of the notification according to the type of anomaly, a more appropriate response becomes possible. Types of anomalies include, but are not limited to, falls, prolonged immobility, and approaching dangerous places. Some or all of the above processing in the notification unit may be performed using, for example, AI, or not using AI. For example, the notification unit can input anomaly data into a generating AI and have the generating AI adjust the urgency of the notification.

[0050] The notification unit can select the most appropriate notification method when sending a notification, taking into account the living environment of the guardian or caregiver. For example, if the guardian is at work, the notification unit may send a notification by email. For example, if the guardian is at home, the notification unit may send a notification by phone. For example, if the guardian is out, the notification unit may send a notification by SMS. This allows for more appropriate notifications by selecting the most appropriate notification method based on the living environment. The living environment includes, but is not limited to, the structure of the residence, the surrounding environment, and lifestyle habits. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input living environment data into a generating AI and have the generating AI select the most appropriate notification method.

[0051] The notification unit can adjust the content of a notification when it is sent, taking into account the location where the anomaly occurred. For example, if a child approaches a dangerous place, the notification unit will send a notification including details of that location. For example, if an elderly person falls, the notification unit will record the location and send a notification including details of that location. For example, if a child is likely to engage in dangerous behavior in a particular location, the notification unit will send a notification including details of that location. This allows for a more appropriate response by adjusting the content of the notification based on the location where the anomaly occurred. The location of the anomaly may include, but is not limited to, a room, outdoors, or a specific location. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input data on the location of the anomaly into a generating AI and have the generating AI adjust the content of the notification.

[0052] The natural language processing unit can select the optimal dialogue method by referring to the past dialogue history of infants and elderly people during a conversation. For example, the natural language processing unit may conduct a conversation based on topics that infants have enjoyed in the past. For example, the natural language processing unit may conduct a conversation based on topics that elderly people have shown interest in in the past. For example, the natural language processing unit may conduct a conversation while avoiding topics that infants have disliked in the past. In this way, the optimal dialogue method can be selected by referring to past dialogue history. Past dialogue history includes, but is not limited to, the frequency and content of conversations. Some or all of the processing described above in the natural language processing unit may be performed using, for example, AI, or not using AI. For example, the natural language processing unit can input past dialogue data into a generating AI and have the generating AI select the optimal dialogue method.

[0053] The natural language processing unit can adjust the frequency of conversations during dialogue, taking into account the health status of infants and elderly individuals. For example, if an infant is unwell, the natural language processing unit will reduce the frequency of conversations and prioritize rest. For example, if an elderly person is in good health, the natural language processing unit will increase the frequency of conversations to reduce feelings of loneliness. For example, if an infant's health is deteriorating, the natural language processing unit will reduce the frequency of conversations and prioritize rest. By adjusting the frequency of conversations based on health status, more appropriate conversations become possible. Health status includes, but is not limited to, medical history, current health status, and medical data. Some or all of the processing described above in the natural language processing unit may be performed using, for example, AI, or not using AI. For example, the natural language processing unit can input health status data into a generating AI and have the generating AI adjust the frequency of conversations.

[0054] The natural language processing unit can adjust the content of a conversation to take into account the living environment of infants and elderly people. For example, if an infant is at home, the natural language processing unit will focus the conversation on topics related to the home. If an elderly person is in a care facility, the natural language processing unit will focus the conversation on topics related to the facility. If an infant is out, the natural language processing unit will focus the conversation on topics related to the destination. By adjusting the content of the conversation based on the living environment, more appropriate conversations become possible. The living environment includes, but is not limited to, the structure of the residence, the surrounding environment, and lifestyle habits. Some or all of the processing described above in the natural language processing unit may be performed using AI, for example, or without AI. For example, the natural language processing unit can input data on the living environment into a generating AI and have the generating AI adjust the content of the conversation.

[0055] The natural language processing unit can improve the accuracy of conversations by referring to the activity history of infants and elderly people during dialogue. For example, the natural language processing unit conducts conversations based on activities that infants have enjoyed in the past. For example, the natural language processing unit conducts conversations based on activities that elderly people have shown interest in in the past. For example, the natural language processing unit conducts conversations while avoiding activities that infants have disliked in the past. In this way, the accuracy of the conversation is improved by referring to the activity history. Activity history includes, but is not limited to, daily behavior patterns and exercise levels. Some or all of the processing described above in the natural language processing unit may be performed using, for example, AI, or not using AI. For example, the natural language processing unit can input activity history data into a generating AI and have the generating AI perform the task of improving the accuracy of the conversation.

[0056] The analysis unit can improve the accuracy of its analysis by referring to past health data of infants and the elderly during the analysis process. For example, the analysis unit can perform an analysis based on data showing that infants have shown poor health in the past. For example, the analysis unit can perform an analysis based on data showing that the elderly have experienced a deterioration in their health in the past. For example, the analysis unit can perform an analysis based on data showing that infants have shown specific symptoms in the past. In this way, the accuracy of the analysis is improved by referring to past health data. Past health data includes, but is not limited to, medical history and health checkup results. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input past health data into a generating AI and have the generating AI perform the task of improving the accuracy of the analysis.

[0057] The analysis unit can adjust the scope of the analysis during the analysis process, taking into account the living environment of infants and the elderly. For example, if an infant is at home, the analysis unit will focus on data within the home. If an elderly person is in a facility, the analysis unit will focus on data within the facility. If an infant is out, the analysis unit will focus on data from their destination. By adjusting the scope of the analysis based on the living environment, a more appropriate analysis becomes possible. The living environment includes, but is not limited to, the structure of the residence, the surrounding environment, and lifestyle habits. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input living environment data into a generating AI and have the generating AI adjust the scope of the analysis.

[0058] The analysis unit can improve the accuracy of its analysis by referring to the activity history of infants and elderly people during the analysis process. For example, the analysis unit may perform the analysis based on activities that infants have enjoyed in the past. For example, the analysis unit may perform the analysis based on activities that elderly people have shown interest in in the past. For example, the analysis unit may perform the analysis while avoiding activities that infants have disliked in the past. In this way, the accuracy of the analysis is improved by referring to the activity history. Activity history includes, but is not limited to, daily behavior patterns and exercise levels. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit may input activity history data into a generating AI and have the generating AI perform the task of improving the accuracy of the analysis.

[0059] The analysis unit can adjust the content of the analysis by considering the location where the anomaly occurred. For example, if a child approaches a dangerous place, the analysis unit will focus on the data from that location. For example, if an elderly person falls, the analysis unit will record the location and focus on the data from that location. For example, if a child is likely to engage in dangerous behavior in a specific location, the analysis unit will focus on the data from that location. By adjusting the content of the analysis based on the location where the anomaly occurred, a more appropriate analysis becomes possible. The location where the anomaly occurred includes, but is not limited to, a room, outdoors, or a specific location. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input data on the location of the anomaly into a generating AI and have the generating AI perform the adjustment of the analysis content.

