Motion detection and feedback intervention system for obese patients

Abstract

The invention discloses a movement detection and feedback intervention system for obese patients, and relates to the technical field of movement intervention for obese patients, the system comprises a data acquisition module, a personalized movement scheme generation module, a movement monitoring module and an interaction module; according to the method, artificial intelligence and big data analysis technologies are deeply fused, multivariate data of a patient is comprehensively and accurately collected, a personalized exercise scheme meeting individual requirements can be generated, the pertinence of the exercise scheme is improved, and during exercise monitoring, the multi-modal data fusion technology is applied, so that the accuracy of exercise monitoring is improved. Various physiological parameters and exercise environment data of a patient are collected in an omnibearing mode, the state of the patient is accurately controlled in real time, once monitoring data deviates from a preset target, parameters such as exercise items, strength, time and frequency in an exercise scheme can be rapidly and dynamically adjusted according to a real-time deviation correction algorithm, the safety of the exercise process is practically guaranteed, and the exercise efficiency is improved. The goal of losing weight is effectively promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of exercise intervention for obese patients, and in particular to an exercise detection and feedback intervention system for obese patients. Background Art

[0002] Obesity is a complex chronic metabolic disease, the causes of which involve genetics, environment, lifestyle and other factors. In clinical practice, body mass index is usually used as a measurement indicator. When the body mass index exceeds the threshold set by the World Health Organization or relevant domestic standards, it can be determined to be obesity. Obesity not only affects the individual's appearance, but also significantly increases the risk of various chronic diseases such as cardiovascular disease, diabetes, and hypertension, which seriously threatens physical health. Exercise intervention, as an important part of comprehensive obesity treatment, refers to carefully planning exercise programs for obese patients based on scientific exercise principles and methods, reasonably setting exercise intensity, accurately arranging exercise time and determining appropriate exercise frequency. Its core purpose is to encourage patients to increase calorie consumption, improve body metabolism, enhance muscle strength and endurance and other physical qualities through exercise, thereby effectively reducing fat accumulation in the body, improving body composition ratio, achieving weight loss and improvement of overall health.

[0003] However, existing technologies still have certain defects when conducting exercise interventions for obese patients. In the formulation of exercise plans, existing technologies generally use universal templates and do not fully consider individual physical indicators, exercise ability, preferences and goal differences, resulting in poor targeted plans and difficulty in meeting the personalized needs of different obese patients. During exercise process monitoring, only limited physiological data can be obtained, and the patient's condition cannot be fully understood. It is difficult to achieve real-time and accurate adjustment of exercise plans, which can easily lead to sports injuries or poor exercise effects in patients. Therefore, it is of great significance to develop an exercise detection and feedback intervention system for obese patients. Summary of the Invention

[0004] The purpose of this invention is to make up for the shortcomings of the existing technology and provide an exercise detection and feedback intervention system for obese patients. It can integrate artificial intelligence and big data analysis technology to comprehensively collect multi-dimensional data of patients, realize accurate personalized exercise plan customization, use multimodal data fusion monitoring, and dynamically adjust the exercise plan in real time to provide obese patients with safe, effective and personalized exercise therapy services.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an exercise detection and feedback intervention system for obese patients, the system comprising: a data acquisition module, a personalized exercise program generation module, an exercise monitoring module, a dynamic adjustment module and an interaction module;

[0006] The data collection module is used to collect basic physical indicators, exercise capacity, exercise preferences and weight loss target data of obese patients;

[0007] The personalized exercise plan generation module generates a personalized exercise plan based on the data collected by the data acquisition module using a deep fusion adaptive algorithm. The objective function formula of the algorithm is: Among them, M i is the actual value of the i-th indicator, T i is the target value, w i is the weight coefficient;

[0008] The motion monitoring module uses multi-sensor fusion technology to monitor the patient's physical reaction data during exercise in real time. The dynamic adjustment module adjusts the exercise plan through a real-time deviation correction algorithm based on the data from the motion monitoring module. The adjustment coefficient calculation formula of this algorithm is: Among them C actual is the actual monitoring value, and C target ≠0, C target It is the target value set by the plan;

[0009] The interactive module is used for patients and medical staff to interact with the system.

