Health management scheme generation method and device based on body index monitoring

Abstract

The invention relates to a health management scheme generation method and device based on body index monitoring, and the method comprises the steps: obtaining the body index monitoring data of a user, carrying out the classification of the body index monitoring data, obtaining a classification result, carrying out the retrieval and matching of the classification result through a rule engine, and generating a corresponding health management scheme. Specific data of each user are collected, individual differences such as age, gender and basic diseases are considered by utilizing a machine learning algorithm and a rule engine, a highly personalized model is constructed and integrated into an actual health management system, and automation of health assessment, scheme making and feedback adjustment can be realized. Therefore, the workload of the medical staff is reduced, the time of waiting for the health management scheme by the user is shortened, and the overall service efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of computer science and technology, and in particular to a method, device and electronic device for generating a health management plan based on physical indicator monitoring. Background Art

[0002] In the prior art, healthy diet plans are widely available, aiming to help users manage their daily diet to maintain health. These plans usually calculate daily calorie needs based on basic information of the user, such as age, gender, weight and activity level, and provide corresponding dietary recommendations. Some technical solutions can even provide specific recipes, detailing the types and quantities of food that should be consumed at each meal. However, these healthy diet plans are usually general and are not specifically formulated for patients with diseases such as high blood pressure that require dietary control.

[0003] Although existing healthy diet plans can provide some guidance, these plans have significant shortcomings for diseases that require dietary control. First, general healthy diet plans lack personalization and precision, and cannot specifically target the special needs of people who need to control their diet due to illness. Secondly, existing plans usually cannot provide specific daily recommended food intake and optional ranges, resulting in a lack of alternative choices when users face foods they don’t like. Common recipe plans are too single in choice in actual applications and are not enough to meet the diverse needs of patients. In addition, current technical solutions lack detailed guidance on dietary taboos and precautions for patients with diseases such as hypertension, and cannot meet the complex needs of hypertensive patients who also suffer from multiple chronic diseases such as diabetes. In this case, users cannot obtain a comprehensive and personalized health management plan, including various aspects such as diet, exercise, and health monitoring. Summary of the invention

[0004] In view of this, the present application proposes a method for generating a health management plan based on body indicator monitoring to solve the problems reflected in the above-mentioned background technology.

[0005] According to one aspect of the present application, a method for generating a health management program based on physical indicator monitoring is provided, comprising: Obtain the user's physical indicator monitoring data; Classifying the body indicator monitoring data into categories to obtain classification results; A rule engine is used to retrieve and match the classification results to generate a corresponding health management plan.

[0006] As an optional implementation scheme of the present application, the body index monitoring data is classified into categories to obtain classification results, including: Get the center point coordinates of each category data; Calculate the distance between the body index monitoring data and the center point coordinates, and determine the center point coordinates that are closest; The body index monitoring data is classified into the category corresponding to the coordinates of the nearest center point to obtain a classification result.

[0007] As an optional implementation scheme of the present application, the body index monitoring data is classified into the category corresponding to the coordinates of the nearest center point, and after the classification result is obtained, the method further includes: Adding the body index monitoring data to the corresponding category data according to the classification result; The category data updates the center point coordinates according to the newly added body index monitoring data.

[0008] As an optional implementation scheme of the present application, before using a rule engine to search and match the classification results and generate a corresponding health management plan, the method further includes: Obtain guidance information related to health management; The guide information is converted into rule entries in a rule engine.

[0009] As an optional implementation scheme of the present application, a rule engine is used to retrieve and match the classification results to generate a corresponding health management plan, including: Searching according to the classification result to obtain the rule entry; The body index monitoring data corresponding to the classification result is matched with the rule entry, and a corresponding health management plan is generated according to the matching result.

[0010] As an optional implementation scheme of the present application, using a rule engine to retrieve and match the classification results to generate a corresponding health management plan also includes: Combining the rule items; The body index monitoring data corresponding to the classification result is matched with the combined rule items, and a corresponding health management plan is generated according to the matching result.

