system

Abstract

We provide the system. [Solution] A sensing means for collecting user movement data, A storage means for storing the aforementioned momentum in a database, An analysis means for comparing the aforementioned amount of movement with the movement data of other users or reference data, A generation means for generating an optimal exercise plan for the user based on the comparison results, A notification means for notifying the user of the generated exercise plan, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including 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] Modern office workers tend to lack exercise in their daily lives due to being chased by work. Since such lack of exercise often has an adverse effect on health, a method for eliminating it is required. Furthermore, even though many office workers understand the necessity of exercise, the problem is that they lack the motivation to take specific actions and specific exercise plans.

Means for Solving the Problems

[0005] This invention aims to address users' lack of exercise by collecting user activity levels using sensing means and storing that data in a database. Next, analysis means are used to compare the user's activity level with that of other users and reference data to identify areas where exercise is lacking. Furthermore, generation means create an optimal exercise plan for the user, and notification means notify the user of the plan. In this way, the invention provides a system that allows users to easily understand their exercise status and increase their motivation. In addition, by using preprocessing means to detect outliers and normalize data, and by performing optimization using an AI agent, it is possible to provide an even more accurate exercise plan.

[0006] "Sensing means" refers to a group of devices and sensors used to measure a user's physical activity in real time and acquire that movement data.

[0007] A "memory device" refers to a data storage device or system that stores motion data acquired by a sensing device, making it available for later processing and analysis.

[0008] "Analysis means" refers to processing devices and algorithms that compare collected exercise data with data from other users and reference values ​​to determine insufficient exercise.

[0009] "Generation means" refers to a processing device or software that automatically creates an exercise plan suitable for the user based on the missing information obtained by the analysis means.

[0010] "Notification means" refers to display devices or communication devices used to communicate the generated exercise plan to the user.

[0011] "Preprocessing means" refers to devices or algorithms that detect abnormal values ​​contained in motion data and perform processing to normalize the data.

[0012] An "AI agent" is a processing program that uses artificial intelligence technology to provide an individually optimized exercise plan, taking into account the user's profile information. [Brief explanation of the drawing]

[0013] [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. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0025] 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.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] The 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.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a system for addressing the lack of exercise among working adults and is designed for daily use by users. The system mainly consists of sensing means, storage means, analysis means, generation means, notification means, and preprocessing means.

[0035] As a sensing method, smartwatches and smart rings, which are terminals, detect the user's physical activity in real time. This includes pedometers, accelerometers, heart rate sensors, etc., and these sensors record the user's daily exercise data.

[0036] The memory system periodically transmits the collected motion data from the terminal to the server and stores it in a database on the server. This stored data is then used for detailed analysis later on.

[0037] As a preprocessing step, the server reviews the stored data, detects any anomalies, and normalizes the data to prepare it for analysis. This ensures that the data is suitable for input to the analysis tool.

[0038] The analysis is performed on a server and compares stored exercise data with data from other users and national baseline data. This allows the system to assess the user's level of inactivity. This assessment utilizes data such as the average number of steps taken per week and daily activity levels.

[0039] The generation method utilizes these analysis results and uses an AI agent to generate an optimal exercise plan for the user. This exercise plan includes specific details tailored to the user's habits and lifestyle. For example, if the user has time to exercise during their daily commute or at the office, a walking and stretching plan tailored to that will be suggested.

[0040] The notification system sends the aforementioned exercise plan to the user's smart device. A push notification is sent to the device, allowing the user to check it and begin their exercise. For example, a specific plan such as "We recommend a 20-minute run today" might be displayed.

[0041] For example, if a user tends to be less active on weekends, the server will detect this and suggest increasing their exercise during the weekend. Furthermore, if a user has had a busy week with few opportunities for exercise, the server can recommend light exercises or stretches that can be done at home.

[0042] By combining these methods, users can easily manage their daily exercise habits and receive assistance in maintaining their health. As a result, an environment is provided where even busy working adults can easily overcome a lack of exercise.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The device is worn on the user's body and collects exercise data such as steps, heart rate, and calories burned in real time. This allows for a detailed record of the user's daily activity level.

[0046] Step 2:

[0047] The device transmits the collected exercise data to the server at regular intervals. For security reasons, this transmission is encrypted and carried out over the internet.

[0048] Step 3:

[0049] The server stores the received motion data in a database. Here, the stored data is organized for later analysis and comparison.

[0050] Step 4:

[0051] The server preprocesses the stored motion data, detects outliers, and normalizes the data. This ensures the accuracy of the data before it is passed to the analysis tools.

[0052] Step 5:

[0053] The server starts comparing normalized exercise data with data from other users and regional baselines. Through this comparison, if a user's exercise level is lower than the baseline, the server identifies the deficit.

[0054] Step 6:

[0055] Based on the analysis results, the server's AI agent generates an exercise plan optimized for the user. This plan proposes exercises that take into account the user's lifestyle and health condition.

[0056] Step 7:

[0057] The server pushes the generated exercise plan to the user's device. The user receives this notification and can easily understand and perform the specific exercise activities.

[0058] Step 8:

[0059] The user performs the exercise according to the exercise plan received from the server. The user then records the exercise status again on their device and sends feedback based on that data to the server.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] In modern society, lack of exercise is a chronic problem, especially among working adults. This lack of exercise negatively impacts health, and there is a need for the development of specific and personalized plans for effective exercise. Conventional technologies lack systems that can provide exercise plans tailored to each user, making it difficult to effectively encourage exercise habits.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes a sensor unit that measures the user's physical activity level, a storage unit that stores the activity level in a recording device, and an analysis unit that compares the activity level with standard data. This makes it possible to individually create and notify the user of a physical activity plan that is suitable for them.

[0065] The "sensor unit" is a device used to measure the user's physical activity level and can acquire data such as steps, heart rate, and acceleration.

[0066] The "storage unit" is a device that records and stores measured physical activity data, and functions as a database or storage device.

[0067] The "analysis unit" is a device that compares stored physical activity data with standard data to evaluate the user's level of physical inactivity and activity trends.

[0068] The "creation unit" is a device that generates a physical activity plan suitable for the user based on the evaluation results obtained from the analysis unit, and it uses an AI agent to perform personalized planning.

[0069] The "notification unit" is a device that transmits the physical activity plan generated by the creation unit to the user in an appropriate manner, such as by sending push notifications to smart devices.

[0070] This invention is a system designed to address the lack of exercise among working adults and is designed for daily use by users. This system mainly consists of a sensor unit, a storage unit, an analysis unit, a creation unit, and a notification unit.

[0071] First, the sensor unit will utilize a smartwatch or smart ring, which will act as a terminal. This terminal will detect the user's physical activity in real time. For example, it will collect the user's daily exercise data using a pedometer, accelerometer, and heart rate sensor.

[0072] Next, the storage unit periodically sends the motion data collected from the terminal to the server and stores it in a database on the server. This allows for the accumulation of data necessary for later analysis.

[0073] The analysis unit runs on a server and evaluates the user's level of inactivity by comparing stored exercise data with standard data. This evaluation enables appropriate analysis tailored to the user's current situation.

[0074] Subsequently, the creation department uses an AI agent based on the analysis results to generate an optimal physical activity plan for the user. This plan is tailored to the user's lifestyle and daily activities. For example, if the user's life revolves around desk work, the plan can suggest walking during lunch breaks and stretching after returning home.

[0075] Finally, the notification unit sends the created physical activity plan as a push notification to the user's smart device. The user can then review this notification and engage in the suggested exercise. An example of the notification content is a specific plan such as, "We recommend a 20-minute walk before you head home today."

[0076] For example, if a user tends to be less active on weekends, the server will detect this and suggest a plan to increase their exercise during the weekend. It can also recommend light exercises or stretches that can be done at home during weeks when exercise opportunities are limited due to consecutive commitments.

[0077] An example of a prompt for the generating AI model would be: "Based on this week's exercise data, please create a specific exercise plan for next week. Please take into account the user's activity patterns and weekend time, and include suggestions for outdoor walking and indoor stretching."

[0078] In this way, the system analyzes the user's daily exercise habits in detail and provides effective and easy-to-follow exercise plans, helping to alleviate a lack of exercise even in busy lifestyles.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] Data collection

[0082] The device detects the user's physical activity in real time using a smartwatch or smart ring. The input here is raw data related to body movement (e.g., acceleration, steps, heart rate, etc.). The device collects this data through sensors and outputs basic exercise data that indicates the user's exercise status.

[0083] Step 2:

[0084] Data transmission

[0085] The device transmits collected exercise data to the server at regular intervals. The input for this step is the collected exercise data. The device transmits the data to the server using Wi-Fi or Bluetooth, and the server confirms receipt of the data. The output is the user-specific exercise data stored on the server.

[0086] Step 3:

[0087] Data storage

[0088] The server stores the received exercise data in a database. The input is the exercise data sent from the terminal. The server organizes this data by user and indexes it for quick access in subsequent processes. The output is the exercise data in the well-organized database.

[0089] Step 4:

[0090] Data preprocessing

[0091] The server reviews the motion data in the database, detecting and normalizing outliers. The input is the stored raw motion data. The server uses statistical methods to identify outliers and correct them to within the normal range. The output is the normalized data with the anomalies corrected.

[0092] Step 5:

[0093] Data Analysis

[0094] The server analyzes normalized data and compares the user's level of exercise inactivity with data from other users and baseline data. The input is normalized exercise data. An AI model is used for analysis to quantify the user's daily activity level and exercise quality. The output is an evaluation of the specific exercise status.

[0095] Step 6:

[0096] Activity plan generation

[0097] The server uses the evaluation results and an AI agent to generate an exercise plan tailored to the user. The input is the evaluation results based on data analysis. The server also considers the user's profile information to create appropriate exercise suggestions (e.g., step goals, stretching recommendations, etc.). The output is an exercise plan tailored to the user's lifestyle.

[0098] Step 7:

[0099] notification

[0100] The server sends the generated exercise plan to the user's smart device. The input is the generated exercise plan. The server forwards the plan as a push notification for the user to review. The output is the possible actions the user can take based on the notified exercise plan.

[0101] (Application Example 1)

[0102] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0103] In today's aging society, the negative health effects of lack of exercise among the elderly are a serious problem. The elderly tend to have fewer opportunities for exercise, making it difficult to establish a regular exercise routine. Therefore, there is a need for effective and simple methods to promote exercise and support health maintenance based on individual health conditions.

[0104] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0105] In this invention, the server includes a measurement unit for collecting the user's biometric indicators, a storage unit for storing the biometric indicators in an information set, and an analysis unit for comparing the biometric indicators with the health data or reference data of other users. This makes it possible to generate exercise plans tailored to the health status of individual elderly people and to easily form exercise habits.

[0106] "Biometric indicators" refer to data that indicates an individual's health status, including information such as heart rate, steps taken, and activity level.

[0107] A "measurement unit" refers to a system that includes devices and sensors that detect and collect a user's biometric indicators.

[0108] An "information collection" refers to a database or storage system used to organize and store collected data.

[0109] A "memory unit" is a function that includes the structure and processes for storing data in an information set.

[0110] An "analysis unit" is a mechanism that performs processing to evaluate the status of individual users based on stored data and compare it with other users and reference data.

[0111] A "generated unit" refers to a function that includes the process and algorithms for creating an optimal exercise plan for the user based on the analysis results.

[0112] A "notification unit" is a means of communicating the generated exercise plan to the user, and includes notifications and alerts to the device.

[0113] A "proposal unit" refers to a structure or process for making specific suggestions for exercise and lifestyle improvements to maintain the health of the elderly.

[0114] An "inference agent" is a type of artificial intelligence that uses user attribute information to provide individually optimized advice and plans.

[0115] This invention uses a smartwatch or smartphone as a terminal to collect the user's biometric data. The smartwatch measures heart rate, steps, acceleration, etc., in real time and transmits the data to the smartphone. The smartphone temporarily stores this data and transmits it to a server via the internet.

[0116] The server stores the received data in the form of an information set. Next, the analysis unit compares the data with other users' health data and baseline data to detect insufficient exercise or abnormal trends. The generation unit utilizes these analysis results to generate an exercise plan optimized for each individual user. Using a generation AI model, it creates a specific and actionable plan to address the detected lack of exercise.

[0117] Once an exercise plan is created, the notification unit sends a notification to the user's smartphone or smartwatch, prompting them to perform specific exercises. The suggestion unit recommends simple stretches, indoor exercises, and walks, aimed at maintaining the health of older adults.

[0118] For example, if an elderly user's weekly activity level is detected to be below a certain threshold, a plan is created for them to take a 30-minute walk in a nearby park on the weekend. This plan is notified to the smartwatch and displayed with the message, "How about a walk in the park? It can have positive health benefits."

[0119] Examples of prompts include, "Generate suggestions for indoor exercises that are easy for seniors to perform," and "Create an effective stretching plan to improve seniors' exercise habits." These prompts can be input into the AI ​​model to create exercise plans tailored to individual needs.

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The device continuously measures the user's biometrics using a smartwatch. These biometric inputs include heart rate, steps, and accelerometer data. This data is temporarily stored within the device and updated in real time.

[0123] Step 2:

[0124] The device transmits the collected biometric data to the smartphone. The smartphone receives this data and performs preprocessing to standardize the data format. It then prepares this standardized data to send to the server.

[0125] Step 3:

[0126] The server receives data sent from smartphones and stores it in a database. The data processing performed here involves structuring the data as an information set and preparing it to enable efficient searching and access.

[0127] Step 4:

[0128] The server processes stored data in units of analysis. The input to the analysis is stored biometric indicators, and the output generates an exercise deficiency assessment result. It compares this data with other users' data and baseline data, using algorithms to identify specific activity deficiencies or abnormalities.

[0129] Step 5:

[0130] The server creates an optimal exercise plan for the user based on the exercise deficiency assessment results from the analysis unit. The generating AI model receives the exercise deficiency assessment results and user attributes as input and generates a personalized exercise plan as output. The prompt used is, "Please create an effective stretching plan to improve the exercise habits of elderly people."

