Fat-reducing health risk analysis method and system based on multi-data fusion

Abstract

This application relates to the field of health data analysis and discloses a method and system for analyzing health risks associated with weight loss based on multi-data fusion. The method includes: acquiring physiological response data of the user collected during the execution cycle of each weight loss plan, including weight change, fatigue level, and heart rate indicators; determining a health risk score corresponding to each weight loss plan based on the physiological response data; ranking multiple weight loss plans based on the health risk score and determining the plan with the lowest health risk score as the optimal weight loss plan; obtaining the user's weight loss cycle adjustment instructions during the execution cycle of the weight loss plan; when the user extends the weight loss cycle, proportionally reducing the exercise intensity of the optimal weight loss plan to maintain stable health risks; when the user shortens the weight loss cycle, proportionally increasing the calorie deficit to maintain weight loss efficiency. This application can accurately and effectively adjust weight loss plans.

Description

Technical Field

[0001] This application relates to the field of health data analysis technology, and more specifically, to a method and system for analyzing health risks related to weight loss based on multi-data fusion. Background Technology

[0002] Currently, weight loss plans are primarily based on user data such as weight, BMI, dietary records, and exercise intensity. This approach is widely used in health management apps and smart fitness devices. Data is typically acquired through user input or automatic device collection. Weight data is usually collected periodically, BMI is calculated from weight and height, dietary records include daily food types and intake, and exercise intensity is assessed based on duration and type. Subsequently, a pre-set health database and basic algorithms can be used to match users with weight loss plans that include daily calorie intake standards, recommended exercises, and phased weight loss goals to meet their specific needs.

[0003] Methods that determine weight loss plans based on user data such as weight, BMI, dietary records, and exercise intensity are difficult to adjust accurately and effectively in practice. These plans are often based on static data and fail to adequately consider dynamic changes in the user's physical condition. For example, fluctuations in metabolic rate due to lifestyle changes, omissions or errors in dietary records, and the inability to maintain the preset exercise intensity due to fatigue are all not included in the real-time adjustment logic. Furthermore, existing weight loss plan adjustment mechanisms lack specific consideration for individual differences, making it difficult to adapt plans to the personalized needs of different users. This often results in delayed adjustments, unreasonable adjustments, and consequently, affects weight loss effectiveness and may even have potential health consequences due to a mismatch between the plan and the user's physical condition. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for analyzing the health risks of weight loss based on multi-data fusion, which solves the technical problem of difficulty in accurately and effectively adjusting weight loss plans, and achieves the technical effect of being able to accurately and effectively adjust weight loss plans.

[0005] This application provides a method for analyzing health risks associated with weight loss based on multi-data fusion. The method includes: acquiring a user's historical health data and the user's set weight loss goals; the historical health data includes weight, BMI, dietary records, and exercise intensity; determining multiple weight loss plans based on the historical health data and the user's set weight loss goals, each corresponding to a different calorie deficit and exercise plan; acquiring physiological response data collected during the execution cycle of each weight loss plan, including weight change, fatigue level, and heart rate indicators; determining a health risk score corresponding to each weight loss plan based on the physiological response data; ranking the multiple weight loss plans based on the health risk score and determining the weight loss plan with the lowest health risk score as the optimal weight loss plan; wherein the execution cycle of the weight loss plan is shorter than the detection cycle corresponding to the historical health data; acquiring the user's weight loss cycle adjustment instructions during the execution cycle of the weight loss plan; when the user extends the weight loss cycle, proportionally reducing the exercise intensity of the optimal weight loss plan to maintain stable health risks; when the user shortens the weight loss cycle, proportionally increasing the calorie deficit to maintain weight loss efficiency.