[0011] As an optional implementation scheme of the present application, the physical index monitoring data corresponding to the classification result is matched with the combined rule items, and when the corresponding health management plan is generated according to the matching result, it also includes: For the generated diet plan, a diet pyramid structure corresponding to the diet plan is constructed based on the composition of the diet pyramid structure.

[0012] The present application also provides a device for generating a health management plan based on physical indicator monitoring, comprising: The data acquisition module is used to acquire the user's physical indicator monitoring data; A data classification module, used to classify the body index monitoring data into categories to obtain classification results; The plan generation module is used to use a rule engine to retrieve and match the classification results and generate a corresponding health management plan.

[0013] As an optional implementation scheme of the present application, the data classification module includes: A module for obtaining center point coordinates is used to obtain the center point coordinates of each category of data; A calculation module, used to calculate the distance between the body index monitoring data and the center point coordinates, and determine the center point coordinates that are closest to the distance; The classification module is used to classify the body index monitoring data into the category corresponding to the coordinates of the nearest center point to obtain a classification result.

[0014] The present application also provides an electronic device, including: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the above-mentioned method for generating a health management plan based on physical indicator monitoring when executing the executable instructions.

[0015] Beneficial effects of this application: The present invention obtains the user's physical indicator monitoring data, classifies the physical indicator monitoring data into categories, obtains the classification results, uses the rule engine to retrieve and match the classification results, generates the corresponding health management plan, collects the specific data of each user, uses the machine learning algorithm and the rule engine to consider their individual differences, such as age, gender, basic diseases, etc., to build a highly personalized model and integrate it into the actual health management system, which can realize the automation of health assessment, plan formulation and feedback adjustment. This not only reduces the workload of medical staff, but also shortens the time users wait for health management plans, and improves the overall service efficiency.

[0016] Other features and aspects of the present application will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the present application and, together with the description, serve to explain the principles of the present application.

[0018] Figure 1 A flowchart showing a method for generating a health management plan based on physical indicator monitoring according to an embodiment of the present application; Figure 2 Iterative update category center point diagram of an embodiment of the present application is shown; Figure 3 A matching rule condition flow chart of an embodiment of the present application is shown; Figure 4 A block diagram of a device for generating a health management plan based on body indicator monitoring according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0019] Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0020] Among them, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application or simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0021] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0022] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0023] In addition, in order to better illustrate the present application, numerous specific details are provided in the following specific embodiments. It should be understood by those skilled in the art that the present application can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present application.

[0024] The present application is a processing method for basic body indicator monitoring. Specifically, body monitoring data is first obtained from the user, and the body monitoring data is uploaded to the server side of the present application for analysis and processing. The server side of the present application analyzes and classifies the body indicator monitoring data uploaded by the client or user, and generates a health management plan based on the classification results and all the customer's data.

[0025] Example 1 Figure 1 A flow chart showing a method for generating a health management plan based on physical indicator monitoring according to an embodiment of the present application is shown. Figure 1 As shown, the flow chart includes: S100, obtaining user's physical index monitoring data; The exercise status and physical condition are obtained through user input or addition by medical staff. For patients with chronic diseases such as hypertension and diabetes, the data are collected through different blood pressure and blood sugar testing devices, and the collected data are used as the user's physical indicator monitoring data.