[0060] The analysis unit can adjust the analysis content during the analysis, taking into account the health status of infants and the elderly. For example, if an infant is unwell, the analysis unit will perform a detailed analysis. For example, if an elderly person is in good health, the analysis unit will perform a concise analysis. For example, if an infant's health is deteriorating, the analysis unit will perform a detailed analysis. By adjusting the analysis content based on health status, a more appropriate analysis becomes possible. Health status includes, but is not limited to, medical history, current health status, and medical data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input health status data into a generating AI and have the generating AI perform the adjustment of the analysis content.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] The rescue robot system can also be equipped with a temperature sensor. This temperature sensor can monitor the body temperature of infants and the elderly in real time and detect abnormalities. For example, if an infant's body temperature rises rapidly or an elderly person's body temperature drops abnormally, the temperature sensor can detect the abnormality and notify the guardian or caregiver. The temperature sensor can also monitor the ambient temperature and perform appropriate temperature control. This allows for early detection of abnormalities in body temperature and ambient temperature, enabling appropriate responses.

[0063] The rescue robot system can also be equipped with a location information acquisition unit. This unit can track the location of infants and elderly people in real time and detect anomalies. For example, if an infant leaves a designated safety area or an elderly person stays in a specific area for an extended period, the location information acquisition unit can detect the anomaly and notify the guardian or caregiver. The location information acquisition unit can also record the movement history of infants and elderly people, which can be used to predict anomalies. This makes it possible to detect anomalies through location information and respond quickly.

[0064] The rescue robot system can also be equipped with a vibration sensor. This vibration sensor can monitor the movements of infants and the elderly in real time and detect abnormalities. For example, if an infant moves around violently or an elderly person falls, the vibration sensor can detect the abnormality and notify the guardian or caregiver. Furthermore, the vibration sensor can analyze the movement patterns of infants and the elderly to help predict abnormalities. This allows for the detection of abnormalities through movement and enables a rapid response.

[0065] The rescue robot system can also be equipped with a light sensor. This light sensor can monitor ambient brightness in real time and detect anomalies. For example, if a child enters a dark area or an elderly person is in an overly bright area, the light sensor can detect the anomaly and notify a guardian or caregiver. Furthermore, the light sensor can adjust the lighting to provide a suitable environment for the activities of children and the elderly. This allows for the detection of anomalies through the lighting environment and enables appropriate responses.

[0066] The rescue robot system can also be equipped with a pressure sensor. This pressure sensor can monitor changes in the weight and pressure of infants and the elderly in real time and detect abnormalities. For example, if an infant lifts a heavy object or an elderly person falls, the pressure sensor can detect the abnormality and notify the guardian or caregiver. Furthermore, the pressure sensor can analyze changes in the weight of infants and the elderly and estimate changes in their health condition. This allows for the detection of abnormalities through pressure and enables a rapid response.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The image analysis unit monitors the movements of infants and elderly people. For example, it can monitor the movements of infants and elderly people in real time via a camera, observing how infants walk or how elderly people stand up from a seated position. It can also detect abnormalities if infants or elderly people remain still for extended periods. Step 2: The detection unit detects anomalies based on the movement monitored by the image analysis unit. For example, it can detect anomalies when a child approaches a dangerous place or when an elderly person falls. Furthermore, it can also detect anomalies when a child approaches stairs, when an elderly person tries to go out onto the road, when someone is near a fire, or when someone remains stationary for a long period of time. Step 3: The notification unit notifies parents or caregivers of any abnormalities detected by the detection unit. For example, it can alert parents or caregivers by emitting an alert sound. It can also notify parents or caregivers by sending a message, or even by making a phone call. Step 4: The natural language processing unit interacts with infants and the elderly. For example, it can engage in conversation when infants are looking for a playmate, when the elderly need someone to talk to, or when infants or the elderly are feeling lonely. Step 5: The analysis unit analyzes the content of the conversation conducted by the natural language processing unit. For example, it can analyze the emotions, behaviors, and health status of infants and the elderly.

[0069] (Example of form 2) The rescue robot system according to an embodiment of the present invention aims to develop a rescue robot that uses an AI agent to monitor children and the elderly, anticipating a sharp increase in the double care of childcare and elderly care due to the declining birthrate, aging population, later marriages, and later childbirths, and in order to create an environment in which working people can work flexibly. The rescue robot system is equipped with an image analysis function for monitoring infants and the elderly. The AI ​​agent monitors the movements of infants and the elderly in real time through a camera and notifies parents or caregivers if an abnormality is detected. For example, immediate action is possible if an infant approaches a dangerous place or if an elderly person falls. Next, the rescue robot system is equipped with a natural language processing function to act as a conversation partner for infants and the elderly. The AI ​​agent can converse with infants and the elderly to alleviate feelings of loneliness. For example, the rescue robot system can respond if an infant asks for a playmate or if an elderly person needs someone to talk to. Furthermore, the rescue robot system is equipped with an automatic analysis processing function for contacting parents or caregivers. The AI ​​agent analyzes the condition of infants and the elderly and notifies parents or caregivers as needed. For example, a quick response is possible if an infant becomes ill or an elderly person complains of feeling unwell. Thus, the rescue robot system is equipped with image analysis, natural language processing, and automatic analysis functions for monitoring infants and the elderly, creating an environment where parents and caregivers do not need to be constantly present. This provides a flexible work environment for employees and reduces the burden of childcare and elder care. In this way, the rescue robot system can reduce the burden of childcare and elder care by monitoring the movements of infants and the elderly, detecting and notifying of abnormalities, engaging in dialogue, and performing analysis.

[0070] The rescue robot system according to this embodiment comprises an image analysis unit, a detection unit, a notification unit, a natural language processing unit, and an analysis unit. The image analysis unit monitors the movements of infants and elderly people. The image analysis unit monitors the movements of infants and elderly people in real time, for example, through a camera. The image analysis unit can monitor, for example, how infants walk or how elderly people stand up from a seated position. The image analysis unit can also detect abnormalities when infants or elderly people remain still for a long period of time. The detection unit detects abnormalities based on the movements monitored by the image analysis unit. The detection unit detects abnormalities, for example, when infants approach a dangerous place or when elderly people fall. The detection unit can detect abnormalities, for example, when infants approach stairs or when elderly people try to go out onto the road. The detection unit can also detect abnormalities when infants are near a fire or when elderly people remain still for a long period of time. The notification unit notifies guardians or caregivers of abnormalities detected by the detection unit. The notification unit can inform guardians or caregivers of abnormalities, for example, by emitting an alert sound. Furthermore, the notification unit can also notify parents or caregivers of abnormalities by sending messages. In addition, the notification unit can also notify parents or caregivers of abnormalities by making phone calls. The natural language processing unit interacts with infants and the elderly. For example, the natural language processing unit can interact when an infant is seeking a playmate. It can also interact when an elderly person needs someone to talk to. Furthermore, the natural language processing unit can interact when infants or the elderly are feeling lonely. The analysis unit analyzes the content of the conversation conducted by the natural language processing unit. For example, the analysis unit can analyze the emotions of infants and the elderly. It can also analyze the behavior of infants and the elderly. Furthermore, the analysis unit can analyze the health status of infants and the elderly. As a result, the rescue robot system according to this embodiment can reduce the burden of childcare and caregiving by monitoring the movements of infants and the elderly, detecting and notifying of abnormalities, interacting with them, and analyzing the data.