[0006] In one possible implementation, when a user extends their fat loss cycle, the exercise intensity of the optimal fat loss plan is proportionally reduced to maintain stable health risks; when a user shortens their fat loss cycle, the calorie deficit is proportionally increased to maintain fat loss efficiency. This includes: when a user extends their fat loss cycle to the first cycle, obtaining the current remaining total fat loss time, determining the ratio of the remaining total fat loss time to the first cycle as an adjustment ratio value; determining the product of the adjustment ratio value and the exercise intensity as the adjusted exercise intensity, and determining the product of the adjustment ratio value and the calorie deficit as the adjusted calorie deficit. Calorie deficit; where the first cycle is longer than the remaining total fat loss time, the adjusted exercise intensity value is not lower than the baseline exercise intensity; when the user shortens the fat loss cycle to the second cycle, the current remaining total fat loss time is obtained, and the ratio of the second cycle to the remaining total fat loss time is determined as the adjustment ratio value; the product of the adjustment ratio value and the exercise intensity is determined as the adjusted exercise intensity, and the product of the adjustment ratio value and the calorie deficit is determined as the adjusted calorie deficit; where the second cycle is shorter than the remaining total fat loss time, the increased calorie deficit does not exceed the calorie deficit limit.

[0007] In another possible implementation, the method further includes: when the duration of the first cycle is greater than or equal to the detection cycle corresponding to the historical health data, prompting the user to reduce the duration of the first cycle to a preset ratio value of the detection cycle corresponding to the historical health data; wherein the preset ratio value is 1 / 5 to 1 / 2.

[0008] In another possible implementation, the method further includes: when the user extends the fat loss cycle to the first cycle, obtaining the remaining total exercise intensity of the current fat loss plan, determining the ratio of the remaining total exercise intensity to the preset total exercise intensity as an adjustment ratio value; multiplying the exercise intensity by the adjustment ratio value to adjust the exercise intensity, and multiplying the calorie deficit by the adjustment ratio value to adjust the calorie deficit; wherein the remaining total exercise intensity is less than the preset total exercise intensity, and the adjusted exercise intensity value is not lower than the baseline exercise intensity; when the user shortens the fat loss cycle to the second cycle, obtaining the remaining total calorie deficit of the current fat loss plan, determining the ratio of the preset total calorie deficit to the remaining total calorie deficit as an adjustment ratio value; multiplying the exercise intensity by the adjustment ratio value to adjust the exercise intensity, and multiplying the calorie deficit by the adjustment ratio value to adjust the calorie deficit; wherein the preset total calorie deficit is less than the remaining total calorie deficit, and the adjusted calorie deficit does not exceed the calorie deficit limit.

[0009] In another possible implementation, the method further includes: acquiring the user's real-time health data, and determining a weight loss health risk coefficient based on the real-time health data; wherein the real-time health data includes weight change rate, body fat percentage, metabolic indicators, and exercise data, and the weight loss health risk coefficient is determined by weight change trend, body fat fluctuation rate, and metabolic abnormality index; determining a dynamic risk threshold based on the user's historical health data and weight loss goals; generating a weight loss risk warning signal when the weight loss health risk coefficient is greater than or equal to the dynamic risk threshold, and determining the difference between the real-time health data and the baseline health data; determining the risk level through the difference between the real-time health data and the baseline health data, and obtaining a weight loss intervention plan corresponding to the risk level.

[0010] In another possible implementation, the method further includes: when the duration for which the weight loss health risk coefficient is greater than or equal to the dynamic risk threshold reaches a preset duration, determining the ratio of the weight loss health risk coefficient to the dynamic risk threshold as an intervention adjustment ratio; multiplying the adjustment period of the intervention plan by the intervention adjustment ratio to adjust the adjustment period of the intervention plan; when the duration for which the weight loss health risk coefficient is less than the dynamic risk threshold reaches a preset duration, determining the ratio of the weight loss health risk coefficient to the dynamic risk threshold as an intervention adjustment ratio; multiplying the adjustment period of the intervention plan by the intervention adjustment ratio to adjust the adjustment period of the intervention plan.

[0011] In another possible implementation, the method further includes: determining multiple intervention strategies based on physiological response data and health risk scores; sending the intervention strategies to a user terminal, where the user executes the multiple intervention strategies sequentially; obtaining real-time feedback data on the user's sequential execution of the multiple intervention strategies; wherein each intervention strategy corresponds to a specific exercise intensity, dietary adjustment plan, and rest recommendations, and the real-time feedback data includes exercise completion rate and changes in the user's physiological indicators; the execution cycle of the intervention strategy is shorter than the execution cycle of the fat loss plan; when the real-time feedback data identifies a change in the user's state that leads to an increase in health risk, the priority of the intervention strategy corresponding to the real-time feedback data is reduced; when the real-time feedback data identifies a change in the user's state that leads to a decrease in health risk, the priority of the intervention strategy corresponding to the real-time feedback data is increased.