[0010] Furthermore, the data collection module collects basic body indicators covering body fat percentage, muscle mass, cardiopulmonary function, joint flexibility, bone density and metabolic rate. Athletic ability assessment includes endurance, strength, flexibility, balance and agility. Sports preference collection includes specific sports scenarios such as aerobic exercise, strength training, yoga, outdoor cycling, indoor aerobics, and water sports. Weight loss goal collection includes weight loss value, body fat percentage reduction, and body circumference changes.

[0011] Furthermore, the personalized exercise plan generation module uses the deep fusion adaptive algorithm to generate a personalized exercise plan as follows:

[0012] Pre-process the basic physical indicators, exercise capacity, exercise preference and weight loss target data collected by the data acquisition module;

[0013] Construct a deep neural network model consisting of an input layer, multiple hidden layers, and an output layer. The input layer receives preprocessed data, the hidden layer extracts and transforms the input data through nonlinear transformation, and the output layer outputs preliminary motion plan parameters.

[0014] The training process uses the objective function formula as the loss function and uses the stochastic gradient descent algorithm to optimize the model parameters. The weight coefficient w iAccording to the importance of each indicator to the exercise plan, through multiple experimental iterations, optimization is carried out with the goal of minimizing the objective function formula;

[0015] A reinforcement learning mechanism is introduced to dynamically adjust the parameters of the deep neural network model based on patient feedback in simulated exercise scenarios. Different reward mechanisms are set for simulated exercise scenarios to enable the model to learn better exercise plan generation strategies.

[0016] After multiple rounds of training and optimization, the model generates a personalized exercise plan based on the input patient data, including exercise selection, exercise intensity setting, exercise time arrangement and exercise frequency planning.

[0017] Furthermore, the multi-sensor fusion technology of the motion monitoring module adopts a method that combines complementary filtering and Kalman filtering. Complementary filtering is used to fuse static data from different types of sensors, and Kalman filtering is used to process dynamic data. The sensors include heart rate belts, sports bracelets, smart insoles, and smart sportswear. Smart insoles monitor the patient's gait and plantar pressure distribution, and smart sportswear monitors the patient's muscle activity in real time.

[0018] Furthermore, the dynamic adjustment module adjusts the motion plan through a real-time deviation correction algorithm as follows:

[0019] The motion monitoring module collects the patient's physical reaction data during exercise in real time as the actual monitoring value C actual ;

[0020] The actual monitoring value is compared with the target value set by the personalized exercise plan C target Substitute into the adjustment coefficient calculation formula to calculate the adjustment coefficient A;

[0021] Introducing time series analysis methods to model and predict deviation data, taking into account the changing trend of deviation;

[0022] The weight of the adjustment coefficient is dynamically adjusted according to the individual differences in the patient's age, gender, and health status. The weight of the individual difference factor is determined by the hierarchical analysis method based on the degree of influence of different factors on exercise;

[0023] Considering the influence of exercise environment factors on exercise programs, the degree of influence of exercise environment factors is determined by establishing an environmental impact model. This model quantifies the influence coefficients of exercise intensity and exercise time parameters under different environmental conditions based on historical experimental data and theoretical analysis;

[0024] Taking the above factors into consideration, the exercise items, exercise intensity, exercise time and exercise frequency parameters in the personalized exercise plan are adjusted.

[0025] Furthermore, the interactive module provides patients with a personalized exercise guidance interface, showing standard exercise postures, exercise intensity and timing in the form of charts and animations, and has a voice prompt function.

[0026] Furthermore, the data collection module uses blockchain technology for data encryption and storage. The patient's personal data and movement data are encrypted and stored in the blockchain network, and only authorized users can access them.

[0027] Furthermore, the personalized exercise plan generation module optimizes the exercise plan based on the patient's dietary factors. The system is integrated with the patient's diet record application to obtain the patient's diet information, including food types, intake, and nutrients. According to the patient's weight loss goals and physical indicators, the exercise plan is adjusted based on the dietary information. At the same time, personalized dietary advice is provided to the patient to develop a reasonable diet plan that includes food choices, meal time and frequency.

