System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving body composition data and basal physical performance data entered by a user; means for analyzing the entered data and generating a recommendation list for recommending an exercise program suitable for the user based on an analysis result; and means for displaying the recommendation list to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Finding the optimal way to continue exercising or playing sports is a difficult challenge for many users, both young and old. Young people, in particular, often quit sports due to poor performance or a sense of frustration, while older people have difficulty finding an appropriate exercise program to maintain their health. To solve these problems, there is a need for a system that can automatically suggest optimal exercise programs based on a user's body composition data, basic physical ability data, interests, etc. [Means for solving the problem]

[0005] The present invention provides a system including: means for receiving body composition data and basic physical ability data input by a user; means for analyzing the input data and generating a recommendation list for recommending an exercise program suitable for the user based on the analysis results; and means for displaying the recommendation list to the user. The system further includes means for cleansing the input data and supplementing inaccurate or missing data, and means for receiving user feedback regarding an exercise program attempted based on the recommendation list and improving the recommendation algorithm based on the feedback, thereby enabling the provision of a more suitable and lasting exercise program to the user.

[0006] "User" refers to an individual who uses the system to input body composition data and basic physical ability data and receives suggestions for an optimal exercise program.

[0007] "Body composition data" is numerical information relating to the user's body, specifically data including height, weight, body fat percentage, and the like.

[0008] "Basic physical ability data" is information about the user's physical ability, specifically data including grip strength, endurance test results, flexibility test results, and the like.

[0009] "Analysis" means processing data using mathematical and logical methods to recommend an optimal exercise program based on the body composition data and basic physical ability data received from the user.

[0010] The "recommended list" is a list that specifically lists exercise programs and sports that are suitable for the user based on the analysis results.

[0011] "Display" refers to visually presenting the generated recommendation list to the user.

[0012] "Cleansing" refers to the process of detecting inaccurate or missing values ​​from input data and correcting or completing them.

[0013] "Feedback" refers to the user providing the system with their thoughts, satisfaction, and opinions on areas for improvement after implementing the proposed exercise program.

[0014] An "algorithm" is a defined set of procedures or calculations for analyzing input data and recommending an appropriate exercise program. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The system of the present invention receives and analyzes a user's body composition data and basic physical ability data, and recommends an optimal exercise program. The specific processing flow of the program of this system will be explained below in natural language.

[0037] User data input phase

[0038] The user accesses the system using a terminal. The terminal displays a user interface, prompting the user to enter body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter information about their interests and sports. This data is used in subsequent analysis steps, so it is important that it is entered accurately.

[0039] Data transmission phase

[0040] The data entered by the user is sent by the terminal to the server. The terminal formats the data to be sent and sends it to the server using a secure communication protocol. The server receives the data at a receiving port and stores it in an internal database.

[0041] Data Preprocessing Phase

[0042] The server cleanses the received data and fills in inaccurate data or missing values. For example, if the weight or height value is clearly abnormal, it fills in the data using past data or average values. This ensures the quality of the data used for analysis.

[0043] Data analysis phase

[0044] The server then uses the cleansed data for the actual analysis, applying machine learning algorithms and statistical methods to create models to recommend optimal exercise programs for users. Based on the analysis results, the server identifies the sports and exercise programs that best suit the user's body composition and basic physical abilities.

[0045] Recommendation List Generation Phase

[0046] Based on the analysis results, the server generates a list of recommended exercise programs and sports that are optimal for the user. This list also includes detailed descriptions of each sport and the reasons why that sport is suitable for the user. The generated recommendation list is then saved in a database in JSON format or similar.

[0047] Result display phase

[0048] The server sends the generated recommendation list to the device. The device displays the received recommendation list on the user interface, allowing the user to easily understand and select. Specific explanations of each exercise program and the reasons for its recommendation are provided in detail.

[0049] User Feedback Phase

[0050] After the user practices the proposed exercise program, they provide feedback on their impressions and satisfaction with the program. The device then sends this feedback to the server, which uses it to improve the recommendation algorithm.

[0051] As a concrete example, let's say a 14-year-old junior high school student is 160 cm tall, weighs 50 kg, and has a body fat percentage of 15%. If this user inputs their 100m sprint time and their interest in basketball, the server will use this data to recommend three events: track and field (especially sprinting), basketball, and soccer. The user can then select and execute an exercise program that suits them based on this list, and receive feedback afterwards.

[0052] In this way, this system automates a series of processes, from receiving user data to generating and presenting optimal exercise programs, and even improving the algorithm based on feedback, helping users establish exercise habits.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The user starts the application and accesses a screen for entering body composition data and basic physical ability data, including height, weight, body fat percentage, grip strength, endurance test results, flexibility test results, and sports of interest.

[0056] Step 2:

[0057] The terminal receives data entered by the user, converts it into an internal format, formats the converted data, and sends it to the server using a secure communication protocol.

[0058] Step 3:

[0059] The server receives the data at the receiving port and saves it in the database. The received data is stored in a temporary table and prepared for data analysis.

[0060] Step 4:

[0061] The server cleanses the data it receives, detects outliers and missing values, and imputes them as needed using historical data or averages, and then formats the cleansed data for analysis.

[0062] Step 5:

[0063] The server then applies machine learning algorithms to the cleansed data, using techniques such as clustering and recommender systems to analyze the exercise program and sport that best suits the user.

[0064] Step 6:

[0065] Based on the analysis results, the server generates a list of recommendations for exercise programs and sports that are optimal for the user, including detailed descriptions of each sport and the reasons for its recommendation.

[0066] Step 7:

[0067] The server converts the generated recommendation list into JSON or another appropriate data format and sends it to the device.

[0068] Step 8:

[0069] The device analyzes the received recommendation list and displays it on the user interface, allowing the user to confirm the suggested exercise programs and sports.

[0070] Step 9:

[0071] After the user has completed the proposed exercise program, they can input their impressions and satisfaction level through the feedback screen. The input feedback data is sent to the server via the device.

[0072] Step 10:

[0073] The server analyzes the received feedback data and stores it for algorithm refinement. The next analysis will use this feedback to improve accuracy.

[0074] The above is the specific processing flow of the system of the present invention. This series of steps allows the user to continuously carry out an optimal exercise program, which can help maintain health and improve sports performance.

[0075] Example 1

[0076] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0077] In modern health management, it is important to provide optimal exercise programs for individual users, but accurately analyzing the user's body composition data and basic physical ability data to generate an appropriate recommendation list is a challenge. In addition, it is necessary to supplement inaccurate or missing data and reflect user feedback to continuously improve the recommendation algorithm.

[0078] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0079] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for transmitting the input data to the server using a secure communication protocol, means for storing the transmitted data in an internal database and cleansing it to supplement inaccurate or missing data, means for analyzing the cleansed data using a machine learning algorithm and generating a recommendation list for recommending exercise programs suitable for the user based on the analysis results, means for displaying the recommendation list to the user, and means for receiving user feedback on exercise programs attempted based on the recommendation list and improving the recommendation algorithm based on the feedback. This makes it possible to provide each user with a highly accurate exercise program and to supplement inaccurate data and improve the algorithm based on the feedback.

[0080] "Body composition data" refers to basic data about the user's body, including height, weight, body fat percentage, and the like.

[0081] "Basic physical ability data" is data that indicates the user's basic physical strength and athletic ability, and includes grip strength, endurance test results, flexibility test results, and the like.

[0082] A "secure communication protocol" is a protocol that ensures security when sending and receiving data, and HTTPS is an example of this.

[0083] "Server" refers to a computer system that receives, stores, analyzes data, and provides information to users.

[0084] The "internal database" is a data storage system installed within the server for storing received data and analysis results.

[0085] "Cleansing" refers to the process of correcting inaccurate data and filling in missing values ​​in order to improve data quality.

[0086] "Machine learning algorithms" are artificial intelligence techniques used to analyze data and find patterns and trends, such as random forests and support vector machines.

[0087] The "recommended list" refers to a list of exercise programs and sports that are optimal for the user, generated based on the analysis results.

[0088] "User interface" refers to the screen and operating environment through which a user interacts with a system.

[0089] "Feedback" refers to information about the user's impressions and satisfaction with the exercise program they have completed, and is used to improve the system.

[0090] The system of the present invention receives and analyzes the user's body composition data and basic physical ability data, and recommends an optimal exercise program. The flow of the system for specifically implementing the present invention will now be described.

[0091] Users access this system using a device such as a personal computer or smartphone. The device displays a user interface through a web browser or mobile application, allowing users to input body composition data (height, weight, body fat percentage, etc.) and basic physical ability data (grip strength, endurance test results, flexibility test results, etc.). Users are also prompted to input their interests and sports.

[0092] When a user enters data and clicks the "Submit" button, the terminal formats the input data into JSON format. The formatted data is then sent to the server using a secure communication protocol (e.g., HTTPS). The server receives the data sent from the terminal on a specific receiving port and stores it in an internal database.

[0093] Next, the server cleanses the data stored in the database. Cleansing is a process that corrects inaccurate data and fills in missing values ​​to improve data quality. For example, it detects abnormal values ​​such as a weight of 0 kg and fills them in using past data or average values.

[0094] The cleansed data is then analyzed using machine learning algorithms (e.g., random forests and support vector machines). The server then performs the analysis to identify the best exercise program for the user and generates a list of recommendations based on the results. The recommendation list includes a detailed description of each exercise program or sport and the reasons why that sport is suitable for the user.

[0095] The generated recommendation list is stored in the database again and sent from the server to the device, which displays the received recommendation list on the user interface, allowing the user to easily understand and select.

[0096] The user reviews the displayed list of recommendations and selects the most suitable exercise program. After completing the exercise program, the user provides feedback by entering their impressions and satisfaction. The device sends this feedback to the server, which then stores it in a database. The feedback information is used to improve the recommendation algorithm for the next exercise program.

[0097] For example, if a 14-year-old junior high school student inputs his / her height of 160 cm, weight of 50 kg, body fat percentage of 15%, 13 seconds for 100 m sprint time, and interest in basketball, the server will use this data to recommend three sports: track and field (especially sprinting), basketball, and soccer. The user can then select an appropriate exercise program and provide feedback later.

[0098] An example of a prompt sentence would be, "A 14-year-old junior high school student has entered his body composition data and basic physical ability data. His height is 160 cm, his weight is 50 kg, his body fat percentage is 15%, his 100m sprint time is 13 seconds, and he has an interest in basketball. Based on this data, please recommend the most suitable exercise program for this junior high school student." This sentence is input into the generative AI model.

[0099] The above is a specific embodiment of the present invention, which provides an automated series of processes, from receiving user data, analyzing it, generating and presenting a recommendation list, and improving the algorithm based on the feedback, to help users establish exercise habits.

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1:

[0102] Users access the system using a terminal such as a personal computer or smartphone. A user interface is displayed, and the user inputs body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results), as well as the sports they are interested in. The terminal receives the input data, which is then collected and saved on the terminal.

[0103] Step 2:

[0104] When the user has completed entering all the data and clicked the "Submit" button, the device will format the data into JSON format and send it to the server using a secure communication protocol such as HTTPS. In this operation, the device sends the input data, and the server stores the received data in its internal database.

[0105] Step 3:

[0106] The server stores the received data in an internal database. The stored data is then cleansed. Specifically, inaccurate data and missing values ​​are detected and filled in using past data and average values. For example, if an extremely low or abnormal weight value is entered, the server replaces it with the average value. The output is the cleansed data.

[0107] Step 4:

[0108] The cleansed data is then analyzed on the server using machine learning algorithms. Specifically, algorithms such as random forests and support vector machines are applied to the user's data to create a model that recommends the optimal exercise program. This process produces the analysis results.

[0109] Step 5:

[0110] Based on the analysis results, the server generates a list of recommendations for exercise programs and sports that are optimal for the user. This list includes a detailed description of each exercise program and the reasons why that sport is suitable for the user. The generated recommendation list is saved in a database in a format such as JSON. The output is the recommendation list.

[0111] Step 6:

[0112] The server sends the recommendation list stored in the database to the terminal, which displays the received recommendation list on the user interface so that the user can easily understand and select. The output of this step is the recommendation list that is displayed to the user.

[0113] Step 7:

[0114] The user checks the proposed exercise program and carries it out as necessary. After practicing the program, the user again inputs data into the device to provide feedback on their impressions and satisfaction. This data is collected as input data.

[0115] Step 8:

[0116] The device sends user feedback data to the server, which stores the feedback in an internal database and uses this data to refine the recommendation algorithm. This process allows the system to continually improve the accuracy of exercise program recommendations based on user feedback.

[0117] Through the above steps, the system receives the user's body composition data and basic physical ability data, and supports continuous health management by recommending daily exercise programs and providing feedback.

[0118] (Application example 1)

[0119] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0120] Users who aim to manage their health and establish exercise habits need not only to be provided with effective exercise programs based on body composition data and basic physical ability data, but also to be provided with comprehensive health support by optimizing daily dietary content and proposing healthy delivery menus. The present invention aims to solve this problem and provide a system that allows users to easily maintain their health.

[0121] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0122] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for analyzing the input data and generating a recommendation list for recommending exercise programs and meal menus suitable for the user based on the analysis results, means for displaying the recommendation list to the user, and means for proposing healthy delivery menus suitable for the user based on the recommendation list. This allows the user to easily receive effective exercise programs and optimal meal menus, thereby enabling comprehensive health management.

[0123] "Body composition data input by the user" refers to information that the user inputs or provides via the terminal, data relating to the user's body composition, such as weight, height, and body fat percentage.

[0124] "Basic physical ability data" is data relating to the user's basic physical abilities such as grip strength, endurance, flexibility, etc.

[0125] "Analysis" is the process of evaluating received data using machine learning algorithms and statistical methods to derive analytical results suitable for a specific purpose.

[0126] The "recommended list" is a list of exercise programs and meal menus that are optimal for the user, organized based on the results of the analysis.

[0127] A "healthy delivery menu" is a set of healthy meal options recommended based on the user's health condition and physical data.

[0128] "Feedback" refers to information that a user sends back to the system about the results and impressions of the exercise program or meal menu provided to them after they have put it into practice.

[0129] A "recommendation algorithm" is a calculation method or logic for automatically selecting the optimal exercise program or meal menu based on user data.

[0130] The present invention provides a system for proposing optimal exercise programs and meal menus based on body composition data and basic physical ability data acquired from a user. This system comprises the following steps.

[0131] System Configuration

[0132] Hardware and Software Configuration

[0133] This system consists of a user device (smartphone app), a server (cloud server), and a database. The specific technology stack is as follows:

[0134] On the user device, a smartphone application using React Native is implemented.

[0135] On the server side, a web server is built using Node.js and Express, and MongoDB is used as the database.

[0136] HTTPS is used for data communication to ensure secure communication, and JWT (JSON Web Token) is used for authentication.

[0137] User data input phase

[0138] Users operate the device to input their body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results), as well as the types of cuisine they are interested in and their food preferences.

[0139] Data transmission phase

[0140] The device collects data entered by the user and securely transmits it to the server using HTTPS, where it is formatted into a standard format such as JSON.

[0141] Data Preprocessing Phase

[0142] The server cleanses the data it receives, and if there are any inaccurate or missing data, it fills them in using historical data or average values.

[0143] Data analysis phase

[0144] The server then uses the cleansed data to analyze it using machine learning algorithms and statistical methods. Specifically, it analyzes the user's body composition data and basic physical ability data, and applies a model to recommend optimal exercise programs and healthy delivery menus.

[0145] Recommendation List Generation Phase

[0146] Based on the analysis, the server generates a list of recommended exercise programs and dietary menus that are optimal for the user, including detailed descriptions of each exercise and diet and the reasons why they are suitable for the user.

[0147] Result display phase

[0148] The server sends the generated recommendation list to the user's device, which then displays the received recommendation list on its user interface, allowing the user to easily understand and select items.

[0149] User Feedback Phase

[0150] After the user has put into practice the suggested exercise program or meal menu, the system also has a function to provide feedback on the results and impressions. The feedback data is then sent back to the server and used to improve the algorithm.

[0151] Specific examples

[0152] For example, suppose a user enters their height (170cm), weight (65kg), and body fat percentage (20%) as body composition data, and their basic physical ability data (grip strength, endurance, and flexibility test results), and also enters that they are interested in "Italian cuisine." Based on this information, the server generates the following prompt and performs analysis:

[0153] Example prompt sentence:

[0154] The user's body composition data is as follows:

[0155] Height: 170 cm

[0156] Weight: 65 kg

[0157] Body fat percentage: 20%

[0158] The user has the following basic physical ability data:

[0159] Grip strength: 40kg

[0160] Endurance: Moderate

[0161] Flexibility: High

[0162] Suggest a healthy Italian menu suitable for this user.

[0163] Based on these prompts, the system generates and provides optimal exercise programs and meal plans to the user, such as healthy delivery menu suggestions like "bruschetta and fruit for breakfast, grilled chicken salad for lunch, and Italian salmon and vegetable soup for dinner."

[0164] In this way, users receive individually optimized exercise programs and meal menus, enabling comprehensive health management.

[0165] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0166] Step 1:

[0167] The user enters body composition data and basic physical ability data through the device. Specifically, the user enters information such as height, weight, body fat percentage, grip strength, endurance test results, and flexibility test results. The user also enters their interests and the types of cuisine they are interested in. The entered data is saved in temporary storage on the device and formatted into JSON format. Once the input data has been formatted, the system proceeds to the next step.

[0168] Step 2:

[0169] The formatted user data is sent from the device to the server. Here, secure communication is performed using HTTPS. The server receives the received JSON-formatted data via a receiving port and stores it in a database. In this step, the input data (body composition data, basic physical ability data, and types of cuisine of interest) is transmitted to the server, which stores it in the server's database.

[0170] Step 3:

[0171] The server begins the process of cleansing the data received from the database. Specifically, if there are abnormal values ​​for weight or height, they are filled in using past data or average values. Also, if there is missing data, they are filled in with estimated values. After the inaccurate data has been cleansed, the accurate data can be used for analysis.

[0172] Step 4:

[0173] After the cleansing process is complete, the server performs data analysis. This analysis uses machine learning algorithms and statistical methods. The goal is to identify the optimal exercise program and meal plan for the user. The server generates prompts for the analysis. For example, the server might include something like, "The user's body composition data is as follows: height: 170 cm, weight: 65 kg...Please suggest a healthy Italian menu suitable for this user." The analysis results are organized into a recommendation list.

[0174] Step 5:

[0175] The server stores the generated recommendation list in a database and sends it to the device. The data is formatted appropriately and displayed on the device. The recommendation list includes detailed descriptions of each exercise program and meal plan, as well as reasons for its recommendation.

[0176] Step 6:

[0177] The user can view the recommended list of exercise programs and dietary menus displayed on the device and put them into practice. Each program includes detailed instructions on specific methods, procedures, and precautions.

[0178] Step 7:

[0179] After practicing, users enter feedback via their device. The feedback includes the effectiveness of the program, their impressions, and their level of satisfaction. The feedback data is then sent back to the server, which receives the data and stores it in a database. Based on the feedback information, the analysis algorithm is improved, and the accuracy of recommendations will increase in the future.

[0180] Through these steps, users receive individually optimized exercise programs and meal plans, enabling them to achieve comprehensive health management.

[0181] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0182] The system of the present invention receives and analyzes the user's body composition data and basic physical ability data, and recommends the optimal exercise program. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the recommendations can be optimized with even greater precision.

[0183] User data input phase

[0184] The user accesses the system using a terminal. The terminal displays a user interface, prompting the user to enter body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter information about their interests and sports. Since this data is used in the analysis step, it is important that it is entered accurately.

[0185] Data transmission phase

[0186] The device receives the data entered by the user, formats it, and sends it to the server, which stores the data in an internal database and prepares it for analysis.

[0187] Data Preprocessing Phase

[0188] The server cleanses the data it receives and fills in outliers and missing values. It ensures data quality by using historical data and average values. The cleansed data is then formatted for analysis.

[0189] Data analysis phase

[0190] The server performs analysis based on the cleansed data. Using machine learning algorithms and statistical methods, it applies a model to recommend the most suitable exercise program for the user. Based on the analysis results, it identifies the sports and exercise programs that are best suited to the user's body composition and basic physical abilities.

[0191] Emotional Engine Phase

[0192] When displaying the recommendation list, the device activates an emotion engine. The emotion engine analyzes the user's facial expressions, voice tone, input behavior, etc. to recognize the user's emotional state. The emotion data recognized by the emotion engine helps prioritize the most suitable exercise program for the user in the recommendation list. The content of the list is also optimized in real time based on the emotion data.