[0012] In another possible implementation, the method further includes: establishing a personalized intervention path optimization model based on physiological response data, health risk scores, fat loss goals, and constraints; wherein the objective function of the personalized intervention path optimization model is to maximize health benefits, which are determined by weighted calculation of fat loss effect and user satisfaction, and the constraints include user compliance limits and physiological indicator safety limits; through the personalized intervention path optimization model, the combination of intervention actions with the highest health benefits is selected first according to a greedy strategy to obtain the initial intervention path; the initial intervention path is optimized and solved by an improved genetic algorithm to obtain the personalized fat loss intervention path; wherein the improved genetic algorithm includes selection, crossover, and mutation operations, the initial intervention path is generated by a greedy strategy to accelerate convergence, and the personalized fat loss intervention path includes a daily exercise plan, dietary recommendations, and fat loss progress monitoring points.

[0013] In another possible implementation, the method further includes: when the duration during which the weight loss health risk coefficient is less than the dynamic risk threshold reaches a preset first duration, the length of the initial intervention path corresponding to the preset first duration is reduced according to a preset path adjustment ratio to adjust the length of the initial intervention path; wherein, different preset first durations correspond to different initial intervention path lengths.

[0014] This application also provides a weight loss health risk analysis system based on multi-data fusion, including a unit for implementing the above-mentioned weight loss health risk analysis method based on multi-data fusion.

[0015] The beneficial effects of the embodiments in this application compared with the prior art are: This application provides a method for analyzing health risks associated with weight loss based on multi-data fusion. The method includes: determining multiple weight loss plans, each corresponding to a different calorie deficit and exercise plan; acquiring physiological response data of the user collected during the execution cycle of each weight loss plan, including weight change, fatigue level, and heart rate indicators; determining a health risk score for each weight loss plan based on the physiological response data; ranking the multiple weight loss plans based on the health risk score and determining the weight loss plan with the lowest health risk score as the optimal weight loss plan; acquiring the user's weight loss cycle adjustment instructions during the execution cycle of the weight loss plan; when the user extends the weight loss cycle, proportionally reducing the exercise intensity of the optimal weight loss plan to maintain stable health risks; when the user shortens the weight loss cycle, proportionally increasing the calorie deficit to maintain weight loss efficiency. The method in this application embodiment can obtain the user's fat loss cycle adjustment instructions during the fat loss program execution cycle. When the user extends the cycle, the optimal planned exercise intensity is reduced proportionally to maintain a balance between health risks and the cycle is shortened proportionally to increase the calorie deficit to ensure fat loss efficiency. This dynamic adjustment mechanism can flexibly adapt to changes in user needs. When the user adjusts the cycle, it can maintain the bottom line of health without affecting the fat loss effect, thus achieving a dual balance between health protection and fat loss efficiency. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating the first weight loss health risk analysis method based on multi-data fusion provided in this application embodiment; Figure 2 A schematic diagram of the workflow of the first weight loss health risk analysis method based on multi-data fusion provided in the embodiments of this application; Figure 3 A flowchart illustrating the second method for analyzing health risks related to weight loss based on multi-data fusion, provided in this application embodiment; Figure 4 A schematic diagram of the workflow for the second weight loss health risk analysis method based on multi-data fusion provided in this application embodiment; Figure 5 A flowchart illustrating the third method for analyzing health risks related to weight loss based on multi-data fusion, provided in this application embodiment; Figure 6 A schematic diagram of the workflow of the third weight loss health risk analysis method based on multi-data fusion provided in the embodiments of this application; Figure 7 A flowchart illustrating the fourth method for analyzing health risks related to weight loss based on multi-data fusion, provided in this application embodiment; Figure 8 This is a schematic diagram of the logical structure of a weight loss health risk analysis system based on multi-data fusion, provided in an embodiment of this application. Detailed Implementation

[0018] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0019] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0020] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0021] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0022] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0023] Existing methods for determining weight loss plans based on data such as a user's weight, BMI, diet records, and exercise intensity are insufficient for accurately and effectively adjusting weight loss plans.