[0071] The image analysis unit monitors the movements of infants and the elderly. For example, the image analysis unit monitors the movements of infants and the elderly in real time through cameras. Specifically, the cameras acquire high-resolution video and use image analysis algorithms to detect movement. It can monitor infants walking or elderly people standing up from a seated position. The image analysis unit can also detect abnormalities if infants or the elderly remain still for extended periods. For example, if an infant does not move for a certain period of time or an elderly person remains in the same posture for a long time, this is detected as an abnormality. The image analysis unit analyzes these movements in real time and immediately notifies the detection unit when an abnormality occurs. Furthermore, the image analysis unit can achieve wide-area monitoring by linking multiple cameras. For example, cameras can be installed in multiple locations such as each room in the house or the garden, and the video obtained from each camera can be integrated and analyzed. This allows for accurate monitoring of the movements of infants and the elderly no matter where they are. In addition, the image analysis unit can use infrared cameras and low-light cameras to detect movement even at night or in dark places. This ensures the safety of infants and the elderly at all times, day and night.

[0072] The detection unit detects anomalies based on movements monitored by the image analysis unit. For example, the detection unit detects anomalies when a child approaches a dangerous area or when an elderly person falls. Specifically, the detection unit analyzes data sent from the image analysis unit to identify abnormal movements and locations. For example, it can detect anomalies when a child approaches stairs or when an elderly person tries to go out onto the road. The detection unit can also detect anomalies when a child is near a fire or when an elderly person remains stationary for a long time. The detection unit detects these anomalies in real time and immediately notifies the notification unit. Furthermore, the detection unit can select an appropriate response depending on the type and urgency of the anomaly. For example, if a child is near a fire, it will immediately issue an alert and notify the guardian. Also, if an elderly person falls, it will quickly contact the caregiver as emergency response is required. By quickly and accurately detecting these anomalies, the detection unit can ensure the safety of children and the elderly. Furthermore, the detection unit can learn anomaly patterns based on past data and perform more accurate detection. This allows the detection unit to provide highly accurate anomaly detection based on the latest information at all times, supporting a quick and appropriate response.

[0073] The notification unit notifies parents or caregivers of anomalies detected by the detection unit. For example, the notification unit can alert parents or caregivers of an anomaly by emitting an alert sound. Specifically, when an anomaly is detected, the notification unit immediately emits an alert sound to draw the attention of those nearby. The notification unit can also notify parents or caregivers of an anomaly by sending a message. For example, it can send a notification to a smartphone or tablet providing detailed information about the anomaly. Furthermore, the notification unit can also notify parents or caregivers of an anomaly by making a phone call. This allows parents or caregivers to respond immediately. By combining these notification methods, the notification unit can reliably communicate anomalies and encourage a rapid response. Moreover, the notification unit can flexibly change the notification content and method depending on the type and urgency of the anomaly. For example, for minor anomalies, only a message notification is sent, while for serious anomalies, both an alert sound and a phone call are used. The notification unit can also improve the notification content and method based on feedback from parents and caregivers, resulting in more effective notifications. This allows the notification unit to quickly and reliably inform parents and caregivers of any abnormalities, ensuring the safety of infants and the elderly.

[0074] The natural language processing unit (NLP) interacts with infants and the elderly. For example, it can interact with infants when they are seeking a playmate. Specifically, it recognizes the infant's speech and generates an appropriate response. For instance, if an infant says, "Let's play together," the NLP will respond, "What would you like to play?" The NLP can also interact with elderly individuals when they need someone to talk to. For example, if an elderly person says, "The weather is nice today," the NLP will respond, "It really is nice weather. Shall we go for a walk?" Furthermore, the NLP can interact with infants and the elderly when they are feeling lonely. For example, if an infant says, "I'm lonely," the NLP will respond, "Let's talk together," and if an elderly person says, "There's no one here," the NLP will respond, "I'm here." Through these interactions, the NLP can provide psychological support to infants and the elderly. In addition, the NLP can record the content of the interactions and provide it to the analysis unit, providing data to understand the state of the infants and the elderly. This allows the natural language processing unit to provide psychological support to infants and the elderly through dialogue, ensuring their safety and security.

[0075] The analysis unit analyzes the content of conversations conducted by the natural language processing unit. For example, the analysis unit can analyze the emotions of infants and elderly people. Specifically, the analysis unit analyzes the content of the conversation, tone of voice, facial expressions, etc., to understand the emotional state of infants and elderly people. For example, if an infant is speaking happily, it will be analyzed as "joy," and if an elderly person is speaking in a depressed voice, it will be analyzed as "sadness." The analysis unit can also analyze the behavior of infants and elderly people. For example, if an infant frequently walks around in the same place, it will be analyzed as "excitement," and if an elderly person stays in the same place for a long time, it will be analyzed as "fatigue." Furthermore, the analysis unit can also analyze the health status of infants and elderly people. For example, based on the content of the conversation and behavioral patterns, it will analyze the possibility that an infant has a cold or that an elderly person is unwell. Based on these analysis results, the analysis unit can provide appropriate advice to parents and caregivers. For example, if there is a possibility that an infant has a cold, it will notify them that "we recommend that you see a doctor," and if there is a possibility that an elderly person is unwell, it will notify them that "we recommend that you get some rest." This allows the analysis unit to analyze the emotions, behaviors, and health status of infants and the elderly, and to provide appropriate advice to parents and caregivers, thereby supporting their safety and health.

[0076] The image analysis unit can monitor the movements of infants and the elderly in real time via a camera. For example, the image analysis unit can monitor in real time the movements of infants walking or the movements of elderly people standing up from a seated position via a camera. For example, the image analysis unit can immediately detect abnormalities if an infant approaches a dangerous place or if an elderly person falls. The image analysis unit can also detect abnormalities if infants or elderly people remain still for a long period of time. In this way, abnormalities can be detected immediately by monitoring movements in real time via a camera. Real-time monitoring is performed with a delay of, for example, seconds. Some or all of the above processing in the image analysis unit may be performed using, for example, AI, or without AI. For example, the image analysis unit can input video data acquired by the camera into a generating AI and have the generating AI perform motion analysis from the video data.

[0077] The detection unit can detect anomalies, such as when a child approaches a dangerous place or when an elderly person falls. For example, the detection unit can detect anomalies when a child approaches stairs or when an elderly person tries to go out onto the road. The detection unit can also detect anomalies, such as when a child is near a fire or when an elderly person remains stationary for a long time. This allows for a quick response by detecting dangerous places and falls. Dangerous places include, but are not limited to, stairs, roads, and areas near fire. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input motion data acquired by the image analysis unit into a generating AI and have the generating AI perform anomaly detection.

[0078] The notification unit can notify parents or caregivers when it detects an anomaly. For example, the notification unit can notify parents or caregivers of an anomaly by emitting an alert sound. The notification unit can also notify parents or caregivers of an anomaly by sending a message. Furthermore, the notification unit can notify parents or caregivers of an anomaly by making a telephone notification. This allows for appropriate action to be taken by promptly notifying when an anomaly is detected. Notification methods include, but are not limited to, alert sounds, messages, and telephone notifications. Some or all of the above-described processes in the notification unit may be performed using, for example, AI, or not using AI. For example, the notification unit can input data on anomalies detected by the detection unit into a generation AI and have the generation AI generate notifications.