[0131] Step 6:

[0132] The server sends the generated exercise plan to the smartphone or smartwatch in notification units. The device receives this and notifies the user with a message suggesting specific exercises, such as "How about a walk in the park?"

[0133] Step 7:

[0134] The user reviews the received exercise plan notification and performs the exercise based on it. The device then collects the user's exercise data again and stores it as new data to be used for future analysis.

[0135] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0136] This invention is an innovative system that integrates emotion recognition technology to effectively address users' lack of exercise, and provides a personalized exercise plan that takes into account the user's physical and emotional state. The system consists of sensing means, memory means, analysis means, generation means, notification means, preprocessing means, and an emotion engine.

[0137] Regarding sensing methods, smartwatches and smart rings, acting as terminals, play a role in collecting exercise data such as the user's steps, heart rate, and calories burned. This allows for a detailed understanding of the user's daily activities.

[0138] The emotion engine infers the user's emotional state from their voice tone, facial expressions, or physiological data. It can also directly obtain the user's current emotions through text or voice input. This emotional data is used to determine the user's state of mind while exercising or about to exercise.

[0139] The memory system stores collected motor and emotional data in a database on a server. The server combines and analyzes this data to record the motor and emotional tendencies of individual users.

[0140] As a preprocessing step, the server performs anomaly detection and data normalization to prepare the data for analysis. At this stage, the relationship between emotional data and motor data is also preliminaryly evaluated.

[0141] The analysis method not only compares stored data with other users' exercise data and regional baseline values, but also analyzes emotional data to understand the user's emotional trends. This identifies emotional states that make it easier for a user to exercise, as well as emotional states that act as barriers to exercise.

[0142] The generation method involves an AI agent creating an optimal exercise plan for the user based on the analysis results. Here, the duration and content of the exercise are adjusted based on the user's emotional state; for example, yoga is recommended if the user wants to relax, and running is recommended if they need to relieve stress.

[0143] The notification system promptly informs users of the generated exercise plan. This allows users to confirm the optimal exercise tailored to their emotional state and engage in it with a sense of satisfaction. For example, if a user feels stressed at work, the system can detect this and immediately suggest an exercise plan suitable for stress reduction.

[0144] Based on the above, this system is expected to help users develop exercise habits and contribute to their daily health management. The emotional engine enables users to maintain comprehensive health, taking into account not only their physical but also mental aspects.

[0145] The following describes the processing flow.

[0146] Step 1:

[0147] The device detects the user's daily physical activity in real time through sensors. It continuously collects information such as steps taken, activity time, and heart rate, allowing users to monitor their exercise levels.

[0148] Step 2:

[0149] The device utilizes an emotion engine to detect the user's emotional state. This engine obtains information from voice input, facial recognition, and physiological responses to analyze the user's current emotions. For example, if the user inputs a voice message and says, "I'm a little tired," the device collects that emotional information.

[0150] Step 3:

[0151] The device transmits collected motor and emotional data to the server. The data is encrypted and securely stored in the server's database.

[0152] Step 4:

[0153] The server preprocesses the stored data, detects outliers, and normalizes the data as needed. This provides a clean dataset for analysis.

[0154] Step 5:

[0155] The server analyzes the user's physical activity and emotional state based on pre-processed data. By comparing it with data from other users and baseline values, it identifies areas where physical activity is lacking and elements necessary to elicit positive emotions.

[0156] Step 6:

[0157] Based on the analysis results, the server uses an AI agent to generate an exercise plan. Taking into account the user's emotional state, it recommends yoga or stretching if the user desires relaxation, while suggesting short interval training sessions if the user wants to maintain energy.

[0158] Step 7:

[0159] The server pushes the generated exercise plan to the user's device. This notification is sent at the optimal time, tailored to the user's schedule and emotional state.

[0160] Step 8:

[0161] The user checks the notification and begins the activity according to the suggested exercise plan. After completing the activity, they enter feedback on their device, which is sent to the server and used as a reference for their next exercise plan.

[0162] (Example 2)

[0163] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0164] In modern society, it is well known that lack of exercise has a significant impact on health, but there are limited systems that can provide exercise plans that take into account the physical and emotional state of individual users. Furthermore, it is technically difficult to grasp a user's emotional state in real time and suggest appropriate exercise based on that. Conventional systems have been unable to process emotional and exercise data in an integrated manner, resulting in limited effectiveness in improving users' exercise habits.

[0165] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0166] In this invention, the server includes means for collecting biometric data, means for processing voice and image information to infer emotions, and means for storing the collected and inferred data in an information recording device. This makes it possible to provide an exercise plan optimized for each individual user and to more effectively improve the user's exercise habits.

[0167] A "biometric data collection device" is a device that uses sensors to acquire data such as heart rate, steps taken, and calories burned in order to understand the user's physical condition.

[0168] A "device that processes voice and image information to infer emotions" is a device that analyzes the tone of the user's voice and facial expressions to infer and digitize the user's emotional state.

[0169] "Means of storing information in an information recording device" refers to means of securely recording collected data and storing it for future analysis and comparison.

[0170] A "preprocessing device that detects and normalizes outliers" is a device that removes inappropriate values ​​from collected data and converts it into a standard format suitable for data analysis.

[0171] A "device for comparing with reference values" is a device that compares collected user data with reference data to relatively evaluate the user's activity level and emotional state.

[0172] A "device including an AI agent that generates the optimal exercise plan" is a device with artificial intelligence capabilities that automatically generate the most suitable exercise plan for each individual user based on analyzed data.

[0173] A "device for communicating exercise plans to users" is a device that notifies users of the generated exercise plan and encourages them to perform appropriate exercises.

[0174] This invention is a system that provides an individualized and optimized exercise plan based on an understanding of the user's physical and emotional state. To achieve this, the system consists of multiple devices.

[0175] First, smart devices, such as smartwatches and smart rings, collect biometric data such as the user's heart rate, steps taken, and calories burned. This information is used to record the user's daily activities in detail. The devices also use microphones and cameras to analyze the user's voice tone and facial expressions to infer their emotional state. This data helps to understand the user's emotional state while exercising.

[0176] The collected data is sent to a server and stored in a database. The server preprocesses the data, detects outliers, and normalizes it. It also compares the user's data to baseline values ​​and analyzes motor and emotional tendencies.

[0177] Based on the analyzed information, the server uses a generative AI model to generate an optimal exercise plan suited to the user's emotional state. This AI agent suggests exercises that match the user's emotional state, such as recommending yoga if the user is judged to have a high stress level.

[0178] The generated exercise plan is transmitted from the server to the terminal and notified to the user. The user can then follow this plan and provide feedback to help with future analysis.

[0179] For example, if a user is experiencing work-related stress, the system can detect this stress level and recommend a 30-minute yoga session, which helps the user relax more easily. This system provides support for users to effectively maintain both their physical and mental health.

[0180] An example of a prompt is, "Suggest a new exercise plan based on the user's emotional state." This prompt instructs the generative AI model to create an appropriate exercise plan.

[0181] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0182] Step 1:

[0183] The device collects the user's biometric data. Using sensors equipped on the device, it acquires heart rate, steps taken, and calories burned in real time. This data serves as basic information for understanding the user's activity level. The input is biometric data measured by the device, and the output is data temporarily stored on the device. Specifically, the smartwatch's heart rate sensor measures and records the heart rate every minute.

[0184] Step 2:

[0185] The device uses voice and image information to infer the user's emotions. It analyzes voice tone captured by the microphone and facial expressions captured by the camera to quantify the user's emotional state. The input is the user's voice and image data, and the output is inferred emotion data. For example, when the user says "I'm tired," the voice is recorded and analyzed as emotion data.

[0186] Step 3:

[0187] The device transmits collected biometric and emotional data to a server. Using Bluetooth or Wi-Fi, the data is encrypted and securely uploaded to the server. The input is the biometric and emotional data stored on the device, and the output is the data transferred to the server. Specifically, at the end of the day, the device automatically transmits the collected data to the server.

[0188] Step 4:

[0189] The server continuously saves received data to a database. After saving the data, it performs preprocessing such as detecting anomalies and normalizing the data. The normalized data is a preparatory step for accurately understanding the user's state. The input is biometric and emotional data sent to the server, and the output is normalized, clean data. Specifically, the server processes any detected anomalies in heart rate to bring them back within a specified range.

[0190] Step 5:

[0191] The server analyzes normalized data and compares it to other users and baseline values. This allows for a detailed understanding of the user's exercise and emotional tendencies. The input is normalized data, and the output is the result of the comparative analysis. Specifically, if a user's exercise level is lower than other users, the server generates an analytical report that highlights this fact.

[0192] Step 6:

[0193] The server uses a generative AI model to generate an optimal exercise plan based on the analysis results. It adjusts the exercise content and duration while considering the user's emotional state. The input is comparatively analyzed data, and the output is an exercise plan tailored to the user. For example, for a user with high stress levels, an exercise plan recommending "30 minutes of yoga" is generated.

[0194] Step 7:

[0195] The server sends the generated exercise plan to the device and notifies the user. The user can then receive and execute this plan. The input is the generated exercise plan, and the output is the notification to the user. Specifically, a message with the recommended exercise plan is displayed on the smartwatch's display.

[0196] (Application Example 2)

[0197] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0198] In modern society, a major challenge is that people's health suffers due to a lack of physical activity. Furthermore, since a user's emotional state influences their motivation for physical activity, there is a need for personalized exercise plans. However, there are few existing systems that take emotional states into consideration and provide appropriate exercise plans, resulting in insufficient guidance on effective physical activity tailored to an individual's mental state.

[0199] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0200] In this invention, the server includes a sensor device for collecting the user's physical activity level, a storage device for storing the physical activity level in a data collection device, and an emotion recognition device for estimating the user's emotional state. This makes it possible to create an optimal physical activity plan that reflects the user's physical and emotional state.

[0201] A "sensor device" is a device used to measure and collect a user's physical activity level in real time, and its main role is to acquire movement and physiological data.

[0202] A "storage device" is a device that securely and efficiently stores collected data on physical activity levels, and plays a role in data aggregation.

[0203] An "analysis device" is a device used to analyze collected physical activity data and compare it with data from other users or reference data.

[0204] An "emotion recognition device" is a device that analyzes a user's voice and facial expressions to estimate their emotional state, and is used to understand the mental state of individual users.

[0205] A "generation device" is a device that creates an optimal physical activity plan for a user based on the results of an analysis of their emotional state and physical activity data.

[0206] A "notification device" is a device that informs the user of the generated physical activity plan at the appropriate time, and is responsible for communicating the plan through voice or visual means.

[0207] To implement this invention, a system is constructed that comprehensively analyzes the user's activities and emotional state and provides an optimal physical activity plan. The server plays a central role in this system and functions using various hardware and software.

[0208] The server first collects the user's physical activity data through sensor devices. Wearable devices such as smartwatches and smart rings are used for this purpose. These devices record the user's steps, heart rate, calories burned, and other data in real time.

[0209] Next, the server analyzes the user's emotional state using an emotion recognition device. This process utilizes speech recognition and facial expression analysis technologies. Specifically, it infers emotions from voice tone and facial expressions by analyzing data from high-sensitivity microphones and cameras. Open-source libraries (e.g., OpenCV, DeepFace) are used to improve the accuracy of emotion analysis.

[0210] Once data is collected, the server stores it in memory, and an analysis device performs data cleansing and standardization. Pandas, a Python data analysis library, is used for this data processing. As a result of the cleansing, outliers are removed, allowing for a smooth evaluation of the relationship between emotional state and physical activity levels.

[0211] After analysis, the generation device creates an optimal physical activity plan based on the data. The generated plan is based on the user's emotional state and harmonizes their mental and physical condition. This generation process utilizes AI technology, with the generation AI model adjusting the plan. Prompts such as "Please generate an exercise plan suitable for the user based on today's emotional state and physical fatigue level" are used.

[0212] Finally, the notification device informs the user of the generated plan. This notification is delivered via the robot's voice or display, providing exercise guidance and motivational approaches based on the plan.

[0213] For example, if a user returns home tired from work and the emotion recognition device detects this state, the system can recommend stretching exercises to relax, and a robot can provide guidance. In this way, the system can provide personalized and appropriate physical activity support in a home environment.

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The server acquires user physical activity data from the device, such as a smartwatch or smart ring. Inputs include the user's steps, heart rate, and calories burned. This data is temporarily stored and prepared.

[0217] Step 2:

[0218] The server uses an emotion recognition device to analyze the user's emotional state. Inputs include the user's voice data and images captured by the camera. By analyzing these, the server infers emotions from the user's tone of voice and facial expressions. The output is an emotion label such as joy, excitement, or sadness.

[0219] Step 3:

[0220] The server stores the acquired physical activity and emotional data in storage. This process includes detecting outliers, normalizing the data, and processing it into a format suitable for processing. The output is a clean, normalized dataset.

[0221] Step 4:

[0222] The analysis device uses stored data to perform comparative analysis with other user data and reference data. The input consists of the user's normalized data and the comparison data. This comparison evaluates the user's current activity level and emotional state.

[0223] Step 5:

[0224] The server uses a generation device to create an optimal physical activity plan for the user based on the analysis results. To select appropriate exercise content and duration, it uses a generation AI model and employs the prompt message, "Generate an exercise plan suitable for the user based on today's emotional state and physical fatigue level." The output is a personalized exercise plan.

[0225] Step 6:

[0226] The notification device informs the user of the generated exercise plan. The robot verbally communicates the details of the plan to the user and displays the exercise content on the screen. The input is the generated exercise plan, and the robot suggests actions to the user based on this information.

[0227] Step 7:

[0228] The user begins physical activity at home according to the suggested exercise plan. The robot monitors the user and provides assistance and encouragement as needed. This step allows the user to effectively manage their health.

[0229] 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.