[0024] Based on the above reasons, this application provides a method for analyzing health risks related to weight loss based on multi-data fusion. The method includes: acquiring the user's historical health data and the user's set weight loss goals, whereby the historical health data includes weight, BMI, dietary records, and exercise intensity; determining multiple weight loss plans based on the historical health data and the user's set weight loss goals, each corresponding to a different calorie deficit and exercise plan; acquiring the user's physiological response data collected during the execution cycle of each weight loss plan, whereby the physiological response data includes weight change, fatigue level, and heart rate indicators; determining a health risk score corresponding to each weight loss plan based on the physiological response data; ranking the multiple weight loss plans based on the health risk scores and determining the weight loss plan with the lowest health risk score as the optimal weight loss plan; acquiring the user's weight loss cycle adjustment instructions during the execution cycle of the weight loss plan; when the user extends the weight loss cycle, proportionally reducing the exercise intensity of the optimal weight loss plan to maintain stable health risks; and when the user shortens the weight loss cycle, proportionally increasing the calorie deficit to maintain weight loss efficiency. The method in this application embodiment can obtain the user's fat loss cycle adjustment instructions during the fat loss program execution cycle. When the user extends the cycle, the optimal planned exercise intensity is reduced proportionally to maintain a balance between health risks and the cycle is shortened proportionally to increase the calorie deficit to ensure fat loss efficiency. This dynamic adjustment mechanism can flexibly adapt to changes in user needs. When the user adjusts the cycle, it can maintain the bottom line of health without affecting the fat loss effect, thus achieving a dual balance between health protection and fat loss efficiency.

[0025] In some scenarios, the weight loss health risk analysis method based on multi-data fusion of this application embodiment can be applied to the planning of weight loss plans and can be applied to scenarios such as fitness management apps used for weight loss planning, thereby improving the effect of weight loss and fitness.

[0026] The following specific examples illustrate a weight loss health risk analysis method based on multi-data fusion provided in this application.

[0027] Figure 1 A flowchart illustrating the first method for analyzing health risks related to weight loss based on multi-data fusion, as provided in this application embodiment, is shown below. Figure 1 As shown in the embodiment of this application, a weight loss health risk analysis method based on multi-data fusion is provided, including S110 to S130. S110 to S130 will be described in detail below.

[0028] S110. Obtain the user's historical health data and the user's set weight loss goals. Historical health data includes weight, BMI, diet records, and exercise intensity. Based on the historical health data and the user's set weight loss goals, determine multiple weight loss plans, each with a different calorie deficit and exercise plan.

[0029] Figure 2 A schematic diagram of the workflow of the first weight loss health risk analysis method based on multi-data fusion provided in the embodiments of this application is shown below. Figure 2 As shown in this implementation, when conducting a weight loss health risk analysis, the user's historical health data and set weight loss goals can be obtained first. The historical health data includes weight, BMI, diet records, and exercise intensity. This data can comprehensively reflect the user's basic physical condition and weight loss needs, providing a basis for generating a subsequent weight loss plan.

[0030] In this implementation, multiple weight loss plans can be determined by combining the user's historical health data and weight loss goals. Each weight loss plan corresponds to a different calorie deficit and exercise plan, which can cover different weight loss paths and facilitate subsequent assessment of the health risks of each plan.

[0031] It should be noted that BMI is the Body Mass Index, which is calculated by dividing weight (in kilograms) by the square of height (in meters). It is used to measure a person's fatness or thinness and health status. Adults' BMI is usually divided into categories such as underweight, normal weight, overweight, and obese. Different categories correspond to different health risk benchmarks and are one of the important indicators for assessing a user's basic health status.

[0032] It should be noted that, for example, if a user weighs 70 kg and is 1.75 m tall, their BMI is 70 ÷ (1.75 × 1.75) = 22.86, which is within the normal range; if the user weighs 80 kg and is 1.75 m tall, their BMI is 80 ÷ (1.75 × 1.75) = 26.12, which is within the overweight range. These values ​​can directly reflect the user's weight status.