[0193] Recommendation list generation and display phase

[0194] The server combines the analysis results with the emotion engine data to generate a list of recommendations for optimal exercise programs and sports. The generated recommendation list is formatted in JSON format or similar and sent to the device. The device displays this list on its user interface, allowing the user to easily understand and select.

[0195] User Feedback Phase

[0196] After the user practices the suggested exercise program, they enter their impressions and satisfaction as feedback. This feedback is combined with emotional data to refine the algorithm for optimal performance. The device then sends this data to the server, which then analyzes the feedback and emotional data to further improve the accuracy of the next recommendation.

[0197] As a concrete example, consider the case where a 14-year-old junior high school student is 160 cm tall, weighs 50 kg, and has a body fat percentage of 15%, and enters his or her 100-meter sprint time and interest in basketball. Based on this data, the server will create a recommendation list of three events: track and field (especially sprinting), basketball, and soccer. Furthermore, the emotion engine analyzes the user's facial expressions and input behavior, and can prioritize events that the user is particularly interested in or enjoys. The user can select and perform an exercise program that suits them based on this list, and then enter feedback afterwards.

[0198] In this way, this system automates a series of processes, from receiving user data to generating and presenting optimal exercise programs, and even making highly accurate suggestions that incorporate emotional data and improvements based on feedback, thereby helping users establish exercise habits.

[0199] The processing flow will be explained below.

[0200] Step 1:

[0201] The user starts the application and accesses a screen for entering body composition data and basic physical ability data, including height, weight, body fat percentage, grip strength, endurance test results, flexibility test results, and sports of interest.

[0202] Step 2:

[0203] The terminal receives data entered by the user, converts it into an internal format, formats the converted data, and sends it to the server using a secure communication protocol.

[0204] Step 3:

[0205] The server receives the data at the receiving port and saves it in the database. The received data is stored in a temporary table and prepared for data analysis.

[0206] Step 4:

[0207] The server cleanses the data it receives, detects outliers and missing values, and imputes them as needed using historical data or average values, and then formats the cleansed data for analysis.

[0208] Step 5:

[0209] The server then applies machine learning algorithms to the cleansed data, using techniques such as clustering and recommender systems to analyze the exercise program and sport that best suits the user.

[0210] Step 6:

[0211] Based on the analysis results, the server generates a list of recommendations for exercise programs and sports that are optimal for the user, including detailed descriptions of each sport and the reasons for its recommendation.

[0212] Step 7:

[0213] The device activates the emotion engine, and when the user browses the recommendation list, it analyzes parameters such as facial expressions, voice tone, and input behavior. Based on this data, the emotion engine recognizes the user's emotional state and generates emotion data.

[0214] Step 8:

[0215] The server receives the emotion data generated by the emotion engine and optimizes the recommendation list in real time, for example, by prioritizing the display of sports that the user is interested in or enjoys.

[0216] Step 9:

[0217] The device receives the optimized recommendation list and displays it on the user interface, allowing the user to confirm the suggested exercise program or sport based on the display.

[0218] Step 10:

[0219] After the user has completed the proposed exercise program, they can input their impressions and satisfaction level through the feedback screen. The input feedback data is sent to the server via the device.

[0220] Step 11:

[0221] The server analyzes the received feedback data and stores it for algorithm refinement, including sentiment data, to improve the accuracy of the next recommendation.

[0222] The above is the specific processing flow of the system of the present invention. This series of steps allows the user to continuously carry out an optimal exercise program, which can help maintain health and improve sports performance.

[0223] Example 2

[0224] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0225] Conventional exercise program recommendation systems have problems with reduced recommendation accuracy due to inaccuracies or missing data when analyzing individual user data. Furthermore, these systems do not take into account the user's emotional state, making it difficult to provide optimal exercise programs based on the user's motivation and interests. Furthermore, they do not fully utilize user feedback, resulting in insufficient improvements to improve recommendation accuracy for the next time.

[0226] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0227] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for cleansing the input data and completing inaccurate or missing data, means for analyzing the cleansed data using a machine learning algorithm and generating a recommendation list for recommending exercise programs suitable for the user based on the analysis results, means for displaying the recommendation list to the user, and means for recognizing the user's emotional state and optimizing the contents of the recommendation list in real time based on the emotional state. This makes it possible to provide an optimal exercise program based on the user's emotional state while ensuring data quality, and further to utilize user feedback to improve the accuracy of next recommendations.

[0228] The "means for receiving body composition data and basic physical ability data input by the user" refers to a mechanism by which a user accesses the system using a terminal and inputs data such as height, weight, body fat percentage, grip strength, endurance test results, and flexibility test results.

[0229] The "means for cleansing the input data and supplementing inaccurate or missing data" refers to a mechanism in which the server analyzes the data it receives, corrects and supplements outliers and missing values, and performs processing to ensure the quality of the data.

[0230] "Means for analyzing using a machine learning algorithm and generating a recommendation list for recommending suitable exercise programs to the user based on the analysis results" refers to a mechanism in which the server applies a machine learning algorithm to the cleansed data, identifies the exercise program that is best suited to the user's body composition and basic physical abilities, and generates the results as a list.

[0231] The "means for displaying the recommendation list to the user" is a mechanism for formatting the generated recommendation list in JSON format or the like and displaying it to the user through a user interface.

[0232] The "means for recognizing the emotional state of the user and optimizing the contents of the recommendation list in real time based on said emotional state" is a mechanism that uses an emotion engine to analyze the user's facial expressions, voice tone, and input behavior, recognizes the user's emotional state, and then optimizes the contents of the recommendation list.

[0233] The "means for receiving user feedback and improving the recommendation algorithm based on said feedback" is a mechanism for receiving feedback such as user impressions and satisfaction regarding the exercise program that the user has performed, and improving the recommendation algorithm based on that feedback.

[0234] The "emotion engine" is a mechanism that analyzes the user's facial expressions, voice tone, input behavior, etc. to recognize the user's real-time emotional state.

[0235] The system of the present invention receives and analyzes the user's body composition data and basic physical ability data, and recommends the optimal exercise program. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the recommendations can be optimized with even greater precision.

[0236] User data input phase

[0237] The user accesses the system using a terminal. The terminal displays a dedicated user interface, prompting the user to enter detailed body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter their interests and sports that interest them. Accurate data entry is important for the analysis step, so the user is urged to enter the data appropriately.

[0238] Data transmission phase

[0239] The terminal formats the data entered by the user and converts it into a unified format (e.g., JSON format). The terminal sends the formatted data to the server. If an error occurs during transmission, it attempts to resend. The server stores the received data in a database and prepares it for analysis.

[0240] Data Preprocessing Phase

[0241] The server cleanses the data it receives and corrects and completes outliers and missing values. For example, if the height entered by the user is very small, it will automatically be completed by referring to past data and average values. The server then formats the cleansed data for analysis. Specifically, it standardizes the necessary numerical values ​​(for example, to a range of 0 to 1).

[0242] Data analysis phase

[0243] The server then uses machine learning algorithms to analyze the cleansed data. Specific algorithms include regression analysis and clustering. The server then selects the optimal exercise program based on the analysis results. For example, if a user's endurance test results are high, an exercise program that emphasizes endurance will be recommended.

[0244] Emotional Engine Phase

[0245] When the device displays the recommendation list, it activates an emotion engine. The emotion engine analyzes the user's facial expressions, voice tone, and input behavior in real time to recognize the user's emotional state. Based on the recognized emotion data, it prioritizes the most suitable exercise program for the user from the recommendation list. It is also possible to optimize the list contents in real time.

[0246] Recommendation list generation and display phase

[0247] The server combines the analysis results with data from the emotion engine to generate a list of recommendations for optimal exercise programs and sports. The generated recommendation list is formatted in JSON format or similar and sent to the device. The device then displays the recommendation list on its user interface, making it easy for the user to understand and select. Specific examples include a function to display videos explaining the benefits of each exercise program and how to perform them.

[0248] User Feedback Phase

[0249] The user practices the proposed exercise program and then inputs feedback, such as their impressions and level of satisfaction, into the device. This effectively collects the user's actual level of satisfaction. The device then sends the feedback data to the server, which analyzes it along with emotional data and uses it to improve the accuracy of the next recommendation.

[0250] Specific examples

[0251] For example, if a 14-year-old junior high school student inputs his / her height of 160 cm, weight of 50 kg, and body fat percentage of 15%, as well as data indicating his / her 100-meter sprint time and interest in basketball, the server will use this data to recommend three events: track and field (especially sprinting), basketball, and soccer. Furthermore, the emotion engine analyzes the user's facial expressions and input behavior, and prioritizes events that the user is particularly interested in or enjoys. The user can select an exercise program that suits them based on this list, and then provide feedback to help improve the system's accuracy.

[0252] Prompt Sentence Examples

[0253] An example of a prompt to input to a generative AI model is as follows:

[0254] "Enter the following information for a 14-year-old junior high school student: height 160cm, weight 50kg, body fat percentage 15%, 100m sprint time, and interest in basketball. Generate and present a list of optimal exercise programs and sports."

[0255] In this way, this system automates a series of processes, from receiving user data to generating and presenting optimal exercise programs, and even making highly accurate suggestions that incorporate emotional data and improvements based on feedback, thereby helping users establish exercise habits.

[0256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0257] Step 1: User data input phase

[0258] A user accesses the system using a terminal. The terminal displays a user interface and prompts the user to input body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results).

[0259] Input: The user manually inputs each piece of data (e.g., height 160 cm, weight 50 kg).

[0260] Data processing: The terminal checks input data for errors in real time and prompts correction of any inaccurate data.

[0261] Output: The formatted input data after error checking.

[0262] Step 2: Data transmission phase

[0263] The terminal sends the formatted data to the server, where it is converted into a unified format (e.g., JSON format).

[0264] Input: Body composition data and basic physical ability data entered by the user.

[0265] Data processing: The terminal converts the formatted data into JSON format.

[0266] Output: JSON formatted data is sent to the server.

[0267] Step 3: Data preprocessing phase

[0268] The server analyzes the received data, cleansing it, and complements outliers and missing values.

[0269] Input: Body composition data and basic physical ability data sent in JSON format.

[0270] Data processing: Carry out a cleansing process, for example, to fill in missing body fat percentages.

[0271] Output: Cleansed, high-quality data.

[0272] Step 4: Data analysis phase

[0273] The server analyzes the cleansed data using machine learning algorithms and applies a model that recommends the most suitable exercise program for the user.

[0274] Input: Cleansed body composition data and basic physical performance data.

[0275] Data calculations: Apply machine learning algorithms (e.g., regression analysis, clustering) to obtain analytical results.

[0276] Output: A list of recommended exercise programs based on the analysis results.

[0277] Step 5: Emotional Engine Phase

[0278] The device activates an emotion engine to analyze the user's emotional state, analyzing facial expressions, voice tone, and input behavior in real time to obtain emotional data.

[0279] Input: User's facial expression data, voice data, and input behavior data.

[0280] Data Calculation: The emotion engine analyzes these data and recognizes the user's emotional state (e.g., excitement, interest).

[0281] Output: Emotion data is sent to the server.

[0282] Step 6: Recommendation list generation and display phase

[0283] The server combines the analysis results with the emotion data to generate a recommendation list, which is then formatted in JSON format or similar and sent to the device.

[0284] Input: Analysis results of machine learning algorithms and sentiment data.

[0285] Data processing: Format the recommendation list and convert it into a format suitable for the user interface (e.g., JSON format).

[0286] Output: The formatted recommendation list is sent to the terminal and displayed on the user interface.

[0287] Step 7: User Feedback Phase

[0288] The user practices the proposed exercise program and inputs their impressions and satisfaction level into the device, and the feedback data is sent to the server.

[0289] Input: Feedback data entered by the user after practice.

[0290] Data calculation: The server analyzes the feedback data and refines the algorithm to improve the accuracy of the next recommendation.

[0291] Output: A list of recommendations for next time with an improved algorithm.

[0292] Through this series of processes, the system can provide the user with the optimal exercise program and continue to improve the accuracy of its next suggestions based on feedback and emotional data.

[0293] (Application example 2)

[0294] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0295] Conventional robot maintenance systems face challenges in creating efficient maintenance programs because it is difficult to fully analyze robot operation and maintenance data and they are unable to optimize programs taking into account the emotional state of workers. This leads to incomplete robot maintenance, increasing the risk of breakdowns and reduced productivity. Furthermore, maintenance plans that ignore worker stress and fatigue can have a negative impact on worker health and work efficiency.

[0296] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0297] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for analyzing the input data and generating a recommendation list for recommending an exercise program suitable for the user based on the analysis results, means for displaying the recommendation list to the user, means for receiving robot operation data and recommending an optimal maintenance program based on the data, and means for analyzing worker emotion data and optimizing the maintenance program based on the emotion data. This makes it possible to create a more effective and efficient maintenance program based on the robot operation data and the worker emotion data.

[0298] "Body composition data" refers to information about a user's physical components, such as height, weight, and body fat percentage.

[0299] "Basic physical ability data" refers to data that indicates the user's basic physical abilities, such as grip strength, endurance test results, and flexibility test results.

[0300] "Analysis" refers to the process of processing received data and drawing conclusions or recommendations based on it.

[0301] The "recommended list" is a list of optimal exercise programs and maintenance programs provided to the user based on the analysis results.

[0302] "Operational data" refers to data related to the operation of a robot, such as the robot's operating time, number of errors, and maintenance history.

[0303] A "maintenance program" is a plan for a series of construction works, cleaning, part replacement, etc. required to maintain the normal operation of a robot.

[0304] "Worker emotional data" refers to information indicating stress or fatigue levels obtained from the worker's facial expressions, voice tone, and input behavior.

[0305] "Optimization" refers to the adjustment or refinement of something to find the best possible state or solution for a particular purpose.

[0306] A "server" is a computer that processes and stores data and provides services to client terminals over a network.

[0307] In this invention, the system receives and analyzes the user's body composition data and basic physical ability data, and also analyzes the robot's operation data and the worker's emotional data, thereby recommending optimal exercise and maintenance programs. Specific embodiments are described below.

[0308] User data input phase

[0309] Users access the system using a smartphone. The smartphone displays a user interface and prompts the user to enter body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter their interests and sports.

[0310] Data transmission phase

[0311] The smartphone receives data entered by the user, formats it, and sends it to the server, which stores the data in an internal database and prepares it for analysis.

[0312] Data Preprocessing Phase

[0313] The server cleanses the data it receives, filling in outliers and missing values, and ensuring data quality using historical data and average values. The cleansed data is then formatted for analysis.

[0314] Data analysis phase

[0315] The server performs analysis based on the cleansed data, using machine learning algorithms and statistical methods to apply a model that recommends the most suitable exercise program for the user.

[0316] Emotional Engine Phase

[0317] The smartphone activates the emotion engine, which uses the smartphone's camera to analyze the user's facial expressions, voice tone, input behavior, etc. to recognize the user's emotional state. The recognized emotion data is used to prioritize the most suitable exercise program in the recommendation list.

[0318] Robot operation data input phase

[0319] The server receives and analyzes the operation data of the factory robots, including operating time, number of errors, maintenance history, etc.

[0320] Robot Maintenance Recommendation Phase

[0321] The optimal maintenance program is displayed on the user interface based on the operational data analyzed by the server, enabling efficient maintenance of the robot.

[0322] Worker emotion data input phase

[0323] The server receives the worker's emotional data, which is analyzed from camera footage and audio data to evaluate stress levels, fatigue, and other factors.

[0324] Maintenance program optimization phase

[0325] Based on the collected emotional data, the server optimizes the maintenance program in real time, thereby improving work efficiency and maintaining the health of workers.

[0326] Recommendation list generation and display phase

[0327] The server combines the analysis results with emotion data to generate a list of recommendations for optimal exercise and maintenance programs. The recommendation list is formatted in JSON format and sent to the smartphone. The smartphone displays this list on its user interface, allowing the user to easily understand and select.

[0328] User Feedback Phase

[0329] After practicing the suggested exercise program, users enter their impressions and satisfaction as feedback. This feedback is combined with emotional data to refine the algorithm for optimal performance. The smartphone then sends this data to a server, which then analyzes the feedback and emotional data to further improve the accuracy of the next recommendation.

[0330] Hardware and software used

[0331] The system mainly uses a smartphone and a server. Sentiment analysis is performed using the smartphone's camera and voice input device, and analysis software includes a machine learning algorithm (e.g., RandomForestRegressor) and a sentiment analysis engine (e.g., Affdex SDK).

[0332] Specific examples

[0333] The user enters body composition data, and the smartphone transmits the data to the server.

[0334] The server cleanses the data and generates a recommendation list based on the analysis results.

[0335] The smartphone displays a list of recommendations, and the user can select the most suitable exercise program.

[0336] The server receives operational data from factory robots and recommends new maintenance programs.

[0337] Obtains worker emotional data and provides optimized maintenance programs.

[0338] Example prompts to input to the generative AI model

[0339] "Create an application that uses robot operating data to recommend optimal maintenance programs and adds sentiment analysis for optimization."

[0340] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0341] Step 1:

[0342] The user inputs body composition data and basic physical ability data into a smartphone.

[0343] As specific examples of input, the user may enter data such as height (e.g., 160 cm), weight (e.g., 50 kg), body fat percentage (e.g., 15%), grip strength (e.g., 30 kg), endurance test results, and flexibility test results.

[0344] The entered data is temporarily stored in the smartphone's memory.

[0345] Step 2:

[0346] The terminal receives the data entered by the user and formats the data.

[0347] Specifically, the values ​​of each data field are formatted correctly and it is checked whether there are any missing values.

[0348] The formatted data is converted into a transmittable format such as JSON.

[0349] After this processing, the data is sent to the server.

[0350] Step 3:

[0351] The server stores the received data in a database.

[0352] First, the server parses the received JSON format data and stores it in each field of the database.

[0353] The data is appropriately labeled for analysis and used in subsequent processing.

[0354] Step 4:

[0355] The server retrieves the data from the database and performs the cleansing.

[0356] Specific examples include detecting and correcting outliers (e.g., body fat percentage above 100%) and filling in missing values ​​(using average data from the past).

[0357] The cleansed data is used as input for machine learning algorithms.

[0358] Step 5:

[0359] The server analyzes the cleansed data and generates a list of recommendations.

[0360] Specifically, we use a machine learning algorithm (e.g., RandomForestRegressor) to recommend the optimal exercise program based on the input data.

[0361] The analysis results in a recommendation list, which includes recommended exercises and programs.

[0362] Step 6:

[0363] The terminal receives the recommendation list from the server and displays it on the user interface.

[0364] Specifically, the server generates a recommendation list and sends it to the device in JSON format, which the device then analyzes and displays on the screen.

[0365] The user can review the recommendation list and select an exercise program based on it.

[0366] Step 7:

[0367] The user enters the operation data of the factory robot into a smartphone.

[0368] Specific examples of input include the robot's operating time (e.g., 2000 hours), the number of errors (e.g., 5), and maintenance history.

[0369] The entered data is temporarily stored in the smartphone's memory.

[0370] Step 8:

[0371] The terminal sends the robot's operation data to the server.

[0372] As with the user data transmission phase described above, the data is formatted, converted to JSON format, etc., and sent to the server.

[0373] The server stores the received data in a database and prepares it for analysis.

[0374] Step 9:

[0375] The server analyzes the operational data and generates the optimal maintenance program.

[0376] As a specific example of analysis, it predicts the risk of failure based on operational data and recommends necessary part replacements and regular inspection schedules.

[0377] The analysis results are formatted as a recommendation list in JSON format and sent to the device.

[0378] Step 10:

[0379] The terminal receives the recommendation list from the server and displays it on the user interface.

[0380] Users can review the recommended list and select the most suitable maintenance program.

[0381] Step 11:

[0382] The smartphone camera captures the worker's emotional data and sends it to the server.

[0383] Specifically, emotion analysis software (e.g., Affdex SDK) is used to analyze the facial expressions and vocal tones of workers to extract emotional data.

[0384] The extracted emotion data is sent to the server.

[0385] Step 12:

[0386] The server optimizes the maintenance program based on emotional data.

[0387] Analyzes emotional data and adjusts maintenance plans to take into account workers' stress levels and fatigue levels.

[0388] An optimized maintenance program is generated and sent to the terminal.

[0389] Step 13:

[0390] The terminal receives the optimized maintenance program and displays it on the user interface.

[0391] Users can check the optimal maintenance program and create an implementation plan.

[0392] Step 14:

[0393] Users carry out exercise and maintenance programs and then enter feedback into their smartphones.

[0394] Specific examples of input include impressions and satisfaction with the results of the practice.

[0395] The input feedback is sent from the terminal to the server.

[0396] Step 15:

[0397] The server analyzes the feedback data and refines the recommendation algorithm.

[0398] Specifically, the machine learning model is retrained based on the feedback data to improve the accuracy of the next recommendation.

