Sports training reminder system and smart bracelet based on physical examination data analysis

Abstract

The present invention belongs to the technical field of power anomaly detection. The present invention discloses an exercise training reminder system and a smart bracelet based on physical examination data analysis; a user body state data set and a user calorie intake data are collected and preprocessed, the user body state data set including basic body data, important body data and body metabolism data; the user body state data set is analyzed to obtain a user state reference value, and the data is classified to obtain a classification result; analysis is performed based on the classification result to obtain exercise decision data; the user exercise volume and the user calorie intake data are analyzed to obtain a periodic exercise achievement report, and the user exercise volume, exercise decision data and exercise achievement report are displayed through the smart bracelet. Generally speaking, the present invention has the significant advantages of good user exercise assistance effect, strong ability to prevent exercise risks and high degree of decision assistance.

Description

Technical Field

[0001] The present invention relates to the technical field of power anomaly detection, and more specifically, to a sports training reminder system and a smart bracelet based on physical examination data analysis. Background Art

[0002] Currently, 90% of the main consumers of weight loss are young women who love beauty, and the majority are still women between 20 and 50 years old. However, the market structure will change in the future. The share of weight loss for beauty and the share of weight loss for health will each account for 50%, and the ratio of men to women will each be half. The weight loss business is imminent. Under such a huge market demand, how to closely fit the most concerned weight loss issue at the moment, follow the trend, bring good news to many people who want to lose weight, so that everyone can lose weight easily and better manage and control themselves has become a new social issue.

[0003] The patent application publication number CN110314344B discloses a motion reminder method, device and system. It collects and extracts the feature information of a three-dimensional model set of captured motion images, obtains the standard feature information corresponding to the three-dimensional model set, compares the two, and when the difference between the feature information of the three-dimensional model set and the corresponding standard feature information is greater than a preset difference value, performs a reminder operation, so that the user can correct his or her motion posture based on the reminder operation, making the posture correction process more objective and thus improving the accuracy of posture correction.

[0004] Although the above-mentioned exercise reminder method, device and system collect, analyze and remind the user's exercise posture through a set of three-dimensional models, and to a certain extent achieve the purpose of correcting the user's exercise posture standard, there are many problems involved in the current exercise weight loss industry. For example, how do users control their own calorie intake, exercise according to their own condition and choose sports? Most people find it difficult to have professional knowledge, and blindly engaging in weight loss exercises can easily cause physical injuries, thereby bringing more problems.

[0005] In view of this, the present invention proposes an exercise training reminder system and a smart bracelet based on physical examination data analysis to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned objectives, the present invention provides the following technical solutions: comprising:

[0007] The data collection module is used to collect the user's physical status data set and the user's calorie intake data, and pre-process the user's physical status data set to include basic physical data, important physical data and body metabolism data;

[0008] Furthermore, the method of collecting the user's physical status data set and the user's calorie intake data includes:

[0009] By reading the hospital physical examination data platform or manually inputting, the user's height, weight and gender are collected and substituted into the calculation formula: Get basic body data, where A2 is the user's weight and A3 is the user's height;

[0010] By reading the hospital's physical examination data platform, the user's physical condition is collected to determine whether they have any major diseases, and important physical data is obtained by referring to the exercise and disease comparison table;

[0011] Through metabolic rate testing, the user's body metabolism is collected to obtain the user's metabolic data;

[0012] The installed micro camera scans and records the calories of the food consumed by the user each time, adds them up and records them in days, and obtains the user's calorie intake data;

[0013] Preprocessing methods include data cleaning and data denoising;

[0014] The data processing module is used to analyze the user's physical status data set, obtain the user's status reference value, and classify it to obtain the classification result;

[0015] Furthermore, the step of analyzing the user's physical status data set includes:

[0016] Q1: Obtain the user's body reference value by substituting the formula: Aa = (A1 × B1) × (Ab × B2) × (Ac × B3), where Ab represents important body data, Ac represents body metabolic data, and B1, B2, and B3 are preset weighting factors.