[0026] S200, classifying the body index monitoring data into categories to obtain classification results; In this embodiment, a model based on a machine learning algorithm is used to classify the collected physical index monitoring data. The idea of ​​the model is to divide n instances into k clusters, so that the data similarity within the same cluster is high and the data similarity between different clusters is low. The objective function acquisition formula is as follows: For a given sample set D = {x1, x2, ... m}, k is divided into clusters C = {C1, C2, ... C k}, whose goal is to minimize the square error E: in: It is a cluster The mean vector, x i is the body monitoring data, in this example x1, x2, ... x m is a plurality of clustered body monitoring data, C1, C2, ... C k There are k clusters, and x in each cluster iThe data similarity is high, while the data similarity of the body monitoring data indicators in different clusters is low. In this embodiment, when acquiring data, the body monitoring data that is directly numerical is acquired normally, including blood sugar, age, BMI, etc., which directly acquire the user's parameter data. For parameter data that is not a numerical type, such as gender, in this solution, the parameters are pre-set. For example, for gender, the corresponding number transmitted for males is 1, and the corresponding data transmitted for females is 2. When setting data, it will be set to distinguish it from other numerical parameters, so that it can be distinguished from other monitoring data when clustering.

[0027] For multiple clustering, n instances can be n pieces of body index monitoring data, and the n pieces of body index monitoring data are divided into k clusters, that is, the data similarity within each cluster is high, and the data similarity between clusters is low. For example, the data about gender in n pieces of body index monitoring data are divided into one cluster, and the data in this cluster are all related to gender, and the similarity between the data is high. Similarly, for example, the data about age are divided into one cluster, and the data similarity between the cluster about gender and the cluster about age is low.

[0028] Machine learning algorithms can capture nonlinear relationships and hidden patterns in data, thereby improving the accuracy of predictions about future health status. This helps identify potential health problems in advance and take corresponding preventive measures to avoid worsening of the disease.

[0029] In this embodiment, the data type is classified by directly analyzing the acquired body monitoring data, thereby greatly reducing the data transmission volume of the data monitoring end. The data value can be directly sent without explaining or limiting the data, and unified numerical data can be used for sending and statistics, which is convenient for data storage and analysis. Improve the transmission efficiency and analysis efficiency of body monitoring data. Moreover, the use of this method for data transmission and identification has a stronger tolerance for data, and there is no limit on the number of data transmitted by the user or the client, for example, there is no limit on the data data and type that must be transmitted. In this application, the data sent can be combined at will. For example, only age and gender can be sent, or only age BMI can be sent, and the server side can perform accurate data identification. Moreover, a physical health management plan can be issued directly based on the acquired data and the corresponding category in the future. Instead of having to limit the input of age or gender, etc. The entire plan has high flexibility and efficiency.

[0030] S300, using a rule engine to retrieve and match the classification results, and generate a corresponding health management plan.

[0031] The rule engine is responsible for dynamically adjusting the plan based on preset medical knowledge and expert advice, combined with the model's predictive classification results, to ensure that it always matches the user's current health status and needs.

[0032] As an optional implementation scheme of the present application, the body indicator monitoring data is classified into categories to obtain classification results, including: obtaining the center point coordinates of each category of data; calculating the distance between the body indicator monitoring data and the center point coordinates, and determining the center point coordinates with the closest distance; classifying the body indicator monitoring data into the category corresponding to the center point coordinates with the closest distance to obtain a classification result.

[0033] The core idea of ​​the model is to iteratively update the coordinates of the category center point, that is, the coordinates of the center point of each category data, so that the distance between the sample point and the center point of its category is minimized.

[0034] In this embodiment, if Figure 2 As shown in the figure, it is the process of identifying the initial data type. The three solid circles in the first figure are the center points of the initial gender sample, the center point of the age sample, and the center point of the bmi sample. The three clusters of data are the results of clustering the parameters of multiple users that have been obtained. After clustering, the body monitoring data type corresponding to each cluster of data cannot be determined. In this application, according to Figure 2 The steps shown in the diagram are used to determine the data type corresponding to the initial cluster of body monitoring data. First, the center point of the initial monitoring data is set, and the initial monitoring data center point is pre-set based on experience. For example, the initial center point of age can be set to 56, the initial center point of BMI can be set to 25, and the initial center point of gender can be set to 1.5. At this time, the initial monitoring data center point is treated as the monitoring data to be analyzed for clustering, and the corresponding initial monitoring data center point is divided into the corresponding monitoring data cluster according to the aforementioned clustering method, so as to determine the monitoring data type corresponding to each cluster data according to the initial monitoring data center point, whether it is gender clustering, age clustering, BMI clustering, or height, blood sugar clustering, etc. Furthermore, in this embodiment, after the monitoring data category corresponding to the cluster is identified by the initial monitoring data center point, and the center point of the corresponding cluster is further iteratively updated according to the initial monitoring data center point. Two iterations can be performed. It should also be noted that Figure 2 The horizontal and vertical axes have no actual meaning and are only used to illustrate the data clusters.