[0079] The natural language processing unit can interact with infants and the elderly to alleviate feelings of loneliness. For example, the natural language processing unit can engage in dialogue when an infant is seeking a playmate. It can also engage in dialogue when an elderly person needs someone to talk to. Furthermore, the natural language processing unit can engage in dialogue when infants or the elderly are feeling lonely. This allows for the alleviation of loneliness and the provision of emotional support through dialogue. The content of the dialogue includes, but is not limited to, voice dialogue, text dialogue, and dialogue topics. Some or all of the processing described above in the natural language processing unit may be performed using, for example, AI, or not using AI. For example, the natural language processing unit can input dialogue data with infants or the elderly into a generating AI, and have the generating AI perform the generation of dialogues.

[0080] The analysis unit can analyze the condition of infants and the elderly and notify parents or caregivers as needed. For example, the analysis unit can analyze the emotions of infants and the elderly. The analysis unit can also analyze the behavior of infants and the elderly. Furthermore, the analysis unit can analyze the health status of infants and the elderly. This allows for appropriate responses by analyzing the condition and notifying as needed. Conditions include, but are not limited to, health status, emotional status, and behavioral status. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input dialogue data acquired by the natural language processing unit into a generating AI and have the generating AI perform the condition analysis.

[0081] The image analysis unit can estimate the emotions of infants and elderly individuals and adjust the monitoring focus based on the estimated emotions. For example, if an infant is feeling anxious, the AI ​​in the image analysis unit can detect that emotion and pay special attention to them. For example, if an elderly person is calm, the image analysis unit can reduce the frequency of monitoring and allocate resources to other important tasks. For example, if an infant is agitated, the AI ​​in the image analysis unit can detect that emotion and intensify monitoring to prevent dangerous behavior. This allows for more appropriate monitoring by adjusting the monitoring focus based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the image analysis unit may be performed using AI or not using AI. For example, the image analysis unit can input video data acquired by a camera into a generative AI and have the generative AI perform emotion estimation.

[0082] The image analysis unit can improve the accuracy of anomaly prediction by referring to the past behavioral patterns of infants and the elderly during image analysis. For example, if an infant has engaged in dangerous behavior during a specific time period in the past, the image analysis unit will pay particular attention to that time period. For example, the image analysis unit will record the locations where an elderly person has fallen in the past and strengthen monitoring at those locations. For example, if an infant has repeated a specific behavior in the past, the image analysis unit will predict the likelihood of that behavior recurring and strengthen monitoring. This improves the accuracy of anomaly prediction by referring to past behavioral patterns. Past behavioral patterns include, but are not limited to, behavioral history data and behavioral frequency. Some or all of the above processing in the image analysis unit may be performed using, for example, AI, or not using AI. For example, the image analysis unit can input past behavioral data into a generating AI and have the generating AI perform anomaly prediction.

[0083] The image analysis unit can adjust the monitoring frequency during image analysis, taking into account the health status of infants and the elderly. For example, if an infant is unwell, the image analysis unit increases the monitoring frequency to detect abnormalities early. For example, if an elderly person is in good health, the image analysis unit decreases the monitoring frequency and allocates resources to other important tasks. For example, if an infant's health is deteriorating, the image analysis unit increases the monitoring frequency to detect abnormalities early. This allows for more appropriate monitoring by adjusting the monitoring frequency based on health status. Health status includes, but is not limited to, medical history, current health status, and medical data. Some or all of the above processing in the image analysis unit may be performed using, for example, AI, or not using AI. For example, the image analysis unit can input health status data into a generating AI and have the generating AI adjust the monitoring frequency.

[0084] The image analysis unit can estimate the emotions of infants and elderly individuals and determine monitoring priorities based on the estimated emotions. For example, if an infant is feeling anxious, the AI ​​in the image analysis unit can detect that emotion and pay special attention to them. For example, if an elderly person is calm, the image analysis unit can reduce the frequency of monitoring and allocate resources to other important tasks. For example, if an infant is agitated, the AI ​​in the image analysis unit can detect that emotion and intensify monitoring to prevent dangerous behavior. This allows for more appropriate monitoring by determining monitoring priorities based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the image analysis unit may be performed using AI or not using AI. For example, the image analysis unit can input video data acquired by a camera into a generative AI and have the generative AI perform emotion estimation.

[0085] The image analysis unit can adjust the monitoring range during image analysis, taking into account the living environment of infants and the elderly. For example, if an infant approaches a dangerous area, the AI ​​will monitor that area with particular attention. For example, the image analysis unit can record places where the elderly are prone to falling and strengthen monitoring in those areas. For example, if an infant is likely to engage in dangerous behavior in a particular area, the image analysis unit will strengthen monitoring in that area. This allows for more appropriate monitoring by adjusting the monitoring range based on the living environment. The living environment includes, but is not limited to, the structure of the residence, the surrounding environment, and lifestyle habits. Some or all of the above processing in the image analysis unit may be performed using, for example, AI, or not using AI. For example, the image analysis unit can input living environment data into a generating AI and have the generating AI adjust the monitoring range.

[0086] The image analysis unit can improve the accuracy of monitoring by referring to the activity history of infants and the elderly during image analysis. For example, if an infant has engaged in dangerous behavior during a specific time period in the past, the image analysis unit will pay particular attention to that time period. For example, the image analysis unit will record the location where an elderly person has fallen in the past and strengthen monitoring at that location. For example, if an infant has repeated a specific behavior in the past, the image analysis unit will predict the likelihood of that behavior recurring and strengthen monitoring. In this way, the accuracy of monitoring is improved by referring to the activity history. The activity history includes, but is not limited to, daily behavior patterns and exercise levels. Some or all of the above processing in the image analysis unit may be performed using, for example, AI, or not using AI. For example, the image analysis unit can input activity history data into a generating AI and have the generating AI perform the improvement of monitoring accuracy.

[0087] The detection unit can estimate the emotions of infants and elderly people and adjust the abnormality detection criteria based on the estimated emotions. For example, if an infant is feeling anxious, the AI ​​in the detection unit will detect that emotion and tighten the abnormality detection criteria. For example, if an elderly person is calm, the detection unit will loosen the abnormality detection criteria. For example, if an infant is excited, the AI ​​in the detection unit will detect that emotion and tighten the abnormality detection criteria. This allows for more appropriate abnormality detection by adjusting the abnormality detection criteria based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input emotion data into the generative AI and have the generative AI perform the adjustment of the abnormality detection criteria.

[0088] The detection unit can improve detection accuracy by referring to the past abnormality history of infants and elderly individuals when detection occurs. For example, if an infant has shown abnormality during a specific time period in the past, the detection unit will pay particular attention to that time period. For example, the detection unit will record the locations where elderly individuals have fallen in the past and enhance detection at those locations. For example, if an infant has repeated a specific behavior in the past, the detection unit will predict the likelihood of that behavior recurring and enhance detection. In this way, detection accuracy is improved by referring to past abnormality history. Past abnormality history includes, but is not limited to, the frequency of abnormality occurrences and the type of abnormality. Some or all of the above processing in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input past abnormality data into a generating AI and have the generating AI perform the improvement of detection accuracy.