[0017] Q2: Collect M groups of historical user body reference values ​​as a sample set, and divide the sample set into a training set (70% M), a test set (15% M), and a validation set (15% M);

[0018] A classification model is established based on the training set, and three initial cluster centers K1, K2, and K2 are preset. By substituting the calculation formula: Get the distance between the data points, calculate the distance between the sub-data items in the training set and the initial cluster center, assign the sub-data items to the initial cluster center closest to them, and recalculate the mean of the three initial cluster centers respectively, and use them as the new initial cluster center for secondary calculation, where x and y are the coordinate values ​​of the data points, xi and yi are the values ​​of the two data points on the i sub-data items respectively, and n is the number of sub-data items;

[0019] After reaching the preset number of iterations, a proposed motion classification model is obtained;

[0020] Q3: Input the user's body reference value into the recommended exercise classification model, and output the user's state reference value;

[0021] Further classification methods include:

[0022] A preset exercise recommendation threshold interval [0, W1, W2) is provided. When the user status reference value is 0, a stop text message is sent to the user receiving terminal through the communication unit. When the user status reference value is greater than 0 and less than W1, a light text message is sent to the user receiving terminal through the unit. When the user status reference value is greater than W1 and less than W2, a general text message is sent to the user receiving terminal through the unit. When the user status reference value is greater than W2, a health text message is sent to the user interaction module through the unit.

[0023] Stop messages include those that explain the user's current physical condition is extremely poor and require the user to temporarily stop exercising. Mild messages include those that explain the user's current physical condition is poor and require the user to always pay attention to whether there is any discomfort during exercise. General messages include those that explain the user's current physical condition is good and recommend that the user choose appropriate sports during exercise. Health messages include those that explain the user's current physical condition is excellent and remind the user to pay attention to safety precautions during exercise.

[0024] Pack stop text messages, mild text messages, general text messages and health text messages to obtain classification results;

[0025] The intelligent allocation model exercise reminder module is used to analyze the classification results and obtain exercise decision data;

[0026] Further, the analysis methods based on the classification results include:

[0027] When the classification result is a stop message, a stop recommendation decision is generated. When the classification result is a mild message, a mild recommendation decision is generated. When the classification result is a general message, a general recommendation decision is generated. When the classification result is a healthy message, a healthy recommendation decision is generated.

[0028] The stop suggestion decision includes explaining that it is recommended that the user cancel the exercise plan and stop exercising, and recommending that the user seek a review and treatment from a relevant medical institution as soon as possible. The mild suggestion decision includes reading the user's physical status data set, and formulating mild exercise programs based on the user's physical status data set to avoid conflicts with diseases in important physical data. The general suggestion decision includes reading the user's physical status data set, and formulating moderate and targeted exercise programs for users with poor physical data based on the user's physical status data set. The health suggestion decision includes formulating exercise programs based on user preferences.

[0029] The stop recommendation decision, light recommendation decision, general recommendation decision and health recommendation decision are packaged to obtain exercise decision data;

[0030] The user interaction module is used to analyze the user's exercise volume and calorie intake data, obtain a periodic exercise results report, and display the user's exercise volume, exercise decision data and exercise results report through the smart bracelet;

[0031] Furthermore, the methods for analyzing the user's exercise volume and the user's physical data include:

[0032] Based on the exercise decision data, the calorie consumption value is obtained by substituting into the calculation formula: Ca = A1 × Af, where Af is the activity consumption factor;

[0033] By substituting into the calculation formula: Get the weight consumption value, where Cb is the user's calorie intake data and Cc is the static calorie consumption factor;

[0034] Based on the preset time unit, the user's exercise volume, calorie intake data and weight loss value are packaged to generate a periodic exercise results report;

[0035] Further, S1: collecting a user's physical state data set and a user's calorie intake data, and preprocessing the data, the user's physical state data set including basic physical data, important physical data, and body metabolism data;

[0036] S2: Analyze the user's physical status data set to obtain a user status reference value, and classify it to obtain a classification result;

[0037] S3: Analyze the classification results to obtain movement decision data;

[0038] S4: Analyze the user's exercise volume and calorie intake data to obtain a periodic exercise results report, and display the user's exercise volume, exercise decision data and exercise results report through the smart bracelet.