[0399] The improved algorithm will be used in the next analysis.

[0400] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0401] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0402] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0403] [Second embodiment]

[0404] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0405] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0406] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0407] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0408] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0409] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0410] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0411] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0412] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0413] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0414] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0415] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0416] The system of the present invention receives and analyzes a user's body composition data and basic physical ability data, and recommends an optimal exercise program. The specific processing flow of the program of this system will be explained below in natural language.

[0417] User data input phase

[0418] The user accesses the system using a terminal. The terminal displays a user interface, prompting the user to enter body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter information about their interests and sports. This data is used in subsequent analysis steps, so it is important that it is entered accurately.

[0419] Data transmission phase

[0420] The data entered by the user is sent by the terminal to the server. The terminal formats the data to be sent and sends it to the server using a secure communication protocol. The server receives the data at a receiving port and stores it in an internal database.

[0421] Data Preprocessing Phase

[0422] The server cleanses the received data and fills in inaccurate data or missing values. For example, if the weight or height value is clearly abnormal, it fills in the data using past data or average values. This ensures the quality of the data used for analysis.

[0423] Data analysis phase

[0424] The server then uses the cleansed data for the actual analysis, applying machine learning algorithms and statistical methods to create models to recommend optimal exercise programs for users. Based on the analysis results, the server identifies the sports and exercise programs that best suit the user's body composition and basic physical abilities.

[0425] Recommendation List Generation Phase

[0426] Based on the analysis results, the server generates a list of recommended exercise programs and sports that are optimal for the user. This list also includes detailed descriptions of each sport and the reasons why that sport is suitable for the user. The generated recommendation list is then saved in a database in JSON format or similar.

[0427] Result display phase

[0428] The server sends the generated recommendation list to the device. The device displays the received recommendation list on the user interface, allowing the user to easily understand and select. Specific explanations of each exercise program and the reasons for its recommendation are provided in detail.

[0429] User Feedback Phase

[0430] After the user practices the proposed exercise program, they provide feedback on their impressions and satisfaction with the program. The device then sends this feedback to the server, which uses it to improve the recommendation algorithm.

[0431] As a concrete example, let's say a 14-year-old junior high school student is 160 cm tall, weighs 50 kg, and has a body fat percentage of 15%. If this user inputs their 100m sprint time and their interest in basketball, the server will use this data to recommend three events: track and field (especially sprinting), basketball, and soccer. The user can then select and execute an exercise program that suits them based on this list, and receive feedback afterwards.

[0432] In this way, this system automates a series of processes, from receiving user data to generating and presenting optimal exercise programs, and even improving the algorithm based on feedback, helping users establish exercise habits.

[0433] The processing flow will be explained below.

[0434] Step 1:

[0435] The user starts the application and accesses a screen for entering body composition data and basic physical ability data, including height, weight, body fat percentage, grip strength, endurance test results, flexibility test results, and sports of interest.

[0436] Step 2:

[0437] The terminal receives data entered by the user, converts it into an internal format, formats the converted data, and sends it to the server using a secure communication protocol.

[0438] Step 3:

[0439] The server receives the data at the receiving port and saves it in the database. The received data is stored in a temporary table and prepared for data analysis.

[0440] Step 4:

[0441] The server cleanses the data it receives, detects outliers and missing values, and imputes them as needed using historical data or averages, and then formats the cleansed data for analysis.

[0442] Step 5:

[0443] The server then applies machine learning algorithms to the cleansed data, using techniques such as clustering and recommender systems to analyze the exercise program and sport that best suits the user.

[0444] Step 6:

[0445] Based on the analysis results, the server generates a list of recommendations for exercise programs and sports that are optimal for the user, including detailed descriptions of each sport and the reasons for its recommendation.

[0446] Step 7:

[0447] The server converts the generated recommendation list into JSON or another appropriate data format and sends it to the device.

[0448] Step 8:

[0449] The device analyzes the received recommendation list and displays it on the user interface, allowing the user to confirm the suggested exercise programs and sports.

[0450] Step 9:

[0451] After the user has completed the proposed exercise program, they can input their impressions and satisfaction level through the feedback screen. The input feedback data is sent to the server via the device.

[0452] Step 10:

[0453] The server analyzes the received feedback data and stores it for algorithm refinement. The next analysis will use this feedback to improve accuracy.

[0454] The above is the specific processing flow of the system of the present invention. This series of steps allows the user to continuously carry out an optimal exercise program, which can help maintain health and improve sports performance.

[0455] Example 1

[0456] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0457] In modern health management, it is important to provide optimal exercise programs for individual users, but accurately analyzing the user's body composition data and basic physical ability data to generate an appropriate recommendation list is a challenge. In addition, it is necessary to supplement inaccurate or missing data and reflect user feedback to continuously improve the recommendation algorithm.

[0458] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0459] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for transmitting the input data to the server using a secure communication protocol, means for storing the transmitted data in an internal database and cleansing it to supplement inaccurate or missing data, means for analyzing the cleansed data using a machine learning algorithm and generating a recommendation list for recommending exercise programs suitable for the user based on the analysis results, means for displaying the recommendation list to the user, and means for receiving user feedback on exercise programs attempted based on the recommendation list and improving the recommendation algorithm based on the feedback. This makes it possible to provide each user with a highly accurate exercise program and to supplement inaccurate data and improve the algorithm based on the feedback.

[0460] "Body composition data" refers to basic data about the user's body, including height, weight, body fat percentage, and the like.

[0461] "Basic physical ability data" is data that indicates the user's basic physical strength and athletic ability, and includes grip strength, endurance test results, flexibility test results, and the like.

[0462] A "secure communication protocol" is a protocol that ensures security when sending and receiving data, and HTTPS is an example of this.

[0463] "Server" refers to a computer system that receives, stores, analyzes data, and provides information to users.

[0464] The "internal database" is a data storage system installed within the server for storing received data and analysis results.

[0465] "Cleansing" refers to the process of correcting inaccurate data and filling in missing values ​​in order to improve data quality.

[0466] "Machine learning algorithms" are artificial intelligence techniques used to analyze data and find patterns and trends, such as random forests and support vector machines.

[0467] The "recommended list" refers to a list of exercise programs and sports that are optimal for the user, generated based on the analysis results.

[0468] "User interface" refers to the screen and operating environment through which a user interacts with a system.

[0469] "Feedback" refers to information about the user's impressions and satisfaction with the exercise program they have completed, and is used to improve the system.

[0470] The system of the present invention receives and analyzes the user's body composition data and basic physical ability data, and recommends an optimal exercise program. The flow of the system for specifically implementing the present invention will now be described.

[0471] Users access this system using a device such as a personal computer or smartphone. The device displays a user interface through a web browser or mobile application, allowing users to input body composition data (height, weight, body fat percentage, etc.) and basic physical ability data (grip strength, endurance test results, flexibility test results, etc.). Users are also prompted to input their interests and sports.

[0472] When a user enters data and clicks the "Submit" button, the terminal formats the input data into JSON format. The formatted data is then sent to the server using a secure communication protocol (e.g., HTTPS). The server receives the data sent from the terminal on a specific receiving port and stores it in an internal database.

[0473] Next, the server cleanses the data stored in the database. Cleansing is a process that corrects inaccurate data and fills in missing values ​​to improve data quality. For example, it detects abnormal values ​​such as a weight of 0 kg and fills them in using past data or average values.

[0474] The cleansed data is then analyzed using machine learning algorithms (e.g., random forests and support vector machines). The server then performs the analysis to identify the best exercise program for the user and generates a list of recommendations based on the results. The recommendation list includes a detailed description of each exercise program or sport and the reasons why that sport is suitable for the user.

[0475] The generated recommendation list is stored in the database again and sent from the server to the device, which displays the received recommendation list on the user interface, allowing the user to easily understand and select.

[0476] The user reviews the displayed list of recommendations and selects the most suitable exercise program. After completing the exercise program, the user provides feedback by entering their impressions and satisfaction. The device sends this feedback to the server, which then stores it in a database. The feedback information is used to improve the recommendation algorithm for the next exercise program.

[0477] For example, if a 14-year-old junior high school student inputs his / her height of 160 cm, weight of 50 kg, body fat percentage of 15%, 13 seconds for 100 m sprint time, and interest in basketball, the server will use this data to recommend three sports: track and field (especially sprinting), basketball, and soccer. The user can then select an appropriate exercise program and provide feedback later.

[0478] An example of a prompt sentence would be, "A 14-year-old junior high school student has entered his body composition data and basic physical ability data. His height is 160 cm, his weight is 50 kg, his body fat percentage is 15%, his 100m sprint time is 13 seconds, and he has an interest in basketball. Based on this data, please recommend the most suitable exercise program for this junior high school student." This sentence is input into the generative AI model.

[0479] The above is a specific embodiment of the present invention, which provides an automated series of processes, from receiving user data, analyzing it, generating and presenting a recommendation list, and improving the algorithm based on the feedback, to help users establish exercise habits.

[0480] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0481] Step 1:

[0482] Users access the system using a terminal such as a personal computer or smartphone. A user interface is displayed, and the user inputs body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results), as well as the sports they are interested in. The terminal receives the input data, which is then collected and saved on the terminal.

[0483] Step 2:

[0484] When the user has completed entering all the data and clicked the "Submit" button, the device will format the data into JSON format and send it to the server using a secure communication protocol such as HTTPS. In this operation, the device sends the input data, and the server stores the received data in its internal database.

[0485] Step 3:

[0486] The server stores the received data in an internal database. The stored data is then cleansed. Specifically, inaccurate data and missing values ​​are detected and filled in using past data and average values. For example, if an extremely low or abnormal weight value is entered, the server replaces it with the average value. The output is the cleansed data.

[0487] Step 4:

[0488] The cleansed data is then analyzed on the server using machine learning algorithms. Specifically, algorithms such as random forests and support vector machines are applied to the user's data to create a model that recommends the optimal exercise program. This process produces the analysis results.

[0489] Step 5:

[0490] Based on the analysis results, the server generates a list of recommendations for exercise programs and sports that are optimal for the user. This list includes a detailed description of each exercise program and the reasons why that sport is suitable for the user. The generated recommendation list is saved in a database in a format such as JSON. The output is the recommendation list.

[0491] Step 6:

[0492] The server sends the recommendation list stored in the database to the terminal, which displays the received recommendation list on the user interface so that the user can easily understand and select. The output of this step is the recommendation list that is displayed to the user.

[0493] Step 7:

[0494] The user checks the proposed exercise program and carries it out as necessary. After practicing the program, the user again inputs data into the device to provide feedback on their impressions and satisfaction. This data is collected as input data.

[0495] Step 8:

[0496] The device sends user feedback data to the server, which stores the feedback in an internal database and uses this data to refine the recommendation algorithm. This process allows the system to continually improve the accuracy of exercise program recommendations based on user feedback.

[0497] Through the above steps, the system receives the user's body composition data and basic physical ability data, and supports continuous health management by recommending daily exercise programs and providing feedback.

[0498] (Application example 1)

[0499] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0500] Users who aim to manage their health and establish exercise habits need not only to be provided with effective exercise programs based on body composition data and basic physical ability data, but also to be provided with comprehensive health support by optimizing daily dietary content and proposing healthy delivery menus. The present invention aims to solve this problem and provide a system that allows users to easily maintain their health.

[0501] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0502] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for analyzing the input data and generating a recommendation list for recommending exercise programs and meal menus suitable for the user based on the analysis results, means for displaying the recommendation list to the user, and means for proposing healthy delivery menus suitable for the user based on the recommendation list. This allows the user to easily receive effective exercise programs and optimal meal menus, thereby enabling comprehensive health management.

[0503] "Body composition data input by the user" refers to information that the user inputs or provides via the terminal, data relating to the user's body composition, such as weight, height, and body fat percentage.

[0504] "Basic physical ability data" is data relating to the user's basic physical abilities such as grip strength, endurance, flexibility, etc.

[0505] "Analysis" is the process of evaluating received data using machine learning algorithms and statistical methods to derive analytical results suitable for a specific purpose.

[0506] The "recommended list" is a list of exercise programs and meal menus that are optimal for the user, organized based on the results of the analysis.

[0507] A "healthy delivery menu" is a set of healthy meal options recommended based on the user's health condition and physical data.

[0508] "Feedback" refers to information that a user sends back to the system about the results and impressions of the exercise program or meal menu provided to them after they have put it into practice.

[0509] A "recommendation algorithm" is a calculation method or logic for automatically selecting the optimal exercise program or meal menu based on user data.

[0510] The present invention provides a system for proposing optimal exercise programs and meal menus based on body composition data and basic physical ability data acquired from a user. This system comprises the following steps.

[0511] System Configuration

[0512] Hardware and Software Configuration

[0513] This system consists of a user device (smartphone app), a server (cloud server), and a database. The specific technology stack is as follows:

[0514] On the user device, a smartphone application using React Native is implemented.

[0515] On the server side, a web server is built using Node.js and Express, and MongoDB is used as the database.

[0516] HTTPS is used for data communication to ensure secure communication, and JWT (JSON Web Token) is used for authentication.

[0517] User data input phase

[0518] Users operate the device to input their body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results), as well as the types of cuisine they are interested in and their food preferences.

[0519] Data transmission phase

[0520] The device collects data entered by the user and securely transmits it to the server using HTTPS, where it is formatted into a standard format such as JSON.

[0521] Data Preprocessing Phase

[0522] The server cleanses the data it receives, and if there are any inaccurate or missing data, it fills them in using historical data or average values.

[0523] Data analysis phase

[0524] The server then uses the cleansed data to analyze it using machine learning algorithms and statistical methods. Specifically, it analyzes the user's body composition data and basic physical ability data, and applies a model to recommend optimal exercise programs and healthy delivery menus.

[0525] Recommendation List Generation Phase

[0526] Based on the analysis, the server generates a list of recommended exercise programs and dietary menus that are optimal for the user, including detailed descriptions of each exercise and diet and the reasons why they are suitable for the user.

[0527] Result display phase

[0528] The server sends the generated recommendation list to the user's device, which then displays the received recommendation list on its user interface, allowing the user to easily understand and select items.

[0529] User Feedback Phase

[0530] After the user has put into practice the suggested exercise program or meal menu, the system also has a function to provide feedback on the results and impressions. The feedback data is then sent back to the server and used to improve the algorithm.

[0531] Specific examples

[0532] For example, suppose a user enters their height (170cm), weight (65kg), and body fat percentage (20%) as body composition data, and their basic physical ability data (grip strength, endurance, and flexibility test results), and also enters that they are interested in "Italian cuisine." Based on this information, the server generates the following prompt and performs analysis:

[0533] Example prompt sentence:

[0534] The user's body composition data is as follows:

[0535] Height: 170 cm

[0536] Weight: 65 kg

[0537] Body fat percentage: 20%

[0538] The user has the following basic physical ability data:

[0539] Grip strength: 40kg

[0540] Endurance: Moderate

[0541] Flexibility: High

[0542] Suggest a healthy Italian menu suitable for this user.

[0543] Based on these prompts, the system generates and provides optimal exercise programs and meal plans to the user, such as healthy delivery menu suggestions like "bruschetta and fruit for breakfast, grilled chicken salad for lunch, and Italian salmon and vegetable soup for dinner."

[0544] In this way, users receive individually optimized exercise programs and meal menus, enabling comprehensive health management.

[0545] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0546] Step 1:

[0547] The user enters body composition data and basic physical ability data through the device. Specifically, the user enters information such as height, weight, body fat percentage, grip strength, endurance test results, and flexibility test results. The user also enters their interests and the types of cuisine they are interested in. The entered data is saved in temporary storage on the device and formatted into JSON format. Once the input data has been formatted, the system proceeds to the next step.

[0548] Step 2:

[0549] The formatted user data is sent from the device to the server. Here, secure communication is performed using HTTPS. The server receives the received JSON-formatted data via a receiving port and stores it in a database. In this step, the input data (body composition data, basic physical ability data, and types of cuisine of interest) is transmitted to the server, which stores it in the server's database.

[0550] Step 3:

[0551] The server begins the process of cleansing the data received from the database. Specifically, if there are abnormal values ​​for weight or height, they are filled in using past data or average values. Also, if there is missing data, they are filled in with estimated values. After the inaccurate data has been cleansed, the accurate data can be used for analysis.

[0552] Step 4:

[0553] After the cleansing process is complete, the server performs data analysis. This analysis uses machine learning algorithms and statistical methods. The goal is to identify the optimal exercise program and meal plan for the user. The server generates prompts for the analysis. For example, the server might include something like, "The user's body composition data is as follows: height: 170 cm, weight: 65 kg...Please suggest a healthy Italian menu suitable for this user." The analysis results are organized into a recommendation list.

[0554] Step 5:

[0555] The server stores the generated recommendation list in a database and sends it to the device. The data is formatted appropriately and displayed on the device. The recommendation list includes detailed descriptions of each exercise program and meal plan, as well as reasons for its recommendation.

[0556] Step 6:

[0557] The user can view the recommended list of exercise programs and dietary menus displayed on the device and put them into practice. Each program includes detailed instructions on specific methods, procedures, and precautions.

[0558] Step 7:

[0559] After practicing, users enter feedback via their device. The feedback includes the effectiveness of the program, their impressions, and their level of satisfaction. The feedback data is then sent back to the server, which receives the data and stores it in a database. Based on the feedback information, the analysis algorithm is improved, and the accuracy of recommendations will increase in the future.

[0560] Through these steps, users receive individually optimized exercise programs and meal plans, enabling them to achieve comprehensive health management.

[0561] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0562] The system of the present invention receives and analyzes the user's body composition data and basic physical ability data, and recommends the optimal exercise program. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the recommendations can be optimized with even greater precision.

[0563] User data input phase

[0564] The user accesses the system using a terminal. The terminal displays a user interface, prompting the user to enter body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter information about their interests and sports. Since this data is used in the analysis step, it is important that it is entered accurately.

[0565] Data transmission phase

[0566] The device receives the data entered by the user, formats it, and sends it to the server, which stores the data in an internal database and prepares it for analysis.

[0567] Data Preprocessing Phase

[0568] The server cleanses the data it receives and fills in outliers and missing values. It ensures data quality by using historical data and average values. The cleansed data is then formatted for analysis.

[0569] Data analysis phase

[0570] The server performs analysis based on the cleansed data. Using machine learning algorithms and statistical methods, it applies a model to recommend the most suitable exercise program for the user. Based on the analysis results, it identifies the sports and exercise programs that are best suited to the user's body composition and basic physical abilities.

[0571] Emotional Engine Phase

[0572] When displaying the recommendation list, the device activates an emotion engine. The emotion engine analyzes the user's facial expressions, voice tone, input behavior, etc. to recognize the user's emotional state. The emotion data recognized by the emotion engine helps prioritize the most suitable exercise program for the user in the recommendation list. The content of the list is also optimized in real time based on the emotion data.

[0573] Recommendation list generation and display phase

[0574] The server combines the analysis results with the emotion engine data to generate a list of recommendations for optimal exercise programs and sports. The generated recommendation list is formatted in JSON format or similar and sent to the device. The device displays this list on its user interface, allowing the user to easily understand and select.

[0575] User Feedback Phase

[0576] After the user practices the suggested exercise program, they enter their impressions and satisfaction as feedback. This feedback is combined with emotional data to refine the algorithm for optimal performance. The device then sends this data to the server, which then analyzes the feedback and emotional data to further improve the accuracy of the next recommendation.

[0577] As a concrete example, consider the case where a 14-year-old junior high school student is 160 cm tall, weighs 50 kg, and has a body fat percentage of 15%, and enters his or her 100-meter sprint time and interest in basketball. Based on this data, the server will create a recommendation list of three events: track and field (especially sprinting), basketball, and soccer. Furthermore, the emotion engine analyzes the user's facial expressions and input behavior, and can prioritize events that the user is particularly interested in or enjoys. The user can select and perform an exercise program that suits them based on this list, and then enter feedback afterwards.

[0578] In this way, this system automates a series of processes, from receiving user data to generating and presenting optimal exercise programs, and even making highly accurate suggestions that incorporate emotional data and improvements based on feedback, thereby helping users establish exercise habits.

[0579] The processing flow will be explained below.

[0580] Step 1:

[0581] The user starts the application and accesses a screen for entering body composition data and basic physical ability data, including height, weight, body fat percentage, grip strength, endurance test results, flexibility test results, and sports of interest.

[0582] Step 2:

[0583] The terminal receives data entered by the user, converts it into an internal format, formats the converted data, and sends it to the server using a secure communication protocol.

[0584] Step 3:

[0585] The server receives the data at the receiving port and saves it in the database. The received data is stored in a temporary table and prepared for data analysis.