[0089] The detection unit can adjust the frequency of abnormality detection when detecting an abnormality, taking into account the health status of infants and the elderly. For example, if an infant is unwell, the detection unit increases the detection frequency to detect abnormalities earlier. For example, if an elderly person is in good health, the detection unit decreases the detection frequency to allocate resources to other important tasks. For example, if an infant's health is deteriorating, the detection unit increases the detection frequency to detect abnormalities earlier. This allows for more appropriate abnormality detection by adjusting the abnormality detection frequency based on health status. Health status includes, but is not limited to, medical history, current health status, and medical data. Some or all of the above processing in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input health status data into a generating AI and have the generating AI adjust the abnormality detection frequency.

[0090] The detection unit can estimate the emotions of infants and elderly people and determine the priority of anomalies based on the estimated emotions. For example, if an infant is feeling anxious, the AI ​​in the detection unit will detect that emotion and raise the priority of the anomaly. For example, if an elderly person is calm, the detection unit will lower the priority of the anomaly. For example, if an infant is excited, the AI ​​in the detection unit will detect that emotion and raise the priority of the anomaly. This allows for more appropriate anomaly detection by determining the priority of anomalies based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input emotion data into a generative AI and have the generative AI perform the determination of anomaly priorities.

[0091] The detection unit can adjust the detection range for anomalies when detecting an anomaly, taking into account the living environment of infants and the elderly. For example, if an infant approaches a dangerous place, the AI ​​will pay particular attention to detecting that place. For example, the detection unit can record places where the elderly are prone to falling and strengthen detection in those places. For example, if an infant is likely to engage in dangerous behavior in a particular place, the detection unit will strengthen detection in that place. This allows for more appropriate anomaly detection by adjusting the detection range for anomalies based on the living environment. The living environment includes, but is not limited to, the structure of the residence, the surrounding environment, and lifestyle habits. Some or all of the above processing in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input living environment data into a generating AI and have the generating AI perform the adjustment of the anomaly detection range.

[0092] The detection unit can improve the accuracy of anomaly detection by referring to the activity history of infants and elderly people when detecting anomalies. For example, if an infant has shown abnormalities during a specific time period in the past, the detection unit will pay particular attention to that time period. For example, the detection unit will record the locations where elderly people have fallen in the past and strengthen detection at those locations. For example, if an infant has repeated a specific behavior in the past, the detection unit will predict the likelihood of that behavior recurring and strengthen detection. In this way, the accuracy of anomaly detection is improved by referring to the activity history. The activity history includes, but is not limited to, daily behavior patterns and exercise levels. Some or all of the above processing in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input activity history data into a generating AI and have the generating AI perform the improvement of anomaly detection accuracy.

[0093] The notification unit can estimate the emotions of infants and elderly people and adjust the content of notifications based on the estimated emotions. For example, if an infant is feeling anxious, the notification unit will send a detailed notification to the guardian. For example, if an elderly person is calm, the notification unit will send a concise notification. For example, if an infant is agitated, the notification unit will send a detailed notification to the guardian. This allows for more appropriate notifications by adjusting the content of notifications based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI, for example, or not using AI. For example, the notification unit can input emotion data into a generative AI and have the generative AI adjust the content of the notification.

[0094] The notification unit can select the optimal notification method by referring to the past response history of the guardian or caregiver when issuing a notification. For example, the notification unit may prioritize suggesting notification methods (email, phone, etc.) that the guardian has used in the past. For example, the notification unit may select the optimal notification method based on the type of anomaly the guardian has responded to in the past. For example, the notification unit may select the optimal notification method based on the time period the guardian has responded in the past. In this way, the optimal notification method can be selected by referring to the past response history. The past response history includes, but is not limited to, the frequency and content of responses. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit may input past response data into a generating AI and have the generating AI select the optimal notification method.

[0095] The notification unit can adjust the urgency of the notification according to the type of anomaly. For example, the notification unit sends a high-urgency notification if a child approaches a dangerous place. For example, the notification unit sends a high-urgency notification if an elderly person falls. For example, the notification unit sends a high-urgency notification if a child is unwell. By adjusting the urgency of the notification according to the type of anomaly, a more appropriate response becomes possible. Types of anomalies include, but are not limited to, falls, prolonged immobility, and approaching dangerous places. Some or all of the above processing in the notification unit may be performed using, for example, AI, or not using AI. For example, the notification unit can input anomaly data into a generating AI and have the generating AI adjust the urgency of the notification.

[0096] The notification unit can estimate the emotions of infants and the elderly and determine the priority of notifications based on the estimated emotions. For example, if an infant is feeling anxious, the notification unit will prioritize sending a notification to the guardian. For example, if an elderly person is calm, the notification unit will lower the priority of the notification. For example, if an infant is agitated, the notification unit will prioritize sending a notification to the guardian. This allows for more appropriate notifications by determining the priority of notifications based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI, for example, or not using AI. For example, the notification unit can input emotion data into a generative AI and have the generative AI determine the priority of notifications.

[0097] The notification unit can select the most appropriate notification method when sending a notification, taking into account the living environment of the guardian or caregiver. For example, if the guardian is at work, the notification unit may send a notification by email. For example, if the guardian is at home, the notification unit may send a notification by phone. For example, if the guardian is out, the notification unit may send a notification by SMS. This allows for more appropriate notifications by selecting the most appropriate notification method based on the living environment. The living environment includes, but is not limited to, the structure of the residence, the surrounding environment, and lifestyle habits. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input living environment data into a generating AI and have the generating AI select the most appropriate notification method.

[0098] The notification unit can adjust the content of a notification when it is sent, taking into account the location where the anomaly occurred. For example, if a child approaches a dangerous place, the notification unit will send a notification including details of that location. For example, if an elderly person falls, the notification unit will record the location and send a notification including details of that location. For example, if a child is likely to engage in dangerous behavior in a particular location, the notification unit will send a notification including details of that location. This allows for a more appropriate response by adjusting the content of the notification based on the location where the anomaly occurred. The location of the anomaly may include, but is not limited to, a room, outdoors, or a specific location. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input data on the location of the anomaly into a generating AI and have the generating AI adjust the content of the notification.

[0099] The natural language processing unit can estimate the emotions of infants and elderly people and adjust the content of the dialogue based on the estimated emotions. For example, if an infant is feeling anxious, the AI ​​in the natural language processing unit can detect that emotion and engage in reassuring dialogue. For example, if an elderly person is calm, the natural language processing unit can engage in relaxing dialogue. For example, if an infant is excited, the AI ​​in the natural language processing unit can detect that emotion and engage in calming dialogue. This allows for more appropriate dialogue by adjusting the content of the dialogue based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the natural language processing unit may be performed using AI, for example, or not using AI. For example, the natural language processing unit can input emotion data into the generative AI and have the generative AI adjust the content of the dialogue.