[0028] Compared with existing technologies, this exercise detection and feedback intervention system for obese patients has the following beneficial effects:

[0029] The present invention deeply integrates artificial intelligence and big data analysis technology to comprehensively and accurately collect multi-dimensional data of patients, and can generate personalized exercise plans that meet individual needs, thereby improving the targeted nature of exercise plans. During exercise monitoring, by using multimodal data fusion technology, it can comprehensively collect various physiological parameters and exercise environment data of patients, and control the patient's status in real time and accurately. Once the monitoring data deviates from the preset target, the real-time deviation correction algorithm can be used to quickly and dynamically adjust the parameters such as exercise items, intensity, time and frequency in the exercise plan, thereby ensuring the safety of the exercise process and effectively promoting the achievement of weight loss goals.

[0030] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0032] Figure 1 This is a schematic diagram of the structure of an exercise detection and feedback intervention system for obese patients;

[0033] Figure 2 This is a workflow diagram of an exercise detection and feedback intervention system for obese patients. DETAILED DESCRIPTION

[0034] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0035] Example 1

[0036] See also Figure 1 and Figure 2 In a professional obesity rehabilitation treatment center, every day there are many patients who are eager to improve their obesity through scientific exercise. These patients have different basic physical conditions, exercise abilities and weight loss goals. Traditional unified exercise programs often cannot meet their personalized needs, resulting in uneven exercise effects. In order to provide patients with more accurate and efficient exercise intervention services, the treatment center introduced the above-mentioned exercise detection and feedback intervention system for obese patients.

[0037] The medical staff of the treatment center use professional equipment and data acquisition modules to collect comprehensive basic physical indicators of patients, use body fat scales to measure body fat percentage, determine bone density through dual-energy X-ray absorptiometry, use indirect calorimetry to measure metabolic rate, and use professional joint movement measurement instruments to quantitatively assess joint flexibility. For the assessment of athletic ability, a number of tests are carried out, including endurance, strength, flexibility, balance and agility. Among them, balance ability is determined by recording the patient's stability time and center of gravity offset in different postures through a balance test platform, and agility is evaluated by recording the time it takes for the patient to complete the prescribed movements through a specific agility test track.

[0038] During the communication process with the patient, we will understand the patient's exercise preferences in detail, covering specific exercise scenarios such as aerobic exercise, strength training, yoga, outdoor cycling, indoor aerobics, water sports, etc. At the same time, we will clarify the patient's weight loss goals, including the desired weight reduction value, body fat percentage, and body circumference changes. Patients can also upload their own dietary information to the system through multiple channels such as mobile phone applications, smart wearable devices or medical institutions' testing equipment. This information includes food types, intake, nutrients, etc.

[0039] The data collection module uses blockchain technology to encrypt and store the collected patient personal data and movement data. The distributed ledger characteristics of the blockchain ensure that the data cannot be tampered with and is secure. Only authorized users can access it. The smart contract function of the blockchain also realizes the automated management and sharing of data. Its encryption algorithm parameters and execution rule weights are determined based on data security requirements and the importance of business processes through security expert evaluation and business analysis.

[0040] After receiving the data collected by the data acquisition module, the personalized exercise plan generation module first preprocesses the data, including data cleaning and normalization, to eliminate the dimensional differences between different data. Then, it constructs a deep neural network model, which includes an input layer, multiple hidden layers and an output layer. The input layer receives the preprocessed data, the hidden layer extracts and converts the input data through nonlinear transformation, and the output layer outputs the preliminary exercise plan parameters.

[0041] During the training process, the objective function As the loss function, where M i is the actual value of the i-th indicator, T i is the target value, w i is the weight coefficient, weight coefficient w i Based on the importance of various indicators to the exercise plan, a preliminary determination is first made through expert evaluation combined with statistical analysis of historical data. Then, during multiple experimental iterations, further optimization is carried out with the goal of minimizing the objective function F. At the same time, a reinforcement learning mechanism is introduced to dynamically adjust the parameters of the deep neural network model based on the patient's feedback in the simulated exercise scene. Different reward mechanisms are set in the simulated exercise scene to enable the model to learn a better exercise plan generation strategy.