[0230] Data generation model 58 is a 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0231] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0232] [Second Embodiment]

[0233] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0234] 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.

[0235] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0236] 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.

[0237] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0238] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0239] 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.

[0240] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0241] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0242] The 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.

[0243] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0244] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0245] This invention is a system for addressing the lack of exercise among working adults and is designed for daily use by users. The system mainly consists of sensing means, storage means, analysis means, generation means, notification means, and preprocessing means.

[0246] As a sensing method, smartwatches and smart rings, which are terminals, detect the user's physical activity in real time. This includes pedometers, accelerometers, heart rate sensors, etc., and these sensors record the user's daily exercise data.

[0247] The memory system periodically transmits the collected motion data from the terminal to the server and stores it in a database on the server. This stored data is then used for detailed analysis later on.

[0248] As a preprocessing step, the server reviews the stored data, detects any anomalies, and normalizes the data to prepare it for analysis. This ensures that the data is suitable for input to the analysis tool.

[0249] The analysis is performed on a server and compares stored exercise data with data from other users and national baseline data. This allows the system to assess the user's level of inactivity. This assessment utilizes data such as the average number of steps taken per week and daily activity levels.

[0250] The generation method utilizes these analysis results and uses an AI agent to generate an optimal exercise plan for the user. This exercise plan includes specific details tailored to the user's habits and lifestyle. For example, if the user has time to exercise during their daily commute or at the office, a walking and stretching plan tailored to that will be suggested.

[0251] The notification system sends the aforementioned exercise plan to the user's smart device. A push notification is sent to the device, allowing the user to check it and begin their exercise. For example, a specific plan such as "We recommend a 20-minute run today" might be displayed.

[0252] For example, if a user tends to be less active on weekends, the server will detect this and suggest increasing their exercise during the weekend. Furthermore, if a user has had a busy week with few opportunities for exercise, the server can recommend light exercises or stretches that can be done at home.

[0253] By combining these methods, users can easily manage their daily exercise habits and receive assistance in maintaining their health. As a result, an environment is provided where even busy working adults can easily overcome a lack of exercise.

[0254] The following describes the processing flow.

[0255] Step 1:

[0256] The device is worn on the user's body and collects exercise data such as steps, heart rate, and calories burned in real time. This allows for a detailed record of the user's daily activity level.

[0257] Step 2:

[0258] The device transmits the collected exercise data to the server at regular intervals. For security reasons, this transmission is encrypted and carried out over the internet.

[0259] Step 3:

[0260] The server stores the received motion data in a database. Here, the stored data is organized for later analysis and comparison.

[0261] Step 4:

[0262] The server preprocesses the stored motion data, detects outliers, and normalizes the data. This ensures the accuracy of the data before it is passed to the analysis tools.

[0263] Step 5:

[0264] The server starts comparing normalized exercise data with data from other users and regional baselines. Through this comparison, if a user's exercise level is lower than the baseline, the server identifies the deficit.

[0265] Step 6:

[0266] Based on the analysis results, the server's AI agent generates an exercise plan optimized for the user. This plan proposes exercises that take into account the user's lifestyle and health condition.

[0267] Step 7:

[0268] The server pushes the generated exercise plan to the user's device. The user receives this notification and can easily understand and perform the specific exercise activities.

[0269] Step 8:

[0270] The user performs the exercise according to the exercise plan received from the server. The user then records the exercise status again on their device and sends feedback based on that data to the server.

[0271] (Example 1)

[0272] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0273] In modern society, lack of exercise is a chronic problem, especially among working adults. This lack of exercise negatively impacts health, and there is a need for the development of specific and personalized plans for effective exercise. Conventional technologies lack systems that can provide exercise plans tailored to each user, making it difficult to effectively encourage exercise habits.

[0274] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0275] In this invention, the server includes a sensor unit that measures the user's physical activity level, a storage unit that stores the activity level in a recording device, and an analysis unit that compares the activity level with standard data. This makes it possible to individually create and notify the user of a physical activity plan that is suitable for them.

[0276] The "sensor unit" is a device used to measure the user's physical activity level and can acquire data such as steps, heart rate, and acceleration.

[0277] The "storage unit" is a device that records and stores measured physical activity data, and functions as a database or storage device.

[0278] The "analysis unit" is a device that compares stored physical activity data with standard data to evaluate the user's level of physical inactivity and activity trends.

[0279] The "creation unit" is a device that generates a physical activity plan suitable for the user based on the evaluation results obtained from the analysis unit, and it uses an AI agent to perform personalized planning.

[0280] The "notification unit" is a device that transmits the physical activity plan generated by the creation unit to the user in an appropriate manner, such as by sending push notifications to smart devices.

[0281] This invention is a system designed to address the lack of exercise among working adults and is designed for daily use by users. This system mainly consists of a sensor unit, a storage unit, an analysis unit, a creation unit, and a notification unit.

[0282] First, the sensor unit will utilize a smartwatch or smart ring, which will act as a terminal. This terminal will detect the user's physical activity in real time. For example, it will collect the user's daily exercise data using a pedometer, accelerometer, and heart rate sensor.

[0283] Next, the storage unit periodically sends the motion data collected from the terminal to the server and stores it in a database on the server. This allows for the accumulation of data necessary for later analysis.

[0284] The analysis unit is executed on the server and evaluates the user's lack of exercise by comparing the saved exercise data with the standard data. This evaluation enables appropriate analysis according to the user's current situation.

[0285] After that, based on the analysis results, the creation unit uses an AI agent to generate an optimal physical activity plan for the user. This plan is tailored to the user's lifestyle and daily activities. For example, if the user has a desk job-centered lifestyle, it can propose walking during lunch breaks or stretching after returning home.

[0286] Finally, the notification unit sends the created physical activity plan as a push notification to the user's smart device. The user can check this and engage in the proposed exercises. As an example of the notification content, a specific plan such as "It is recommended to walk for 20 minutes before returning home today" is provided.

[0287] As a specific example, if the user tends to lack exercise on weekends, the server detects this and proposes a plan to increase the amount of exercise on weekends. Also, in a week with few exercise opportunities due to consecutive schedules, it is possible to recommend light exercises or stretches that can be done at home.

[0288] An example of a prompt sentence for the generation AI model is "Based on this week's exercise data, please create a specific exercise plan for next week. Please include proposals for outdoor walking and indoor stretching considering the user's activity trends and weekend time."

[0289] In this way, the system analyzes the user's daily exercise situation in detail and provides an effective and easy-to-follow exercise plan to help eliminate the lack of exercise even in a busy life.

[0290] The flow of the specific process in Example 1 will be described using FIG. 11.

[0291] Step 1:

[0292] Data collection

[0293] The device detects the user's physical activity in real time using a smartwatch or smart ring. The input here is raw data related to body movement (e.g., acceleration, steps, heart rate, etc.). The device collects this data through sensors and outputs basic exercise data that indicates the user's exercise status.

[0294] Step 2:

[0295] Data transmission

[0296] The device transmits collected exercise data to the server at regular intervals. The input for this step is the collected exercise data. The device transmits the data to the server using Wi-Fi or Bluetooth, and the server confirms receipt of the data. The output is the user-specific exercise data stored on the server.

[0297] Step 3:

[0298] Data storage

[0299] The server stores the received exercise data in a database. The input is the exercise data sent from the terminal. The server organizes this data by user and indexes it for quick access in subsequent processes. The output is the exercise data in the well-organized database.

[0300] Step 4:

[0301] Data preprocessing

[0302] The server reviews the motion data in the database, detecting and normalizing outliers. The input is the stored raw motion data. The server uses statistical methods to identify outliers and correct them to within the normal range. The output is the normalized data with the anomalies corrected.

[0303] Step 5:

[0304] Data analysis

[0305] The server analyzes the normalized data and compares the user's degree of physical inactivity with the data of other users and reference data. The input is the normalized exercise data. An AI model is used for the analysis to quantify the user's daily activity level and the quality of the exercise. The output is the evaluation result of the specific exercise state.

[0306] Step 6:

[0307] Exercise plan generation

[0308] The server uses the evaluation result and utilizes an AI agent to generate an exercise plan suitable for the user. The input is the evaluation result based on data analysis. The server creates appropriate exercise suggestions (e.g., walking goals, stretching recommendations, etc.) while also considering the user's profile information. The output is an exercise plan tailored to the user's lifestyle.

[0309] Step 7:

[0310] Notification

[0311] The server sends the generated exercise plan to the user's smart device. The input is the generated exercise plan. The server transfers the plan as a push notification so that the user can view it. The output is the likelihood of the user's actions based on the notified exercise plan.

[0312] (Application Example 1)

[0313] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0314] In today's aging society, the negative health effects of lack of exercise among the elderly are a serious problem. The elderly tend to have fewer opportunities for exercise, making it difficult to establish a regular exercise routine. Therefore, there is a need for effective and simple methods to promote exercise and support health maintenance based on individual health conditions.

[0315] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0316] In this invention, the server includes a measurement unit for collecting the user's biometric indicators, a storage unit for storing the biometric indicators in an information set, and an analysis unit for comparing the biometric indicators with the health data or reference data of other users. This makes it possible to generate exercise plans tailored to the health status of individual elderly people and to easily form exercise habits.

[0317] "Biometric indicators" refer to data that indicates an individual's health status, including information such as heart rate, steps taken, and activity level.

[0318] A "measurement unit" refers to a system that includes devices and sensors that detect and collect a user's biometric indicators.

[0319] An "information collection" refers to a database or storage system used to organize and store collected data.

[0320] A "memory unit" is a function that includes the structure and processes for storing data in an information set.

[0321] An "analysis unit" is a mechanism that performs processing to evaluate the status of individual users based on stored data and compare it with other users and reference data.

[0322] A "generated unit" refers to a function that includes the process and algorithms for creating an optimal exercise plan for the user based on the analysis results.

[0323] A "notification unit" is a means of communicating the generated exercise plan to the user, and includes notifications and alerts to the device.

[0324] A "proposal unit" refers to a structure or process for making specific suggestions for exercise and lifestyle improvements to maintain the health of the elderly.

[0325] An "inference agent" is a type of artificial intelligence that uses user attribute information to provide individually optimized advice and plans.

[0326] This invention uses a smartwatch or smartphone as a terminal to collect the user's biometric data. The smartwatch measures heart rate, steps, acceleration, etc., in real time and transmits the data to the smartphone. The smartphone temporarily stores this data and transmits it to a server via the internet.

[0327] The server stores the received data in the form of an information set. Next, the analysis unit compares the data with other users' health data and baseline data to detect insufficient exercise or abnormal trends. The generation unit utilizes these analysis results to generate an exercise plan optimized for each individual user. Using a generation AI model, it creates a specific and actionable plan to address the detected lack of exercise.

[0328] Once an exercise plan is created, the notification unit sends a notification to the user's smartphone or smartwatch, prompting them to perform specific exercises. The suggestion unit recommends simple stretches, indoor exercises, and walks, aimed at maintaining the health of older adults.

[0329] For example, if an elderly user's weekly activity level is detected to be below a certain threshold, a plan is created for them to take a 30-minute walk in a nearby park on the weekend. This plan is notified to the smartwatch and displayed with the message, "How about a walk in the park? It can have positive health benefits."

[0330] Examples of prompts include, "Generate suggestions for indoor exercises that are easy for seniors to perform," and "Create an effective stretching plan to improve seniors' exercise habits." These prompts can be input into the AI ​​model to create exercise plans tailored to individual needs.

[0331] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0332] Step 1:

[0333] The device continuously measures the user's biometrics using a smartwatch. These biometric inputs include heart rate, steps, and accelerometer data. This data is temporarily stored within the device and updated in real time.

[0334] Step 2:

[0335] The device transmits the collected biometric data to the smartphone. The smartphone receives this data and performs preprocessing to standardize the data format. It then prepares this standardized data to send to the server.

[0336] Step 3:

[0337] The server receives data sent from smartphones and stores it in a database. The data processing performed here involves structuring the data as an information set and preparing it to enable efficient searching and access.

[0338] Step 4:

[0339] The server processes stored data in units of analysis. The input to the analysis is stored biometric indicators, and the output generates an exercise deficiency assessment result. It compares this data with other users' data and baseline data, using algorithms to identify specific activity deficiencies or abnormalities.

[0340] Step 5:

[0341] The server creates an optimal exercise plan for the user based on the exercise deficiency assessment results from the analysis unit. The generating AI model receives the exercise deficiency assessment results and user attributes as input and generates a personalized exercise plan as output. The prompt used is, "Please create an effective stretching plan to improve the exercise habits of elderly people."

[0342] Step 6:

[0343] The server sends the generated exercise plan to the smartphone or smartwatch in notification units. The device receives this and notifies the user with a message suggesting specific exercises, such as "How about a walk in the park?"

[0344] Step 7:

[0345] The user reviews the received exercise plan notification and performs the exercise based on it. The device then collects the user's exercise data again and stores it as new data to be used for future analysis.

[0346] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0347] This invention is an innovative system that integrates emotion recognition technology to effectively address users' lack of exercise, and provides a personalized exercise plan that takes into account the user's physical and emotional state. The system consists of sensing means, memory means, analysis means, generation means, notification means, preprocessing means, and an emotion engine.

[0348] Regarding sensing methods, smartwatches and smart rings, acting as terminals, play a role in collecting exercise data such as the user's steps, heart rate, and calories burned. This allows for a detailed understanding of the user's daily activities.

[0349] The emotion engine infers the user's emotional state from their voice tone, facial expressions, or physiological data. It can also directly obtain the user's current emotions through text or voice input. This emotional data is used to determine the user's state of mind while exercising or about to exercise.

[0350] The memory system stores collected motor and emotional data in a database on a server. The server combines and analyzes this data to record the motor and emotional tendencies of individual users.

[0351] As a preprocessing step, the server performs anomaly detection and data normalization to prepare the data for analysis. At this stage, the relationship between emotional data and motor data is also preliminaryly evaluated.