[0100] The natural language processing unit can select the optimal dialogue method by referring to the past dialogue history of infants and elderly people during a conversation. For example, the natural language processing unit may conduct a conversation based on topics that infants have enjoyed in the past. For example, the natural language processing unit may conduct a conversation based on topics that elderly people have shown interest in in the past. For example, the natural language processing unit may conduct a conversation while avoiding topics that infants have disliked in the past. In this way, the optimal dialogue method can be selected by referring to past dialogue history. Past dialogue history includes, but is not limited to, the frequency and content of conversations. Some or all of the processing described above in the natural language processing unit may be performed using, for example, AI, or not using AI. For example, the natural language processing unit can input past dialogue data into a generating AI and have the generating AI select the optimal dialogue method.

[0101] The natural language processing unit can adjust the frequency of conversations during dialogue, taking into account the health status of infants and elderly individuals. For example, if an infant is unwell, the natural language processing unit will reduce the frequency of conversations and prioritize rest. For example, if an elderly person is in good health, the natural language processing unit will increase the frequency of conversations to reduce feelings of loneliness. For example, if an infant's health is deteriorating, the natural language processing unit will reduce the frequency of conversations and prioritize rest. By adjusting the frequency of conversations based on health status, more appropriate conversations become possible. Health status includes, but is not limited to, medical history, current health status, and medical data. Some or all of the processing described above in the natural language processing unit may be performed using, for example, AI, or not using AI. For example, the natural language processing unit can input health status data into a generating AI and have the generating AI adjust the frequency of conversations.

[0102] The natural language processing unit can estimate the emotions of infants and elderly people and determine dialogue priorities based on the estimated emotions. For example, if an infant is feeling anxious, the AI ​​can detect this emotion and prioritize the dialogue. For example, if an elderly person is calm, the AI ​​can lower the dialogue priority. For example, if an infant is excited, the AI ​​can detect this emotion and prioritize the dialogue. This allows for more appropriate dialogue by determining dialogue priorities based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the natural language processing unit may be performed using AI or not using AI. For example, the natural language processing unit can input emotion data into the generative AI and have the generative AI determine the dialogue priorities.

[0103] The natural language processing unit can adjust the content of a conversation to take into account the living environment of infants and elderly people. For example, if an infant is at home, the natural language processing unit will focus the conversation on topics related to the home. If an elderly person is in a care facility, the natural language processing unit will focus the conversation on topics related to the facility. If an infant is out, the natural language processing unit will focus the conversation on topics related to the destination. By adjusting the content of the conversation based on the living environment, more appropriate conversations become possible. The living environment includes, but is not limited to, the structure of the residence, the surrounding environment, and lifestyle habits. Some or all of the processing described above in the natural language processing unit may be performed using AI, for example, or without AI. For example, the natural language processing unit can input data on the living environment into a generating AI and have the generating AI adjust the content of the conversation.

[0104] The natural language processing unit can improve the accuracy of conversations by referring to the activity history of infants and elderly people during dialogue. For example, the natural language processing unit conducts conversations based on activities that infants have enjoyed in the past. For example, the natural language processing unit conducts conversations based on activities that elderly people have shown interest in in the past. For example, the natural language processing unit conducts conversations while avoiding activities that infants have disliked in the past. In this way, the accuracy of the conversation is improved by referring to the activity history. Activity history includes, but is not limited to, daily behavior patterns and exercise levels. Some or all of the processing described above in the natural language processing unit may be performed using, for example, AI, or not using AI. For example, the natural language processing unit can input activity history data into a generating AI and have the generating AI perform the task of improving the accuracy of the conversation.

[0105] The analysis unit can estimate the emotions of infants and elderly people and adjust the analysis based on the estimated emotions. For example, if an infant is feeling anxious, the AI ​​in the analysis unit will detect that emotion and perform a detailed analysis. For example, if an elderly person is calm, the analysis unit will perform a concise analysis. For example, if an infant is excited, the AI ​​in the analysis unit will detect that emotion and perform a detailed analysis. This allows for more appropriate analysis by adjusting the analysis based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input emotion data into the generative AI and have the generative AI perform the adjustment of the analysis content.

[0106] The analysis unit can improve the accuracy of its analysis by referring to past health data of infants and the elderly during the analysis process. For example, the analysis unit can perform an analysis based on data showing that infants have shown poor health in the past. For example, the analysis unit can perform an analysis based on data showing that the elderly have experienced a deterioration in their health in the past. For example, the analysis unit can perform an analysis based on data showing that infants have shown specific symptoms in the past. In this way, the accuracy of the analysis is improved by referring to past health data. Past health data includes, but is not limited to, medical history and health checkup results. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input past health data into a generating AI and have the generating AI perform the task of improving the accuracy of the analysis.

[0107] The analysis unit can adjust the scope of the analysis during the analysis process, taking into account the living environment of infants and the elderly. For example, if an infant is at home, the analysis unit will focus on data within the home. If an elderly person is in a facility, the analysis unit will focus on data within the facility. If an infant is out, the analysis unit will focus on data from their destination. By adjusting the scope of the analysis based on the living environment, a more appropriate analysis becomes possible. The living environment includes, but is not limited to, the structure of the residence, the surrounding environment, and lifestyle habits. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input living environment data into a generating AI and have the generating AI adjust the scope of the analysis.

[0108] The analysis unit can estimate the emotions of infants and elderly people and determine the priority of analysis based on the estimated emotions. For example, if an infant is feeling anxious, the AI ​​in the analysis unit will detect that emotion and increase the priority of the analysis. For example, if an elderly person is calm, the analysis unit will decrease the priority of the analysis. For example, if an infant is excited, the AI ​​in the analysis unit will detect that emotion and increase the priority of the analysis. This allows for more appropriate analysis by determining the priority of analysis based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input emotion data into a generative AI and have the generative AI determine the priority of analysis.

[0109] The analysis unit can improve the accuracy of its analysis by referring to the activity history of infants and elderly people during the analysis process. For example, the analysis unit may perform the analysis based on activities that infants have enjoyed in the past. For example, the analysis unit may perform the analysis based on activities that elderly people have shown interest in in the past. For example, the analysis unit may perform the analysis while avoiding activities that infants have disliked in the past. In this way, the accuracy of the analysis is improved by referring to the activity history. Activity history includes, but is not limited to, daily behavior patterns and exercise levels. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit may input activity history data into a generating AI and have the generating AI perform the task of improving the accuracy of the analysis.

[0110] The analysis unit can adjust the content of the analysis by considering the location where the anomaly occurred. For example, if a child approaches a dangerous place, the analysis unit will focus on the data from that location. For example, if an elderly person falls, the analysis unit will record the location and focus on the data from that location. For example, if a child is likely to engage in dangerous behavior in a specific location, the analysis unit will focus on the data from that location. By adjusting the content of the analysis based on the location where the anomaly occurred, a more appropriate analysis becomes possible. The location where the anomaly occurred includes, but is not limited to, a room, outdoors, or a specific location. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input data on the location of the anomaly into a generating AI and have the generating AI perform the adjustment of the analysis content.