[0042] Finally, after multiple rounds of training and optimization, the module generates a personalized exercise plan, including exercise selection, exercise intensity setting, exercise time arrangement and exercise frequency planning. In addition, taking into account the patient's dietary factors, the system is integrated with the patient's diet record application to optimize the exercise plan based on the patient's weight loss goals and physical indicators combined with dietary information. At the same time, it provides patients with personalized dietary advice and formulates a reasonable diet plan that includes food selection, meal time and frequency. The weight of dietary factors in the optimization of the exercise plan is determined based on the degree of impact of diet on weight loss and physical health, through nutrition expert evaluation and clinical experimental data.

[0043] The patient starts exercising according to the personalized exercise plan, and the exercise monitoring module is activated. This module uses multi-sensor fusion technology to integrate multiple sensors such as heart rate belts, sports bracelets, smart insoles, and smart sportswear to monitor the patient's physical reaction data during exercise in real time. The heart rate belt monitors the patient's heart rate in real time, the sports bracelet can record information such as exercise speed, the smart insole monitors the patient's gait and plantar pressure distribution, and the smart sportswear monitors the patient's muscle activity in real time.

[0044] Multi-sensor fusion technology adopts a method that combines complementary filtering and Kalman filtering. Complementary filtering is used to fuse static data from different types of sensors, and Kalman filtering is used to process dynamic data, such as acceleration and angular velocity during motion. The parameters of complementary filtering and Kalman filtering are determined by analyzing a large amount of experimental data and using the minimum mean square error criterion. At the same time, the sensor also collects motion environment data, such as temperature, humidity, air pressure, etc.

[0045] The dynamic adjustment module obtains the actual monitoring value C according to the patient's physical reaction data collected in real time by the motion monitoring module. actual , and compare it with the target value C set in the personalized exercise plan target Substitute into the adjustment coefficient calculation formula Calculate the adjustment factor A.

[0046] At the same time, the time series analysis method is introduced to model and predict the deviation data, fully considering the changing trend of the deviation. According to individual differences such as the patient's age, gender, and health status, the weight of the adjustment coefficient A is dynamically adjusted through the hierarchical analysis method. In addition, the influence of exercise environment factors such as temperature, humidity, and air pressure on the exercise plan is considered, and the influence coefficients of parameters such as exercise intensity and exercise time under different environmental conditions are quantified through the established environmental impact model.

[0047] Taking all the above factors into consideration, the parameters such as exercise items, exercise intensity, exercise time and exercise frequency in the personalized exercise plan are dynamically adjusted. If the adjustment coefficient A is positive and exceeds a certain threshold, it means that the actual exercise intensity or index is higher than the target value, and the exercise intensity should be appropriately reduced or the exercise time should be shortened; if the adjustment coefficient A is negative and exceeds a certain threshold, it means that the actual exercise intensity or index is lower than the target value, and the exercise intensity should be appropriately increased or the exercise time should be extended.

[0048] The interactive module provides patients with a personalized exercise guidance interface, which displays standard exercise postures, exercise intensity and time arrangements in the form of charts and animations. It also has a voice prompt function to remind patients to pay attention to movement standards and exercise rhythm in time during exercise. For medical staff, a detailed patient data management interface is provided. Medical staff can use this interface to view the patient's historical exercise data and physical indicator change trends, and remotely adjust and intervene in the patient's exercise plan. The interactive module also supports online communication between patients and medical staff. Patients can consult medical staff at any time about problems encountered during exercise, and medical staff can also provide timely guidance and suggestions. The display parameters of the interface and the priority weight of the communication function are determined based on user usage frequency and feedback through user surveys and data analysis.

[0049] In summary, through the application of this system in obesity rehabilitation treatment centers, a highly personalized exercise plan can be tailored for each patient, fully considering the individual differences of patients in basic physical indicators, exercise ability, exercise preferences, weight loss goals, diet, etc., greatly improving the pertinence and effectiveness of the exercise plan. The real-time and comprehensive exercise monitoring and precise dynamic adjustment functions can timely optimize the exercise plan according to the patient's actual exercise situation, physical reaction and exercise environment, ensuring that the exercise process is both safe and efficient. At the same time, the system's complete interactive function strengthens the communication and collaboration between patients and medical staff, improves patient compliance, and helps patients better adhere to exercise, thereby more effectively achieving weight loss goals and significantly improving their physical health.