[0039] The technical effects and advantages of the sports training reminder system and smart bracelet based on physical examination data analysis of the present invention are as follows:

[0040] By collecting the user's physical condition and calorie intake, the present invention can effectively obtain the user's physical condition information, which is convenient for providing the user with healthy and scientific exercise weight loss decisions based on the user's physical condition. Through the analysis of the user's physical condition, the user condition reference value obtained can intuitively display the user's current suitable exercise level, avoiding the user from choosing inappropriate exercise due to lack of understanding of their own physical condition, greatly reducing the risk of physical damage due to blind exercise, and can intuitively provide the user with scientific and healthy exercise projects through exercise decision data, greatly improving the user's usage experience. Through the periodic exercise results report, the user's exercise results within the cycle can be intuitively displayed, which is convenient for the user to make the next exercise level selection based on the periodic exercise results report. Finally, the user can intuitively obtain the above data through the smart bracelet. Overall, the present invention has the significant advantages of good auxiliary user exercise effect, strong ability to prevent exercise risks and high degree of auxiliary decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Schematic diagram of the sports training reminder system based on physical examination data analysis of the present invention;

[0042] Figure 2 Schematic diagram of the exercise training reminder method based on physical examination data analysis of the present invention. DETAILED DESCRIPTION

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0044] Example 1

[0045] See also Figure 1 As shown, the sports training reminder system based on physical examination data analysis in this embodiment includes:

[0046] The data collection module is used to collect the user's physical status data set and the user's calorie intake data, and pre-process the user's physical status data set to include basic physical data, important physical data and body metabolism data;

[0047] Furthermore, the method of collecting the user's physical status data set and the user's calorie intake data includes:

[0048] By reading the hospital physical examination data platform or manually inputting, the user's height, weight and gender are collected and substituted into the calculation formula: Get basic body data, where A2 is the user's weight and A3 is the user's height;

[0049] By reading the hospital's physical examination data platform, the user's physical condition is collected to determine whether they have any major diseases, and important physical data is obtained by referring to the exercise and disease comparison table;

[0050] It should be explained that the exercise and disease comparison table is set up to help users exercise safely based on their disease conditions. For example, if a user has a serious heart problem, the important physical data value is 0; if a user has a common disease, the important physical data value is 1; if the user is healthy, the important physical data value is 2;

[0051] Through metabolic rate testing, the user's body metabolism is collected to obtain the user's metabolic data;

[0052] It should be explained that the user's body metabolism can be assigned a value through a preset body metabolism threshold interval (Z1, Z2). When the user's body metabolism is less than Z1, the user's metabolism data value is 1. When the user's body metabolism is greater than Z1 and less than Z2, the user's metabolism data value is 2. When the user's body metabolism is greater than Z2, the user's metabolism data value is 3.

[0053] The installed micro camera scans and records the calories of the food consumed by the user each time, adds them up and records them in days, and obtains the user's calorie intake data;

[0054] Preprocessing methods include data cleaning and data denoising;

[0055] The data processing module is used to analyze the user's physical status data set, obtain the user's status reference value, and classify it to obtain the classification result;

[0056] Furthermore, the step of analyzing the user's physical status dataset includes:

[0057] Q1: Obtain the user's body reference value by substituting the formula: Aa = (A1 × B1) × (Ab × B2) × (Ac × B3), where Ab represents important body data, Ac represents body metabolic data, and B1, B2, and B3 are preset weighting factors.