[0352] The analysis method not only compares stored data with other users' exercise data and regional baseline values, but also analyzes emotional data to understand the user's emotional trends. This identifies emotional states that make it easier for a user to exercise, as well as emotional states that act as barriers to exercise.

[0353] The generation method involves an AI agent creating an optimal exercise plan for the user based on the analysis results. Here, the duration and content of the exercise are adjusted based on the user's emotional state; for example, yoga is recommended if the user wants to relax, and running is recommended if they need to relieve stress.

[0354] The notification system promptly informs users of the generated exercise plan. This allows users to confirm the optimal exercise tailored to their emotional state and engage in it with a sense of satisfaction. For example, if a user feels stressed at work, the system can detect this and immediately suggest an exercise plan suitable for stress reduction.

[0355] Based on the above, this system is expected to help users develop exercise habits and contribute to their daily health management. The emotional engine enables users to maintain comprehensive health, taking into account not only their physical but also mental aspects.

[0356] The following describes the processing flow.

[0357] Step 1:

[0358] The device detects the user's daily physical activity in real time through sensors. It continuously collects information such as steps taken, activity time, and heart rate, allowing users to monitor their exercise levels.

[0359] Step 2:

[0360] The device utilizes an emotion engine to detect the user's emotional state. This engine obtains information from voice input, facial recognition, and physiological responses to analyze the user's current emotions. For example, if the user inputs a voice message and says, "I'm a little tired," the device collects that emotional information.

[0361] Step 3:

[0362] The device transmits collected motor and emotional data to the server. The data is encrypted and securely stored in the server's database.

[0363] Step 4:

[0364] The server preprocesses the stored data, detects outliers, and normalizes the data as needed. This provides a clean dataset for analysis.

[0365] Step 5:

[0366] The server analyzes the user's physical activity and emotional state based on pre-processed data. By comparing it with data from other users and baseline values, it identifies areas where physical activity is lacking and elements necessary to elicit positive emotions.

[0367] Step 6:

[0368] Based on the analysis results, the server uses an AI agent to generate an exercise plan. Taking into account the user's emotional state, it recommends yoga or stretching if the user desires relaxation, while suggesting short interval training sessions if the user wants to maintain energy.

[0369] Step 7:

[0370] The server pushes the generated exercise plan to the user's device. This notification is sent at the optimal time, tailored to the user's schedule and emotional state.

[0371] Step 8:

[0372] The user checks the notification and begins the activity according to the suggested exercise plan. After completing the activity, they enter feedback on their device, which is sent to the server and used as a reference for their next exercise plan.

[0373] (Example 2)

[0374] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0375] In modern society, it is well known that lack of exercise has a significant impact on health, but there are limited systems that can provide exercise plans that take into account the physical and emotional state of individual users. Furthermore, it is technically difficult to grasp a user's emotional state in real time and suggest appropriate exercise based on that. Conventional systems have been unable to process emotional and exercise data in an integrated manner, resulting in limited effectiveness in improving users' exercise habits.

[0376] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0377] In this invention, the server includes means for collecting biometric data, means for processing voice and image information to infer emotions, and means for storing the collected and inferred data in an information recording device. This makes it possible to provide an exercise plan optimized for each individual user and to more effectively improve the user's exercise habits.

[0378] A "biometric data collection device" is a device that uses sensors to acquire data such as heart rate, steps taken, and calories burned in order to understand the user's physical condition.

[0379] A "device that processes voice and image information to infer emotions" is a device that analyzes the tone of the user's voice and facial expressions to infer and digitize the user's emotional state.

[0380] "Means of storing information in an information recording device" refers to means of securely recording collected data and storing it for future analysis and comparison.

[0381] A "preprocessing device that detects and normalizes outliers" is a device that removes inappropriate values ​​from collected data and converts it into a standard format suitable for data analysis.

[0382] A "device for comparing with reference values" is a device that compares collected user data with reference data to relatively evaluate the user's activity level and emotional state.

[0383] A "device including an AI agent that generates the optimal exercise plan" is a device with artificial intelligence capabilities that automatically generate the most suitable exercise plan for each individual user based on analyzed data.

[0384] A "device for communicating exercise plans to users" is a device that notifies users of the generated exercise plan and encourages them to perform appropriate exercises.

[0385] This invention is a system that provides an individualized and optimized exercise plan based on an understanding of the user's physical and emotional state. To achieve this, the system consists of multiple devices.

[0386] First, smart devices, such as smartwatches and smart rings, collect biometric data such as the user's heart rate, steps taken, and calories burned. This information is used to record the user's daily activities in detail. The devices also use microphones and cameras to analyze the user's voice tone and facial expressions to infer their emotional state. This data helps to understand the user's emotional state while exercising.

[0387] The collected data is sent to a server and stored in a database. The server preprocesses the data, detects outliers, and normalizes it. It also compares the user's data to baseline values ​​and analyzes motor and emotional tendencies.

[0388] Based on the analyzed information, the server uses a generative AI model to generate an optimal exercise plan suited to the user's emotional state. This AI agent suggests exercises that match the user's emotional state, such as recommending yoga if the user is judged to have a high stress level.

[0389] The generated exercise plan is transmitted from the server to the terminal and notified to the user. The user can then follow this plan and provide feedback to help with future analysis.

[0390] For example, if a user is experiencing work-related stress, the system can detect this stress level and recommend a 30-minute yoga session, which helps the user relax more easily. This system provides support for users to effectively maintain both their physical and mental health.

[0391] An example of a prompt is, "Suggest a new exercise plan based on the user's emotional state." This prompt instructs the generative AI model to create an appropriate exercise plan.

[0392] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0393] Step 1:

[0394] The device collects the user's biometric data. Using sensors equipped on the device, it acquires heart rate, steps taken, and calories burned in real time. This data serves as basic information for understanding the user's activity level. The input is biometric data measured by the device, and the output is data temporarily stored on the device. Specifically, the smartwatch's heart rate sensor measures and records the heart rate every minute.

[0395] Step 2:

[0396] The device uses voice and image information to infer the user's emotions. It analyzes voice tone captured by the microphone and facial expressions captured by the camera to quantify the user's emotional state. The input is the user's voice and image data, and the output is inferred emotion data. For example, when the user says "I'm tired," the voice is recorded and analyzed as emotion data.

[0397] Step 3:

[0398] The device transmits collected biometric and emotional data to a server. Using Bluetooth or Wi-Fi, the data is encrypted and securely uploaded to the server. The input is the biometric and emotional data stored on the device, and the output is the data transferred to the server. Specifically, at the end of the day, the device automatically transmits the collected data to the server.

[0399] Step 4:

[0400] The server continuously saves received data to a database. After saving the data, it performs preprocessing such as detecting anomalies and normalizing the data. The normalized data is a preparatory step for accurately understanding the user's state. The input is biometric and emotional data sent to the server, and the output is normalized, clean data. Specifically, the server processes any detected anomalies in heart rate to bring them back within a specified range.

[0401] Step 5:

[0402] The server analyzes normalized data and compares it to other users and baseline values. This allows for a detailed understanding of the user's exercise and emotional tendencies. The input is normalized data, and the output is the result of the comparative analysis. Specifically, if a user's exercise level is lower than other users, the server generates an analytical report that highlights this fact.

[0403] Step 6:

[0404] The server uses a generative AI model to generate an optimal exercise plan based on the analysis results. It adjusts the exercise content and duration while considering the user's emotional state. The input is comparatively analyzed data, and the output is an exercise plan tailored to the user. For example, for a user with high stress levels, an exercise plan recommending "30 minutes of yoga" is generated.

[0405] Step 7:

[0406] The server sends the generated exercise plan to the device and notifies the user. The user can then receive and execute this plan. The input is the generated exercise plan, and the output is the notification to the user. Specifically, a message with the recommended exercise plan is displayed on the smartwatch's display.

[0407] (Application Example 2)

[0408] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0409] In modern society, a major challenge is that people's health suffers due to a lack of physical activity. Furthermore, since a user's emotional state influences their motivation for physical activity, there is a need for personalized exercise plans. However, there are few existing systems that take emotional states into consideration and provide appropriate exercise plans, resulting in insufficient guidance on effective physical activity tailored to an individual's mental state.

[0410] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0411] In this invention, the server includes a sensor device for collecting the user's physical activity level, a storage device for storing the physical activity level in a data collection device, and an emotion recognition device for estimating the user's emotional state. This makes it possible to create an optimal physical activity plan that reflects the user's physical and emotional state.

[0412] A "sensor device" is a device used to measure and collect a user's physical activity level in real time, and its main role is to acquire movement and physiological data.

[0413] A "storage device" is a device that securely and efficiently stores collected data on physical activity levels, and plays a role in data aggregation.

[0414] An "analysis device" is a device used to analyze collected physical activity data and compare it with data from other users or reference data.

[0415] An "emotion recognition device" is a device that analyzes a user's voice and facial expressions to estimate their emotional state, and is used to understand the mental state of individual users.

[0416] A "generation device" is a device that creates an optimal physical activity plan for a user based on the results of an analysis of their emotional state and physical activity data.

[0417] A "notification device" is a device that informs the user of the generated physical activity plan at the appropriate time, and is responsible for communicating the plan through voice or visual means.

[0418] To implement this invention, a system is constructed that comprehensively analyzes the user's activities and emotional state and provides an optimal physical activity plan. The server plays a central role in this system and functions using various hardware and software.

[0419] The server first collects the user's physical activity data through sensor devices. Wearable devices such as smartwatches and smart rings are used for this purpose. These devices record the user's steps, heart rate, calories burned, and other data in real time.

[0420] Next, the server analyzes the user's emotional state using an emotion recognition device. This process utilizes speech recognition and facial expression analysis technologies. Specifically, it infers emotions from voice tone and facial expressions by analyzing data from high-sensitivity microphones and cameras. Open-source libraries (e.g., OpenCV, DeepFace) are used to improve the accuracy of emotion analysis.

[0421] Once data is collected, the server stores it in memory, and an analysis device performs data cleansing and standardization. Pandas, a Python data analysis library, is used for this data processing. As a result of the cleansing, outliers are removed, allowing for a smooth evaluation of the relationship between emotional state and physical activity levels.

[0422] After analysis, the generation device creates an optimal physical activity plan based on the data. The generated plan is based on the user's emotional state and harmonizes their mental and physical condition. This generation process utilizes AI technology, with the generation AI model adjusting the plan. Prompts such as "Please generate an exercise plan suitable for the user based on today's emotional state and physical fatigue level" are used.

[0423] Finally, the notification device informs the user of the generated plan. This notification is delivered via the robot's voice or display, providing exercise guidance and motivational approaches based on the plan.

[0424] For example, if a user returns home tired from work and the emotion recognition device detects this state, the system can recommend stretching exercises to relax, and a robot can provide guidance. In this way, the system can provide personalized and appropriate physical activity support in a home environment.

[0425] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0426] Step 1:

[0427] The server acquires user physical activity data from the device, such as a smartwatch or smart ring. Inputs include the user's steps, heart rate, and calories burned. This data is temporarily stored and prepared.

[0428] Step 2:

[0429] The server uses an emotion recognition device to analyze the user's emotional state. Inputs include the user's voice data and images captured by the camera. By analyzing these, the server infers emotions from the user's tone of voice and facial expressions. The output is an emotion label such as joy, excitement, or sadness.

[0430] Step 3:

[0431] The server stores the acquired physical activity and emotional data in storage. This process includes detecting outliers, normalizing the data, and processing it into a format suitable for processing. The output is a clean, normalized dataset.

[0432] Step 4:

[0433] The analysis device uses stored data to perform comparative analysis with other user data and reference data. The input consists of the user's normalized data and the comparison data. This comparison evaluates the user's current activity level and emotional state.

[0434] Step 5:

[0435] The server uses a generation device to create an optimal physical activity plan for the user based on the analysis results. To select appropriate exercise content and duration, it uses a generation AI model and employs the prompt message, "Generate an exercise plan suitable for the user based on today's emotional state and physical fatigue level." The output is a personalized exercise plan.

[0436] Step 6:

[0437] The notification device informs the user of the generated exercise plan. The robot verbally communicates the details of the plan to the user and displays the exercise content on the screen. The input is the generated exercise plan, and the robot suggests actions to the user based on this information.

[0438] Step 7:

[0439] The user begins physical activity at home according to the suggested exercise plan. The robot monitors the user and provides assistance and encouragement as needed. This step allows the user to effectively manage their health.

[0440] 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.

[0441] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0442] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0443] [Third Embodiment]

[0444] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0445] 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.

[0446] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0447] 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.

[0448] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0449] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0450] 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.

[0451] 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.

[0452] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0453] The 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.

[0454] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0455] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0456] This invention is a system for addressing the lack of exercise among working adults and is designed for daily use by users. The system mainly consists of sensing means, storage means, analysis means, generation means, notification means, and preprocessing means.

[0457] As a sensing method, smartwatches and smart rings, which are terminals, detect the user's physical activity in real time. This includes pedometers, accelerometers, heart rate sensors, etc., and these sensors record the user's daily exercise data.

[0458] The memory system periodically transmits the collected motion data from the terminal to the server and stores it in a database on the server. This stored data is then used for detailed analysis later on.

[0459] As a preprocessing step, the server reviews the stored data, detects any anomalies, and normalizes the data to prepare it for analysis. This ensures that the data is suitable for input to the analysis tool.

[0460] The analysis is performed on a server and compares stored exercise data with data from other users and national baseline data. This allows the system to assess the user's level of inactivity. This assessment utilizes data such as the average number of steps taken per week and daily activity levels.

[0461] The generation method utilizes these analysis results and uses an AI agent to generate an optimal exercise plan for the user. This exercise plan includes specific details tailored to the user's habits and lifestyle. For example, if the user has time to exercise during their daily commute or at the office, a walking and stretching plan tailored to that will be suggested.

[0462] The notification system sends the aforementioned exercise plan to the user's smart device. A push notification is sent to the device, allowing the user to check it and begin their exercise. For example, a specific plan such as "We recommend a 20-minute run today" might be displayed.