[0586] Step 4:

[0587] The server cleanses the data it receives, detects outliers and missing values, and imputes them as needed using historical data or average values, and then formats the cleansed data for analysis.

[0588] Step 5:

[0589] The server then applies machine learning algorithms to the cleansed data, using techniques such as clustering and recommender systems to analyze the exercise program and sport that best suits the user.

[0590] Step 6:

[0591] Based on the analysis results, the server generates a list of recommendations for exercise programs and sports that are optimal for the user, including detailed descriptions of each sport and the reasons for its recommendation.

[0592] Step 7:

[0593] The device activates the emotion engine, and when the user browses the recommendation list, it analyzes parameters such as facial expressions, voice tone, and input behavior. Based on this data, the emotion engine recognizes the user's emotional state and generates emotion data.

[0594] Step 8:

[0595] The server receives the emotion data generated by the emotion engine and optimizes the recommendation list in real time, for example, by prioritizing the display of sports that the user is interested in or enjoys.

[0596] Step 9:

[0597] The device receives the optimized recommendation list and displays it on the user interface, allowing the user to confirm the suggested exercise program or sport based on the display.

[0598] Step 10:

[0599] After the user has completed the proposed exercise program, they can input their impressions and satisfaction level through the feedback screen. The input feedback data is sent to the server via the device.

[0600] Step 11:

[0601] The server analyzes the received feedback data and stores it for algorithm refinement, including sentiment data, to improve the accuracy of the next recommendation.

[0602] The above is the specific processing flow of the system of the present invention. This series of steps allows the user to continuously carry out an optimal exercise program, which can help maintain health and improve sports performance.

[0603] Example 2

[0604] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0605] Conventional exercise program recommendation systems have problems with reduced recommendation accuracy due to inaccuracies or missing data when analyzing individual user data. Furthermore, these systems do not take into account the user's emotional state, making it difficult to provide optimal exercise programs based on the user's motivation and interests. Furthermore, they do not fully utilize user feedback, resulting in insufficient improvements to improve recommendation accuracy for the next time.

[0606] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0607] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for cleansing the input data and completing inaccurate or missing data, means for analyzing the cleansed data using a machine learning algorithm and generating a recommendation list for recommending exercise programs suitable for the user based on the analysis results, means for displaying the recommendation list to the user, and means for recognizing the user's emotional state and optimizing the contents of the recommendation list in real time based on the emotional state. This makes it possible to provide an optimal exercise program based on the user's emotional state while ensuring data quality, and further to utilize user feedback to improve the accuracy of next recommendations.

[0608] The "means for receiving body composition data and basic physical ability data input by the user" refers to a mechanism by which a user accesses the system using a terminal and inputs data such as height, weight, body fat percentage, grip strength, endurance test results, and flexibility test results.

[0609] The "means for cleansing the input data and supplementing inaccurate or missing data" refers to a mechanism in which the server analyzes the data it receives, corrects and supplements outliers and missing values, and performs processing to ensure the quality of the data.

[0610] "Means for analyzing using a machine learning algorithm and generating a recommendation list for recommending suitable exercise programs to the user based on the analysis results" refers to a mechanism in which the server applies a machine learning algorithm to the cleansed data, identifies the exercise program that is best suited to the user's body composition and basic physical abilities, and generates the results as a list.

[0611] The "means for displaying the recommendation list to the user" is a mechanism for formatting the generated recommendation list in JSON format or the like and displaying it to the user through a user interface.

[0612] The "means for recognizing the emotional state of the user and optimizing the contents of the recommendation list in real time based on said emotional state" is a mechanism that uses an emotion engine to analyze the user's facial expressions, voice tone, and input behavior, recognizes the user's emotional state, and then optimizes the contents of the recommendation list.

[0613] The "means for receiving user feedback and improving the recommendation algorithm based on said feedback" is a mechanism for receiving feedback such as user impressions and satisfaction regarding the exercise program that the user has performed, and improving the recommendation algorithm based on that feedback.

[0614] The "emotion engine" is a mechanism that analyzes the user's facial expressions, voice tone, input behavior, etc. to recognize the user's real-time emotional state.

[0615] The system of the present invention receives and analyzes the user's body composition data and basic physical ability data, and recommends the optimal exercise program. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the recommendations can be optimized with even greater precision.

[0616] User data input phase

[0617] The user accesses the system using a terminal. The terminal displays a dedicated user interface, prompting the user to enter detailed body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter their interests and sports that interest them. Accurate data entry is important for the analysis step, so the user is urged to enter the data appropriately.

[0618] Data transmission phase

[0619] The terminal formats the data entered by the user and converts it into a unified format (e.g., JSON format). The terminal sends the formatted data to the server. If an error occurs during transmission, it attempts to resend. The server stores the received data in a database and prepares it for analysis.

[0620] Data Preprocessing Phase

[0621] The server cleanses the data it receives and corrects and completes outliers and missing values. For example, if the height entered by the user is very small, it will automatically be completed by referring to past data and average values. The server then formats the cleansed data for analysis. Specifically, it standardizes the necessary numerical values ​​(for example, to a range of 0 to 1).

[0622] Data analysis phase

[0623] The server then uses machine learning algorithms to analyze the cleansed data. Specific algorithms include regression analysis and clustering. The server then selects the optimal exercise program based on the analysis results. For example, if a user's endurance test results are high, an exercise program that emphasizes endurance will be recommended.

[0624] Emotional Engine Phase

[0625] When the device displays the recommendation list, it activates an emotion engine. The emotion engine analyzes the user's facial expressions, voice tone, and input behavior in real time to recognize the user's emotional state. Based on the recognized emotion data, it prioritizes the most suitable exercise program for the user from the recommendation list. It is also possible to optimize the list contents in real time.

[0626] Recommendation list generation and display phase

[0627] The server combines the analysis results with data from the emotion engine to generate a list of recommendations for optimal exercise programs and sports. The generated recommendation list is formatted in JSON format or similar and sent to the device. The device then displays the recommendation list on its user interface, making it easy for the user to understand and select. Specific examples include a function to display videos explaining the benefits of each exercise program and how to perform them.

[0628] User Feedback Phase

[0629] The user practices the proposed exercise program and then inputs feedback, such as their impressions and level of satisfaction, into the device. This effectively collects the user's actual level of satisfaction. The device then sends the feedback data to the server, which analyzes it along with emotional data and uses it to improve the accuracy of the next recommendation.

[0630] Specific examples

[0631] For example, if a 14-year-old junior high school student inputs his / her height of 160 cm, weight of 50 kg, and body fat percentage of 15%, as well as data indicating his / her 100-meter sprint time and interest in basketball, the server will use this data to recommend three events: track and field (especially sprinting), basketball, and soccer. Furthermore, the emotion engine analyzes the user's facial expressions and input behavior, and prioritizes events that the user is particularly interested in or enjoys. The user can select an exercise program that suits them based on this list, and then provide feedback to help improve the system's accuracy.

[0632] Prompt Sentence Examples

[0633] An example of a prompt to input to a generative AI model is as follows:

[0634] "Enter the following information for a 14-year-old junior high school student: height 160cm, weight 50kg, body fat percentage 15%, 100m sprint time, and interest in basketball. Generate and present a list of optimal exercise programs and sports."

[0635] In this way, this system automates a series of processes, from receiving user data to generating and presenting optimal exercise programs, and even making highly accurate suggestions that incorporate emotional data and improvements based on feedback, thereby helping users establish exercise habits.

[0636] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0637] Step 1: User data input phase

[0638] A user accesses the system using a terminal. The terminal displays a user interface and prompts the user to input body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results).

[0639] Input: The user manually inputs each piece of data (e.g., height 160 cm, weight 50 kg).

[0640] Data processing: The terminal checks input data for errors in real time and prompts correction of any inaccurate data.

[0641] Output: The formatted input data after error checking.

[0642] Step 2: Data transmission phase

[0643] The terminal sends the formatted data to the server, where it is converted into a unified format (e.g., JSON format).

[0644] Input: Body composition data and basic physical ability data entered by the user.

[0645] Data processing: The terminal converts the formatted data into JSON format.

[0646] Output: JSON formatted data is sent to the server.

[0647] Step 3: Data preprocessing phase

[0648] The server analyzes the received data, cleansing it, and complements outliers and missing values.

[0649] Input: Body composition data and basic physical ability data sent in JSON format.

[0650] Data processing: Carry out a cleansing process, for example, to fill in missing body fat percentages.

[0651] Output: Cleansed, high-quality data.

[0652] Step 4: Data analysis phase

[0653] The server analyzes the cleansed data using machine learning algorithms and applies a model that recommends the most suitable exercise program for the user.

[0654] Input: Cleansed body composition data and basic physical performance data.

[0655] Data calculations: Apply machine learning algorithms (e.g., regression analysis, clustering) to obtain analytical results.

[0656] Output: A list of recommended exercise programs based on the analysis results.

[0657] Step 5: Emotional Engine Phase

[0658] The device activates an emotion engine to analyze the user's emotional state, analyzing facial expressions, voice tone, and input behavior in real time to obtain emotional data.

[0659] Input: User's facial expression data, voice data, and input behavior data.

[0660] Data Calculation: The emotion engine analyzes these data and recognizes the user's emotional state (e.g., excitement, interest).

[0661] Output: Emotion data is sent to the server.

[0662] Step 6: Recommendation list generation and display phase

[0663] The server combines the analysis results with the emotion data to generate a recommendation list, which is then formatted in JSON format or similar and sent to the device.

[0664] Input: Analysis results of machine learning algorithms and sentiment data.

[0665] Data processing: Format the recommendation list and convert it into a format suitable for the user interface (e.g., JSON format).

[0666] Output: The formatted recommendation list is sent to the terminal and displayed on the user interface.

[0667] Step 7: User Feedback Phase

[0668] The user practices the proposed exercise program and inputs their impressions and satisfaction level into the device, and the feedback data is sent to the server.

[0669] Input: Feedback data entered by the user after practice.

[0670] Data calculation: The server analyzes the feedback data and refines the algorithm to improve the accuracy of the next recommendation.

[0671] Output: A list of recommendations for next time with an improved algorithm.

[0672] Through this series of processes, the system can provide the user with the optimal exercise program and continue to improve the accuracy of its next suggestions based on feedback and emotional data.

[0673] (Application example 2)

[0674] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0675] Conventional robot maintenance systems face challenges in creating efficient maintenance programs because it is difficult to fully analyze robot operation and maintenance data and they are unable to optimize programs taking into account the emotional state of workers. This leads to incomplete robot maintenance, increasing the risk of breakdowns and reduced productivity. Furthermore, maintenance plans that ignore worker stress and fatigue can have a negative impact on worker health and work efficiency.

[0676] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0677] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for analyzing the input data and generating a recommendation list for recommending an exercise program suitable for the user based on the analysis results, means for displaying the recommendation list to the user, means for receiving robot operation data and recommending an optimal maintenance program based on the data, and means for analyzing worker emotion data and optimizing the maintenance program based on the emotion data. This makes it possible to create a more effective and efficient maintenance program based on the robot operation data and the worker emotion data.

[0678] "Body composition data" refers to information about a user's physical components, such as height, weight, and body fat percentage.

[0679] "Basic physical ability data" refers to data that indicates the user's basic physical abilities, such as grip strength, endurance test results, and flexibility test results.

[0680] "Analysis" refers to the process of processing received data and drawing conclusions or recommendations based on it.

[0681] The "recommended list" is a list of optimal exercise programs and maintenance programs provided to the user based on the analysis results.

[0682] "Operational data" refers to data related to the operation of a robot, such as the robot's operating time, number of errors, and maintenance history.

[0683] A "maintenance program" is a plan for a series of construction works, cleaning, part replacement, etc. required to maintain the normal operation of a robot.

[0684] "Worker emotional data" refers to information indicating stress or fatigue levels obtained from the worker's facial expressions, voice tone, and input behavior.

[0685] "Optimization" refers to the adjustment or refinement of something to find the best possible state or solution for a particular purpose.

[0686] A "server" is a computer that processes and stores data and provides services to client terminals over a network.

[0687] In this invention, the system receives and analyzes the user's body composition data and basic physical ability data, and also analyzes the robot's operation data and the worker's emotional data, thereby recommending optimal exercise and maintenance programs. Specific embodiments are described below.

[0688] User data input phase

[0689] Users access the system using a smartphone. The smartphone displays a user interface and prompts the user to enter body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter their interests and sports.

[0690] Data transmission phase

[0691] The smartphone receives data entered by the user, formats it, and sends it to the server, which stores the data in an internal database and prepares it for analysis.

[0692] Data Preprocessing Phase

[0693] The server cleanses the data it receives, filling in outliers and missing values, and ensuring data quality using historical data and average values. The cleansed data is then formatted for analysis.

[0694] Data analysis phase

[0695] The server performs analysis based on the cleansed data, using machine learning algorithms and statistical methods to apply a model that recommends the most suitable exercise program for the user.

[0696] Emotional Engine Phase

[0697] The smartphone activates the emotion engine, which uses the smartphone's camera to analyze the user's facial expressions, voice tone, input behavior, etc. to recognize the user's emotional state. The recognized emotion data is used to prioritize the most suitable exercise program in the recommendation list.

[0698] Robot operation data input phase

[0699] The server receives and analyzes the operation data of the factory robots, including operating time, number of errors, maintenance history, etc.

[0700] Robot Maintenance Recommendation Phase

[0701] The optimal maintenance program is displayed on the user interface based on the operational data analyzed by the server, enabling efficient maintenance of the robot.

[0702] Worker emotion data input phase

[0703] The server receives the worker's emotional data, which is analyzed from camera footage and audio data to evaluate stress levels, fatigue, and other factors.

[0704] Maintenance program optimization phase

[0705] Based on the collected emotional data, the server optimizes the maintenance program in real time, thereby improving work efficiency and maintaining the health of workers.

[0706] Recommendation list generation and display phase

[0707] The server combines the analysis results with emotion data to generate a list of recommendations for optimal exercise and maintenance programs. The recommendation list is formatted in JSON format and sent to the smartphone. The smartphone displays this list on its user interface, allowing the user to easily understand and select.

[0708] User Feedback Phase

[0709] After practicing the suggested exercise program, users enter their impressions and satisfaction as feedback. This feedback is combined with emotional data to refine the algorithm for optimal performance. The smartphone then sends this data to a server, which then analyzes the feedback and emotional data to further improve the accuracy of the next recommendation.

[0710] Hardware and software used

[0711] The system mainly uses a smartphone and a server. Sentiment analysis is performed using the smartphone's camera and voice input device, and analysis software includes a machine learning algorithm (e.g., RandomForestRegressor) and a sentiment analysis engine (e.g., Affdex SDK).

[0712] Specific examples

[0713] The user enters body composition data, and the smartphone transmits the data to the server.

[0714] The server cleanses the data and generates a recommendation list based on the analysis results.

[0715] The smartphone displays a list of recommendations, and the user can select the most suitable exercise program.

[0716] The server receives operational data from factory robots and recommends new maintenance programs.

[0717] Obtains worker emotional data and provides optimized maintenance programs.

[0718] Example prompts to input to the generative AI model

[0719] "Create an application that uses robot operating data to recommend optimal maintenance programs and adds sentiment analysis for optimization."

[0720] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0721] Step 1:

[0722] The user inputs body composition data and basic physical ability data into a smartphone.

[0723] As specific examples of input, the user may enter data such as height (e.g., 160 cm), weight (e.g., 50 kg), body fat percentage (e.g., 15%), grip strength (e.g., 30 kg), endurance test results, and flexibility test results.

[0724] The entered data is temporarily stored in the smartphone's memory.

[0725] Step 2:

[0726] The terminal receives the data entered by the user and formats the data.

[0727] Specifically, the values ​​of each data field are formatted correctly and it is checked whether there are any missing values.

[0728] The formatted data is converted into a transmittable format such as JSON.

[0729] After this processing, the data is sent to the server.

[0730] Step 3:

[0731] The server stores the received data in a database.

[0732] First, the server parses the received JSON format data and stores it in each field of the database.

[0733] The data is appropriately labeled for analysis and used in subsequent processing.

[0734] Step 4:

[0735] The server retrieves the data from the database and performs the cleansing.

[0736] Specific examples include detecting and correcting outliers (e.g., body fat percentage above 100%) and filling in missing values ​​(using average data from the past).

[0737] The cleansed data is used as input for machine learning algorithms.

[0738] Step 5:

[0739] The server analyzes the cleansed data and generates a list of recommendations.

[0740] Specifically, we use a machine learning algorithm (e.g., RandomForestRegressor) to recommend the optimal exercise program based on the input data.

[0741] The analysis results in a recommendation list, which includes recommended exercises and programs.

[0742] Step 6:

[0743] The terminal receives the recommendation list from the server and displays it on the user interface.

[0744] Specifically, the server generates a recommendation list and sends it to the device in JSON format, which the device then analyzes and displays on the screen.

[0745] The user can review the recommendation list and select an exercise program based on it.

[0746] Step 7:

[0747] The user enters the operation data of the factory robot into a smartphone.

[0748] Specific examples of input include the robot's operating time (e.g., 2000 hours), the number of errors (e.g., 5), and maintenance history.

[0749] The entered data is temporarily stored in the smartphone's memory.

[0750] Step 8:

[0751] The terminal sends the robot's operation data to the server.

[0752] As with the user data transmission phase described above, the data is formatted, converted to JSON format, etc., and sent to the server.

[0753] The server stores the received data in a database and prepares it for analysis.

[0754] Step 9:

[0755] The server analyzes the operational data and generates the optimal maintenance program.

[0756] As a specific example of analysis, it predicts the risk of failure based on operational data and recommends necessary part replacements and regular inspection schedules.

[0757] The analysis results are formatted as a recommendation list in JSON format and sent to the device.

[0758] Step 10:

[0759] The terminal receives the recommendation list from the server and displays it on the user interface.

[0760] Users can review the recommended list and select the most suitable maintenance program.

[0761] Step 11:

[0762] The smartphone camera captures the worker's emotional data and sends it to the server.

[0763] Specifically, emotion analysis software (e.g., Affdex SDK) is used to analyze the facial expressions and vocal tones of workers to extract emotional data.

[0764] The extracted emotion data is sent to the server.

[0765] Step 12:

[0766] The server optimizes the maintenance program based on emotional data.

[0767] Analyzes emotional data and adjusts maintenance plans to take into account workers' stress levels and fatigue levels.

[0768] An optimized maintenance program is generated and sent to the terminal.

[0769] Step 13:

[0770] The terminal receives the optimized maintenance program and displays it on the user interface.

[0771] Users can check the optimal maintenance program and create an implementation plan.

[0772] Step 14:

[0773] Users carry out exercise and maintenance programs and then enter feedback into their smartphones.

[0774] Specific examples of input include impressions and satisfaction with the results of the practice.

[0775] The input feedback is sent from the terminal to the server.

[0776] Step 15:

[0777] The server analyzes the feedback data and refines the recommendation algorithm.

[0778] Specifically, the machine learning model is retrained based on the feedback data to improve the accuracy of the next recommendation.

[0779] The improved algorithm will be used in the next analysis.

[0780] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0781] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0782] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0783] [Third embodiment]

[0784] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0785] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0786] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0787] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0788] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0789] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0790] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0791] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0792] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0793] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0794] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0795] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0796] The system of the present invention receives and analyzes a user's body composition data and basic physical ability data, and recommends an optimal exercise program. The specific processing flow of the program of this system will be explained below in natural language.

[0797] User data input phase

[0798] The user accesses the system using a terminal. The terminal displays a user interface, prompting the user to enter body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter information about their interests and sports. This data is used in subsequent analysis steps, so it is important that it is entered accurately.

[0799] Data transmission phase

[0800] The data entered by the user is sent by the terminal to the server. The terminal formats the data to be sent and sends it to the server using a secure communication protocol. The server receives the data at a receiving port and stores it in an internal database.

[0801] Data Preprocessing Phase

[0802] The server cleanses the received data and fills in inaccurate data or missing values. For example, if the weight or height value is clearly abnormal, it fills in the data using past data or average values. This ensures the quality of the data used for analysis.

[0803] Data analysis phase

[0804] The server then uses the cleansed data for the actual analysis, applying machine learning algorithms and statistical methods to create models to recommend optimal exercise programs for users. Based on the analysis results, the server identifies the sports and exercise programs that best suit the user's body composition and basic physical abilities.

[0805] Recommendation List Generation Phase

[0806] Based on the analysis results, the server generates a list of recommended exercise programs and sports that are optimal for the user. This list also includes detailed descriptions of each sport and the reasons why that sport is suitable for the user. The generated recommendation list is then saved in a database in JSON format or similar.

[0807] Result display phase

[0808] The server sends the generated recommendation list to the device. The device displays the received recommendation list on the user interface, allowing the user to easily understand and select. Specific explanations of each exercise program and the reasons for its recommendation are provided in detail.