[0058] Q2: Collect M groups of historical user body reference values ​​as a sample set, and divide the sample set into a training set (70% M), a test set (15% M), and a validation set (15% M);

[0059] A classification model is established based on the training set, and three initial cluster centers K1, K2, and K2 are preset. By substituting the calculation formula: Get the distance between the data points, calculate the distance between the sub-data items in the training set and the initial cluster center, assign the sub-data items to the initial cluster center closest to them, and recalculate the mean of the three initial cluster centers respectively, and use them as the new initial cluster center for secondary calculation, where x and y are the coordinate values ​​of the data points, xi and yi are the values ​​of the two data points on the i sub-data items respectively, and n is the number of sub-data items;

[0060] After reaching the preset number of iterations, a proposed motion classification model is obtained;

[0061] Q3: Input the user's body reference value into the recommended exercise classification model, and output the user's state reference value;

[0062] Further classification methods include:

[0063] A preset exercise recommendation threshold interval [0, W1, W2) is provided. When the user status reference value is 0, a stop text message is sent to the user receiving terminal through the communication unit. When the user status reference value is greater than 0 and less than W1, a light text message is sent to the user receiving terminal through the unit. When the user status reference value is greater than W1 and less than W2, a general text message is sent to the user receiving terminal through the unit. When the user status reference value is greater than W2, a health text message is sent to the user interaction module through the unit.

[0064] Stop messages include those that explain the user's current physical condition is extremely poor and require the user to temporarily stop exercising. Mild messages include those that explain the user's current physical condition is poor and require the user to always pay attention to whether there is any discomfort during exercise. General messages include those that explain the user's current physical condition is good and recommend that the user choose appropriate sports during exercise. Health messages include those that explain the user's current physical condition is excellent and remind the user to pay attention to safety precautions during exercise.

[0065] Pack stop text messages, mild text messages, general text messages and health text messages to obtain classification results;

[0066] The intelligent allocation model exercise reminder module is used to analyze the classification results and obtain exercise decision data;

[0067] Further analysis methods based on the classification results include:

[0068] When the classification result is a stop message, a stop recommendation decision is generated. When the classification result is a mild message, a mild recommendation decision is generated. When the classification result is a general message, a general recommendation decision is generated. When the classification result is a healthy message, a healthy recommendation decision is generated.

[0069] The stop suggestion decision includes explaining that it is recommended that the user cancel the exercise plan and stop exercising, and recommending that the user seek a review and treatment from a relevant medical institution as soon as possible. The mild suggestion decision includes reading the user's physical status data set, and formulating mild exercise programs based on the user's physical status data set to avoid conflicts with diseases in important physical data. The general suggestion decision includes reading the user's physical status data set, and formulating moderate and targeted exercise programs for users with poor physical data based on the user's physical status data set. The health suggestion decision includes formulating exercise programs based on user preferences.

[0070] It should be explained that, for poor user physical data, such as excessively high basic physical data, low metabolic rate, or high metabolic rate, the user preference specifies an exercise direction for the user, such as reducing body fat, training leg strength, or training waist strength;

[0071] The stop recommendation decision, light recommendation decision, general recommendation decision and health recommendation decision are packaged to obtain exercise decision data;

[0072] The user interaction module is used to analyze the user's exercise volume and calorie intake data, obtain a periodic exercise results report, and display the user's exercise volume, exercise decision data and exercise results report through the smart bracelet;

[0073] Furthermore, methods for analyzing the user's exercise volume and physical data include:

[0074] Based on the exercise decision data, the calorie consumption value is obtained by substituting into the calculation formula: Ca = A1 × Af, where Af is the activity consumption factor;

[0075] By substituting into the calculation formula: Get the weight consumption value, where Cb is the user's calorie intake data and Cc is the static calorie consumption factor;