[0033] It should be noted that the diet record can include the types, quantities, and calories of food consumed by the user each day. For example, breakfast may include an egg, a glass of milk, and a slice of whole wheat bread; lunch may include 150 grams of rice, 100 grams of chicken breast, and 200 grams of broccoli; and dinner may include 100 grams of brown rice, 80 grams of fish, and 150 grams of spinach. Recording these details can help understand the user's calorie intake.

[0034] It should be noted that exercise intensity can be the metabolic equivalent or heart rate percentage during exercise. For example, the metabolic equivalent of brisk walking is about 3-5 METs, jogging is about 6-8 METs, or maintaining a heart rate of 60%-70% of the maximum heart rate during exercise is considered moderate intensity exercise. These indicators can quantify the user's exercise load.

[0035] It's important to note that a calorie deficit is the difference between the calories you burn and the calories you consume each day. For example, if a user has a basal metabolic rate of 1500 kcal and burns 500 kcal through daily activities, for a total of 2000 kcal, and consumes 1800 kcal per day, the calorie deficit will be 200 kcal. This difference determines the speed of fat loss.

[0036] For example, exercise plans can be tailored to different users. For example, for sedentary users, the exercise plan might be 3 times a week, 30 minutes of brisk walking each time; for users with an exercise foundation, it might be 4 times a week, 45 minutes of strength training plus 20 minutes of aerobic exercise each time. Different exercise plans, combined with different calorie deficits, form different fat loss programs.

[0037] S120. Obtain physiological response data from users collected during the execution cycle of each weight loss plan. This data includes weight change, fatigue level, and heart rate. Based on the physiological response data, determine the health risk score corresponding to each weight loss plan. Rank multiple weight loss plans based on their health risk scores, and determine the plan with the lowest health risk score as the optimal weight loss plan. The execution cycle of each weight loss plan should be shorter than the monitoring cycle corresponding to the historical health data.

[0038] In this implementation, physiological response data of the user can be collected during the execution cycle of each weight loss program. The physiological response data includes weight change, fatigue level and heart rate indicators. These data can directly reflect the user's physical response to the weight loss program and are the key basis for assessing health risks.

[0039] It should be noted that the execution cycle of a weight loss program is the length of time for testing each program, such as 2 or 3 weeks. This time should be sufficient to collect effective physiological response data, but not too long to affect the efficiency of analysis. For example, if the execution cycle of a weight loss program is 2 weeks, the user follows the program within these 2 weeks, and data is collected to assess the risks.

[0040] For example, if a weight loss program is implemented for 3 weeks, after the user has implemented it for 3 weeks, data on weight change, fatigue level and heart rate are collected. This data can comprehensively reflect the body's response to the weight loss program and provide sufficient basis for determining health risk scores.

[0041] In this implementation, the health risk score corresponding to each weight loss plan can be determined based on the collected physiological response data. The lower the score, the lower the health risk of the plan, providing a quantitative standard for subsequent selection of the optimal plan.

[0042] It should be noted that a health risk score can be determined using an experience value table. The experience value table contains risk scores corresponding to different physiological response data. For example, a weight loss of more than 1.5 kg per week adds 5 points, fatigue level of more than 7 points adds 3 points, and resting heart rate of more than 90 beats / minute adds 4 points. These scores are then added together to obtain the total score.

[0043] For example, one weight loss program results in a weight loss of 1.2 kg per week (0 points), a fatigue level of 6 (0 points), a resting heart rate of 85 beats / minute (0 points), and a total score of 0 points; another program results in a weight loss of 2 kg per week (5 points), a fatigue level of 8 (3 points), a resting heart rate of 95 beats / minute (4 points), and a total score of 12 points. The former has a lower health risk.

[0044] In this implementation, multiple weight loss plans can be ranked based on health risk scores, and the plan with the lowest health risk score can be selected as the optimal weight loss plan. This ensures that the selected plan meets the weight loss goal while minimizing health risks.