[0809] User Feedback Phase

[0810] After the user practices the proposed exercise program, they provide feedback on their impressions and satisfaction with the program. The device then sends this feedback to the server, which uses it to improve the recommendation algorithm.

[0811] As a concrete example, let's say a 14-year-old junior high school student is 160 cm tall, weighs 50 kg, and has a body fat percentage of 15%. If this user inputs their 100m sprint time and their interest in basketball, the server will use this data to recommend three events: track and field (especially sprinting), basketball, and soccer. The user can then select and execute an exercise program that suits them based on this list, and receive feedback afterwards.

[0812] In this way, this system automates a series of processes, from receiving user data to generating and presenting optimal exercise programs, and even improving the algorithm based on feedback, helping users establish exercise habits.

[0813] The processing flow will be explained below.

[0814] Step 1:

[0815] The user starts the application and accesses a screen for entering body composition data and basic physical ability data, including height, weight, body fat percentage, grip strength, endurance test results, flexibility test results, and sports of interest.

[0816] Step 2:

[0817] The terminal receives data entered by the user, converts it into an internal format, formats the converted data, and sends it to the server using a secure communication protocol.

[0818] Step 3:

[0819] The server receives the data at the receiving port and saves it in the database. The received data is stored in a temporary table and prepared for data analysis.

[0820] Step 4:

[0821] The server cleanses the data it receives, detects outliers and missing values, and imputes them as needed using historical data or averages, and then formats the cleansed data for analysis.

[0822] Step 5:

[0823] The server then applies machine learning algorithms to the cleansed data, using techniques such as clustering and recommender systems to analyze the exercise program and sport that best suits the user.

[0824] Step 6:

[0825] Based on the analysis results, the server generates a list of recommendations for exercise programs and sports that are optimal for the user, including detailed descriptions of each sport and the reasons for its recommendation.

[0826] Step 7:

[0827] The server converts the generated recommendation list into JSON or another appropriate data format and sends it to the device.

[0828] Step 8:

[0829] The device analyzes the received recommendation list and displays it on the user interface, allowing the user to confirm the suggested exercise programs and sports.

[0830] Step 9:

[0831] After the user has completed the proposed exercise program, they can input their impressions and satisfaction level through the feedback screen. The input feedback data is sent to the server via the device.

[0832] Step 10:

[0833] The server analyzes the received feedback data and stores it for algorithm refinement. The next analysis will use this feedback to improve accuracy.

[0834] The above is the specific processing flow of the system of the present invention. This series of steps allows the user to continuously carry out an optimal exercise program, which can help maintain health and improve sports performance.

[0835] Example 1

[0836] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0837] In modern health management, it is important to provide optimal exercise programs for individual users, but accurately analyzing the user's body composition data and basic physical ability data to generate an appropriate recommendation list is a challenge. In addition, it is necessary to supplement inaccurate or missing data and reflect user feedback to continuously improve the recommendation algorithm.

[0838] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0839] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for transmitting the input data to the server using a secure communication protocol, means for storing the transmitted data in an internal database and cleansing it to supplement inaccurate or missing data, means for analyzing the cleansed data using a machine learning algorithm and generating a recommendation list for recommending exercise programs suitable for the user based on the analysis results, means for displaying the recommendation list to the user, and means for receiving user feedback on exercise programs attempted based on the recommendation list and improving the recommendation algorithm based on the feedback. This makes it possible to provide each user with a highly accurate exercise program and to supplement inaccurate data and improve the algorithm based on the feedback.

[0840] "Body composition data" refers to basic data about the user's body, including height, weight, body fat percentage, and the like.

[0841] "Basic physical ability data" is data that indicates the user's basic physical strength and athletic ability, and includes grip strength, endurance test results, flexibility test results, and the like.

[0842] A "secure communication protocol" is a protocol that ensures security when sending and receiving data, and HTTPS is an example of this.

[0843] "Server" refers to a computer system that receives, stores, analyzes data, and provides information to users.

[0844] The "internal database" is a data storage system installed within the server for storing received data and analysis results.

[0845] "Cleansing" refers to the process of correcting inaccurate data and filling in missing values ​​in order to improve data quality.

[0846] "Machine learning algorithms" are artificial intelligence techniques used to analyze data and find patterns and trends, such as random forests and support vector machines.

[0847] The "recommended list" refers to a list of exercise programs and sports that are optimal for the user, generated based on the analysis results.

[0848] "User interface" refers to the screen and operating environment through which a user interacts with a system.

[0849] "Feedback" refers to information about the user's impressions and satisfaction with the exercise program they have completed, and is used to improve the system.

[0850] The system of the present invention receives and analyzes the user's body composition data and basic physical ability data, and recommends an optimal exercise program. The flow of the system for specifically implementing the present invention will now be described.

[0851] Users access this system using a device such as a personal computer or smartphone. The device displays a user interface through a web browser or mobile application, allowing users to input body composition data (height, weight, body fat percentage, etc.) and basic physical ability data (grip strength, endurance test results, flexibility test results, etc.). Users are also prompted to input their interests and sports.

[0852] When a user enters data and clicks the "Submit" button, the terminal formats the input data into JSON format. The formatted data is then sent to the server using a secure communication protocol (e.g., HTTPS). The server receives the data sent from the terminal on a specific receiving port and stores it in an internal database.

[0853] Next, the server cleanses the data stored in the database. Cleansing is a process that corrects inaccurate data and fills in missing values ​​to improve data quality. For example, it detects abnormal values ​​such as a weight of 0 kg and fills them in using past data or average values.

[0854] The cleansed data is then analyzed using machine learning algorithms (e.g., random forests and support vector machines). The server then performs the analysis to identify the best exercise program for the user and generates a list of recommendations based on the results. The recommendation list includes a detailed description of each exercise program or sport and the reasons why that sport is suitable for the user.

[0855] The generated recommendation list is stored in the database again and sent from the server to the device, which displays the received recommendation list on the user interface, allowing the user to easily understand and select.

[0856] The user reviews the displayed list of recommendations and selects the most suitable exercise program. After completing the exercise program, the user provides feedback by entering their impressions and satisfaction. The device sends this feedback to the server, which then stores it in a database. The feedback information is used to improve the recommendation algorithm for the next exercise program.

[0857] For example, if a 14-year-old junior high school student inputs his / her height of 160 cm, weight of 50 kg, body fat percentage of 15%, 13 seconds for 100 m sprint time, and interest in basketball, the server will use this data to recommend three sports: track and field (especially sprinting), basketball, and soccer. The user can then select an appropriate exercise program and provide feedback later.

[0858] An example of a prompt sentence would be, "A 14-year-old junior high school student has entered his body composition data and basic physical ability data. His height is 160 cm, his weight is 50 kg, his body fat percentage is 15%, his 100m sprint time is 13 seconds, and he has an interest in basketball. Based on this data, please recommend the most suitable exercise program for this junior high school student." This sentence is input into the generative AI model.

[0859] The above is a specific embodiment of the present invention, which provides an automated series of processes, from receiving user data, analyzing it, generating and presenting a recommendation list, and improving the algorithm based on the feedback, to help users establish exercise habits.

[0860] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0861] Step 1:

[0862] Users access the system using a terminal such as a personal computer or smartphone. A user interface is displayed, and the user inputs body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results), as well as the sports they are interested in. The terminal receives the input data, which is then collected and saved on the terminal.

[0863] Step 2:

[0864] When the user has completed entering all the data and clicked the "Submit" button, the device will format the data into JSON format and send it to the server using a secure communication protocol such as HTTPS. In this operation, the device sends the input data, and the server stores the received data in its internal database.

[0865] Step 3:

[0866] The server stores the received data in an internal database. The stored data is then cleansed. Specifically, inaccurate data and missing values ​​are detected and filled in using past data and average values. For example, if an extremely low or abnormal weight value is entered, the server replaces it with the average value. The output is the cleansed data.

[0867] Step 4:

[0868] The cleansed data is then analyzed on the server using machine learning algorithms. Specifically, algorithms such as random forests and support vector machines are applied to the user's data to create a model that recommends the optimal exercise program. This process produces the analysis results.

[0869] Step 5:

[0870] Based on the analysis results, the server generates a list of recommendations for exercise programs and sports that are optimal for the user. This list includes a detailed description of each exercise program and the reasons why that sport is suitable for the user. The generated recommendation list is saved in a database in a format such as JSON. The output is the recommendation list.

[0871] Step 6:

[0872] The server sends the recommendation list stored in the database to the terminal, which displays the received recommendation list on the user interface so that the user can easily understand and select. The output of this step is the recommendation list that is displayed to the user.

[0873] Step 7:

[0874] The user checks the proposed exercise program and carries it out as necessary. After practicing the program, the user again inputs data into the device to provide feedback on their impressions and satisfaction. This data is collected as input data.

[0875] Step 8:

[0876] The device sends user feedback data to the server, which stores the feedback in an internal database and uses this data to refine the recommendation algorithm. This process allows the system to continually improve the accuracy of exercise program recommendations based on user feedback.

[0877] Through the above steps, the system receives the user's body composition data and basic physical ability data, and supports continuous health management by recommending daily exercise programs and providing feedback.

[0878] (Application example 1)

[0879] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0880] Users who aim to manage their health and establish exercise habits need not only to be provided with effective exercise programs based on body composition data and basic physical ability data, but also to be provided with comprehensive health support by optimizing daily dietary content and proposing healthy delivery menus. The present invention aims to solve this problem and provide a system that allows users to easily maintain their health.

[0881] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0882] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for analyzing the input data and generating a recommendation list for recommending exercise programs and meal menus suitable for the user based on the analysis results, means for displaying the recommendation list to the user, and means for proposing healthy delivery menus suitable for the user based on the recommendation list. This allows the user to easily receive effective exercise programs and optimal meal menus, thereby enabling comprehensive health management.

[0883] "Body composition data input by the user" refers to information that the user inputs or provides via the terminal, data relating to the user's body composition, such as weight, height, and body fat percentage.

[0884] "Basic physical ability data" is data relating to the user's basic physical abilities such as grip strength, endurance, flexibility, etc.

[0885] "Analysis" is the process of evaluating received data using machine learning algorithms and statistical methods to derive analytical results suitable for a specific purpose.

[0886] The "recommended list" is a list of exercise programs and meal menus that are optimal for the user, organized based on the results of the analysis.

[0887] A "healthy delivery menu" is a set of healthy meal options recommended based on the user's health condition and physical data.

[0888] "Feedback" refers to information that a user sends back to the system about the results and impressions of the exercise program or meal menu provided to them after they have put it into practice.

[0889] A "recommendation algorithm" is a calculation method or logic for automatically selecting the optimal exercise program or meal menu based on user data.

[0890] The present invention provides a system for proposing optimal exercise programs and meal menus based on body composition data and basic physical ability data acquired from a user. This system comprises the following steps.

[0891] System Configuration

[0892] Hardware and Software Configuration

[0893] This system consists of a user device (smartphone app), a server (cloud server), and a database. The specific technology stack is as follows:

[0894] On the user device, a smartphone application using React Native is implemented.

[0895] On the server side, a web server is built using Node.js and Express, and MongoDB is used as the database.

[0896] HTTPS is used for data communication to ensure secure communication, and JWT (JSON Web Token) is used for authentication.

[0897] User data input phase

[0898] Users operate the device to input their body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results), as well as the types of cuisine they are interested in and their food preferences.

[0899] Data transmission phase

[0900] The device collects data entered by the user and securely transmits it to the server using HTTPS, where it is formatted into a standard format such as JSON.

[0901] Data Preprocessing Phase

[0902] The server cleanses the data it receives, and if there are any inaccurate or missing data, it fills them in using historical data or average values.

[0903] Data analysis phase

[0904] The server then uses the cleansed data to analyze it using machine learning algorithms and statistical methods. Specifically, it analyzes the user's body composition data and basic physical ability data, and applies a model to recommend optimal exercise programs and healthy delivery menus.

[0905] Recommendation List Generation Phase

[0906] Based on the analysis, the server generates a list of recommended exercise programs and dietary menus that are optimal for the user, including detailed descriptions of each exercise and diet and the reasons why they are suitable for the user.

[0907] Result display phase

[0908] The server sends the generated recommendation list to the user's device, which then displays the received recommendation list on its user interface, allowing the user to easily understand and select items.

[0909] User Feedback Phase

[0910] After the user has put into practice the suggested exercise program or meal menu, the system also has a function to provide feedback on the results and impressions. The feedback data is then sent back to the server and used to improve the algorithm.

[0911] Specific examples

[0912] For example, suppose a user enters their height (170cm), weight (65kg), and body fat percentage (20%) as body composition data, and their basic physical ability data (grip strength, endurance, and flexibility test results), and also enters that they are interested in "Italian cuisine." Based on this information, the server generates the following prompt and performs analysis:

[0913] Example prompt sentence:

[0914] The user's body composition data is as follows:

[0915] Height: 170 cm

[0916] Weight: 65 kg

[0917] Body fat percentage: 20%

[0918] The user has the following basic physical ability data:

[0919] Grip strength: 40kg

[0920] Endurance: Moderate

[0921] Flexibility: High

[0922] Suggest a healthy Italian menu suitable for this user.

[0923] Based on these prompts, the system generates and provides optimal exercise programs and meal plans to the user, such as healthy delivery menu suggestions like "bruschetta and fruit for breakfast, grilled chicken salad for lunch, and Italian salmon and vegetable soup for dinner."

[0924] In this way, users receive individually optimized exercise programs and meal menus, enabling comprehensive health management.

[0925] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0926] Step 1:

[0927] The user enters body composition data and basic physical ability data through the device. Specifically, the user enters information such as height, weight, body fat percentage, grip strength, endurance test results, and flexibility test results. The user also enters their interests and the types of cuisine they are interested in. The entered data is saved in temporary storage on the device and formatted into JSON format. Once the input data has been formatted, the system proceeds to the next step.

[0928] Step 2:

[0929] The formatted user data is sent from the device to the server. Here, secure communication is performed using HTTPS. The server receives the received JSON-formatted data via a receiving port and stores it in a database. In this step, the input data (body composition data, basic physical ability data, and types of cuisine of interest) is transmitted to the server, which stores it in the server's database.

[0930] Step 3:

[0931] The server begins the process of cleansing the data received from the database. Specifically, if there are abnormal values ​​for weight or height, they are filled in using past data or average values. Also, if there is missing data, they are filled in with estimated values. After the inaccurate data has been cleansed, the accurate data can be used for analysis.

[0932] Step 4:

[0933] After the cleansing process is complete, the server performs data analysis. This analysis uses machine learning algorithms and statistical methods. The goal is to identify the optimal exercise program and meal plan for the user. The server generates prompts for the analysis. For example, the server might include something like, "The user's body composition data is as follows: height: 170 cm, weight: 65 kg...Please suggest a healthy Italian menu suitable for this user." The analysis results are organized into a recommendation list.

[0934] Step 5:

[0935] The server stores the generated recommendation list in a database and sends it to the device. The data is formatted appropriately and displayed on the device. The recommendation list includes detailed descriptions of each exercise program and meal plan, as well as reasons for its recommendation.

[0936] Step 6:

[0937] The user can view the recommended list of exercise programs and dietary menus displayed on the device and put them into practice. Each program includes detailed instructions on specific methods, procedures, and precautions.

[0938] Step 7:

[0939] After practicing, users enter feedback via their device. The feedback includes the effectiveness of the program, their impressions, and their level of satisfaction. The feedback data is then sent back to the server, which receives the data and stores it in a database. Based on the feedback information, the analysis algorithm is improved, and the accuracy of recommendations will increase in the future.

[0940] Through these steps, users receive individually optimized exercise programs and meal plans, enabling them to achieve comprehensive health management.

[0941] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0942] The system of the present invention receives and analyzes the user's body composition data and basic physical ability data, and recommends the optimal exercise program. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the recommendations can be optimized with even greater precision.

[0943] User data input phase

[0944] The user accesses the system using a terminal. The terminal displays a user interface, prompting the user to enter body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter information about their interests and sports. Since this data is used in the analysis step, it is important that it is entered accurately.

[0945] Data transmission phase

[0946] The device receives the data entered by the user, formats it, and sends it to the server, which stores the data in an internal database and prepares it for analysis.

[0947] Data Preprocessing Phase

[0948] The server cleanses the data it receives and fills in outliers and missing values. It ensures data quality by using historical data and average values. The cleansed data is then formatted for analysis.

[0949] Data analysis phase

[0950] The server performs analysis based on the cleansed data. Using machine learning algorithms and statistical methods, it applies a model to recommend the most suitable exercise program for the user. Based on the analysis results, it identifies the sports and exercise programs that are best suited to the user's body composition and basic physical abilities.

[0951] Emotional Engine Phase

[0952] When displaying the recommendation list, the device activates an emotion engine. The emotion engine analyzes the user's facial expressions, voice tone, input behavior, etc. to recognize the user's emotional state. The emotion data recognized by the emotion engine helps prioritize the most suitable exercise program for the user in the recommendation list. The content of the list is also optimized in real time based on the emotion data.

[0953] Recommendation list generation and display phase

[0954] The server combines the analysis results with the emotion engine data to generate a list of recommendations for optimal exercise programs and sports. The generated recommendation list is formatted in JSON format or similar and sent to the device. The device displays this list on its user interface, allowing the user to easily understand and select.

[0955] User Feedback Phase

[0956] After the user practices the suggested exercise program, they enter their impressions and satisfaction as feedback. This feedback is combined with emotional data to refine the algorithm for optimal performance. The device then sends this data to the server, which then analyzes the feedback and emotional data to further improve the accuracy of the next recommendation.

[0957] As a concrete example, consider the case where a 14-year-old junior high school student is 160 cm tall, weighs 50 kg, and has a body fat percentage of 15%, and enters his or her 100-meter sprint time and interest in basketball. Based on this data, the server will create a recommendation list of three events: track and field (especially sprinting), basketball, and soccer. Furthermore, the emotion engine analyzes the user's facial expressions and input behavior, and can prioritize events that the user is particularly interested in or enjoys. The user can select and perform an exercise program that suits them based on this list, and then enter feedback afterwards.

[0958] In this way, this system automates a series of processes, from receiving user data to generating and presenting optimal exercise programs, and even making highly accurate suggestions that incorporate emotional data and improvements based on feedback, thereby helping users establish exercise habits.

[0959] The processing flow will be explained below.

[0960] Step 1:

[0961] The user starts the application and accesses a screen for entering body composition data and basic physical ability data, including height, weight, body fat percentage, grip strength, endurance test results, flexibility test results, and sports of interest.

[0962] Step 2:

[0963] The terminal receives data entered by the user, converts it into an internal format, formats the converted data, and sends it to the server using a secure communication protocol.

[0964] Step 3:

[0965] The server receives the data at the receiving port and saves it in the database. The received data is stored in a temporary table and prepared for data analysis.

[0966] Step 4:

[0967] The server cleanses the data it receives, detects outliers and missing values, and imputes them as needed using historical data or average values, and then formats the cleansed data for analysis.

[0968] Step 5:

[0969] The server then applies machine learning algorithms to the cleansed data, using techniques such as clustering and recommender systems to analyze the exercise program and sport that best suits the user.

[0970] Step 6:

[0971] Based on the analysis results, the server generates a list of recommendations for exercise programs and sports that are optimal for the user, including detailed descriptions of each sport and the reasons for its recommendation.

[0972] Step 7:

[0973] The device activates the emotion engine, and when the user browses the recommendation list, it analyzes parameters such as facial expressions, voice tone, and input behavior. Based on this data, the emotion engine recognizes the user's emotional state and generates emotion data.

[0974] Step 8:

[0975] The server receives the emotion data generated by the emotion engine and optimizes the recommendation list in real time, for example, by prioritizing the display of sports that the user is interested in or enjoys.

[0976] Step 9:

[0977] The device receives the optimized recommendation list and displays it on the user interface, allowing the user to confirm the suggested exercise program or sport based on the display.

[0978] Step 10:

[0979] After the user has completed the proposed exercise program, they can input their impressions and satisfaction level through the feedback screen. The input feedback data is sent to the server via the device.

[0980] Step 11:

[0981] The server analyzes the received feedback data and stores it for algorithm refinement, including sentiment data, to improve the accuracy of the next recommendation.

[0982] The above is the specific processing flow of the system of the present invention. This series of steps allows the user to continuously carry out an optimal exercise program, which can help maintain health and improve sports performance.

[0983] Example 2

[0984] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0985] Conventional exercise program recommendation systems have problems with reduced recommendation accuracy due to inaccuracies or missing data when analyzing individual user data. Furthermore, these systems do not take into account the user's emotional state, making it difficult to provide optimal exercise programs based on the user's motivation and interests. Furthermore, they do not fully utilize user feedback, resulting in insufficient improvements to improve recommendation accuracy for the next time.