[0463] For example, if a user tends to be less active on weekends, the server will detect this and suggest increasing their exercise during the weekend. Furthermore, if a user has had a busy week with few opportunities for exercise, the server can recommend light exercises or stretches that can be done at home.

[0464] By combining these methods, users can easily manage their daily exercise habits and receive assistance in maintaining their health. As a result, an environment is provided where even busy working adults can easily overcome a lack of exercise.

[0465] The following describes the processing flow.

[0466] Step 1:

[0467] The device is worn on the user's body and collects exercise data such as steps, heart rate, and calories burned in real time. This allows for a detailed record of the user's daily activity level.

[0468] Step 2:

[0469] The device transmits the collected exercise data to the server at regular intervals. For security reasons, this transmission is encrypted and carried out over the internet.

[0470] Step 3:

[0471] The server stores the received motion data in a database. Here, the stored data is organized for later analysis and comparison.

[0472] Step 4:

[0473] The server preprocesses the stored motion data, detects outliers, and normalizes the data. This ensures the accuracy of the data before it is passed to the analysis tools.

[0474] Step 5:

[0475] The server starts comparing normalized exercise data with data from other users and regional baselines. Through this comparison, if a user's exercise level is lower than the baseline, the server identifies the deficit.

[0476] Step 6:

[0477] Based on the analysis results, the server's AI agent generates an exercise plan optimized for the user. This plan proposes exercises that take into account the user's lifestyle and health condition.

[0478] Step 7:

[0479] The server pushes the generated exercise plan to the user's device. The user receives this notification and can easily understand and perform the specific exercise activities.

[0480] Step 8:

[0481] The user performs the exercise according to the exercise plan received from the server. The user then records the exercise status again on their device and sends feedback based on that data to the server.

[0482] (Example 1)

[0483] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0484] In modern society, lack of exercise is a chronic problem, especially among working adults. This lack of exercise negatively impacts health, and there is a need for the development of specific and personalized plans for effective exercise. Conventional technologies lack systems that can provide exercise plans tailored to each user, making it difficult to effectively encourage exercise habits.

[0485] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0486] In this invention, the server includes a sensor unit that measures the user's physical activity level, a storage unit that stores the activity level in a recording device, and an analysis unit that compares the activity level with standard data. This makes it possible to individually create and notify the user of a physical activity plan that is suitable for them.

[0487] The "sensor unit" is a device used to measure the user's physical activity level and can acquire data such as steps, heart rate, and acceleration.

[0488] The "storage unit" is a device that records and stores measured physical activity data, and functions as a database or storage device.

[0489] The "analysis unit" is a device that compares stored physical activity data with standard data to evaluate the user's level of physical inactivity and activity trends.

[0490] The "creation unit" is a device that generates a physical activity plan suitable for the user based on the evaluation results obtained from the analysis unit, and it uses an AI agent to perform personalized planning.

[0491] The "notification unit" is a device that transmits the physical activity plan generated by the creation unit to the user in an appropriate manner, such as by sending push notifications to smart devices.

[0492] This invention is a system designed to address the lack of exercise among working adults and is designed for daily use by users. This system mainly consists of a sensor unit, a storage unit, an analysis unit, a creation unit, and a notification unit.

[0493] First, the sensor unit will utilize a smartwatch or smart ring, which will act as a terminal. This terminal will detect the user's physical activity in real time. For example, it will collect the user's daily exercise data using a pedometer, accelerometer, and heart rate sensor.

[0494] Next, the storage unit periodically sends the motion data collected from the terminal to the server and stores it in a database on the server. This allows for the accumulation of data necessary for later analysis.

[0495] The analysis unit runs on a server and evaluates the user's level of inactivity by comparing stored exercise data with standard data. This evaluation enables appropriate analysis tailored to the user's current situation.

[0496] Subsequently, the creation department uses an AI agent based on the analysis results to generate an optimal physical activity plan for the user. This plan is tailored to the user's lifestyle and daily activities. For example, if the user's life revolves around desk work, the plan can suggest walking during lunch breaks and stretching after returning home.

[0497] Finally, the notification unit sends the created physical activity plan as a push notification to the user's smart device. The user can then review this notification and engage in the suggested exercise. An example of the notification content is a specific plan such as, "We recommend a 20-minute walk before you head home today."

[0498] For example, if a user tends to be less active on weekends, the server will detect this and suggest a plan to increase their exercise during the weekend. It can also recommend light exercises or stretches that can be done at home during weeks when exercise opportunities are limited due to consecutive commitments.

[0499] An example of a prompt for the generating AI model would be: "Based on this week's exercise data, please create a specific exercise plan for next week. Please take into account the user's activity patterns and weekend time, and include suggestions for outdoor walking and indoor stretching."

[0500] In this way, the system analyzes the user's daily exercise habits in detail and provides effective and easy-to-follow exercise plans, helping to alleviate a lack of exercise even in busy lifestyles.

[0501] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0502] Step 1:

[0503] Data collection

[0504] The device detects the user's physical activity in real time using a smartwatch or smart ring. The input here is raw data related to body movement (e.g., acceleration, steps, heart rate, etc.). The device collects this data through sensors and outputs basic exercise data that indicates the user's exercise status.

[0505] Step 2:

[0506] Data transmission

[0507] The device transmits collected exercise data to the server at regular intervals. The input for this step is the collected exercise data. The device transmits the data to the server using Wi-Fi or Bluetooth, and the server confirms receipt of the data. The output is the user-specific exercise data stored on the server.

[0508] Step 3:

[0509] Data storage

[0510] The server stores the received exercise data in a database. The input is the exercise data sent from the terminal. The server organizes this data by user and indexes it for quick access in subsequent processes. The output is the exercise data in the well-organized database.

[0511] Step 4:

[0512] Data preprocessing

[0513] The server reviews the motion data in the database, detecting and normalizing outliers. The input is the stored raw motion data. The server uses statistical methods to identify outliers and correct them to within the normal range. The output is the normalized data with the anomalies corrected.

[0514] Step 5:

[0515] Data Analysis

[0516] The server analyzes normalized data and compares the user's level of exercise inactivity with data from other users and baseline data. The input is normalized exercise data. An AI model is used for analysis to quantify the user's daily activity level and exercise quality. The output is an evaluation of the specific exercise status.

[0517] Step 6:

[0518] Activity plan generation

[0519] The server uses the evaluation results and an AI agent to generate an exercise plan tailored to the user. The input is the evaluation results based on data analysis. The server also considers the user's profile information to create appropriate exercise suggestions (e.g., step goals, stretching recommendations, etc.). The output is an exercise plan tailored to the user's lifestyle.

[0520] Step 7:

[0521] notification

[0522] The server sends the generated exercise plan to the user's smart device. The input is the generated exercise plan. The server forwards the plan as a push notification for the user to review. The output is the possible actions the user can take based on the notified exercise plan.

[0523] (Application Example 1)

[0524] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0525] In today's aging society, the negative health effects of lack of exercise among the elderly are a serious problem. The elderly tend to have fewer opportunities for exercise, making it difficult to establish a regular exercise routine. Therefore, there is a need for effective and simple methods to promote exercise and support health maintenance based on individual health conditions.

[0526] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0527] In this invention, the server includes a measurement unit for collecting the user's biometric indicators, a storage unit for storing the biometric indicators in an information set, and an analysis unit for comparing the biometric indicators with the health data or reference data of other users. This makes it possible to generate exercise plans tailored to the health status of individual elderly people and to easily form exercise habits.

[0528] "Biometric indicators" refer to data that indicates an individual's health status, including information such as heart rate, steps taken, and activity level.

[0529] A "measurement unit" refers to a system that includes devices and sensors that detect and collect a user's biometric indicators.

[0530] An "information collection" refers to a database or storage system used to organize and store collected data.

[0531] A "memory unit" is a function that includes the structure and processes for storing data in an information set.

[0532] An "analysis unit" is a mechanism that performs processing to evaluate the status of individual users based on stored data and compare it with other users and reference data.

[0533] A "generated unit" refers to a function that includes the process and algorithms for creating an optimal exercise plan for the user based on the analysis results.

[0534] A "notification unit" is a means of communicating the generated exercise plan to the user, and includes notifications and alerts to the device.

[0535] A "proposal unit" refers to a structure or process for making specific suggestions for exercise and lifestyle improvements to maintain the health of the elderly.

[0536] An "inference agent" is a type of artificial intelligence that uses user attribute information to provide individually optimized advice and plans.

[0537] This invention uses a smartwatch or smartphone as a terminal to collect the user's biometric data. The smartwatch measures heart rate, steps, acceleration, etc., in real time and transmits the data to the smartphone. The smartphone temporarily stores this data and transmits it to a server via the internet.

[0538] The server stores the received data in the form of an information set. Next, the analysis unit compares the data with other users' health data and baseline data to detect insufficient exercise or abnormal trends. The generation unit utilizes these analysis results to generate an exercise plan optimized for each individual user. Using a generation AI model, it creates a specific and actionable plan to address the detected lack of exercise.

[0539] Once an exercise plan is created, the notification unit sends a notification to the user's smartphone or smartwatch, prompting them to perform specific exercises. The suggestion unit recommends simple stretches, indoor exercises, and walks, aimed at maintaining the health of older adults.

[0540] For example, if an elderly user's weekly activity level is detected to be below a certain threshold, a plan is created for them to take a 30-minute walk in a nearby park on the weekend. This plan is notified to the smartwatch and displayed with the message, "How about a walk in the park? It can have positive health benefits."

[0541] Examples of prompts include, "Generate suggestions for indoor exercises that are easy for seniors to perform," and "Create an effective stretching plan to improve seniors' exercise habits." These prompts can be input into the AI ​​model to create exercise plans tailored to individual needs.

[0542] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0543] Step 1:

[0544] The device continuously measures the user's biometrics using a smartwatch. These biometric inputs include heart rate, steps, and accelerometer data. This data is temporarily stored within the device and updated in real time.

[0545] Step 2:

[0546] The device transmits the collected biometric data to the smartphone. The smartphone receives this data and performs preprocessing to standardize the data format. It then prepares this standardized data to send to the server.

[0547] Step 3:

[0548] The server receives data sent from smartphones and stores it in a database. The data processing performed here involves structuring the data as an information set and preparing it to enable efficient searching and access.

[0549] Step 4:

[0550] The server processes stored data in units of analysis. The input to the analysis is stored biometric indicators, and the output generates an exercise deficiency assessment result. It compares this data with other users' data and baseline data, using algorithms to identify specific activity deficiencies or abnormalities.

[0551] Step 5:

[0552] The server creates an optimal exercise plan for the user based on the exercise deficiency assessment results from the analysis unit. The generating AI model receives the exercise deficiency assessment results and user attributes as input and generates a personalized exercise plan as output. The prompt used is, "Please create an effective stretching plan to improve the exercise habits of elderly people."

[0553] Step 6:

[0554] The server sends the generated exercise plan to the smartphone or smartwatch in notification units. The device receives this and notifies the user with a message suggesting specific exercises, such as "How about a walk in the park?"

[0555] Step 7:

[0556] The user reviews the received exercise plan notification and performs the exercise based on it. The device then collects the user's exercise data again and stores it as new data to be used for future analysis.

[0557] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0558] This invention is an innovative system that integrates emotion recognition technology to effectively address users' lack of exercise, and provides a personalized exercise plan that takes into account the user's physical and emotional state. The system consists of sensing means, memory means, analysis means, generation means, notification means, preprocessing means, and an emotion engine.

[0559] Regarding sensing methods, smartwatches and smart rings, acting as terminals, play a role in collecting exercise data such as the user's steps, heart rate, and calories burned. This allows for a detailed understanding of the user's daily activities.

[0560] The emotion engine infers the user's emotional state from their voice tone, facial expressions, or physiological data. It can also directly obtain the user's current emotions through text or voice input. This emotional data is used to determine the user's state of mind while exercising or about to exercise.

[0561] The memory system stores collected motor and emotional data in a database on a server. The server combines and analyzes this data to record the motor and emotional tendencies of individual users.

[0562] As a preprocessing step, the server performs anomaly detection and data normalization to prepare the data for analysis. At this stage, the relationship between emotional data and motor data is also preliminaryly evaluated.

[0563] The analysis method not only compares stored data with other users' exercise data and regional baseline values, but also analyzes emotional data to understand the user's emotional trends. This identifies emotional states that make it easier for a user to exercise, as well as emotional states that act as barriers to exercise.

[0564] The generation method involves an AI agent creating an optimal exercise plan for the user based on the analysis results. Here, the duration and content of the exercise are adjusted based on the user's emotional state; for example, yoga is recommended if the user wants to relax, and running is recommended if they need to relieve stress.

[0565] The notification system promptly informs users of the generated exercise plan. This allows users to confirm the optimal exercise tailored to their emotional state and engage in it with a sense of satisfaction. For example, if a user feels stressed at work, the system can detect this and immediately suggest an exercise plan suitable for stress reduction.

[0566] Based on the above, this system is expected to help users develop exercise habits and contribute to their daily health management. The emotional engine enables users to maintain comprehensive health, taking into account not only their physical but also mental aspects.

[0567] The following describes the processing flow.

[0568] Step 1:

[0569] The device detects the user's daily physical activity in real time through sensors. It continuously collects information such as steps taken, activity time, and heart rate, allowing users to monitor their exercise levels.

[0570] Step 2:

[0571] The device utilizes an emotion engine to detect the user's emotional state. This engine obtains information from voice input, facial recognition, and physiological responses to analyze the user's current emotions. For example, if the user inputs a voice message and says, "I'm a little tired," the device collects that emotional information.

[0572] Step 3:

[0573] The device transmits collected motor and emotional data to the server. The data is encrypted and securely stored in the server's database.

[0574] Step 4:

[0575] The server preprocesses the stored data, detects outliers, and normalizes the data as needed. This provides a clean dataset for analysis.