[0035] For each sample point, calculate its distance from the center point of the three categories of gender, age and BMI, and assign it to the category with the closest distance. After one iteration, the three solid points have been classified. As part of the data of the corresponding category, after updating the coordinates of the category center point, iterate for the second time after receiving new sample points, and update the number of samples of the category and the coordinates of the category center point of the next iteration again. After each iteration, the code shows the classification results by drawing a scatter plot. In the actual process, sample points of different categories can be marked with different symbols and colors.

[0036] When the collected body indicator monitoring data is input into the model, the model will classify the body indicator detection data based on the pre-stored category data, calculate the distance between the body indicator monitoring data and the center point coordinates of all category data, and classify the body indicator monitoring data into the category with the smallest distance to obtain the classification result, that is, the body indicator monitoring data has one or more classification results, for example Figure 3 Gender, age, BMI, medical history, etc. shown.

[0037] As an optional implementation scheme of the present application, the body indicator monitoring data is classified into the category corresponding to the center point coordinates that are closest to the data, and after the classification result is obtained, it also includes: adding the body indicator monitoring data to the corresponding category data according to the classification result; the category data updates the center point coordinates according to the newly added body indicator monitoring data.

[0038] For example, for gender categories, the data about gender in the physical indicator monitoring data is added to the gender category data. However, due to the addition of new data, the data corresponding to the original center point coordinates of the gender category data cannot fully represent the center point of the gender category data. Therefore, it is necessary to re-determine a certain data as the center point, and use its center point coordinates for the next prediction iteration. That is, the center point coordinates in the gender category data are updated before the next prediction iteration. Based on the continuously added category data, the machine learning algorithm can process and analyze a large amount of personal health data, such as age, gender, living habits, physical examination reports, medical history, etc., so as to identify health differences between different individuals. It should be noted that the increase in categories can be set by relevant personnel, and whether to add new categories can also be decided by analyzing the distance of the physical indicator monitoring data from all center point coordinates.

[0039] As an optional implementation scheme of the present application, before using a rule engine to search and match the classification results and generate a corresponding health management plan, it also includes: obtaining guideline information related to health management; and converting the guideline information into rule entries in the rule engine.

[0040] In this embodiment, taking hypertension and diabetes as examples, the parts about diet, exercise and health monitoring in the Chinese Dietary Guidelines, Clinical Nutrition Guidelines, Hypertension Guidelines and Diabetes Guidelines are sorted out, and these guideline information is converted into rule entries in the rule engine, covering the calculation of the user's daily calorie budget, the calculation of the intake of each type of food in the dietary pyramid structure, the classification of suitable foods and taboo foods, dietary precautions, exercise plans and precautions, blood pressure and blood sugar monitoring plans, etc.

[0041] As an optional implementation scheme of the present application, a rule engine is used to retrieve and match the classification results to generate a corresponding health management plan, including: searching according to the classification results to obtain the rule entries; matching the body indicator monitoring data corresponding to the classification results with the rule entries, and generating a corresponding health management plan based on the matching results.

[0042] like Figure 3 As shown in the figure, after the body index monitoring data is classified into gender, age, BMI and medical history, the rule engine is used for retrieval. For gender, an option of whether the gender is male or not appears. If the gender category data in the body index detection data is male, a health management plan for men is generated. Similarly, a health management plan for age, BMI or medical history is generated.