[0111] The analysis unit can adjust the analysis content during the analysis, taking into account the health status of infants and the elderly. For example, if an infant is unwell, the analysis unit will perform a detailed analysis. For example, if an elderly person is in good health, the analysis unit will perform a concise analysis. For example, if an infant's health is deteriorating, the analysis unit will perform a detailed analysis. By adjusting the analysis content based on health status, a more appropriate analysis becomes possible. Health status includes, but is not limited to, medical history, current health status, and medical data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input health status data into a generating AI and have the generating AI perform the adjustment of the analysis content.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The rescue robot system can also be equipped with a voice recognition unit. This unit can recognize the voices of infants and the elderly in real time and detect abnormalities. For example, if an infant cries or an elderly person calls for help, the voice recognition unit can detect the sound and notify the guardian or caregiver. Furthermore, the voice recognition unit can analyze changes in the tone and volume of the infant's or elderly person's voice to estimate emotional changes. This allows for the detection of abnormalities through voice and enables a rapid response.

[0114] The rescue robot system can also be equipped with a temperature sensor. This temperature sensor can monitor the body temperature of infants and the elderly in real time and detect abnormalities. For example, if an infant's body temperature rises rapidly or an elderly person's body temperature drops abnormally, the temperature sensor can detect the abnormality and notify the guardian or caregiver. The temperature sensor can also monitor the ambient temperature and perform appropriate temperature control. This allows for early detection of abnormalities in body temperature and ambient temperature, enabling appropriate responses.

[0115] The rescue robot system can also be equipped with a location information acquisition unit. This unit can track the location of infants and elderly people in real time and detect anomalies. For example, if an infant leaves a designated safety area or an elderly person stays in a specific area for an extended period, the location information acquisition unit can detect the anomaly and notify the guardian or caregiver. The location information acquisition unit can also record the movement history of infants and elderly people, which can be used to predict anomalies. This makes it possible to detect anomalies through location information and respond quickly.

[0116] The rescue robot system can also be equipped with a vibration sensor. This vibration sensor can monitor the movements of infants and the elderly in real time and detect abnormalities. For example, if an infant moves around violently or an elderly person falls, the vibration sensor can detect the abnormality and notify the guardian or caregiver. Furthermore, the vibration sensor can analyze the movement patterns of infants and the elderly to help predict abnormalities. This allows for the detection of abnormalities through movement and enables a rapid response.

[0117] The rescue robot system can also be equipped with a light sensor. This light sensor can monitor ambient brightness in real time and detect anomalies. For example, if a child enters a dark area or an elderly person is in an overly bright area, the light sensor can detect the anomaly and notify a guardian or caregiver. Furthermore, the light sensor can adjust the lighting to provide a suitable environment for the activities of children and the elderly. This allows for the detection of anomalies through the lighting environment and enables appropriate responses.

[0118] The rescue robot system can also be equipped with a speech synthesis unit. This unit can provide information to infants and the elderly via voice. For example, if an infant approaches a dangerous area, the speech synthesis unit can issue a warning to alert the infant. Similarly, if an elderly person complains of feeling unwell, the speech synthesis unit can guide them on appropriate actions. Furthermore, the speech synthesis unit can estimate the emotions of infants and the elderly and speak in an appropriate tone. This enables the provision of information through voice and facilitates a rapid response.

[0119] The rescue robot system can also be equipped with a tactile sensor. This sensor can acquire tactile information from infants and the elderly in real time and detect abnormalities. For example, if an infant touches something hot or an elderly person bumps into something hard, the sensor can detect the abnormality and notify the guardian or caregiver. Furthermore, the sensor can analyze the tactile information from infants and the elderly to estimate changes in their emotions. This allows for the detection of abnormalities through touch and enables a rapid response.

[0120] The rescue robot system can also be equipped with an odor sensor. This odor sensor can monitor the surrounding odors in real time and detect abnormalities. For example, if a child comes into contact with a harmful chemical or an elderly person experiences a gas leak, the odor sensor can detect the abnormality and notify the guardian or caregiver. Furthermore, the odor sensor can analyze changes in odor to estimate the emotions of the child or elderly person. This allows for the detection of abnormalities through odor and enables a rapid response.

[0121] The rescue robot system can also be equipped with a pressure sensor. This pressure sensor can monitor changes in the weight and pressure of infants and the elderly in real time and detect abnormalities. For example, if an infant lifts a heavy object or an elderly person falls, the pressure sensor can detect the abnormality and notify the guardian or caregiver. Furthermore, the pressure sensor can analyze changes in the weight of infants and the elderly and estimate changes in their health condition. This allows for the detection of abnormalities through pressure and enables a rapid response.

[0122] The rescue robot system can also be equipped with a humidity sensor. This humidity sensor can monitor ambient humidity in real time and detect abnormalities. For example, if an infant is in a high-humidity area or an elderly person is in a dry area, the humidity sensor can detect the abnormality and notify the guardian or caregiver. Furthermore, the humidity sensor can analyze changes in humidity to estimate the emotions of the infant or elderly person. This allows for the detection of abnormalities through humidity and enables a rapid response.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The image analysis unit monitors the movements of infants and elderly people. For example, it can monitor the movements of infants and elderly people in real time via a camera, observing how infants walk or how elderly people stand up from a seated position. It can also detect abnormalities if infants or elderly people remain still for extended periods. Step 2: The detection unit detects anomalies based on the movement monitored by the image analysis unit. For example, it can detect anomalies when a child approaches a dangerous place or when an elderly person falls. Furthermore, it can also detect anomalies when a child approaches stairs, when an elderly person tries to go out onto the road, when someone is near a fire, or when someone remains stationary for a long period of time. Step 3: The notification unit notifies parents or caregivers of any abnormalities detected by the detection unit. For example, it can alert parents or caregivers by emitting an alert sound. It can also notify parents or caregivers by sending a message, or even by making a phone call. Step 4: The natural language processing unit interacts with infants and the elderly. For example, it can engage in conversation when infants are looking for a playmate, when the elderly need someone to talk to, or when infants or the elderly are feeling lonely. Step 5: The analysis unit analyzes the content of the conversation conducted by the natural language processing unit. For example, it can analyze the emotions, behaviors, and health status of infants and the elderly.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0127] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the image analysis unit, detection unit, notification unit, natural language processing unit, and analysis unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the image analysis unit monitors the movements of infants and elderly people using the camera 42 of the smart device 14 and analyzes the movements using the control unit 46A. The detection unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and detects abnormalities. The notification unit notifies parents or caregivers of abnormalities using, for example, the output device 40 of the smart device 14. The natural language processing unit is implemented, for example, by the control unit 46A of the smart device 14 and interacts with infants and elderly people. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the content of the interaction. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the smart glasses 214, 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed 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 necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the image analysis unit, detection unit, notification unit, natural language processing unit, and analysis unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the image analysis unit monitors the movements of infants and elderly people using the camera 42 of the smart glasses 214 and analyzes the movements using the control unit 46A. The detection unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and detects abnormalities. The notification unit notifies parents or caregivers of abnormalities using the speaker 240 of the smart glasses 214. The natural language processing unit is implemented, for example, by the control unit 46A of the smart glasses 214 and interacts with infants and elderly people. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the content of the dialogue. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0153] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0155] In the headset terminal 314, 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 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0156] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0157] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0159] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] Each of the multiple elements described above, including the image analysis unit, detection unit, notification unit, natural language processing unit, and analysis unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the image analysis unit monitors the movements of infants and elderly people using the camera 42 of the headset terminal 314 and analyzes the movements using the control unit 46A. The detection unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and detects abnormalities. The notification unit notifies parents or caregivers of abnormalities using, for example, the speaker 240 of the headset terminal 314. The natural language processing unit is implemented, for example, by the control unit 46A of the headset terminal 314 and interacts with infants and elderly people. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the content of the conversation. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] As shown in Figure 7, the 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.