[0576] Step 5:

[0577] The server analyzes the user's physical activity and emotional state based on pre-processed data. By comparing it with data from other users and baseline values, it identifies areas where physical activity is lacking and elements necessary to elicit positive emotions.

[0578] Step 6:

[0579] Based on the analysis results, the server uses an AI agent to generate an exercise plan. Taking into account the user's emotional state, it recommends yoga or stretching if the user desires relaxation, while suggesting short interval training sessions if the user wants to maintain energy.

[0580] Step 7:

[0581] The server pushes the generated exercise plan to the user's device. This notification is sent at the optimal time, tailored to the user's schedule and emotional state.

[0582] Step 8:

[0583] The user checks the notification and begins the activity according to the suggested exercise plan. After completing the activity, they enter feedback on their device, which is sent to the server and used as a reference for their next exercise plan.

[0584] (Example 2)

[0585] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0586] In modern society, it is well known that lack of exercise has a significant impact on health, but there are limited systems that can provide exercise plans that take into account the physical and emotional state of individual users. Furthermore, it is technically difficult to grasp a user's emotional state in real time and suggest appropriate exercise based on that. Conventional systems have been unable to process emotional and exercise data in an integrated manner, resulting in limited effectiveness in improving users' exercise habits.

[0587] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0588] In this invention, the server includes means for collecting biometric data, means for processing voice and image information to infer emotions, and means for storing the collected and inferred data in an information recording device. This makes it possible to provide an exercise plan optimized for each individual user and to more effectively improve the user's exercise habits.

[0589] A "biometric data collection device" is a device that uses sensors to acquire data such as heart rate, steps taken, and calories burned in order to understand the user's physical condition.

[0590] A "device that processes voice and image information to infer emotions" is a device that analyzes the tone of the user's voice and facial expressions to infer and digitize the user's emotional state.

[0591] "Means of storing information in an information recording device" refers to means of securely recording collected data and storing it for future analysis and comparison.

[0592] A "preprocessing device that detects and normalizes outliers" is a device that removes inappropriate values ​​from collected data and converts it into a standard format suitable for data analysis.

[0593] A "device for comparing with reference values" is a device that compares collected user data with reference data to relatively evaluate the user's activity level and emotional state.

[0594] A "device including an AI agent that generates the optimal exercise plan" is a device with artificial intelligence capabilities that automatically generate the most suitable exercise plan for each individual user based on analyzed data.

[0595] A "device for communicating exercise plans to users" is a device that notifies users of the generated exercise plan and encourages them to perform appropriate exercises.

[0596] This invention is a system that provides an individualized and optimized exercise plan based on an understanding of the user's physical and emotional state. To achieve this, the system consists of multiple devices.

[0597] First, smart devices, such as smartwatches and smart rings, collect biometric data such as the user's heart rate, steps taken, and calories burned. This information is used to record the user's daily activities in detail. The devices also use microphones and cameras to analyze the user's voice tone and facial expressions to infer their emotional state. This data helps to understand the user's emotional state while exercising.

[0598] The collected data is sent to a server and stored in a database. The server preprocesses the data, detects outliers, and normalizes it. It also compares the user's data to baseline values ​​and analyzes motor and emotional tendencies.

[0599] Based on the analyzed information, the server uses a generative AI model to generate an optimal exercise plan suited to the user's emotional state. This AI agent suggests exercises that match the user's emotional state, such as recommending yoga if the user is judged to have a high stress level.

[0600] The generated exercise plan is transmitted from the server to the terminal and notified to the user. The user can then follow this plan and provide feedback to help with future analysis.

[0601] For example, if a user is experiencing work-related stress, the system can detect this stress level and recommend a 30-minute yoga session, which helps the user relax more easily. This system provides support for users to effectively maintain both their physical and mental health.

[0602] An example of a prompt is, "Suggest a new exercise plan based on the user's emotional state." This prompt instructs the generative AI model to create an appropriate exercise plan.

[0603] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0604] Step 1:

[0605] The device collects the user's biometric data. Using sensors equipped on the device, it acquires heart rate, steps taken, and calories burned in real time. This data serves as basic information for understanding the user's activity level. The input is biometric data measured by the device, and the output is data temporarily stored on the device. Specifically, the smartwatch's heart rate sensor measures and records the heart rate every minute.

[0606] Step 2:

[0607] The device uses voice and image information to infer the user's emotions. It analyzes voice tone captured by the microphone and facial expressions captured by the camera to quantify the user's emotional state. The input is the user's voice and image data, and the output is inferred emotion data. For example, when the user says "I'm tired," the voice is recorded and analyzed as emotion data.

[0608] Step 3:

[0609] The device transmits collected biometric and emotional data to a server. Using Bluetooth or Wi-Fi, the data is encrypted and securely uploaded to the server. The input is the biometric and emotional data stored on the device, and the output is the data transferred to the server. Specifically, at the end of the day, the device automatically transmits the collected data to the server.

[0610] Step 4:

[0611] The server continuously saves received data to a database. After saving the data, it performs preprocessing such as detecting anomalies and normalizing the data. The normalized data is a preparatory step for accurately understanding the user's state. The input is biometric and emotional data sent to the server, and the output is normalized, clean data. Specifically, the server processes any detected anomalies in heart rate to bring them back within a specified range.

[0612] Step 5:

[0613] The server analyzes normalized data and compares it to other users and baseline values. This allows for a detailed understanding of the user's exercise and emotional tendencies. The input is normalized data, and the output is the result of the comparative analysis. Specifically, if a user's exercise level is lower than other users, the server generates an analytical report that highlights this fact.

[0614] Step 6:

[0615] The server uses a generative AI model to generate an optimal exercise plan based on the analysis results. It adjusts the exercise content and duration while considering the user's emotional state. The input is comparatively analyzed data, and the output is an exercise plan tailored to the user. For example, for a user with high stress levels, an exercise plan recommending "30 minutes of yoga" is generated.

[0616] Step 7:

[0617] The server sends the generated exercise plan to the device and notifies the user. The user can then receive and execute this plan. The input is the generated exercise plan, and the output is the notification to the user. Specifically, a message with the recommended exercise plan is displayed on the smartwatch's display.

[0618] (Application Example 2)

[0619] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0620] In modern society, a major challenge is that people's health suffers due to a lack of physical activity. Furthermore, since a user's emotional state influences their motivation for physical activity, there is a need for personalized exercise plans. However, there are few existing systems that take emotional states into consideration and provide appropriate exercise plans, resulting in insufficient guidance on effective physical activity tailored to an individual's mental state.

[0621] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0622] In this invention, the server includes a sensor device for collecting the user's physical activity level, a storage device for storing the physical activity level in a data collection device, and an emotion recognition device for estimating the user's emotional state. This makes it possible to create an optimal physical activity plan that reflects the user's physical and emotional state.

[0623] A "sensor device" is a device used to measure and collect a user's physical activity level in real time, and its main role is to acquire movement and physiological data.

[0624] A "storage device" is a device that securely and efficiently stores collected data on physical activity levels, and plays a role in data aggregation.

[0625] An "analysis device" is a device used to analyze collected physical activity data and compare it with data from other users or reference data.

[0626] An "emotion recognition device" is a device that analyzes a user's voice and facial expressions to estimate their emotional state, and is used to understand the mental state of individual users.

[0627] A "generation device" is a device that creates an optimal physical activity plan for a user based on the results of an analysis of their emotional state and physical activity data.

[0628] A "notification device" is a device that informs the user of the generated physical activity plan at the appropriate time, and is responsible for communicating the plan through voice or visual means.

[0629] To implement this invention, a system is constructed that comprehensively analyzes the user's activities and emotional state and provides an optimal physical activity plan. The server plays a central role in this system and functions using various hardware and software.

[0630] The server first collects the user's physical activity data through sensor devices. Wearable devices such as smartwatches and smart rings are used for this purpose. These devices record the user's steps, heart rate, calories burned, and other data in real time.

[0631] Next, the server analyzes the user's emotional state using an emotion recognition device. This process utilizes speech recognition and facial expression analysis technologies. Specifically, it infers emotions from voice tone and facial expressions by analyzing data from high-sensitivity microphones and cameras. Open-source libraries (e.g., OpenCV, DeepFace) are used to improve the accuracy of emotion analysis.

[0632] Once data is collected, the server stores it in memory, and an analysis device performs data cleansing and standardization. Pandas, a Python data analysis library, is used for this data processing. As a result of the cleansing, outliers are removed, allowing for a smooth evaluation of the relationship between emotional state and physical activity levels.

[0633] After analysis, the generation device creates an optimal physical activity plan based on the data. The generated plan is based on the user's emotional state and harmonizes their mental and physical condition. This generation process utilizes AI technology, with the generation AI model adjusting the plan. Prompts such as "Please generate an exercise plan suitable for the user based on today's emotional state and physical fatigue level" are used.

[0634] Finally, the notification device informs the user of the generated plan. This notification is delivered via the robot's voice or display, providing exercise guidance and motivational approaches based on the plan.

[0635] For example, if a user returns home tired from work and the emotion recognition device detects this state, the system can recommend stretching exercises to relax, and a robot can provide guidance. In this way, the system can provide personalized and appropriate physical activity support in a home environment.

[0636] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0637] Step 1:

[0638] The server acquires user physical activity data from the device, such as a smartwatch or smart ring. Inputs include the user's steps, heart rate, and calories burned. This data is temporarily stored and prepared.

[0639] Step 2:

[0640] The server uses an emotion recognition device to analyze the user's emotional state. Inputs include the user's voice data and images captured by the camera. By analyzing these, the server infers emotions from the user's tone of voice and facial expressions. The output is an emotion label such as joy, excitement, or sadness.

[0641] Step 3:

[0642] The server stores the acquired physical activity and emotional data in storage. This process includes detecting outliers, normalizing the data, and processing it into a format suitable for processing. The output is a clean, normalized dataset.

[0643] Step 4:

[0644] The analysis device uses stored data to perform comparative analysis with other user data and reference data. The input consists of the user's normalized data and the comparison data. This comparison evaluates the user's current activity level and emotional state.

[0645] Step 5:

[0646] The server uses a generation device to create an optimal physical activity plan for the user based on the analysis results. To select appropriate exercise content and duration, it uses a generation AI model and employs the prompt message, "Generate an exercise plan suitable for the user based on today's emotional state and physical fatigue level." The output is a personalized exercise plan.

[0647] Step 6:

[0648] The notification device informs the user of the generated exercise plan. The robot verbally communicates the details of the plan to the user and displays the exercise content on the screen. The input is the generated exercise plan, and the robot suggests actions to the user based on this information.

[0649] Step 7:

[0650] The user begins physical activity at home according to the suggested exercise plan. The robot monitors the user and provides assistance and encouragement as needed. This step allows the user to effectively manage their health.

[0651] 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.

[0652] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0653] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0654] [Fourth Embodiment]

[0655] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0656] 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.

[0657] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0658] 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.

[0659] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0660] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0661] 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.

[0662] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0663] 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.

[0664] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0665] The 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.

[0666] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0667] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0668] This invention is a system for addressing the lack of exercise among working adults and is designed for daily use by users. The system mainly consists of sensing means, storage means, analysis means, generation means, notification means, and preprocessing means.

[0669] As a sensing method, smartwatches and smart rings, which are terminals, detect the user's physical activity in real time. This includes pedometers, accelerometers, heart rate sensors, etc., and these sensors record the user's daily exercise data.

[0670] The memory system periodically transmits the collected motion data from the terminal to the server and stores it in a database on the server. This stored data is then used for detailed analysis later on.

[0671] As a preprocessing step, the server reviews the stored data, detects any anomalies, and normalizes the data to prepare it for analysis. This ensures that the data is suitable for input to the analysis tool.

[0672] The analysis is performed on a server and compares stored exercise data with data from other users and national baseline data. This allows the system to assess the user's level of inactivity. This assessment utilizes data such as the average number of steps taken per week and daily activity levels.

[0673] The generation method utilizes these analysis results and uses an AI agent to generate an optimal exercise plan for the user. This exercise plan includes specific details tailored to the user's habits and lifestyle. For example, if the user has time to exercise during their daily commute or at the office, a walking and stretching plan tailored to that will be suggested.

[0674] The notification system sends the aforementioned exercise plan to the user's smart device. A push notification is sent to the device, allowing the user to check it and begin their exercise. For example, a specific plan such as "We recommend a 20-minute run today" might be displayed.

[0675] For example, if a user tends to be less active on weekends, the server will detect this and suggest increasing their exercise during the weekend. Furthermore, if a user has had a busy week with few opportunities for exercise, the server can recommend light exercises or stretches that can be done at home.

[0676] By combining these methods, users can easily manage their daily exercise habits and receive assistance in maintaining their health. As a result, an environment is provided where even busy working adults can easily overcome a lack of exercise.

[0677] The following describes the processing flow.

[0678] Step 1:

[0679] The device is worn on the user's body and collects exercise data such as steps, heart rate, and calories burned in real time. This allows for a detailed record of the user's daily activity level.

[0680] Step 2:

[0681] The device transmits the collected exercise data to the server at regular intervals. For security reasons, this transmission is encrypted and carried out over the internet.

[0682] Step 3:

[0683] The server stores the received motion data in a database. Here, the stored data is organized for later analysis and comparison.

[0684] Step 4:

[0685] The server preprocesses the stored motion data, detects outliers, and normalizes the data. This ensures the accuracy of the data before it is passed to the analysis tools.

[0686] Step 5:

[0687] The server starts comparing normalized exercise data with data from other users and regional baselines. Through this comparison, if a user's exercise level is lower than the baseline, the server identifies the deficit.

[0688] Step 6:

[0689] Based on the analysis results, the server's AI agent generates an exercise plan optimized for the user. This plan proposes exercises that take into account the user's lifestyle and health condition.

[0690] Step 7:

[0691] The server pushes the generated exercise plan to the user's device. The user receives this notification and can easily understand and perform the specific exercise activities.