[0043] It should be noted that due to the length limitation of the figure, each category can correspond to one or more options for matching with the body indicator monitoring data, and the corresponding health management plan can be obtained based on the matching results.

[0044] As an optional implementation scheme of the present application, a rule engine is used to retrieve and match the classification results to generate a corresponding health management plan, which also includes: combining the rule entries; matching the body indicator monitoring data corresponding to the classification results with the combined rule entries, and generating a corresponding health management plan based on the matching results.

[0045] like Figure 3 As shown in the figure, the rule items of gender being male and age being over 60 years old are combined, which means that the rule items of gender being male and age being over 60 years old are satisfied at the same time, that is, males over 60 years old. When the body index monitoring data satisfies the rule item, a health management plan suitable for males over 60 years old is generated. In this way, multiple rule items can be combined to further refine the health management plan for a certain group of people, such as people with hypertension and people with diabetes.

[0046] As an optional implementation scheme of the present application, the body indicator monitoring data corresponding to the classification result is matched with the combined rule entries, and a corresponding health management plan is generated according to the matching result, and it also includes: matching the body indicator monitoring data corresponding to the classification result with the combined rule entries, and generating a corresponding health management plan according to the matching result, and also includes: for the generated diet plan, based on the composition of the diet pyramid structure, constructing a diet pyramid structure corresponding to the diet plan.

[0047] In the process of using the rule engine to search for matches, the user's daily calorie needs will be calculated based on the matching results, and the intake of each type of food in the dietary pyramid structure will be generated. Combined with the user's dietary preferences and allergy information, specific food intake and food types will be recommended. For patients with hypertension, a diet plan containing low-salt, low-fat, and high-fiber foods can be specially customized, and detailed dietary precautions can be provided. For users who also suffer from diabetes, the diet plan is adjusted to take into account blood sugar control needs, and low GI (glycemic index) foods are recommended.

[0048] By collecting specific data of each user, using machine learning algorithms and rule engines to consider individual differences such as age, gender, and underlying diseases, a highly personalized model can be built and integrated into the actual health management system, which can realize the automation of health assessment, program formulation, and feedback adjustment. This not only reduces the workload of medical staff, but also shortens the time users wait for health management programs and improves overall service efficiency.

[0049] Example 2 Based on the same principle as the above method, a health management program generation device based on body index monitoring is also proposed, see Figure 4 , a health management program generation device 100 based on body index monitoring according to an embodiment of the present disclosure includes: The data acquisition module 110 is used to acquire the user's physical index monitoring data; The data classification module 120 is used to classify the body index monitoring data into categories to obtain classification results; The plan generation module 130 is used to use a rule engine to retrieve and match the classification results and generate a corresponding health management plan.

[0050] As an optional implementation scheme of the present application, the data classification module 120 includes: A center point coordinate acquisition module 121 is used to acquire the center point coordinates of each category of data; A calculation module 122, used to calculate the distance between the body index monitoring data and the center point coordinates, and determine the center point coordinates that are closest; The classification module 123 is used to classify the body index monitoring data into the category corresponding to the coordinates of the nearest center point to obtain a classification result.

[0051] Obviously, those skilled in the art should understand that all or part of the processes in the above-mentioned embodiment method can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned control methods. The modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by computing devices, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules respectively, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.

[0052] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned control methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0053] Example 3 Furthermore, an electronic device is proposed, comprising: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the method for generating a health management plan based on physical indicator monitoring described in Example 1 when executing the executable instructions.

[0054] The electronic device of the embodiment of the present disclosure includes a processor and a memory for storing instructions executable by the processor, wherein the processor is configured to implement any of the above-mentioned methods for generating a health management program based on body indicator monitoring when executing the executable instructions.

[0055] It should be noted that the number of processors may be one or more. At the same time, the electronic device of the embodiment of the present disclosure may also include an input device and an output device. The processor, memory, input device, and output device may be connected via a bus or in other ways, which are not specifically limited here.