[0050] Example 2

[0051] See also Figure 1 and Figure 2 A large enterprise pays attention to the health of its employees. In order to help obese employees improve their physical condition and work efficiency, it introduced an exercise detection and feedback intervention system for obese patients. There are gyms and sports venues within the enterprise, and employees can exercise after work or during lunch breaks. Employees are busy at work, their exercise time is fragmented, and their physical conditions, exercise foundations and weight loss expectations are different.

[0052] The company's human resources department and health management team use data collection modules to collect relevant data for obese employees. Employees undergo company-specified health examinations to obtain basic physical indicators, use professional equipment to measure body fat percentage and muscle mass, use advanced instruments to detect cardiopulmonary function, joint flexibility and bone density, and use specific methods to measure metabolic rate. To assess athletic ability, employees are organized to participate in endurance, strength, flexibility, balance and agility tests. Among them, balance ability is measured by using balance test equipment to record the balance time and center of gravity offset of employees in specific postures, and agility is measured by setting up specific agility test tracks to record the time it takes employees to complete prescribed actions.

[0053] When communicating with employees, understand their exercise preferences, including indoor aerobics, simple office exercises, outdoor jogging, cycling, etc. At the same time, clarify employees' weight loss goals, such as reducing weight and waist circumference. Employees can also upload their own dietary information through mobile applications developed by the company, including food types, intake, nutritional components, etc. for three meals.

[0054] The data collection module uses blockchain technology to encrypt and store employees' personal data and exercise data, and uses the characteristics of distributed ledgers to ensure data security and prevent data tampering. Only authorized corporate health management teams and employees themselves can access the data. The blockchain's smart contract function realizes the automated management and sharing of data. Its encryption algorithm parameters and execution rule weights are determined by professional security experts' evaluation and business analysis based on data security requirements and the importance of corporate business processes.

[0055] After receiving the data collected by the data acquisition module, the personalized exercise plan generation module first preprocesses the data, including data cleaning and normalization, to eliminate the dimensional differences between different data, and constructs a deep neural network model, which includes an input layer, multiple hidden layers and an output layer. The input layer receives the preprocessed data, the hidden layer extracts and converts the data through nonlinear transformation, and the output layer outputs the preliminary exercise plan parameters.

[0056] The training process is based on the objective function As the loss function, where M i is the actual value of the i-th indicator, T i is the target value, w i is the weight coefficient, weight coefficient w i First, a preliminary determination is made through expert evaluation combined with statistical analysis of historical employee exercise data within the company. Then, in multiple experimental iterations, further optimization is carried out with the goal of minimizing the objective function F. At the same time, a reinforcement learning mechanism is introduced. Based on the feedback from employees in simulated exercise scenarios, the parameters of the deep neural network model are dynamically adjusted. Different reward mechanisms are set in the simulated exercise scenarios to encourage the model to learn better exercise plan generation strategies.

[0057] Finally, after multiple rounds of training and optimization, a personalized exercise plan is generated, including exercise selection suitable for employees' working hours, such as office stretching, jogging during lunch breaks, etc.; reasonable exercise intensity setting; fragmented exercise time arrangement; and scientific exercise frequency planning. At the same time, combined with employees' dietary information, the exercise plan is optimized, and personalized dietary advice is provided to employees, and a diet plan that suits the work scenario is formulated, such as healthy work meal combinations and snack choices. The weight of dietary factors in the optimization of exercise plans is determined according to the impact of diet on weight loss and physical health, through evaluation by nutrition experts and internal employee health data statistics.

[0058] Employees start exercising according to their personalized exercise plans, and the exercise monitoring module is activated. This module uses multi-sensor fusion technology and integrates sensors such as heart rate belts, smart bracelets, and smart office chairs (which can monitor sitting posture and activity) to monitor employees' physical reaction data during exercise in real time. The heart rate belt monitors heart rate in real time, the smart bracelet records information such as the number of steps and exercise speed, and the smart office chair monitors employees' physical activity and sitting posture while working.