[0692] Step 8:

[0693] The user performs the exercise according to the exercise plan received from the server. The user then records the exercise status again on their device and sends feedback based on that data to the server.

[0694] (Example 1)

[0695] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0696] In modern society, lack of exercise is a chronic problem, especially among working adults. This lack of exercise negatively impacts health, and there is a need for the development of specific and personalized plans for effective exercise. Conventional technologies lack systems that can provide exercise plans tailored to each user, making it difficult to effectively encourage exercise habits.

[0697] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0698] In this invention, the server includes a sensor unit that measures the user's physical activity level, a storage unit that stores the activity level in a recording device, and an analysis unit that compares the activity level with standard data. This makes it possible to individually create and notify the user of a physical activity plan that is suitable for them.

[0699] The "sensor unit" is a device used to measure the user's physical activity level and can acquire data such as steps, heart rate, and acceleration.

[0700] The "storage unit" is a device that records and stores measured physical activity data, and functions as a database or storage device.

[0701] The "analysis unit" is a device that compares stored physical activity data with standard data to evaluate the user's level of physical inactivity and activity trends.

[0702] The "creation unit" is a device that generates a physical activity plan suitable for the user based on the evaluation results obtained from the analysis unit, and it uses an AI agent to perform personalized planning.

[0703] The "notification unit" is a device that transmits the physical activity plan generated by the creation unit to the user in an appropriate manner, such as by sending push notifications to smart devices.

[0704] This invention is a system designed to address the lack of exercise among working adults and is designed for daily use by users. This system mainly consists of a sensor unit, a storage unit, an analysis unit, a creation unit, and a notification unit.

[0705] First, the sensor unit will utilize a smartwatch or smart ring, which will act as a terminal. This terminal will detect the user's physical activity in real time. For example, it will collect the user's daily exercise data using a pedometer, accelerometer, and heart rate sensor.

[0706] Next, the storage unit periodically sends the motion data collected from the terminal to the server and stores it in a database on the server. This allows for the accumulation of data necessary for later analysis.

[0707] The analysis unit runs on a server and evaluates the user's level of inactivity by comparing stored exercise data with standard data. This evaluation enables appropriate analysis tailored to the user's current situation.

[0708] Subsequently, the creation department uses an AI agent based on the analysis results to generate an optimal physical activity plan for the user. This plan is tailored to the user's lifestyle and daily activities. For example, if the user's life revolves around desk work, the plan can suggest walking during lunch breaks and stretching after returning home.

[0709] Finally, the notification unit sends the created physical activity plan as a push notification to the user's smart device. The user can then review this notification and engage in the suggested exercise. An example of the notification content is a specific plan such as, "We recommend a 20-minute walk before you head home today."

[0710] For example, if a user tends to be less active on weekends, the server will detect this and suggest a plan to increase their exercise during the weekend. It can also recommend light exercises or stretches that can be done at home during weeks when exercise opportunities are limited due to consecutive commitments.

[0711] An example of a prompt for the generating AI model would be: "Based on this week's exercise data, please create a specific exercise plan for next week. Please take into account the user's activity patterns and weekend time, and include suggestions for outdoor walking and indoor stretching."

[0712] In this way, the system analyzes the user's daily exercise habits in detail and provides effective and easy-to-follow exercise plans, helping to alleviate a lack of exercise even in busy lifestyles.

[0713] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0714] Step 1:

[0715] Data collection

[0716] The device detects the user's physical activity in real time using a smartwatch or smart ring. The input here is raw data related to body movement (e.g., acceleration, steps, heart rate, etc.). The device collects this data through sensors and outputs basic exercise data that indicates the user's exercise status.

[0717] Step 2:

[0718] Data transmission

[0719] The device transmits collected exercise data to the server at regular intervals. The input for this step is the collected exercise data. The device transmits the data to the server using Wi-Fi or Bluetooth, and the server confirms receipt of the data. The output is the user-specific exercise data stored on the server.

[0720] Step 3:

[0721] Data storage

[0722] The server stores the received exercise data in a database. The input is the exercise data sent from the terminal. The server organizes this data by user and indexes it for quick access in subsequent processes. The output is the exercise data in the well-organized database.

[0723] Step 4:

[0724] Data preprocessing

[0725] The server reviews the motion data in the database, detecting and normalizing outliers. The input is the stored raw motion data. The server uses statistical methods to identify outliers and correct them to within the normal range. The output is the normalized data with the anomalies corrected.

[0726] Step 5:

[0727] Data Analysis

[0728] The server analyzes normalized data and compares the user's level of exercise inactivity with data from other users and baseline data. The input is normalized exercise data. An AI model is used for analysis to quantify the user's daily activity level and exercise quality. The output is an evaluation of the specific exercise status.

[0729] Step 6:

[0730] Activity plan generation

[0731] The server uses the evaluation results and an AI agent to generate an exercise plan tailored to the user. The input is the evaluation results based on data analysis. The server also considers the user's profile information to create appropriate exercise suggestions (e.g., step goals, stretching recommendations, etc.). The output is an exercise plan tailored to the user's lifestyle.

[0732] Step 7:

[0733] notification

[0734] The server sends the generated exercise plan to the user's smart device. The input is the generated exercise plan. The server forwards the plan as a push notification for the user to review. The output is the possible actions the user can take based on the notified exercise plan.

[0735] (Application Example 1)

[0736] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0737] In today's aging society, the negative health effects of lack of exercise among the elderly are a serious problem. The elderly tend to have fewer opportunities for exercise, making it difficult to establish a regular exercise routine. Therefore, there is a need for effective and simple methods to promote exercise and support health maintenance based on individual health conditions.

[0738] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0739] In this invention, the server includes a measurement unit for collecting the user's biometric indicators, a storage unit for storing the biometric indicators in an information set, and an analysis unit for comparing the biometric indicators with the health data or reference data of other users. This makes it possible to generate exercise plans tailored to the health status of individual elderly people and to easily form exercise habits.

[0740] "Biometric indicators" refer to data that indicates an individual's health status, including information such as heart rate, steps taken, and activity level.

[0741] A "measurement unit" refers to a system that includes devices and sensors that detect and collect a user's biometric indicators.

[0742] An "information collection" refers to a database or storage system used to organize and store collected data.

[0743] A "memory unit" is a function that includes the structure and processes for storing data in an information set.

[0744] An "analysis unit" is a mechanism that performs processing to evaluate the status of individual users based on stored data and compare it with other users and reference data.

[0745] A "generated unit" refers to a function that includes the process and algorithms for creating an optimal exercise plan for the user based on the analysis results.

[0746] A "notification unit" is a means of communicating the generated exercise plan to the user, and includes notifications and alerts to the device.

[0747] A "proposal unit" refers to a structure or process for making specific suggestions for exercise and lifestyle improvements to maintain the health of the elderly.

[0748] An "inference agent" is a type of artificial intelligence that uses user attribute information to provide individually optimized advice and plans.

[0749] This invention uses a smartwatch or smartphone as a terminal to collect the user's biometric data. The smartwatch measures heart rate, steps, acceleration, etc., in real time and transmits the data to the smartphone. The smartphone temporarily stores this data and transmits it to a server via the internet.

[0750] The server stores the received data in the form of an information set. Next, the analysis unit compares the data with other users' health data and baseline data to detect insufficient exercise or abnormal trends. The generation unit utilizes these analysis results to generate an exercise plan optimized for each individual user. Using a generation AI model, it creates a specific and actionable plan to address the detected lack of exercise.

[0751] Once an exercise plan is created, the notification unit sends a notification to the user's smartphone or smartwatch, prompting them to perform specific exercises. The suggestion unit recommends simple stretches, indoor exercises, and walks, aimed at maintaining the health of older adults.

[0752] For example, if an elderly user's weekly activity level is detected to be below a certain threshold, a plan is created for them to take a 30-minute walk in a nearby park on the weekend. This plan is notified to the smartwatch and displayed with the message, "How about a walk in the park? It can have positive health benefits."

[0753] Examples of prompts include, "Generate suggestions for indoor exercises that are easy for seniors to perform," and "Create an effective stretching plan to improve seniors' exercise habits." These prompts can be input into the AI ​​model to create exercise plans tailored to individual needs.

[0754] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0755] Step 1:

[0756] The device continuously measures the user's biometrics using a smartwatch. These biometric inputs include heart rate, steps, and accelerometer data. This data is temporarily stored within the device and updated in real time.

[0757] Step 2:

[0758] The device transmits the collected biometric data to the smartphone. The smartphone receives this data and performs preprocessing to standardize the data format. It then prepares this standardized data to send to the server.

[0759] Step 3:

[0760] The server receives data sent from smartphones and stores it in a database. The data processing performed here involves structuring the data as an information set and preparing it to enable efficient searching and access.

[0761] Step 4:

[0762] The server processes stored data in units of analysis. The input to the analysis is stored biometric indicators, and the output generates an exercise deficiency assessment result. It compares this data with other users' data and baseline data, using algorithms to identify specific activity deficiencies or abnormalities.

[0763] Step 5:

[0764] The server creates an optimal exercise plan for the user based on the exercise deficiency assessment results from the analysis unit. The generating AI model receives the exercise deficiency assessment results and user attributes as input and generates a personalized exercise plan as output. The prompt used is, "Please create an effective stretching plan to improve the exercise habits of elderly people."

[0765] Step 6:

[0766] The server sends the generated exercise plan to the smartphone or smartwatch in notification units. The device receives this and notifies the user with a message suggesting specific exercises, such as "How about a walk in the park?"

[0767] Step 7:

[0768] The user reviews the received exercise plan notification and performs the exercise based on it. The device then collects the user's exercise data again and stores it as new data to be used for future analysis.

[0769] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0770] This invention is an innovative system that integrates emotion recognition technology to effectively address users' lack of exercise, and provides a personalized exercise plan that takes into account the user's physical and emotional state. The system consists of sensing means, memory means, analysis means, generation means, notification means, preprocessing means, and an emotion engine.

[0771] Regarding sensing methods, smartwatches and smart rings, acting as terminals, play a role in collecting exercise data such as the user's steps, heart rate, and calories burned. This allows for a detailed understanding of the user's daily activities.

[0772] The emotion engine infers the user's emotional state from their voice tone, facial expressions, or physiological data. It can also directly obtain the user's current emotions through text or voice input. This emotional data is used to determine the user's state of mind while exercising or about to exercise.

[0773] The memory system stores collected motor and emotional data in a database on a server. The server combines and analyzes this data to record the motor and emotional tendencies of individual users.

[0774] As a preprocessing step, the server performs anomaly detection and data normalization to prepare the data for analysis. At this stage, the relationship between emotional data and motor data is also preliminaryly evaluated.

[0775] The analysis method not only compares stored data with other users' exercise data and regional baseline values, but also analyzes emotional data to understand the user's emotional trends. This identifies emotional states that make it easier for a user to exercise, as well as emotional states that act as barriers to exercise.

[0776] The generation method involves an AI agent creating an optimal exercise plan for the user based on the analysis results. Here, the duration and content of the exercise are adjusted based on the user's emotional state; for example, yoga is recommended if the user wants to relax, and running is recommended if they need to relieve stress.

[0777] The notification system promptly informs users of the generated exercise plan. This allows users to confirm the optimal exercise tailored to their emotional state and engage in it with a sense of satisfaction. For example, if a user feels stressed at work, the system can detect this and immediately suggest an exercise plan suitable for stress reduction.

[0778] Based on the above, this system is expected to help users develop exercise habits and contribute to their daily health management. The emotional engine enables users to maintain comprehensive health, taking into account not only their physical but also mental aspects.

[0779] The following describes the processing flow.

[0780] Step 1:

[0781] The device detects the user's daily physical activity in real time through sensors. It continuously collects information such as steps taken, activity time, and heart rate, allowing users to monitor their exercise levels.

[0782] Step 2:

[0783] The device utilizes an emotion engine to detect the user's emotional state. This engine obtains information from voice input, facial recognition, and physiological responses to analyze the user's current emotions. For example, if the user inputs a voice message and says, "I'm a little tired," the device collects that emotional information.

[0784] Step 3:

[0785] The device transmits collected motor and emotional data to the server. The data is encrypted and securely stored in the server's database.

[0786] Step 4:

[0787] The server preprocesses the stored data, detects outliers, and normalizes the data as needed. This provides a clean dataset for analysis.

[0788] Step 5:

[0789] The server analyzes the user's physical activity and emotional state based on pre-processed data. By comparing it with data from other users and baseline values, it identifies areas where physical activity is lacking and elements necessary to elicit positive emotions.

[0790] Step 6:

[0791] Based on the analysis results, the server uses an AI agent to generate an exercise plan. Taking into account the user's emotional state, it recommends yoga or stretching if the user desires relaxation, while suggesting short interval training sessions if the user wants to maintain energy.

[0792] Step 7:

[0793] The server pushes the generated exercise plan to the user's device. This notification is sent at the optimal time, tailored to the user's schedule and emotional state.

[0794] Step 8:

[0795] The user checks the notification and begins the activity according to the suggested exercise plan. After completing the activity, they enter feedback on their device, which is sent to the server and used as a reference for their next exercise plan.

[0796] (Example 2)

[0797] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0798] In modern society, it is well known that lack of exercise has a significant impact on health, but there are limited systems that can provide exercise plans that take into account the physical and emotional state of individual users. Furthermore, it is technically difficult to grasp a user's emotional state in real time and suggest appropriate exercise based on that. Conventional systems have been unable to process emotional and exercise data in an integrated manner, resulting in limited effectiveness in improving users' exercise habits.

[0799] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0800] In this invention, the server includes means for collecting biometric data, means for processing voice and image information to infer emotions, and means for storing the collected and inferred data in an information recording device. This makes it possible to provide an exercise plan optimized for each individual user and to more effectively improve the user's exercise habits.

[0801] A "biometric data collection device" is a device that uses sensors to acquire data such as heart rate, steps taken, and calories burned in order to understand the user's physical condition.