[0986] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0987] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for cleansing the input data and completing inaccurate or missing data, means for analyzing the cleansed data using a machine learning algorithm and generating a recommendation list for recommending exercise programs suitable for the user based on the analysis results, means for displaying the recommendation list to the user, and means for recognizing the user's emotional state and optimizing the contents of the recommendation list in real time based on the emotional state. This makes it possible to provide an optimal exercise program based on the user's emotional state while ensuring data quality, and further to utilize user feedback to improve the accuracy of next recommendations.

[0988] The "means for receiving body composition data and basic physical ability data input by the user" refers to a mechanism by which a user accesses the system using a terminal and inputs data such as height, weight, body fat percentage, grip strength, endurance test results, and flexibility test results.

[0989] The "means for cleansing the input data and supplementing inaccurate or missing data" refers to a mechanism in which the server analyzes the data it receives, corrects and supplements outliers and missing values, and performs processing to ensure the quality of the data.

[0990] "Means for analyzing using a machine learning algorithm and generating a recommendation list for recommending suitable exercise programs to the user based on the analysis results" refers to a mechanism in which the server applies a machine learning algorithm to the cleansed data, identifies the exercise program that is best suited to the user's body composition and basic physical abilities, and generates the results as a list.

[0991] The "means for displaying the recommendation list to the user" is a mechanism for formatting the generated recommendation list in JSON format or the like and displaying it to the user through a user interface.

[0992] The "means for recognizing the emotional state of the user and optimizing the contents of the recommendation list in real time based on said emotional state" is a mechanism that uses an emotion engine to analyze the user's facial expressions, voice tone, and input behavior, recognizes the user's emotional state, and then optimizes the contents of the recommendation list.

[0993] The "means for receiving user feedback and improving the recommendation algorithm based on said feedback" is a mechanism for receiving feedback such as user impressions and satisfaction regarding the exercise program that the user has performed, and improving the recommendation algorithm based on that feedback.

[0994] The "emotion engine" is a mechanism that analyzes the user's facial expressions, voice tone, input behavior, etc. to recognize the user's real-time emotional state.

[0995] The system of the present invention receives and analyzes the user's body composition data and basic physical ability data, and recommends the optimal exercise program. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the recommendations can be optimized with even greater precision.

[0996] User data input phase

[0997] The user accesses the system using a terminal. The terminal displays a dedicated user interface, prompting the user to enter detailed body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter their interests and sports that interest them. Accurate data entry is important for the analysis step, so the user is urged to enter the data appropriately.

[0998] Data transmission phase

[0999] The terminal formats the data entered by the user and converts it into a unified format (e.g., JSON format). The terminal sends the formatted data to the server. If an error occurs during transmission, it attempts to resend. The server stores the received data in a database and prepares it for analysis.

[1000] Data Preprocessing Phase

[1001] The server cleanses the data it receives and corrects and completes outliers and missing values. For example, if the height entered by the user is very small, it will automatically be completed by referring to past data and average values. The server then formats the cleansed data for analysis. Specifically, it standardizes the necessary numerical values ​​(for example, to a range of 0 to 1).

[1002] Data analysis phase

[1003] The server then uses machine learning algorithms to analyze the cleansed data. Specific algorithms include regression analysis and clustering. The server then selects the optimal exercise program based on the analysis results. For example, if a user's endurance test results are high, an exercise program that emphasizes endurance will be recommended.

[1004] Emotional Engine Phase

[1005] When the device displays the recommendation list, it activates an emotion engine. The emotion engine analyzes the user's facial expressions, voice tone, and input behavior in real time to recognize the user's emotional state. Based on the recognized emotion data, it prioritizes the most suitable exercise program for the user from the recommendation list. It is also possible to optimize the list contents in real time.

[1006] Recommendation list generation and display phase

[1007] The server combines the analysis results with data from the emotion engine to generate a list of recommendations for optimal exercise programs and sports. The generated recommendation list is formatted in JSON format or similar and sent to the device. The device then displays the recommendation list on its user interface, making it easy for the user to understand and select. Specific examples include a function to display videos explaining the benefits of each exercise program and how to perform them.

[1008] User Feedback Phase

[1009] The user practices the proposed exercise program and then inputs feedback, such as their impressions and level of satisfaction, into the device. This effectively collects the user's actual level of satisfaction. The device then sends the feedback data to the server, which analyzes it along with emotional data and uses it to improve the accuracy of the next recommendation.

[1010] Specific examples

[1011] For example, if a 14-year-old junior high school student inputs his / her height of 160 cm, weight of 50 kg, and body fat percentage of 15%, as well as data indicating his / her 100-meter sprint time and interest in basketball, the server will use this data to recommend three events: track and field (especially sprinting), basketball, and soccer. Furthermore, the emotion engine analyzes the user's facial expressions and input behavior, and prioritizes events that the user is particularly interested in or enjoys. The user can select an exercise program that suits them based on this list, and then provide feedback to help improve the system's accuracy.

[1012] Prompt Sentence Examples

[1013] An example of a prompt to input to a generative AI model is as follows:

[1014] "Enter the following information for a 14-year-old junior high school student: height 160cm, weight 50kg, body fat percentage 15%, 100m sprint time, and interest in basketball. Generate and present a list of optimal exercise programs and sports."

[1015] In this way, this system automates a series of processes, from receiving user data to generating and presenting optimal exercise programs, and even making highly accurate suggestions that incorporate emotional data and improvements based on feedback, thereby helping users establish exercise habits.

[1016] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1017] Step 1: User data input phase

[1018] A user accesses the system using a terminal. The terminal displays a user interface and prompts the user to input body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results).

[1019] Input: The user manually inputs each piece of data (e.g., height 160 cm, weight 50 kg).

[1020] Data processing: The terminal checks input data for errors in real time and prompts correction of any inaccurate data.

[1021] Output: The formatted input data after error checking.

[1022] Step 2: Data transmission phase

[1023] The terminal sends the formatted data to the server, where it is converted into a unified format (e.g., JSON format).

[1024] Input: Body composition data and basic physical ability data entered by the user.

[1025] Data processing: The terminal converts the formatted data into JSON format.

[1026] Output: JSON formatted data is sent to the server.

[1027] Step 3: Data preprocessing phase

[1028] The server analyzes the received data, cleansing it, and complements outliers and missing values.

[1029] Input: Body composition data and basic physical ability data sent in JSON format.

[1030] Data processing: Carry out a cleansing process, for example, to fill in missing body fat percentages.

[1031] Output: Cleansed, high-quality data.

[1032] Step 4: Data analysis phase

[1033] The server analyzes the cleansed data using machine learning algorithms and applies a model that recommends the most suitable exercise program for the user.

[1034] Input: Cleansed body composition data and basic physical performance data.

[1035] Data calculations: Apply machine learning algorithms (e.g., regression analysis, clustering) to obtain analytical results.

[1036] Output: A list of recommended exercise programs based on the analysis results.

[1037] Step 5: Emotional Engine Phase

[1038] The device activates an emotion engine to analyze the user's emotional state, analyzing facial expressions, voice tone, and input behavior in real time to obtain emotional data.

[1039] Input: User's facial expression data, voice data, and input behavior data.

[1040] Data Calculation: The emotion engine analyzes these data and recognizes the user's emotional state (e.g., excitement, interest).

[1041] Output: Emotion data is sent to the server.

[1042] Step 6: Recommendation list generation and display phase

[1043] The server combines the analysis results with the emotion data to generate a recommendation list, which is then formatted in JSON format or similar and sent to the device.

[1044] Input: Analysis results of machine learning algorithms and sentiment data.

[1045] Data processing: Format the recommendation list and convert it into a format suitable for the user interface (e.g., JSON format).

[1046] Output: The formatted recommendation list is sent to the terminal and displayed on the user interface.

[1047] Step 7: User Feedback Phase

[1048] The user practices the proposed exercise program and inputs their impressions and satisfaction level into the device, and the feedback data is sent to the server.

[1049] Input: Feedback data entered by the user after practice.

[1050] Data calculation: The server analyzes the feedback data and refines the algorithm to improve the accuracy of the next recommendation.

[1051] Output: A list of recommendations for next time with an improved algorithm.

[1052] Through this series of processes, the system can provide the user with the optimal exercise program and continue to improve the accuracy of its next suggestions based on feedback and emotional data.

[1053] (Application example 2)

[1054] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1055] Conventional robot maintenance systems face challenges in creating efficient maintenance programs because it is difficult to fully analyze robot operation and maintenance data and they are unable to optimize programs taking into account the emotional state of workers. This leads to incomplete robot maintenance, increasing the risk of breakdowns and reduced productivity. Furthermore, maintenance plans that ignore worker stress and fatigue can have a negative impact on worker health and work efficiency.

[1056] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1057] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for analyzing the input data and generating a recommendation list for recommending an exercise program suitable for the user based on the analysis results, means for displaying the recommendation list to the user, means for receiving robot operation data and recommending an optimal maintenance program based on the data, and means for analyzing worker emotion data and optimizing the maintenance program based on the emotion data. This makes it possible to create a more effective and efficient maintenance program based on the robot operation data and the worker emotion data.

[1058] "Body composition data" refers to information about a user's physical components, such as height, weight, and body fat percentage.

[1059] "Basic physical ability data" refers to data that indicates the user's basic physical abilities, such as grip strength, endurance test results, and flexibility test results.

[1060] "Analysis" refers to the process of processing received data and drawing conclusions or recommendations based on it.

[1061] The "recommended list" is a list of optimal exercise programs and maintenance programs provided to the user based on the analysis results.

[1062] "Operational data" refers to data related to the operation of a robot, such as the robot's operating time, number of errors, and maintenance history.

[1063] A "maintenance program" is a plan for a series of construction works, cleaning, part replacement, etc. required to maintain the normal operation of a robot.

[1064] "Worker emotional data" refers to information indicating stress or fatigue levels obtained from the worker's facial expressions, voice tone, and input behavior.

[1065] "Optimization" refers to the adjustment or refinement of something to find the best possible state or solution for a particular purpose.

[1066] A "server" is a computer that processes and stores data and provides services to client terminals over a network.

[1067] In this invention, the system receives and analyzes the user's body composition data and basic physical ability data, and also analyzes the robot's operation data and the worker's emotional data, thereby recommending optimal exercise and maintenance programs. Specific embodiments are described below.

[1068] User data input phase

[1069] Users access the system using a smartphone. The smartphone displays a user interface and prompts the user to enter body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter their interests and sports.

[1070] Data transmission phase

[1071] The smartphone receives data entered by the user, formats it, and sends it to the server, which stores the data in an internal database and prepares it for analysis.

[1072] Data Preprocessing Phase

[1073] The server cleanses the data it receives, filling in outliers and missing values, and ensuring data quality using historical data and average values. The cleansed data is then formatted for analysis.

[1074] Data analysis phase

[1075] The server performs analysis based on the cleansed data, using machine learning algorithms and statistical methods to apply a model that recommends the most suitable exercise program for the user.

[1076] Emotional Engine Phase

[1077] The smartphone activates the emotion engine, which uses the smartphone's camera to analyze the user's facial expressions, voice tone, input behavior, etc. to recognize the user's emotional state. The recognized emotion data is used to prioritize the most suitable exercise program in the recommendation list.

[1078] Robot operation data input phase

[1079] The server receives and analyzes the operation data of the factory robots, including operating time, number of errors, maintenance history, etc.

[1080] Robot Maintenance Recommendation Phase

[1081] The optimal maintenance program is displayed on the user interface based on the operational data analyzed by the server, enabling efficient maintenance of the robot.

[1082] Worker emotion data input phase

[1083] The server receives the worker's emotional data, which is analyzed from camera footage and audio data to evaluate stress levels, fatigue, and other factors.

[1084] Maintenance program optimization phase

[1085] Based on the collected emotional data, the server optimizes the maintenance program in real time, thereby improving work efficiency and maintaining the health of workers.

[1086] Recommendation list generation and display phase

[1087] The server combines the analysis results with emotion data to generate a list of recommendations for optimal exercise and maintenance programs. The recommendation list is formatted in JSON format and sent to the smartphone. The smartphone displays this list on its user interface, allowing the user to easily understand and select.

[1088] User Feedback Phase

[1089] After practicing the suggested exercise program, users enter their impressions and satisfaction as feedback. This feedback is combined with emotional data to refine the algorithm for optimal performance. The smartphone then sends this data to a server, which then analyzes the feedback and emotional data to further improve the accuracy of the next recommendation.

[1090] Hardware and software used

[1091] The system mainly uses a smartphone and a server. Sentiment analysis is performed using the smartphone's camera and voice input device, and analysis software includes a machine learning algorithm (e.g., RandomForestRegressor) and a sentiment analysis engine (e.g., Affdex SDK).

[1092] Specific examples

[1093] The user enters body composition data, and the smartphone transmits the data to the server.

[1094] The server cleanses the data and generates a recommendation list based on the analysis results.

[1095] The smartphone displays a list of recommendations, and the user can select the most suitable exercise program.

[1096] The server receives operational data from factory robots and recommends new maintenance programs.

[1097] Obtains worker emotional data and provides optimized maintenance programs.

[1098] Example prompts to input to the generative AI model

[1099] "Create an application that uses robot operating data to recommend optimal maintenance programs and adds sentiment analysis for optimization."

[1100] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1101] Step 1:

[1102] The user inputs body composition data and basic physical ability data into a smartphone.

[1103] As specific examples of input, the user may enter data such as height (e.g., 160 cm), weight (e.g., 50 kg), body fat percentage (e.g., 15%), grip strength (e.g., 30 kg), endurance test results, and flexibility test results.

[1104] The entered data is temporarily stored in the smartphone's memory.

[1105] Step 2:

[1106] The terminal receives the data entered by the user and formats the data.

[1107] Specifically, the values ​​of each data field are formatted correctly and it is checked whether there are any missing values.

[1108] The formatted data is converted into a transmittable format such as JSON.

[1109] After this processing, the data is sent to the server.

[1110] Step 3:

[1111] The server stores the received data in a database.

[1112] First, the server parses the received JSON format data and stores it in each field of the database.

[1113] The data is appropriately labeled for analysis and used in subsequent processing.

[1114] Step 4:

[1115] The server retrieves the data from the database and performs the cleansing.

[1116] Specific examples include detecting and correcting outliers (e.g., body fat percentage above 100%) and filling in missing values ​​(using average data from the past).

[1117] The cleansed data is used as input for machine learning algorithms.

[1118] Step 5:

[1119] The server analyzes the cleansed data and generates a list of recommendations.

[1120] Specifically, we use a machine learning algorithm (e.g., RandomForestRegressor) to recommend the optimal exercise program based on the input data.

[1121] The analysis results in a recommendation list, which includes recommended exercises and programs.

[1122] Step 6:

[1123] The terminal receives the recommendation list from the server and displays it on the user interface.

[1124] Specifically, the server generates a recommendation list and sends it to the device in JSON format, which the device then analyzes and displays on the screen.

[1125] The user can review the recommendation list and select an exercise program based on it.

[1126] Step 7:

[1127] The user enters the operation data of the factory robot into a smartphone.

[1128] Specific examples of input include the robot's operating time (e.g., 2000 hours), the number of errors (e.g., 5), and maintenance history.

[1129] The entered data is temporarily stored in the smartphone's memory.

[1130] Step 8:

[1131] The terminal sends the robot's operation data to the server.

[1132] As with the user data transmission phase described above, the data is formatted, converted to JSON format, etc., and sent to the server.

[1133] The server stores the received data in a database and prepares it for analysis.

[1134] Step 9:

[1135] The server analyzes the operational data and generates the optimal maintenance program.

[1136] As a specific example of analysis, it predicts the risk of failure based on operational data and recommends necessary part replacements and regular inspection schedules.

[1137] The analysis results are formatted as a recommendation list in JSON format and sent to the device.

[1138] Step 10:

[1139] The terminal receives the recommendation list from the server and displays it on the user interface.

[1140] Users can review the recommended list and select the most suitable maintenance program.

[1141] Step 11:

[1142] The smartphone camera captures the worker's emotional data and sends it to the server.

[1143] Specifically, emotion analysis software (e.g., Affdex SDK) is used to analyze the facial expressions and vocal tones of workers to extract emotional data.

[1144] The extracted emotion data is sent to the server.

[1145] Step 12:

[1146] The server optimizes the maintenance program based on emotional data.

[1147] Analyzes emotional data and adjusts maintenance plans to take into account workers' stress levels and fatigue levels.

[1148] An optimized maintenance program is generated and sent to the terminal.

[1149] Step 13:

[1150] The terminal receives the optimized maintenance program and displays it on the user interface.

[1151] Users can check the optimal maintenance program and create an implementation plan.

[1152] Step 14:

[1153] Users carry out exercise and maintenance programs and then enter feedback into their smartphones.

[1154] Specific examples of input include impressions and satisfaction with the results of the practice.

[1155] The input feedback is sent from the terminal to the server.

[1156] Step 15:

[1157] The server analyzes the feedback data and refines the recommendation algorithm.

[1158] Specifically, the machine learning model is retrained based on the feedback data to improve the accuracy of the next recommendation.

[1159] The improved algorithm will be used in the next analysis.

[1160] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1161] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1162] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1163] [Fourth embodiment]

[1164] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1165] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1166] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1167] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1168] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1169] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1170] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1171] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1172] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1173] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1174] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1175] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1176] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1177] The system of the present invention receives and analyzes a user's body composition data and basic physical ability data, and recommends an optimal exercise program. The specific processing flow of the program of this system will be explained below in natural language.

[1178] User data input phase

[1179] The user accesses the system using a terminal. The terminal displays a user interface, prompting the user to enter body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter information about their interests and sports. This data is used in subsequent analysis steps, so it is important that it is entered accurately.

[1180] Data transmission phase

[1181] The data entered by the user is sent by the terminal to the server. The terminal formats the data to be sent and sends it to the server using a secure communication protocol. The server receives the data at a receiving port and stores it in an internal database.

[1182] Data Preprocessing Phase

[1183] The server cleanses the received data and fills in inaccurate data or missing values. For example, if the weight or height value is clearly abnormal, it fills in the data using past data or average values. This ensures the quality of the data used for analysis.

[1184] Data analysis phase

[1185] The server then uses the cleansed data for the actual analysis, applying machine learning algorithms and statistical methods to create models to recommend optimal exercise programs for users. Based on the analysis results, the server identifies the sports and exercise programs that best suit the user's body composition and basic physical abilities.

[1186] Recommendation List Generation Phase

[1187] Based on the analysis results, the server generates a list of recommended exercise programs and sports that are optimal for the user. This list also includes detailed descriptions of each sport and the reasons why that sport is suitable for the user. The generated recommendation list is then saved in a database in JSON format or similar.

[1188] Result display phase

[1189] The server sends the generated recommendation list to the device. The device displays the received recommendation list on the user interface, allowing the user to easily understand and select. Specific explanations of each exercise program and the reasons for its recommendation are provided in detail.

[1190] User Feedback Phase

[1191] After the user practices the proposed exercise program, they provide feedback on their impressions and satisfaction with the program. The device then sends this feedback to the server, which uses it to improve the recommendation algorithm.

[1192] As a concrete example, let's say a 14-year-old junior high school student is 160 cm tall, weighs 50 kg, and has a body fat percentage of 15%. If this user inputs their 100m sprint time and their interest in basketball, the server will use this data to recommend three events: track and field (especially sprinting), basketball, and soccer. The user can then select and execute an exercise program that suits them based on this list, and receive feedback afterwards.

[1193] In this way, this system automates a series of processes, from receiving user data to generating and presenting optimal exercise programs, and even improving the algorithm based on feedback, helping users establish exercise habits.

[1194] The processing flow will be explained below.

[1195] Step 1:

[1196] The user starts the application and accesses a screen for entering body composition data and basic physical ability data, including height, weight, body fat percentage, grip strength, endurance test results, flexibility test results, and sports of interest.

[1197] Step 2:

[1198] The terminal receives data entered by the user, converts it into an internal format, formats the converted data, and sends it to the server using a secure communication protocol.

[1199] Step 3:

[1200] The server receives the data at the receiving port and saves it in the database. The received data is stored in a temporary table and prepared for data analysis.

[1201] Step 4:

[1202] The server cleanses the data it receives, detects outliers and missing values, and imputes them as needed using historical data or averages, and then formats the cleansed data for analysis.

[1203] Step 5:

[1204] The server then applies machine learning algorithms to the cleansed data, using techniques such as clustering and recommender systems to analyze the exercise program and sport that best suits the user.