[0045] It should be noted that weight change refers to the fluctuations in a user's weight during the weight loss program. For example, if a user's weight drops from 70 kg to 69 kg after one week of following a program, and then drops to 68.5 kg in the second week, it reflects the progress of weight loss. Fatigue level is the user's self-assessment of their fatigue. For example, using a 1-10 scale, a score of 7 or higher indicates a high level of fatigue. Heart rate indicators include resting heart rate and exercise heart rate. For example, a resting heart rate exceeding 90 beats per minute may indicate a high level of physical strain.

[0046] For example, if a user loses 1 kg per week, has a fatigue score of 5, and a resting heart rate of 75 beats per minute after following a weight loss program, these data indicate that the body is adapting well. However, if the user loses 2 kg per week, has a fatigue score of 8, and a resting heart rate of 90 beats per minute, it may indicate that the program is too strenuous and poses a higher health risk.

[0047] It should be noted that the detection period corresponding to historical health data is the time range for collecting past health data, such as 3 months or 6 months. This time can reflect the user's long-term health status. For example, collecting the user's weight, BMI, diet records and exercise intensity over the past 6 months can provide a comprehensive understanding of their basic physical condition.

[0048] For example, the user's historical health data is monitored over a period of 6 months. The weight fluctuations, dietary patterns, and exercise habits within these 6 months can help to develop a more accurate weight loss plan and avoid the plan becoming unsuitable due to short-term data fluctuations.

[0049] S130. During the execution cycle of the weight loss plan, obtain the user's instructions for adjusting the weight loss cycle. When the user extends the weight loss cycle, proportionally reduce the exercise intensity of the optimal weight loss plan to maintain stable health risks. When the user shortens the weight loss cycle, proportionally increase the calorie deficit to maintain weight loss efficiency.

[0050] In this implementation, the user's weight loss cycle adjustment instructions can be obtained during the execution cycle of the weight loss plan. When the user extends the weight loss cycle, the exercise intensity of the optimal weight loss plan is reduced proportionally to maintain stable health risks; when the user shortens the weight loss cycle, the calorie deficit is increased proportionally to maintain weight loss efficiency, flexibly adapting to changes in the user's needs.

[0051] It should be noted that the weight loss cycle adjustment command is a request issued by the user to change the cycle during the execution of the plan. For example, if a user originally planned to complete the weight loss goal in 8 weeks, but felt physically exhausted after 2 weeks, they would issue a command to extend the cycle to 10 weeks; or if a user wants to shorten the 12-week cycle to 10 weeks, they would issue a command to shorten the cycle.

[0052] For example, if a user's original fat loss cycle is 8 weeks, and after 3 weeks they issue an instruction to extend it to 10 weeks, the intensity of the optimal exercise plan can be reduced from 4 times a week to 3 times a week to maintain stable health risks. If the user shortens the cycle to 6 weeks, the calorie deficit can be increased from 200 calories per day to 300 calories per day to maintain fat loss efficiency.

[0053] This approach acquires historical health data such as a user's weight, BMI, dietary records, and exercise intensity, along with their set weight loss goals. Based on this, multiple weight loss programs are determined, each corresponding to different calorie deficits and exercise plans. Furthermore, physiological response data such as weight changes, fatigue levels, and heart rate are collected during the execution period of each program to determine corresponding health risk scores. By integrating these two types of core data to establish a correlation, the system can accurately match individual user conditions, effectively improving the accuracy of health risk assessment and providing reliable data support for subsequent weight loss program selection.

[0054] This implementation method uses collected physiological response data to derive health risk scores for each weight loss plan. Multiple weight loss plans are then ranked according to their scores, and the plan with the lowest score is selected as the optimal weight loss plan. Furthermore, the execution cycle of the weight loss plan is shorter than the historical health data detection cycle. This risk-score-based screening mechanism can quickly identify low-risk plans suitable for users, significantly reducing the probability of health problems during the weight loss process and improving the safety and suitability of the weight loss plan.

[0055] This implementation method obtains the user's weight loss cycle adjustment instructions during the weight loss plan execution cycle. When the user extends the cycle, the optimal planned exercise intensity is reduced proportionally to maintain a balance between health risks and the cycle is shortened proportionally to increase the calorie deficit to ensure weight loss efficiency. This dynamic adjustment mechanism can flexibly adapt to changes in user needs. When the user adjusts the cycle, it can maintain the bottom line of health without affecting the weight loss effect, thus achieving a dual balance between health protection and weight loss efficiency.