[0059] Multi-sensor fusion technology uses a method that combines complementary filtering and Kalman filtering. Complementary filtering is used to fuse static data from different types of sensors, and Kalman filtering is used to process dynamic data, such as acceleration and angular velocity during motion. The parameters of complementary filtering and Kalman filtering are determined by analyzing a large amount of experimental data and using the minimum mean square error criterion. At the same time, the sensors also collect employee motion environment data, such as office temperature and humidity.

[0060] The dynamic adjustment module obtains the actual monitoring value C according to the physical reaction data of employees during exercise collected in real time by the exercise monitoring module. actual , and compare it with the target value C set in the personalized exercise plan target Substitute into the adjustment coefficient calculation formula Calculate the adjustment factor A.

[0061] The time series analysis method is introduced to model and predict the deviation data. The changing trend of the deviation is taken into account. According to individual differences such as employees' age, gender, work pressure, and health status, the weight of the adjustment coefficient A is dynamically adjusted through the hierarchical analysis method. In addition, the impact of employees' working environment factors, such as long-term sitting and high work intensity on exercise plans, is considered. The influence coefficients of parameters such as exercise intensity and exercise time under different working conditions are quantified through the established work environment impact model.

[0062] Taking all the above factors into consideration, the parameters such as exercise items, exercise intensity, exercise time and exercise frequency in the personalized exercise plan are dynamically adjusted. If the adjustment coefficient A is positive and exceeds a certain threshold, it means that the actual exercise intensity or index is higher than the target value, and the exercise intensity should be appropriately reduced or the exercise time should be shortened; if the adjustment coefficient A is negative and exceeds a certain threshold, it means that the actual exercise intensity or index is lower than the target value, and the exercise intensity should be appropriately increased or the exercise time should be extended.

[0063] The interactive module provides employees with a personalized exercise guidance interface, which displays standard exercise postures, exercise intensity and time arrangements in the form of charts and animations. It has a voice prompt function, which makes it convenient for employees to obtain exercise guidance at any time in scenarios such as the office. For the corporate health management team, a detailed employee data management interface is provided. Team members can use this interface to view employees' historical exercise data and physical indicator change trends, and remotely adjust and intervene in employees' exercise plans. The interactive module also supports online communication between employees and the health management team. Employees can consult the team at any time about problems encountered during exercise, and team members can also provide timely guidance and suggestions. The display parameters of the interface and the priority weight of the communication function are determined based on employee usage frequency and feedback through internal corporate research and data analysis.

[0064] In summary, through the application of this system in enterprises, obese employees are provided with personalized exercise plans that suit their work characteristics and physical conditions. This system fully takes into account the fragmentation of employees' working time and the particularity of their working environment, and improves the enthusiasm and feasibility of employees' participation in exercise. The real-time exercise monitoring and dynamic adjustment functions can timely optimize the exercise plan according to the employees' actual exercise conditions and working environment to ensure the safety and effectiveness of exercise. The interactive function of the system strengthens the communication between employees and the enterprise health management team, which helps employees better adhere to exercise, thereby achieving weight loss goals, improving their physical health, and improving work efficiency and quality of life. At the same time, it also reflects the company's care for the health of employees and enhances their sense of belonging and loyalty.

[0065] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A motion detection and feedback intervention system for obese patients, characterized by: The system includes: data acquisition module, personalized exercise plan generation module, exercise monitoring module, dynamic adjustment module and interaction module; The data collection module is used to collect basic physical indicators, exercise capacity, exercise preferences and weight loss target data of obese patients; The personalized exercise plan generation module generates a personalized exercise plan based on the data collected by the data acquisition module using a deep fusion adaptive algorithm. The objective function formula of the algorithm is: Among them, M i is the actual value of the i-th indicator, T i is the target value, w i is the weight coefficient; The motion monitoring module uses multi-sensor fusion technology to monitor the patient's physical response data during exercise in real time; The dynamic adjustment module adjusts the motion plan based on the data from the motion monitoring module through a real-time deviation correction algorithm. The adjustment coefficient calculation formula of the algorithm is: Among them C actual is the actual monitoring value, and C target ≠0, C target It is the target value set by the plan; The interactive module is used for patients and medical staff to interact with the system.