[0076] Based on the preset time unit, the user's exercise volume, calorie intake data and weight loss value are packaged to generate a periodic exercise results report;

[0077] It needs to be explained that the default time unit is day, week or month;

[0078] The beneficial effects of this embodiment are that by collecting the user's physical condition and calorie intake, the user's physical condition information can be effectively obtained, which is convenient for providing the user with healthy and scientific exercise weight loss decisions based on the user's physical condition. By analyzing the user's physical condition, the user's state reference value obtained can intuitively display the user's current suitable exercise level, avoiding the user from choosing inappropriate sports due to not understanding their own physical condition, greatly reducing the risk of physical damage due to blind exercise, and can intuitively provide the user with scientific and healthy sports through exercise decision data, greatly improving the user's usage experience. Through the periodic exercise results report, the user's exercise results within the cycle can be intuitively displayed, which is convenient for the user to make the next exercise level selection based on the periodic exercise results report. Finally, the user can intuitively obtain the above data through the smart bracelet. Overall, the present invention has the significant advantages of assisting users in exercise, strong ability to prevent exercise risks, and high degree of decision-making assistance.

[0079] Example 2

[0080] See also Figure 2 As shown, for parts not described in detail in this embodiment, please refer to the description of Example 1. A sports training reminder method based on physical examination data analysis is provided, including: S1: collecting a user's physical status data set and user's calorie intake data, and preprocessing them, the user's physical status data set including basic physical data, important physical data and body metabolism data;

[0081] S2: Analyze the user's physical status data set to obtain a user status reference value, and classify it to obtain a classification result;

[0082] S3: Analyze the classification results to obtain movement decision data;

[0083] S4: Analyze the user's exercise volume and calorie intake data to obtain a periodic exercise results report, and display the user's exercise volume, exercise decision data and exercise results report through the smart bracelet.

[0084] Example 3

[0085] This embodiment discloses a smart bracelet, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the above-mentioned exercise training reminder method based on physical examination data analysis is implemented.

[0086] Since the electronic device introduced in this embodiment is the electronic device used to implement the sports training reminder method based on physical examination data analysis in the embodiment of the present application, based on the sports training reminder method based on physical examination data analysis introduced in the embodiment of the present application, those skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application will not be described in detail here. As long as those skilled in the art implement the electronic device used in the sports training reminder method based on physical examination data analysis in the embodiment of the present application, it falls within the scope of protection of this application.