[1205] Step 6:

[1206] Based on the analysis results, the server generates a list of recommendations for exercise programs and sports that are optimal for the user, including detailed descriptions of each sport and the reasons for its recommendation.

[1207] Step 7:

[1208] The server converts the generated recommendation list into JSON or another appropriate data format and sends it to the device.

[1209] Step 8:

[1210] The device analyzes the received recommendation list and displays it on the user interface, allowing the user to confirm the suggested exercise programs and sports.

[1211] Step 9:

[1212] After the user has completed the proposed exercise program, they can input their impressions and satisfaction level through the feedback screen. The input feedback data is sent to the server via the device.

[1213] Step 10:

[1214] The server analyzes the received feedback data and stores it for algorithm refinement. The next analysis will use this feedback to improve accuracy.

[1215] The above is the specific processing flow of the system of the present invention. This series of steps allows the user to continuously carry out an optimal exercise program, which can help maintain health and improve sports performance.

[1216] Example 1

[1217] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1218] In modern health management, it is important to provide optimal exercise programs for individual users, but accurately analyzing the user's body composition data and basic physical ability data to generate an appropriate recommendation list is a challenge. In addition, it is necessary to supplement inaccurate or missing data and reflect user feedback to continuously improve the recommendation algorithm.

[1219] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1220] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for transmitting the input data to the server using a secure communication protocol, means for storing the transmitted data in an internal database and cleansing it to supplement inaccurate or missing data, means for analyzing the cleansed data using a machine learning algorithm and generating a recommendation list for recommending exercise programs suitable for the user based on the analysis results, means for displaying the recommendation list to the user, and means for receiving user feedback on exercise programs attempted based on the recommendation list and improving the recommendation algorithm based on the feedback. This makes it possible to provide each user with a highly accurate exercise program and to supplement inaccurate data and improve the algorithm based on the feedback.

[1221] "Body composition data" refers to basic data about the user's body, including height, weight, body fat percentage, and the like.

[1222] "Basic physical ability data" is data that indicates the user's basic physical strength and athletic ability, and includes grip strength, endurance test results, flexibility test results, and the like.

[1223] A "secure communication protocol" is a protocol that ensures security when sending and receiving data, and HTTPS is an example of this.

[1224] "Server" refers to a computer system that receives, stores, analyzes data, and provides information to users.

[1225] The "internal database" is a data storage system installed within the server for storing received data and analysis results.

[1226] "Cleansing" refers to the process of correcting inaccurate data and filling in missing values ​​in order to improve data quality.

[1227] "Machine learning algorithms" are artificial intelligence techniques used to analyze data and find patterns and trends, such as random forests and support vector machines.

[1228] The "recommended list" refers to a list of exercise programs and sports that are optimal for the user, generated based on the analysis results.

[1229] "User interface" refers to the screen and operating environment through which a user interacts with a system.

[1230] "Feedback" refers to information about the user's impressions and satisfaction with the exercise program they have completed, and is used to improve the system.

[1231] The system of the present invention receives and analyzes the user's body composition data and basic physical ability data, and recommends an optimal exercise program. The flow of the system for specifically implementing the present invention will now be described.

[1232] Users access this system using a device such as a personal computer or smartphone. The device displays a user interface through a web browser or mobile application, allowing users to input body composition data (height, weight, body fat percentage, etc.) and basic physical ability data (grip strength, endurance test results, flexibility test results, etc.). Users are also prompted to input their interests and sports.

[1233] When a user enters data and clicks the "Submit" button, the terminal formats the input data into JSON format. The formatted data is then sent to the server using a secure communication protocol (e.g., HTTPS). The server receives the data sent from the terminal on a specific receiving port and stores it in an internal database.

[1234] Next, the server cleanses the data stored in the database. Cleansing is a process that corrects inaccurate data and fills in missing values ​​to improve data quality. For example, it detects abnormal values ​​such as a weight of 0 kg and fills them in using past data or average values.

[1235] The cleansed data is then analyzed using machine learning algorithms (e.g., random forests and support vector machines). The server then performs the analysis to identify the best exercise program for the user and generates a list of recommendations based on the results. The recommendation list includes a detailed description of each exercise program or sport and the reasons why that sport is suitable for the user.

[1236] The generated recommendation list is stored in the database again and sent from the server to the device, which displays the received recommendation list on the user interface, allowing the user to easily understand and select.

[1237] The user reviews the displayed list of recommendations and selects the most suitable exercise program. After completing the exercise program, the user provides feedback by entering their impressions and satisfaction. The device sends this feedback to the server, which then stores it in a database. The feedback information is used to improve the recommendation algorithm for the next exercise program.

[1238] For example, if a 14-year-old junior high school student inputs his / her height of 160 cm, weight of 50 kg, body fat percentage of 15%, 13 seconds for 100 m sprint time, and interest in basketball, the server will use this data to recommend three sports: track and field (especially sprinting), basketball, and soccer. The user can then select an appropriate exercise program and provide feedback later.

[1239] An example of a prompt sentence would be, "A 14-year-old junior high school student has entered his body composition data and basic physical ability data. His height is 160 cm, his weight is 50 kg, his body fat percentage is 15%, his 100m sprint time is 13 seconds, and he has an interest in basketball. Based on this data, please recommend the most suitable exercise program for this junior high school student." This sentence is input into the generative AI model.

[1240] The above is a specific embodiment of the present invention, which provides an automated series of processes, from receiving user data, analyzing it, generating and presenting a recommendation list, and improving the algorithm based on the feedback, to help users establish exercise habits.

[1241] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1242] Step 1:

[1243] Users access the system using a terminal such as a personal computer or smartphone. A user interface is displayed, and the user inputs body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results), as well as the sports they are interested in. The terminal receives the input data, which is then collected and saved on the terminal.

[1244] Step 2:

[1245] When the user has completed entering all the data and clicked the "Submit" button, the device will format the data into JSON format and send it to the server using a secure communication protocol such as HTTPS. In this operation, the device sends the input data, and the server stores the received data in its internal database.

[1246] Step 3:

[1247] The server stores the received data in an internal database. The stored data is then cleansed. Specifically, inaccurate data and missing values ​​are detected and filled in using past data and average values. For example, if an extremely low or abnormal weight value is entered, the server replaces it with the average value. The output is the cleansed data.

[1248] Step 4:

[1249] The cleansed data is then analyzed on the server using machine learning algorithms. Specifically, algorithms such as random forests and support vector machines are applied to the user's data to create a model that recommends the optimal exercise program. This process produces the analysis results.

[1250] Step 5:

[1251] Based on the analysis results, the server generates a list of recommendations for exercise programs and sports that are optimal for the user. This list includes a detailed description of each exercise program and the reasons why that sport is suitable for the user. The generated recommendation list is saved in a database in a format such as JSON. The output is the recommendation list.

[1252] Step 6:

[1253] The server sends the recommendation list stored in the database to the terminal, which displays the received recommendation list on the user interface so that the user can easily understand and select. The output of this step is the recommendation list that is displayed to the user.

[1254] Step 7:

[1255] The user checks the proposed exercise program and carries it out as necessary. After practicing the program, the user again inputs data into the device to provide feedback on their impressions and satisfaction. This data is collected as input data.

[1256] Step 8:

[1257] The device sends user feedback data to the server, which stores the feedback in an internal database and uses this data to refine the recommendation algorithm. This process allows the system to continually improve the accuracy of exercise program recommendations based on user feedback.

[1258] Through the above steps, the system receives the user's body composition data and basic physical ability data, and supports continuous health management by recommending daily exercise programs and providing feedback.

[1259] (Application example 1)

[1260] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1261] Users who aim to manage their health and establish exercise habits need not only to be provided with effective exercise programs based on body composition data and basic physical ability data, but also to be provided with comprehensive health support by optimizing daily dietary content and proposing healthy delivery menus. The present invention aims to solve this problem and provide a system that allows users to easily maintain their health.

[1262] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1263] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for analyzing the input data and generating a recommendation list for recommending exercise programs and meal menus suitable for the user based on the analysis results, means for displaying the recommendation list to the user, and means for proposing healthy delivery menus suitable for the user based on the recommendation list. This allows the user to easily receive effective exercise programs and optimal meal menus, thereby enabling comprehensive health management.

[1264] "Body composition data input by the user" refers to information that the user inputs or provides via the terminal, data relating to the user's body composition, such as weight, height, and body fat percentage.

[1265] "Basic physical ability data" is data relating to the user's basic physical abilities such as grip strength, endurance, flexibility, etc.

[1266] "Analysis" is the process of evaluating received data using machine learning algorithms and statistical methods to derive analytical results suitable for a specific purpose.

[1267] The "recommended list" is a list of exercise programs and meal menus that are optimal for the user, organized based on the results of the analysis.

[1268] A "healthy delivery menu" is a set of healthy meal options recommended based on the user's health condition and physical data.

[1269] "Feedback" refers to information that a user sends back to the system about the results and impressions of the exercise program or meal menu provided to them after they have put it into practice.

[1270] A "recommendation algorithm" is a calculation method or logic for automatically selecting the optimal exercise program or meal menu based on user data.

[1271] The present invention provides a system for proposing optimal exercise programs and meal menus based on body composition data and basic physical ability data acquired from a user. This system comprises the following steps.

[1272] System Configuration

[1273] Hardware and Software Configuration

[1274] This system consists of a user device (smartphone app), a server (cloud server), and a database. The specific technology stack is as follows:

[1275] On the user device, a smartphone application using React Native is implemented.

[1276] On the server side, a web server is built using Node.js and Express, and MongoDB is used as the database.

[1277] HTTPS is used for data communication to ensure secure communication, and JWT (JSON Web Token) is used for authentication.

[1278] User data input phase

[1279] Users operate the device to input their body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results), as well as the types of cuisine they are interested in and their food preferences.

[1280] Data transmission phase

[1281] The device collects data entered by the user and securely transmits it to the server using HTTPS, where it is formatted into a standard format such as JSON.

[1282] Data Preprocessing Phase

[1283] The server cleanses the data it receives, and if there are any inaccurate or missing data, it fills them in using historical data or average values.

[1284] Data analysis phase

[1285] The server then uses the cleansed data to analyze it using machine learning algorithms and statistical methods. Specifically, it analyzes the user's body composition data and basic physical ability data, and applies a model to recommend optimal exercise programs and healthy delivery menus.

[1286] Recommendation List Generation Phase

[1287] Based on the analysis, the server generates a list of recommended exercise programs and dietary menus that are optimal for the user, including detailed descriptions of each exercise and diet and the reasons why they are suitable for the user.

[1288] Result display phase

[1289] The server sends the generated recommendation list to the user's device, which then displays the received recommendation list on its user interface, allowing the user to easily understand and select items.

[1290] User Feedback Phase

[1291] After the user has put into practice the suggested exercise program or meal menu, the system also has a function to provide feedback on the results and impressions. The feedback data is then sent back to the server and used to improve the algorithm.

[1292] Specific examples

[1293] For example, suppose a user enters their height (170cm), weight (65kg), and body fat percentage (20%) as body composition data, and their basic physical ability data (grip strength, endurance, and flexibility test results), and also enters that they are interested in "Italian cuisine." Based on this information, the server generates the following prompt and performs analysis:

[1294] Example prompt sentence:

[1295] The user's body composition data is as follows:

[1296] Height: 170 cm

[1297] Weight: 65 kg

[1298] Body fat percentage: 20%

[1299] The user has the following basic physical ability data:

[1300] Grip strength: 40kg

[1301] Endurance: Moderate

[1302] Flexibility: High

[1303] Suggest a healthy Italian menu suitable for this user.

[1304] Based on these prompts, the system generates and provides optimal exercise programs and meal plans to the user, such as healthy delivery menu suggestions like "bruschetta and fruit for breakfast, grilled chicken salad for lunch, and Italian salmon and vegetable soup for dinner."

[1305] In this way, users receive individually optimized exercise programs and meal menus, enabling comprehensive health management.

[1306] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1307] Step 1:

[1308] The user enters body composition data and basic physical ability data through the device. Specifically, the user enters information such as height, weight, body fat percentage, grip strength, endurance test results, and flexibility test results. The user also enters their interests and the types of cuisine they are interested in. The entered data is saved in temporary storage on the device and formatted into JSON format. Once the input data has been formatted, the system proceeds to the next step.

[1309] Step 2:

[1310] The formatted user data is sent from the device to the server. Here, secure communication is performed using HTTPS. The server receives the received JSON-formatted data via a receiving port and stores it in a database. In this step, the input data (body composition data, basic physical ability data, and types of cuisine of interest) is transmitted to the server, which stores it in the server's database.

[1311] Step 3:

[1312] The server begins the process of cleansing the data received from the database. Specifically, if there are abnormal values ​​for weight or height, they are filled in using past data or average values. Also, if there is missing data, they are filled in with estimated values. After the inaccurate data has been cleansed, the accurate data can be used for analysis.

[1313] Step 4:

[1314] After the cleansing process is complete, the server performs data analysis. This analysis uses machine learning algorithms and statistical methods. The goal is to identify the optimal exercise program and meal plan for the user. The server generates prompts for the analysis. For example, the server might include something like, "The user's body composition data is as follows: height: 170 cm, weight: 65 kg...Please suggest a healthy Italian menu suitable for this user." The analysis results are organized into a recommendation list.

[1315] Step 5:

[1316] The server stores the generated recommendation list in a database and sends it to the device. The data is formatted appropriately and displayed on the device. The recommendation list includes detailed descriptions of each exercise program and meal plan, as well as reasons for its recommendation.

[1317] Step 6:

[1318] The user can view the recommended list of exercise programs and dietary menus displayed on the device and put them into practice. Each program includes detailed instructions on specific methods, procedures, and precautions.

[1319] Step 7:

[1320] After practicing, users enter feedback via their device. The feedback includes the effectiveness of the program, their impressions, and their level of satisfaction. The feedback data is then sent back to the server, which receives the data and stores it in a database. Based on the feedback information, the analysis algorithm is improved, and the accuracy of recommendations will increase in the future.

[1321] Through these steps, users receive individually optimized exercise programs and meal plans, enabling them to achieve comprehensive health management.

[1322] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1323] The system of the present invention receives and analyzes the user's body composition data and basic physical ability data, and recommends the optimal exercise program. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the recommendations can be optimized with even greater precision.

[1324] User data input phase

[1325] The user accesses the system using a terminal. The terminal displays a user interface, prompting the user to enter body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter information about their interests and sports. Since this data is used in the analysis step, it is important that it is entered accurately.

[1326] Data transmission phase

[1327] The device receives the data entered by the user, formats it, and sends it to the server, which stores the data in an internal database and prepares it for analysis.

[1328] Data Preprocessing Phase

[1329] The server cleanses the data it receives and fills in outliers and missing values. It ensures data quality by using historical data and average values. The cleansed data is then formatted for analysis.

[1330] Data analysis phase

[1331] The server performs analysis based on the cleansed data. Using machine learning algorithms and statistical methods, it applies a model to recommend the most suitable exercise program for the user. Based on the analysis results, it identifies the sports and exercise programs that are best suited to the user's body composition and basic physical abilities.

[1332] Emotional Engine Phase

[1333] When displaying the recommendation list, the device activates an emotion engine. The emotion engine analyzes the user's facial expressions, voice tone, input behavior, etc. to recognize the user's emotional state. The emotion data recognized by the emotion engine helps prioritize the most suitable exercise program for the user in the recommendation list. The content of the list is also optimized in real time based on the emotion data.

[1334] Recommendation list generation and display phase

[1335] The server combines the analysis results with the emotion engine data to generate a list of recommendations for optimal exercise programs and sports. The generated recommendation list is formatted in JSON format or similar and sent to the device. The device displays this list on its user interface, allowing the user to easily understand and select.

[1336] User Feedback Phase

[1337] After the user practices the suggested exercise program, they enter their impressions and satisfaction as feedback. This feedback is combined with emotional data to refine the algorithm for optimal performance. The device then sends this data to the server, which then analyzes the feedback and emotional data to further improve the accuracy of the next recommendation.

[1338] As a concrete example, consider the case where a 14-year-old junior high school student is 160 cm tall, weighs 50 kg, and has a body fat percentage of 15%, and enters his or her 100-meter sprint time and interest in basketball. Based on this data, the server will create a recommendation list of three events: track and field (especially sprinting), basketball, and soccer. Furthermore, the emotion engine analyzes the user's facial expressions and input behavior, and can prioritize events that the user is particularly interested in or enjoys. The user can select and perform an exercise program that suits them based on this list, and then enter feedback afterwards.

[1339] In this way, this system automates a series of processes, from receiving user data to generating and presenting optimal exercise programs, and even making highly accurate suggestions that incorporate emotional data and improvements based on feedback, thereby helping users establish exercise habits.

[1340] The processing flow will be explained below.

[1341] Step 1:

[1342] The user starts the application and accesses a screen for entering body composition data and basic physical ability data, including height, weight, body fat percentage, grip strength, endurance test results, flexibility test results, and sports of interest.

[1343] Step 2:

[1344] The terminal receives data entered by the user, converts it into an internal format, formats the converted data, and sends it to the server using a secure communication protocol.

[1345] Step 3:

[1346] The server receives the data at the receiving port and saves it in the database. The received data is stored in a temporary table and prepared for data analysis.

[1347] Step 4:

[1348] The server cleanses the data it receives, detects outliers and missing values, and imputes them as needed using historical data or average values, and then formats the cleansed data for analysis.

[1349] Step 5:

[1350] The server then applies machine learning algorithms to the cleansed data, using techniques such as clustering and recommender systems to analyze the exercise program and sport that best suits the user.

[1351] Step 6:

[1352] Based on the analysis results, the server generates a list of recommendations for exercise programs and sports that are optimal for the user, including detailed descriptions of each sport and the reasons for its recommendation.

[1353] Step 7:

[1354] The device activates the emotion engine, and when the user browses the recommendation list, it analyzes parameters such as facial expressions, voice tone, and input behavior. Based on this data, the emotion engine recognizes the user's emotional state and generates emotion data.

[1355] Step 8:

[1356] The server receives the emotion data generated by the emotion engine and optimizes the recommendation list in real time, for example, by prioritizing the display of sports that the user is interested in or enjoys.

[1357] Step 9:

[1358] The device receives the optimized recommendation list and displays it on the user interface, allowing the user to confirm the suggested exercise program or sport based on the display.

[1359] Step 10:

[1360] After the user has completed the proposed exercise program, they can input their impressions and satisfaction level through the feedback screen. The input feedback data is sent to the server via the device.

[1361] Step 11:

[1362] The server analyzes the received feedback data and stores it for algorithm refinement, including sentiment data, to improve the accuracy of the next recommendation.

[1363] The above is the specific processing flow of the system of the present invention. This series of steps allows the user to continuously carry out an optimal exercise program, which can help maintain health and improve sports performance.

[1364] Example 2

[1365] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1366] Conventional exercise program recommendation systems have problems with reduced recommendation accuracy due to inaccuracies or missing data when analyzing individual user data. Furthermore, these systems do not take into account the user's emotional state, making it difficult to provide optimal exercise programs based on the user's motivation and interests. Furthermore, they do not fully utilize user feedback, resulting in insufficient improvements to improve recommendation accuracy for the next time.

[1367] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1368] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for cleansing the input data and completing inaccurate or missing data, means for analyzing the cleansed data using a machine learning algorithm and generating a recommendation list for recommending exercise programs suitable for the user based on the analysis results, means for displaying the recommendation list to the user, and means for recognizing the user's emotional state and optimizing the contents of the recommendation list in real time based on the emotional state. This makes it possible to provide an optimal exercise program based on the user's emotional state while ensuring data quality, and further to utilize user feedback to improve the accuracy of next recommendations.

[1369] The "means for receiving body composition data and basic physical ability data input by the user" refers to a mechanism by which a user accesses the system using a terminal and inputs data such as height, weight, body fat percentage, grip strength, endurance test results, and flexibility test results.

[1370] The "means for cleansing the input data and supplementing inaccurate or missing data" refers to a mechanism in which the server analyzes the data it receives, corrects and supplements outliers and missing values, and performs processing to ensure the quality of the data.

[1371] "Means for analyzing using a machine learning algorithm and generating a recommendation list for recommending suitable exercise programs to the user based on the analysis results" refers to a mechanism in which the server applies a machine learning algorithm to the cleansed data, identifies the exercise program that is best suited to the user's body composition and basic physical abilities, and generates the results as a list.

[1372] The "means for displaying the recommendation list to the user" is a mechanism for formatting the generated recommendation list in JSON format or the like and displaying it to the user through a user interface.

[1373] The "means for recognizing the emotional state of the user and optimizing the contents of the recommendation list in real time based on said emotional state" is a mechanism that uses an emotion engine to analyze the user's facial expressions, voice tone, and input behavior, recognizes the user's emotional state, and then optimizes the contents of the recommendation list.