[0056] In some implementations, in S130 above, when a user extends the fat loss cycle, the exercise intensity of the optimal fat loss plan is reduced proportionally to maintain stable health risks. When a user shortens the fat loss cycle, the calorie deficit is increased proportionally to maintain fat loss efficiency, including: when the user extends the fat loss cycle to the first cycle, obtaining the current remaining total fat loss time, determining the ratio of the remaining total fat loss time to the first cycle as an adjustment ratio value, determining the product of the adjustment ratio value and the exercise intensity as the adjusted exercise intensity, and determining the product of the adjustment ratio value and the calorie deficit as the adjusted calorie deficit. Wherein, the first cycle is greater than the remaining total fat loss time, and the adjusted exercise intensity value is not lower than the baseline exercise intensity.

[0057] In this implementation, when a user extends their weight loss cycle to the first cycle, the remaining total weight loss time is first obtained. The ratio of the remaining total weight loss time to the first cycle is then used as an adjustment ratio. This adjustment ratio is multiplied by the original exercise intensity of the optimal weight loss plan to obtain the adjusted exercise intensity. Simultaneously, the adjustment ratio is multiplied by the original calorie deficit to obtain the adjusted calorie deficit. The duration of the first cycle must be greater than the remaining total weight loss time, and the adjusted exercise intensity cannot be lower than the baseline exercise intensity.

[0058] It should be noted that users can obtain the extended weight loss cycle by actively inputting the extended cycle duration through the interactive interface of the weight loss management application, or by triggering the system to obtain it through voice commands, selecting preset cycle options, etc.

[0059] For example, if a user originally had 4 weeks left to lose weight and wanted to extend it to 6 weeks, they could enter "6 weeks" on the "Cycle Adjustment" page of the app to get and record the duration of this first cycle.

[0060] It should be noted that the process of obtaining extended weight loss cycles for users can also be optimized by incorporating historical operating habits. For example, the system can pre-recommend several commonly used extended cycle options based on the user's previous adjustment records, and the user can simply click to select one to complete the process.

[0061] For example, if a user has previously extended the cycle from 4 weeks to 5 weeks, options such as 5 weeks or 6 weeks can be recommended. The user can quickly complete the first cycle setting by clicking "6 weeks".

[0062] It should be noted that baseline exercise intensity is the minimum exercise intensity standard that a user can consistently maintain over a long period of time while maintaining good health and avoiding excessive fatigue or sports injuries. It is usually determined based on the user's historical exercise data, cardiopulmonary function test results, and physical endurance assessment.

[0063] For example, a user's historical exercise data shows that brisk walking for 30 minutes three times a week does not make him feel tired, and his heart rate remains at 50%-60% of his maximum heart rate. This intensity can be determined as the user's baseline exercise intensity.

[0064] It should be noted that the basic exercise intensity setting should ensure that the user's adjusted exercise plan will not be affected by the low intensity, thus avoiding the health risks caused by the high intensity.

[0065] For example, if a user's basic exercise intensity is 30 minutes of brisk walking 3 times a week, it is recommended that the adjusted exercise intensity after extending the cycle not be lower than this standard, in order to prevent insufficient exercise from causing a decrease in metabolic rate and affecting the fat loss progress.

[0066] In some implementations, in S130 above, when the user extends the fat loss cycle, the exercise intensity of the optimal fat loss plan is reduced proportionally to maintain stable health risks. When the user shortens the fat loss cycle, the calorie deficit is increased proportionally to maintain fat loss efficiency. This also includes: when the user shortens the fat loss cycle to the second cycle, obtaining the current remaining total fat loss time, determining the ratio of the second cycle to the remaining total fat loss time as an adjustment ratio value, determining the product of the adjustment ratio value and the exercise intensity as the adjusted exercise intensity, and determining the product of the adjustment ratio value and the calorie deficit as the adjusted calorie deficit. Wherein, the second cycle is less than the remaining total fat loss time, and the increased calorie deficit does not exceed the calorie deficit limit.