[0087] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0088] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the principles of the present invention are within the scope of protection of the present invention. It should be noted that for users of ordinary skill in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. The sports training reminder system based on physical examination data analysis is characterized by: include: The data collection module is used to collect the user's physical status data set and the user's calorie intake data, and pre-process the user's physical status data set to include basic physical data, important physical data and body metabolism data; The data processing module is used to analyze the user's physical status data set, obtain the user's status reference value, and classify it to obtain the classification result; The intelligent allocation model exercise reminder module is used to analyze the classification results and obtain exercise decision data; The user interaction module is used to analyze the user's exercise volume and calorie intake data, obtain a periodic exercise results report, and display the user's exercise volume, exercise decision data and exercise results report through the smart bracelet; Methods for collecting user physical status data sets and user calorie intake data include: By reading the hospital physical examination data platform or manually inputting, the user's height, weight and gender are collected and substituted into the calculation formula: Get basic body data, where is the user's weight, is the user's height; By reading the hospital's physical examination data platform, the user's physical condition is collected to determine whether they have any major diseases, and important physical data is obtained by referring to the exercise and disease comparison table; Through metabolic rate testing, the user's body metabolism is collected to obtain the user's metabolic data; The installed micro camera scans and records the calories of the food consumed by the user each time, adds them up and records them in days, and obtains the user's calorie intake data; Preprocessing methods include data cleaning and data denoising; The steps for analyzing the user's physical status dataset include: Q1: By substituting into the calculation formula: Get the user's body reference value, where For important body data, For body metabolism data, and are the preset weight factors respectively; Q2: Collect M groups of historical user body reference values ​​as a sample set, and divide the sample set into a training set (70%M), a test set (15%M), and a validation set (15%M); A classification model is established based on the training set, and three initial cluster centers K1, K2, and K2 are preset. By substituting the calculation formula: Get the distance between the data points, calculate the distance between the sub-data items in the training set and the initial cluster center, assign the sub-data items to the initial cluster center closest to them, and recalculate the mean of the three initial cluster centers respectively, and use them as the new initial cluster center for secondary calculation, where x and y are the coordinate values ​​of the data points. and For two data points, The value of the sub-data item, is the number of sub-data items; After reaching the preset number of iterations, a proposed motion classification model is obtained; Q3: Input the user's body reference value into the recommended exercise classification model, and output the user's state reference value; The classification methods include: The preset exercise recommendation threshold interval is [0, W1, W2). When the user status reference value is 0, a stop text message is sent to the user receiving terminal through the communication unit. When the user status reference value is greater than 0 and less than W1, a light text message is sent to the user receiving terminal through the unit. When the user status reference value is greater than W1 and less than W2, a general text message is sent to the user receiving terminal through the unit. When the user status reference value is greater than W2, a health text message is sent to the user interaction module through the unit. Stop messages include those that explain the user's current physical condition is extremely poor and require the user to temporarily stop exercising. Mild messages include those that explain the user's current physical condition is poor and require the user to always pay attention to whether there is any discomfort during exercise. General messages include those that explain the user's current physical condition is good and recommend that the user choose appropriate sports during exercise. Health messages include those that explain the user's current physical condition is excellent and remind the user to pay attention to safety precautions during exercise. Stop text messages, light text messages, general text messages and health text messages are packaged to obtain classification results.

2. The sports training reminder system based on physical examination data analysis according to claim 1, characterized in that: Methods of analysis based on classification results include: When the classification result is a stop message, a stop recommendation decision is generated. When the classification result is a mild message, a mild recommendation decision is generated. When the classification result is a general message, a general recommendation decision is generated. When the classification result is a healthy message, a healthy recommendation decision is generated. The stop suggestion decision includes explaining that it is recommended that the user cancel the exercise plan and stop exercising, and recommending that the user seek a review and treatment from a relevant medical institution as soon as possible. The mild suggestion decision includes reading the user's physical status data set, and formulating mild exercise programs based on the user's physical status data set to avoid conflicts with diseases in important physical data. The general suggestion decision includes reading the user's physical status data set, and formulating moderate and targeted exercise programs for users with poor physical data based on the user's physical status data set. The health suggestion decision includes formulating exercise programs based on user preferences. The stop recommendation decision, light recommendation decision, general recommendation decision and health recommendation decision are packaged to obtain the exercise decision data.

3. A smart bracelet, based on the reminder system according to claim 2, characterized in that: Methods for analyzing user exercise volume and user body data include: Based on the motion decision data, by substituting into the calculation formula: Get the calorie consumption value, where is the activity consumption factor; By substituting into the calculation formula: Get the weight consumption value, where Provide users with calorie intake data, is the static heat consumption factor; Based on the preset time unit, the user's exercise volume, calorie intake data and weight consumption value are packaged to generate a periodic exercise results report.

4. A method for reminding sports training based on physical examination data analysis, implemented using the smart bracelet of claim 3, characterized in that: S1: Collect user body status data sets and user calorie intake data, and perform preprocessing. The user body status data sets include basic body data, important body data, and body metabolism data; S2: Analyze the user's physical status data set to obtain a user status reference value, and classify it to obtain a classification result; S3: Analyze the classification results to obtain movement decision data; S4: Analyze the user's exercise volume and calorie intake data to obtain a periodic exercise results report, and display the user's exercise volume, exercise decision data and exercise results report through the smart bracelet.

Images