[0802] A "device that processes voice and image information to infer emotions" is a device that analyzes the tone of the user's voice and facial expressions to infer and digitize the user's emotional state.

[0803] "Means of storing information in an information recording device" refers to means of securely recording collected data and storing it for future analysis and comparison.

[0804] A "preprocessing device that detects and normalizes outliers" is a device that removes inappropriate values ​​from collected data and converts it into a standard format suitable for data analysis.

[0805] A "device for comparing with reference values" is a device that compares collected user data with reference data to relatively evaluate the user's activity level and emotional state.

[0806] A "device including an AI agent that generates the optimal exercise plan" is a device with artificial intelligence capabilities that automatically generate the most suitable exercise plan for each individual user based on analyzed data.

[0807] A "device for communicating exercise plans to users" is a device that notifies users of the generated exercise plan and encourages them to perform appropriate exercises.

[0808] This invention is a system that provides an individualized and optimized exercise plan based on an understanding of the user's physical and emotional state. To achieve this, the system consists of multiple devices.

[0809] First, smart devices, such as smartwatches and smart rings, collect biometric data such as the user's heart rate, steps taken, and calories burned. This information is used to record the user's daily activities in detail. The devices also use microphones and cameras to analyze the user's voice tone and facial expressions to infer their emotional state. This data helps to understand the user's emotional state while exercising.

[0810] The collected data is sent to a server and stored in a database. The server preprocesses the data, detects outliers, and normalizes it. It also compares the user's data to baseline values ​​and analyzes motor and emotional tendencies.

[0811] Based on the analyzed information, the server uses a generative AI model to generate an optimal exercise plan suited to the user's emotional state. This AI agent suggests exercises that match the user's emotional state, such as recommending yoga if the user is judged to have a high stress level.

[0812] The generated exercise plan is transmitted from the server to the terminal and notified to the user. The user can then follow this plan and provide feedback to help with future analysis.

[0813] For example, if a user is experiencing work-related stress, the system can detect this stress level and recommend a 30-minute yoga session, which helps the user relax more easily. This system provides support for users to effectively maintain both their physical and mental health.

[0814] An example of a prompt is, "Suggest a new exercise plan based on the user's emotional state." This prompt instructs the generative AI model to create an appropriate exercise plan.

[0815] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0816] Step 1:

[0817] The device collects the user's biometric data. Using sensors equipped on the device, it acquires heart rate, steps taken, and calories burned in real time. This data serves as basic information for understanding the user's activity level. The input is biometric data measured by the device, and the output is data temporarily stored on the device. Specifically, the smartwatch's heart rate sensor measures and records the heart rate every minute.

[0818] Step 2:

[0819] The device uses voice and image information to infer the user's emotions. It analyzes voice tone captured by the microphone and facial expressions captured by the camera to quantify the user's emotional state. The input is the user's voice and image data, and the output is inferred emotion data. For example, when the user says "I'm tired," the voice is recorded and analyzed as emotion data.

[0820] Step 3:

[0821] The device transmits collected biometric and emotional data to a server. Using Bluetooth or Wi-Fi, the data is encrypted and securely uploaded to the server. The input is the biometric and emotional data stored on the device, and the output is the data transferred to the server. Specifically, at the end of the day, the device automatically transmits the collected data to the server.

[0822] Step 4:

[0823] The server continuously saves received data to a database. After saving the data, it performs preprocessing such as detecting anomalies and normalizing the data. The normalized data is a preparatory step for accurately understanding the user's state. The input is biometric and emotional data sent to the server, and the output is normalized, clean data. Specifically, the server processes any detected anomalies in heart rate to bring them back within a specified range.

[0824] Step 5:

[0825] The server analyzes normalized data and compares it to other users and baseline values. This allows for a detailed understanding of the user's exercise and emotional tendencies. The input is normalized data, and the output is the result of the comparative analysis. Specifically, if a user's exercise level is lower than other users, the server generates an analytical report that highlights this fact.

[0826] Step 6:

[0827] The server uses a generative AI model to generate an optimal exercise plan based on the analysis results. It adjusts the exercise content and duration while considering the user's emotional state. The input is comparatively analyzed data, and the output is an exercise plan tailored to the user. For example, for a user with high stress levels, an exercise plan recommending "30 minutes of yoga" is generated.

[0828] Step 7:

[0829] The server sends the generated exercise plan to the device and notifies the user. The user can then receive and execute this plan. The input is the generated exercise plan, and the output is the notification to the user. Specifically, a message with the recommended exercise plan is displayed on the smartwatch's display.

[0830] (Application Example 2)

[0831] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0832] In modern society, a major challenge is that people's health suffers due to a lack of physical activity. Furthermore, since a user's emotional state influences their motivation for physical activity, there is a need for personalized exercise plans. However, there are few existing systems that take emotional states into consideration and provide appropriate exercise plans, resulting in insufficient guidance on effective physical activity tailored to an individual's mental state.

[0833] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0834] In this invention, the server includes a sensor device for collecting the user's physical activity level, a storage device for storing the physical activity level in a data collection device, and an emotion recognition device for estimating the user's emotional state. This makes it possible to create an optimal physical activity plan that reflects the user's physical and emotional state.

[0835] A "sensor device" is a device used to measure and collect a user's physical activity level in real time, and its main role is to acquire movement and physiological data.

[0836] A "storage device" is a device that securely and efficiently stores collected data on physical activity levels, and plays a role in data aggregation.

[0837] An "analysis device" is a device used to analyze collected physical activity data and compare it with data from other users or reference data.

[0838] An "emotion recognition device" is a device that analyzes a user's voice and facial expressions to estimate their emotional state, and is used to understand the mental state of individual users.

[0839] A "generation device" is a device that creates an optimal physical activity plan for a user based on the results of an analysis of their emotional state and physical activity data.

[0840] A "notification device" is a device that informs the user of the generated physical activity plan at the appropriate time, and is responsible for communicating the plan through voice or visual means.

[0841] To implement this invention, a system is constructed that comprehensively analyzes the user's activities and emotional state and provides an optimal physical activity plan. The server plays a central role in this system and functions using various hardware and software.

[0842] The server first collects the user's physical activity data through sensor devices. Wearable devices such as smartwatches and smart rings are used for this purpose. These devices record the user's steps, heart rate, calories burned, and other data in real time.

[0843] Next, the server analyzes the user's emotional state using an emotion recognition device. This process utilizes speech recognition and facial expression analysis technologies. Specifically, it infers emotions from voice tone and facial expressions by analyzing data from high-sensitivity microphones and cameras. Open-source libraries (e.g., OpenCV, DeepFace) are used to improve the accuracy of emotion analysis.

[0844] Once data is collected, the server stores it in memory, and an analysis device performs data cleansing and standardization. Pandas, a Python data analysis library, is used for this data processing. As a result of the cleansing, outliers are removed, allowing for a smooth evaluation of the relationship between emotional state and physical activity levels.

[0845] After analysis, the generation device creates an optimal physical activity plan based on the data. The generated plan is based on the user's emotional state and harmonizes their mental and physical condition. This generation process utilizes AI technology, with the generation AI model adjusting the plan. Prompts such as "Please generate an exercise plan suitable for the user based on today's emotional state and physical fatigue level" are used.

[0846] Finally, the notification device informs the user of the generated plan. This notification is delivered via the robot's voice or display, providing exercise guidance and motivational approaches based on the plan.

[0847] For example, if a user returns home tired from work and the emotion recognition device detects this state, the system can recommend stretching exercises to relax, and a robot can provide guidance. In this way, the system can provide personalized and appropriate physical activity support in a home environment.

[0848] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0849] Step 1:

[0850] The server acquires user physical activity data from the device, such as a smartwatch or smart ring. Inputs include the user's steps, heart rate, and calories burned. This data is temporarily stored and prepared.

[0851] Step 2:

[0852] The server uses an emotion recognition device to analyze the user's emotional state. Inputs include the user's voice data and images captured by the camera. By analyzing these, the server infers emotions from the user's tone of voice and facial expressions. The output is an emotion label such as joy, excitement, or sadness.

[0853] Step 3:

[0854] The server stores the acquired physical activity and emotional data in storage. This process includes detecting outliers, normalizing the data, and processing it into a format suitable for processing. The output is a clean, normalized dataset.

[0855] Step 4:

[0856] The analysis device uses stored data to perform comparative analysis with other user data and reference data. The input consists of the user's normalized data and the comparison data. This comparison evaluates the user's current activity level and emotional state.

[0857] Step 5:

[0858] The server uses a generation device to create an optimal physical activity plan for the user based on the analysis results. To select appropriate exercise content and duration, it uses a generation AI model and employs the prompt message, "Generate an exercise plan suitable for the user based on today's emotional state and physical fatigue level." The output is a personalized exercise plan.

[0859] Step 6:

[0860] The notification device informs the user of the generated exercise plan. The robot verbally communicates the details of the plan to the user and displays the exercise content on the screen. The input is the generated exercise plan, and the robot suggests actions to the user based on this information.

[0861] Step 7:

[0862] The user begins physical activity at home according to the suggested exercise plan. The robot monitors the user and provides assistance and encouragement as needed. This step allows the user to effectively manage their health.

[0863] 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.

[0864] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0865] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0866] 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.

[0867] Figure 9 shows an 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.

[0868] 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.

[0869] 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.

[0870] 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, motorcycles, etc., 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, for example, based 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.

[0871] 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."

[0872] 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.

[0873] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0874] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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 the like 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.

[0883] 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.

[0884] The following is further disclosed regarding the embodiments described above.

[0885] (Claim 1)

[0886] A sensing means for collecting user movement data,

[0887] A storage means for storing the aforementioned momentum in a database,

[0888] An analysis means for comparing the aforementioned amount of movement with the movement data of other users or reference data,

[0889] A generation means for generating an optimal exercise plan for the user based on the comparison results,

[0890] A notification means for notifying the user of the generated exercise plan,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, further comprising preprocessing means for detecting abnormal values ​​in the user's exercise data and normalizing the data.

[0894] (Claim 3)

[0895] The system according to claim 1, comprising an AI agent for optimizing an exercise plan taking into account the user's profile information.

[0896] "Example 1"

[0897] (Claim 1)

[0898] A sensor unit that measures the user's physical activity level,

[0899] A storage unit that stores the aforementioned activity levels in a recording device,

[0900] An analysis unit that compares the aforementioned activity level with standard data,

[0901] A creation unit that creates a physical activity plan suitable for the user based on the aforementioned matching results,

[0902] A notification unit that sends the aforementioned physical activity plan to the user,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, further comprising an adjustment unit that recognizes abnormal values ​​in the user's physical activity data and standardizes the data.

[0906] (Claim 3)

[0907] The system according to claim 1, comprising an intelligent agent for improving physical activity suggestions while taking into account the user's personal information.

[0908] "Application Example 1"

[0909] (Claim 1)

[0910] The unit of measurement for collecting user biometric indicators,

[0911] A memory unit that stores the aforementioned biometric indicators in an information set,

[0912] An analysis unit that compares the aforementioned biometric indicators with the health data or reference data of other users,

[0913] A generation unit that generates an optimal exercise plan for the user based on the comparison results,

[0914] A notification unit that notifies the user of the generated exercise plan,

[0915] A proposal unit that includes recommendations for exercise aimed at maintaining the health of the elderly,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, further comprising a preprocessing unit for detecting abnormal values ​​in the user's exercise data and normalizing the data.

[0919] (Claim 3)

[0920] The system according to claim 1, comprising an inference agent for optimizing an exercise plan by taking user attribute information into consideration, thereby supporting the health management of the elderly.

[0921] "Example 2 of combining an emotion engine"

[0922] (Claim 1)

[0923] A device for collecting biometric data,

[0924] A device that processes audio and image information to infer emotions,

[0925] A device for storing the collected and estimated data in an information recording device,

[0926] A device that preprocesses the aforementioned data and detects and normalizes abnormal values,

[0927] A device for analyzing the normalized data and comparing it with a reference value,

[0928] A device including an AI agent that generates an optimal exercise plan based on the user's emotional state,

[0929] A device for communicating the aforementioned exercise plan to the user,

[0930] A system that includes this.

[0931] (Claim 2)

[0932] The system according to claim 1, further comprising a device that provides an exercise plan generated based on the user's movements.

[0933] (Claim 3)

[0934] The system according to claim 1, comprising a device for generating an exercise plan suitable for an emotional state using a generative AI model.

[0935] "Application example 2 when combining with an emotional engine"

[0936] (Claim 1)

[0937] A sensor device that collects the user's physical activity level,

[0938] A storage device for storing the aforementioned physical activity levels in a data collection device,

[0939] An analysis device that compares the aforementioned physical activity data with the activity data or reference data of other users,

[0940] An emotion recognition device that estimates the user's emotional state,

[0941] A generating device that creates an optimal physical activity plan for the user based on the aforementioned emotional state and comparison results,

[0942] A notification device that informs the user of the physical activity plan created above,

[0943] A system that includes this.

[0944] (Claim 2)

[0945] The system according to claim 1, further comprising a preprocessing device that detects abnormal values ​​in the user's physical activity data and normalizes the data, and provides guidance on physical activity based on the emotional state.

[0946] (Claim 3)

[0947] The system according to claim 1, comprising an artificial intelligence agent that optimizes a physical activity plan by taking into account the user's personal information and utilizing emotion recognition information. [Explanation of symbols]

[0948] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A sensing means for collecting user movement data, A storage means for storing the aforementioned momentum in a database, An analysis means for comparing the aforementioned amount of movement with the movement data of other users or reference data, A generation means for generating an optimal exercise plan for the user based on the comparison results, A notification means for notifying the user of the generated exercise plan, A system that includes this.

2. The system according to claim 1, further comprising preprocessing means for detecting abnormal values ​​in the user's exercise data and normalizing the data.

3. The system according to claim 1, comprising an AI agent for optimizing an exercise plan taking into account the user's profile information.

Images