[0163] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0164] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0165] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0167] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0168] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0169] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0170] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0171] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0172] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0173] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0174] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0175] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0176] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed 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 necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0177] Each of the multiple elements described above, including the image analysis unit, detection unit, notification unit, natural language processing unit, and analysis unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the image analysis unit monitors the movements of infants and elderly people using the camera 42 of the robot 414 and analyzes the movements using the control unit 46A. The detection unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and detects abnormalities. The notification unit notifies guardians and caregivers of abnormalities using the speaker 240 of the robot 414. The natural language processing unit is implemented, for example, by the control unit 46A of the robot 414 and interacts with infants and elderly people. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the content of the dialogue. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0178] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0179] Figure 9 shows the emotion map 400, in 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 the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0180] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0181] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0182] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0183] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it 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 emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0184] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0185] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0186] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0187] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0188] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0189] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0190] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0191] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0192] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0193] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0194] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0195] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0196] (Note 1) An image analysis unit for monitoring the movements of infants and the elderly, A detection unit that detects abnormalities based on the movement monitored by the aforementioned image analysis unit, A notification unit that notifies the guardian or caregiver of any abnormalities detected by the aforementioned detection unit, A natural language processing unit for communicating with infants and the elderly, The system comprises an analysis unit that analyzes the content of the conversation conducted by the natural language processing unit. A system characterized by the following features. (Note 2) The aforementioned image analysis unit, Monitoring the movements of infants and the elderly in real time via cameras. The system described in Appendix 1, characterized by the features described herein. (Note 3) The detection unit, It detects abnormalities such as when a toddler approaches a dangerous place or when an elderly person falls. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned notification unit, If an abnormality is detected, the system will notify the guardian or caregiver. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned natural language processing unit, Interacting with infants and the elderly to alleviate feelings of loneliness. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, Analyze the condition of infants and the elderly, and notify parents or caregivers as needed. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned image analysis unit, The system estimates the emotions of infants and the elderly, and adjusts monitoring priorities based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned image analysis unit, During image analysis, we improve the accuracy of anomaly prediction by referencing past behavioral patterns of infants and the elderly. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned image analysis unit, During image analysis, the monitoring frequency is adjusted considering the health status of infants and the elderly. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned image analysis unit, The system estimates the emotions of infants and the elderly, and determines monitoring priorities based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned image analysis unit, During image analysis, the monitoring range is adjusted to take into account the living environment of infants and the elderly. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned image analysis unit, During image analysis, the accuracy of monitoring is improved by referring to the activity history of infants and the elderly. The system described in Appendix 1, characterized by the features described herein. (Note 13) The detection unit, We estimate the emotions of infants and the elderly, and adjust the detection criteria for abnormalities based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The detection unit, When detection occurs, the accuracy of the detection is improved by referring to the past abnormal history of infants and the elderly. The system described in Appendix 1, characterized by the features described herein. (Note 15) The detection unit, When detecting an abnormality, the frequency of detection is adjusted considering the health status of infants and the elderly. The system described in Appendix 1, characterized by the features described herein. (Note 16) The detection unit, The system estimates the emotions of infants and the elderly, and prioritizes abnormalities based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The detection unit, When detecting an anomaly, the detection range is adjusted to take into account the living environment of infants and the elderly. The system described in Appendix 1, characterized by the features described herein. (Note 18) The detection unit, When detection occurs, the activity history of infants and the elderly is referenced to improve the accuracy of anomaly detection. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned notification unit, The system estimates the emotions of infants and the elderly, and adjusts the content of notifications based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned notification unit, When sending a notification, the system will refer to the past response history of the parent or caregiver to select the most appropriate notification method. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned notification unit, When a notification is sent, the urgency of the notification will be adjusted according to the type of anomaly. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned notification unit, It estimates the emotions of infants and the elderly and prioritizes notifications based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned notification unit, When sending notifications, the most suitable notification method will be selected, taking into consideration the living environment of the guardian or caregiver. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned notification unit, When sending a notification, the content of the notification will be adjusted to take into account the location where the anomaly occurred. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned natural language processing unit, It estimates the emotions of infants and the elderly, and adjusts the content of the dialogue based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned natural language processing unit, During conversations, the system selects the most appropriate method of communication by referring to the past conversation history of infants and the elderly. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned natural language processing unit, When engaging in dialogue, adjust the frequency of conversations to take into account the health status of infants and the elderly. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned natural language processing unit, It estimates the emotions of infants and the elderly, and determines the priority of conversations based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned natural language processing unit, When engaging in dialogue, adjust the content of the conversation to take into consideration the living environment of infants and the elderly. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned natural language processing unit, During conversations, referencing the activity history of infants and the elderly improves the accuracy of the dialogue. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned analysis unit, We estimate the emotions of infants and the elderly, and adjust the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned analysis unit, During analysis, past health data of infants and the elderly is referenced to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned analysis unit, During the analysis, the scope of the analysis will be adjusted to take into account the living environments of infants and the elderly. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned analysis unit, The system estimates the emotions of infants and the elderly, and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned analysis unit, During analysis, the activity history of infants and the elderly is referenced to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned analysis unit, During the analysis, the analysis content is adjusted considering the location where the anomaly occurred. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned analysis unit, During the analysis, the analysis content will be adjusted to take into account the health status of infants and the elderly. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0197] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An image analysis unit for monitoring the movements of infants and the elderly, A detection unit that detects abnormalities based on the movement monitored by the aforementioned image analysis unit, A notification unit that notifies the guardian or caregiver of any abnormalities detected by the aforementioned detection unit, A natural language processing unit for communicating with infants and the elderly, The system comprises an analysis unit that analyzes the content of the conversation conducted by the natural language processing unit. A system characterized by the following features.

2. The aforementioned image analysis unit, Monitoring the movements of infants and the elderly in real time via cameras. The system according to feature 1.

3. The detection unit, It detects abnormalities such as when a toddler approaches a dangerous place or when an elderly person falls. The system according to feature 1.

4. The aforementioned notification unit, If an abnormality is detected, the system will notify the guardian or caregiver. The system according to feature 1.

5. The aforementioned natural language processing unit, Interacting with infants and the elderly to alleviate feelings of loneliness. The system according to feature 1.

6. The aforementioned analysis unit, Analyze the condition of infants and the elderly, and notify parents or caregivers as needed. The system according to feature 1.

7. The aforementioned image analysis unit, The system estimates the emotions of infants and the elderly, and adjusts monitoring priorities based on these estimated emotions. The system according to feature 1.

8. The aforementioned image analysis unit, During image analysis, we improve the accuracy of anomaly prediction by referencing past behavioral patterns of infants and the elderly. The system according to feature 1.

Images