[1374] The "means for receiving user feedback and improving the recommendation algorithm based on said feedback" is a mechanism for receiving feedback such as user impressions and satisfaction regarding the exercise program that the user has performed, and improving the recommendation algorithm based on that feedback.

[1375] The "emotion engine" is a mechanism that analyzes the user's facial expressions, voice tone, input behavior, etc. to recognize the user's real-time emotional state.

[1376] The system of the present invention receives and analyzes the user's body composition data and basic physical ability data, and recommends the optimal exercise program. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the recommendations can be optimized with even greater precision.

[1377] User data input phase

[1378] The user accesses the system using a terminal. The terminal displays a dedicated user interface, prompting the user to enter detailed body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter their interests and sports that interest them. Accurate data entry is important for the analysis step, so the user is urged to enter the data appropriately.

[1379] Data transmission phase

[1380] The terminal formats the data entered by the user and converts it into a unified format (e.g., JSON format). The terminal sends the formatted data to the server. If an error occurs during transmission, it attempts to resend. The server stores the received data in a database and prepares it for analysis.

[1381] Data Preprocessing Phase

[1382] The server cleanses the data it receives and corrects and completes outliers and missing values. For example, if the height entered by the user is very small, it will automatically be completed by referring to past data and average values. The server then formats the cleansed data for analysis. Specifically, it standardizes the necessary numerical values ​​(for example, to a range of 0 to 1).

[1383] Data analysis phase

[1384] The server then uses machine learning algorithms to analyze the cleansed data. Specific algorithms include regression analysis and clustering. The server then selects the optimal exercise program based on the analysis results. For example, if a user's endurance test results are high, an exercise program that emphasizes endurance will be recommended.

[1385] Emotional Engine Phase

[1386] When the device displays the recommendation list, it activates an emotion engine. The emotion engine analyzes the user's facial expressions, voice tone, and input behavior in real time to recognize the user's emotional state. Based on the recognized emotion data, it prioritizes the most suitable exercise program for the user from the recommendation list. It is also possible to optimize the list contents in real time.

[1387] Recommendation list generation and display phase

[1388] The server combines the analysis results with data from the emotion engine to generate a list of recommendations for optimal exercise programs and sports. The generated recommendation list is formatted in JSON format or similar and sent to the device. The device then displays the recommendation list on its user interface, making it easy for the user to understand and select. Specific examples include a function to display videos explaining the benefits of each exercise program and how to perform them.

[1389] User Feedback Phase

[1390] The user practices the proposed exercise program and then inputs feedback, such as their impressions and level of satisfaction, into the device. This effectively collects the user's actual level of satisfaction. The device then sends the feedback data to the server, which analyzes it along with emotional data and uses it to improve the accuracy of the next recommendation.

[1391] Specific examples

[1392] For example, if a 14-year-old junior high school student inputs his / her height of 160 cm, weight of 50 kg, and body fat percentage of 15%, as well as data indicating his / her 100-meter sprint time and interest in basketball, the server will use this data to recommend three events: track and field (especially sprinting), basketball, and soccer. Furthermore, the emotion engine analyzes the user's facial expressions and input behavior, and prioritizes events that the user is particularly interested in or enjoys. The user can select an exercise program that suits them based on this list, and then provide feedback to help improve the system's accuracy.

[1393] Prompt Sentence Examples

[1394] An example of a prompt to input to a generative AI model is as follows:

[1395] "Enter the following information for a 14-year-old junior high school student: height 160cm, weight 50kg, body fat percentage 15%, 100m sprint time, and interest in basketball. Generate and present a list of optimal exercise programs and sports."

[1396] In this way, this system automates a series of processes, from receiving user data to generating and presenting optimal exercise programs, and even making highly accurate suggestions that incorporate emotional data and improvements based on feedback, thereby helping users establish exercise habits.

[1397] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1398] Step 1: User data input phase

[1399] A user accesses the system using a terminal. The terminal displays a user interface and prompts the user to input body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results).

[1400] Input: The user manually inputs each piece of data (e.g., height 160 cm, weight 50 kg).

[1401] Data processing: The terminal checks input data for errors in real time and prompts correction of any inaccurate data.

[1402] Output: The formatted input data after error checking.

[1403] Step 2: Data transmission phase

[1404] The terminal sends the formatted data to the server, where it is converted into a unified format (e.g., JSON format).

[1405] Input: Body composition data and basic physical ability data entered by the user.

[1406] Data processing: The terminal converts the formatted data into JSON format.

[1407] Output: JSON formatted data is sent to the server.

[1408] Step 3: Data preprocessing phase

[1409] The server analyzes the received data, cleansing it, and complements outliers and missing values.

[1410] Input: Body composition data and basic physical ability data sent in JSON format.

[1411] Data processing: Carry out a cleansing process, for example, to fill in missing body fat percentages.

[1412] Output: Cleansed, high-quality data.

[1413] Step 4: Data analysis phase

[1414] The server analyzes the cleansed data using machine learning algorithms and applies a model that recommends the most suitable exercise program for the user.

[1415] Input: Cleansed body composition data and basic physical performance data.

[1416] Data calculations: Apply machine learning algorithms (e.g., regression analysis, clustering) to obtain analytical results.

[1417] Output: A list of recommended exercise programs based on the analysis results.

[1418] Step 5: Emotional Engine Phase

[1419] The device activates an emotion engine to analyze the user's emotional state, analyzing facial expressions, voice tone, and input behavior in real time to obtain emotional data.

[1420] Input: User's facial expression data, voice data, and input behavior data.

[1421] Data Calculation: The emotion engine analyzes these data and recognizes the user's emotional state (e.g., excitement, interest).

[1422] Output: Emotion data is sent to the server.

[1423] Step 6: Recommendation list generation and display phase

[1424] The server combines the analysis results with the emotion data to generate a recommendation list, which is then formatted in JSON format or similar and sent to the device.

[1425] Input: Analysis results of machine learning algorithms and sentiment data.

[1426] Data processing: Format the recommendation list and convert it into a format suitable for the user interface (e.g., JSON format).

[1427] Output: The formatted recommendation list is sent to the terminal and displayed on the user interface.

[1428] Step 7: User Feedback Phase

[1429] The user practices the proposed exercise program and inputs their impressions and satisfaction level into the device, and the feedback data is sent to the server.

[1430] Input: Feedback data entered by the user after practice.

[1431] Data calculation: The server analyzes the feedback data and refines the algorithm to improve the accuracy of the next recommendation.

[1432] Output: A list of recommendations for next time with an improved algorithm.

[1433] Through this series of processes, the system can provide the user with the optimal exercise program and continue to improve the accuracy of its next suggestions based on feedback and emotional data.

[1434] (Application example 2)

[1435] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1436] Conventional robot maintenance systems face challenges in creating efficient maintenance programs because it is difficult to fully analyze robot operation and maintenance data and they are unable to optimize programs taking into account the emotional state of workers. This leads to incomplete robot maintenance, increasing the risk of breakdowns and reduced productivity. Furthermore, maintenance plans that ignore worker stress and fatigue can have a negative impact on worker health and work efficiency.

[1437] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1438] In this invention, the server includes means for receiving body composition data and basic physical ability data input by a user, means for analyzing the input data and generating a recommendation list for recommending an exercise program suitable for the user based on the analysis results, means for displaying the recommendation list to the user, means for receiving robot operation data and recommending an optimal maintenance program based on the data, and means for analyzing worker emotion data and optimizing the maintenance program based on the emotion data. This makes it possible to create a more effective and efficient maintenance program based on the robot operation data and the worker emotion data.

[1439] "Body composition data" refers to information about a user's physical components, such as height, weight, and body fat percentage.

[1440] "Basic physical ability data" refers to data that indicates the user's basic physical abilities, such as grip strength, endurance test results, and flexibility test results.

[1441] "Analysis" refers to the process of processing received data and drawing conclusions or recommendations based on it.

[1442] The "recommended list" is a list of optimal exercise programs and maintenance programs provided to the user based on the analysis results.

[1443] "Operational data" refers to data related to the operation of a robot, such as the robot's operating time, number of errors, and maintenance history.

[1444] A "maintenance program" is a plan for a series of construction works, cleaning, part replacement, etc. required to maintain the normal operation of a robot.

[1445] "Worker emotional data" refers to information indicating stress or fatigue levels obtained from the worker's facial expressions, voice tone, and input behavior.

[1446] "Optimization" refers to the adjustment or refinement of something to find the best possible state or solution for a particular purpose.

[1447] A "server" is a computer that processes and stores data and provides services to client terminals over a network.

[1448] In this invention, the system receives and analyzes the user's body composition data and basic physical ability data, and also analyzes the robot's operation data and the worker's emotional data, thereby recommending optimal exercise and maintenance programs. Specific embodiments are described below.

[1449] User data input phase

[1450] Users access the system using a smartphone. The smartphone displays a user interface and prompts the user to enter body composition data (e.g., height, weight, body fat percentage) and basic physical ability data (e.g., grip strength, endurance test results, flexibility test results). The user is also prompted to enter their interests and sports.

[1451] Data transmission phase

[1452] The smartphone receives data entered by the user, formats it, and sends it to the server, which stores the data in an internal database and prepares it for analysis.

[1453] Data Preprocessing Phase

[1454] The server cleanses the data it receives, filling in outliers and missing values, and ensuring data quality using historical data and average values. The cleansed data is then formatted for analysis.

[1455] Data analysis phase

[1456] The server performs analysis based on the cleansed data, using machine learning algorithms and statistical methods to apply a model that recommends the most suitable exercise program for the user.

[1457] Emotional Engine Phase

[1458] The smartphone activates the emotion engine, which uses the smartphone's camera to analyze the user's facial expressions, voice tone, input behavior, etc. to recognize the user's emotional state. The recognized emotion data is used to prioritize the most suitable exercise program in the recommendation list.

[1459] Robot operation data input phase

[1460] The server receives and analyzes the operation data of the factory robots, including operating time, number of errors, maintenance history, etc.

[1461] Robot Maintenance Recommendation Phase

[1462] The optimal maintenance program is displayed on the user interface based on the operational data analyzed by the server, enabling efficient maintenance of the robot.

[1463] Worker emotion data input phase

[1464] The server receives the worker's emotional data, which is analyzed from camera footage and audio data to evaluate stress levels, fatigue, and other factors.

[1465] Maintenance program optimization phase

[1466] Based on the collected emotional data, the server optimizes the maintenance program in real time, thereby improving work efficiency and maintaining the health of workers.

[1467] Recommendation list generation and display phase

[1468] The server combines the analysis results with emotion data to generate a list of recommendations for optimal exercise and maintenance programs. The recommendation list is formatted in JSON format and sent to the smartphone. The smartphone displays this list on its user interface, allowing the user to easily understand and select.

[1469] User Feedback Phase

[1470] After practicing the suggested exercise program, users enter their impressions and satisfaction as feedback. This feedback is combined with emotional data to refine the algorithm for optimal performance. The smartphone then sends this data to a server, which then analyzes the feedback and emotional data to further improve the accuracy of the next recommendation.

[1471] Hardware and software used

[1472] The system mainly uses a smartphone and a server. Sentiment analysis is performed using the smartphone's camera and voice input device, and analysis software includes a machine learning algorithm (e.g., RandomForestRegressor) and a sentiment analysis engine (e.g., Affdex SDK).

[1473] Specific examples

[1474] The user enters body composition data, and the smartphone transmits the data to the server.

[1475] The server cleanses the data and generates a recommendation list based on the analysis results.

[1476] The smartphone displays a list of recommendations, and the user can select the most suitable exercise program.

[1477] The server receives operational data from factory robots and recommends new maintenance programs.

[1478] Obtains worker emotional data and provides optimized maintenance programs.

[1479] Example prompts to input to the generative AI model

[1480] "Create an application that uses robot operating data to recommend optimal maintenance programs and adds sentiment analysis for optimization."

[1481] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1482] Step 1:

[1483] The user inputs body composition data and basic physical ability data into a smartphone.

[1484] As specific examples of input, the user may enter data such as height (e.g., 160 cm), weight (e.g., 50 kg), body fat percentage (e.g., 15%), grip strength (e.g., 30 kg), endurance test results, and flexibility test results.

[1485] The entered data is temporarily stored in the smartphone's memory.

[1486] Step 2:

[1487] The terminal receives the data entered by the user and formats the data.

[1488] Specifically, the values ​​of each data field are formatted correctly and it is checked whether there are any missing values.

[1489] The formatted data is converted into a transmittable format such as JSON.

[1490] After this processing, the data is sent to the server.

[1491] Step 3:

[1492] The server stores the received data in a database.

[1493] First, the server parses the received JSON format data and stores it in each field of the database.

[1494] The data is appropriately labeled for analysis and used in subsequent processing.

[1495] Step 4:

[1496] The server retrieves the data from the database and performs the cleansing.

[1497] Specific examples include detecting and correcting outliers (e.g., body fat percentage above 100%) and filling in missing values ​​(using average data from the past).

[1498] The cleansed data is used as input for machine learning algorithms.

[1499] Step 5:

[1500] The server analyzes the cleansed data and generates a list of recommendations.

[1501] Specifically, we use a machine learning algorithm (e.g., RandomForestRegressor) to recommend the optimal exercise program based on the input data.

[1502] The analysis results in a recommendation list, which includes recommended exercises and programs.

[1503] Step 6:

[1504] The terminal receives the recommendation list from the server and displays it on the user interface.

[1505] Specifically, the server generates a recommendation list and sends it to the device in JSON format, which the device then analyzes and displays on the screen.

[1506] The user can review the recommendation list and select an exercise program based on it.

[1507] Step 7:

[1508] The user enters the operation data of the factory robot into a smartphone.

[1509] Specific examples of input include the robot's operating time (e.g., 2000 hours), the number of errors (e.g., 5), and maintenance history.

[1510] The entered data is temporarily stored in the smartphone's memory.

[1511] Step 8:

[1512] The terminal sends the robot's operation data to the server.

[1513] As with the user data transmission phase described above, the data is formatted, converted to JSON format, etc., and sent to the server.

[1514] The server stores the received data in a database and prepares it for analysis.

[1515] Step 9:

[1516] The server analyzes the operational data and generates the optimal maintenance program.

[1517] As a specific example of analysis, it predicts the risk of failure based on operational data and recommends necessary part replacements and regular inspection schedules.

[1518] The analysis results are formatted as a recommendation list in JSON format and sent to the device.

[1519] Step 10:

[1520] The terminal receives the recommendation list from the server and displays it on the user interface.

[1521] Users can review the recommended list and select the most suitable maintenance program.

[1522] Step 11:

[1523] The smartphone camera captures the worker's emotional data and sends it to the server.

[1524] Specifically, emotion analysis software (e.g., Affdex SDK) is used to analyze the facial expressions and vocal tones of workers to extract emotional data.

[1525] The extracted emotion data is sent to the server.

[1526] Step 12:

[1527] The server optimizes the maintenance program based on emotional data.

[1528] Analyzes emotional data and adjusts maintenance plans to take into account workers' stress levels and fatigue levels.

[1529] An optimized maintenance program is generated and sent to the terminal.

[1530] Step 13:

[1531] The terminal receives the optimized maintenance program and displays it on the user interface.

[1532] Users can check the optimal maintenance program and create an implementation plan.

[1533] Step 14:

[1534] Users carry out exercise and maintenance programs and then enter feedback into their smartphones.

[1535] Specific examples of input include impressions and satisfaction with the results of the practice.

[1536] The input feedback is sent from the terminal to the server.

[1537] Step 15:

[1538] The server analyzes the feedback data and refines the recommendation algorithm.

[1539] Specifically, the machine learning model is retrained based on the feedback data to improve the accuracy of the next recommendation.

[1540] The improved algorithm will be used in the next analysis.

[1541] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1542] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1543] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1544] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1545] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1546] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1547] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1548] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1549] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1550] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1551] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1552] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1553] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1554] 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.

[1555] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1556] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1557] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1558] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1559] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1560] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1561] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1562] The following is further disclosed regarding the above embodiment.

[1563] (Claim 1)

[1564] means for receiving body composition data and basic physical ability data input by a user;

[1565] means for analyzing the input data and generating a recommendation list for recommending an exercise program suitable for the user based on the analysis results;

[1566] means for displaying the recommendation list to a user;

[1567] A system including:

[1568] (Claim 2)

[1569] 10. The system of claim 1, further comprising means for cleansing the input data and for completing inaccurate or missing data.

[1570] (Claim 3)

[1571] 10. The system of claim 1, further comprising means for receiving user feedback regarding exercise programs attempted based on the recommendation list and for improving a recommendation algorithm based on the feedback.

[1572] "Example 1"

[1573] (Claim 1)

[1574] means for receiving body composition data and basic physical ability data input by a user;

[1575] means for transmitting the input data to a server using a secure communication protocol;

[1576] means for storing the transmitted data in an internal database and for cleansing and completing inaccurate or missing data;

[1577] a means for analyzing the cleansed data using a machine learning algorithm and generating a recommendation list for recommending an exercise program suitable for the user based on the analysis results;

[1578] means for displaying the recommendation list to a user;

[1579] means for receiving user feedback regarding exercise programs attempted based on the recommendation list and refining a recommendation algorithm based on the feedback;

[1580] A system including:

[1581] (Claim 2)

[1582] 2. The system of claim 1, further comprising means for detecting outliers during the data cleansing stage and supplementing them with historical data or average values.

[1583] (Claim 3)

[1584] The system of claim 1 , further comprising: means for including a detailed description of each exercise program and a reason for recommendation in the recommendation list generated based on the machine learning algorithm.

[1585] "Application Example 1"

[1586] (Claim 1)

[1587] means for receiving body composition data and basic physical ability data input by a user;

[1588] means for analyzing the input data and generating a recommendation list for recommending an exercise program and a meal menu suitable for the user based on the analysis results;

[1589] means for displaying the recommendation list to a user;

[1590] means for suggesting a healthy delivery menu suitable for the user based on the recommendation list;

[1591] …

[1592] A system including:

[1593] (Claim 2)

[1594] 10. The system of claim 1, further comprising means for cleansing the input data and for completing inaccurate or missing data.

[1595] (Claim 3)

[1596] 10. The system of claim 1, further comprising means for receiving user feedback regarding exercise programs and meal plans attempted based on the recommendation list, and for improving a recommendation algorithm based on the feedback.

[1597] "Example 2: Combining Emotion Engines"

[1598] (Claim 1)

[1599] means for receiving body composition data and basic physical ability data input by a user;

[1600] means for cleansing the input data and completing inaccurate or missing data;

[1601] a means for analyzing the cleansed data using a machine learning algorithm and generating a recommendation list for recommending an exercise program suitable for the user based on the analysis results;

[1602] means for displaying the recommendation list to a user;

[1603] means for recognizing an emotional state of a user and optimizing the content of a recommendation list in real time based on said emotional state;

[1604] A system including:

[1605] (Claim 2)

[1606] 10. The system of claim 1, further comprising means for receiving user feedback regarding exercise programs attempted based on the recommendation list and for improving a recommendation algorithm based on the feedback.

[1607] (Claim 3)

[1608] 10. The system of claim 1, further comprising: an emotion engine that analyzes a user's facial expressions, voice tone, and input behavior to recognize an emotional state; and means for optimizing a recommendation list based on emotion data obtained by the emotion engine.

[1609] "Application example 2 when combining emotion engines"

[1610] (Claim 1)

[1611] means for receiving body composition data and basic physical ability data input by a user;

[1612] means for analyzing the input data and generating a recommendation list for recommending an exercise program suitable for the user based on the analysis results;

[1613] means for displaying the recommendation list to a user;

[1614] means for receiving operational data of the robot and recommending an optimal maintenance program based on the data;

[1615] means for analyzing emotion data of workers and optimizing a maintenance program based on the emotion data;

[1616] A system including:

[1617] (Claim 2)

[1618] 10. The system of claim 1, further comprising means for cleansing the input data and for completing inaccurate or missing data.

[1619] (Claim 3)

[1620] 10. The system of claim 1, further comprising means for receiving user feedback regarding exercise programs attempted based on the recommendation list and for improving a recommendation algorithm based on the feedback. [Explanation of symbols]

[1621] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving body composition data and basic physical ability data input by a user; means for analyzing the input data and generating a recommendation list for recommending an exercise program suitable for the user based on the analysis results; means for displaying the recommendation list to a user; A system including:

2. The system of claim 1 , further comprising means for cleansing the input data and for completing inaccurate or missing data.

3. The system of claim 1 , further comprising means for receiving user feedback regarding exercise programs attempted based on the recommendation list and for improving a recommendation algorithm based on the feedback.

Images