[0056] The memory is a computer-readable storage medium for the method for generating a health management program based on physical indicator monitoring, and can be used to store software programs, computer executable programs, and various modules, such as the program or module corresponding to the method for generating a health management program based on physical indicator monitoring in the embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0057] The input device can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output device can include a display device such as a display screen.

[0058] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for generating a health management plan based on physical index monitoring, characterized in that: include: Obtain the user's physical indicator monitoring data; Classifying the body indicator monitoring data into categories to obtain classification results; A rule engine is used to retrieve and match the classification results to generate a corresponding health management plan.

2. The method for generating a health management plan based on physical indicator monitoring according to claim 1, characterized in that: The body index monitoring data is classified into categories to obtain classification results, including: Get the coordinates of the center point of each category of data; Calculate the distance between the body index monitoring data and the center point coordinates, and determine the center point coordinates that are closest; The body index monitoring data is classified into the category corresponding to the coordinates of the nearest center point to obtain a classification result.

3. The method for generating a health management plan based on physical indicator monitoring according to claim 2, characterized in that: Classifying the body index monitoring data into the category corresponding to the coordinates of the nearest center point, and obtaining the classification result, further comprising: Adding the body index monitoring data to the corresponding category data according to the classification result; The category data updates the center point coordinates according to the newly added body index monitoring data.

4. The method for generating a health management plan based on physical index monitoring according to claim 1, characterized in that: Before using the rule engine to search and match the classification results and generate a corresponding health management plan, the method further includes: Obtain guidance information related to health management; The guide information is converted into rule entries in a rule engine.

5. The method for generating a health management plan based on physical index monitoring according to claim 4, characterized in that: The classification results are retrieved and matched using a rule engine to generate a corresponding health management plan, including: Searching according to the classification result to obtain the rule entry; The body index monitoring data corresponding to the classification result is matched with the rule entry, and a corresponding health management plan is generated according to the matching result.

6. The method for generating a health management plan based on physical index monitoring according to claim 5, characterized in that: Using a rule engine to retrieve and match the classification results to generate a corresponding health management plan also includes: Combining the rule items; The body index monitoring data corresponding to the classification result is matched with the combined rule items, and a corresponding health management plan is generated according to the matching result.

7. The method for generating a health management plan based on physical index monitoring according to claim 1, characterized in that: A model based on machine learning algorithm is used to classify the collected physical indicator monitoring data, and m instances are divided into k clusters, so that the data similarity within the same cluster is high and the data similarity between different clusters is low. The objective function is obtained as follows: For a given sample set D = {x1, x2, ... m }, k is divided into clusters C = {C1, C2, ... C k }, whose goal is to minimize the square error E: in: It is a cluster The mean vector, x i is the body monitoring data, in this example x1, x2, ... x m is a plurality of clustered body monitoring data, C1, C2, ... C k There are k clusters, and x in each cluster i The data similarity is high, while the data similarity of body monitoring data indicators in different clusters is low.

8. A device for generating a health management plan based on physical index monitoring, characterized in that: include: The data acquisition module is used to acquire the user's physical indicator monitoring data; A data classification module, used to classify the body index monitoring data into categories to obtain classification results; The plan generation module is used to use a rule engine to retrieve and match the classification results and generate a corresponding health management plan.

9. The device for generating a health management plan based on body index monitoring according to claim 8, characterized in that: The data classification module comprises: A module for obtaining center point coordinates is used to obtain the center point coordinates of each category of data; A calculation module, used to calculate the distance between the body index monitoring data and the center point coordinates, and determine the center point coordinates that are closest to the distance; The classification module is used to classify the body index monitoring data into the category corresponding to the coordinates of the nearest center point to obtain a classification result.

10. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the method for generating a health management plan based on physical indicator monitoring as described in any one of claims 1 to 7 when executing the executable instructions.

Images