2. The exercise detection and feedback intervention system for obese patients according to claim 1, characterized in that: The basic body indicators collected by the data collection module include body fat percentage, muscle mass, cardiopulmonary function, joint flexibility, bone density and metabolic rate. Athletic ability assessment includes endurance, strength, flexibility, balance and agility. Sports preference collection includes specific sports scenarios such as aerobic exercise, strength training, yoga, outdoor cycling, indoor aerobics, and water sports. Weight loss goal collection includes weight loss value, body fat percentage reduction, and body circumference changes.

3. The exercise detection and feedback intervention system for obese patients according to claim 1, characterized in that: The process of using the deep fusion adaptive algorithm to generate personalized exercise plans in the personalized exercise plan generation module is as follows: Pre-process the basic physical indicators, exercise capacity, exercise preference and weight loss target data collected by the data acquisition module; Construct a deep neural network model consisting of an input layer, multiple hidden layers, and an output layer. The input layer receives preprocessed data, the hidden layer extracts and transforms the input data through nonlinear transformation, and the output layer outputs preliminary motion plan parameters. The training process uses the objective function formula as the loss function and uses the stochastic gradient descent algorithm to optimize the model parameters. The weight coefficient w i According to the importance of each indicator to the exercise plan, through multiple experimental iterations, optimization is carried out with the goal of minimizing the objective function formula; A reinforcement learning mechanism is introduced to dynamically adjust the parameters of the deep neural network model based on patient feedback in simulated exercise scenarios. Different reward mechanisms are set for simulated exercise scenarios to enable the model to learn better exercise plan generation strategies. After multiple rounds of training and optimization, the model generates a personalized exercise plan based on the input patient data, including exercise selection, exercise intensity setting, exercise time arrangement and exercise frequency planning.

4. The exercise detection and feedback intervention system for obese patients according to claim 1, characterized in that: The multi-sensor fusion technology of the motion monitoring module adopts a method that combines complementary filtering and Kalman filtering. Complementary filtering is used to fuse static data from different types of sensors, and Kalman filtering is used to process dynamic data. The sensors include heart rate belts, sports bracelets, smart insoles, and smart sportswear. Smart insoles monitor the patient's gait and plantar pressure distribution, and smart sportswear monitors the patient's muscle activity in real time.

5. The exercise detection and feedback intervention system for obese patients according to claim 1, characterized in that: The dynamic adjustment module adjusts the motion plan through the real-time deviation correction algorithm as follows: The motion monitoring module collects the patient's physical reaction data during exercise in real time as the actual monitoring value C actual ; The actual monitoring value is compared with the target value set by the personalized exercise plan C target Substitute into the adjustment coefficient calculation formula to calculate the adjustment coefficient A; Introducing time series analysis methods to model and predict deviation data, taking into account the changing trend of deviation; The weight of the adjustment coefficient is dynamically adjusted according to the individual differences in the patient's age, gender, and health status. The weight of the individual difference factor is determined by the hierarchical analysis method based on the degree of influence of different factors on exercise; Considering the influence of exercise environment factors on exercise programs, the degree of influence of exercise environment factors is determined by establishing an environmental impact model. This model quantifies the influence coefficients of exercise intensity and exercise time parameters under different environmental conditions based on historical experimental data and theoretical analysis; Taking the above factors into consideration, the exercise items, exercise intensity, exercise time and exercise frequency parameters in the personalized exercise plan are adjusted.

6. The exercise detection and feedback intervention system for obese patients according to claim 1, characterized in that: The interactive module provides patients with a personalized exercise guidance interface, showing standard exercise postures, exercise intensity and timing in the form of charts and animations, and has a voice prompt function.

7. The exercise detection and feedback intervention system for obese patients according to claim 1, characterized in that: The data collection module uses blockchain technology for data encryption and storage. The patient's personal data and movement data are encrypted and stored in the blockchain network, and only authorized users can access them.

8. The exercise detection and feedback intervention system for obese patients according to claim 1, characterized in that: The personalized exercise plan generation module optimizes the exercise plan based on the patient's dietary factors. The system is integrated with the patient's diet record application to obtain the patient's diet information, including food types, intake, and nutrients. According to the patient's weight loss goals and physical indicators, the exercise plan is adjusted based on the dietary information. At the same time, personalized dietary advice is provided to the patient, and a reasonable diet plan that includes food selection, meal time and frequency is formulated.

Images