[0067] In this implementation, when a user shortens their fat loss cycle to the second cycle, the remaining total fat loss time can be obtained. The ratio of the second cycle to the remaining total fat loss time is determined as an adjustment ratio. Simultaneously, the adjusted exercise intensity is obtained by multiplying the adjustment ratio by the original exercise intensity, and then by multiplying it by the original calorie deficit to obtain the adjusted calorie deficit. The duration of the second cycle is less than the remaining total fat loss time, and the increased calorie deficit cannot exceed the calorie deficit limit.

[0068] It should be noted that the calorie deficit limit is the maximum calorie deficit a user can tolerate daily or weekly during the fat loss process. Exceeding this limit may lead to health problems such as muscle loss, metabolic disorders, and decreased immunity. It is usually calculated based on the user's basal metabolic rate, body fat percentage, age, and fat loss goals.

[0069] For example, if a user's basal metabolic rate is 1600 kcal and their body fat percentage is 25%, then their daily calorie deficit limit can be set at 500 kcal.

[0070] It should be noted that the calorie deficit limit should be set in a way that balances fat loss efficiency and physical health, ensuring that even if the fat loss period is shortened, the increased calorie deficit will still be within a safe range.

[0071] For example, if a user's original daily calorie deficit was 300 kcal, when shortening the cycle, the adjusted calorie deficit can be set to 500 kcal. This limit must not be exceeded to prevent problems such as dizziness and fatigue caused by excessive dieting.

[0072] This implementation allows users to adjust their exercise intensity based on the following: When extending a weight loss cycle to the first cycle, the remaining total weight loss time is obtained and its ratio to the first cycle is determined as an adjustment ratio. The exercise intensity is then reduced according to this ratio. When shortening to the second cycle, the remaining total weight loss time is obtained and its ratio to the second cycle is determined as an adjustment ratio. The exercise intensity is then increased according to this ratio. This ensures that the exercise intensity accurately adapts to the changes in the weight loss cycle, avoiding excessive exercise intensity that could damage the body or insufficient exercise intensity that could affect weight loss, thus stabilizing health risks during the weight loss process. It also allows the calorie deficit to change reasonably with the cycle adjustment, preventing excessive deficit from affecting physical condition when extending the cycle and ensuring sufficient deficit when shortening the cycle, effectively balancing physical tolerance and weight loss efficiency during the weight loss process.

[0073] With this implementation, when users adjust their weight loss cycle, the remaining total weight loss time is first obtained to determine the adjustment ratio. Then, the exercise intensity and calorie deficit are adjusted proportionally. Through coordinated regulation, the weight loss plan is closely adapted to the cycle adjustment, achieving a precise match between exercise intensity, calorie deficit, and weight loss cycle. This maintains stable health risks while ensuring weight loss efficiency, significantly improving the adaptability of the weight loss plan to the user's cycle adjustment.

[0074] In some implementations, the above method further includes: when the duration of the first cycle is greater than or equal to the detection cycle corresponding to the historical health data, prompting the user to reduce the duration of the first cycle to a preset proportion of the detection cycle corresponding to the historical health data. The preset proportion is between 1 / 5 and 1 / 2.

[0075] In this implementation, when a user extends the weight loss cycle to the first cycle, the duration of the first cycle can be compared with the detection cycle corresponding to the historical health data. If the duration of the first cycle is greater than or equal to the detection cycle corresponding to the historical health data, the user can be prompted to shorten the duration of the first cycle to control the shortened duration to not exceed the preset ratio value of the detection cycle corresponding to the historical health data, where the preset ratio value is between 1 / 5 and 1 / 2.

[0076] It should be noted that the detection period corresponding to historical health data is the time period during which the user previously collected historical health data. For example, if a user's historical health data consists of daily records of weight, BMI, diet, and exercise intensity over the past 3 months, then the detection period for historical health data is 3 months. Or, if the historical health data consists of exercise intensity and diet records twice a week over the past 40 days, then the detection period is 40 days. This detection period can reflect the user's previous physical condition and data change patterns, and is an important reference for adjusting the weight loss plan.

[0077] It should be noted that the preset ratio value is a value between 1 / 5 and 1 / 2 of the detection cycle corresponding to the historical health data. For example, if the detection cycle corresponding to the historical health data is 50 days, the preset ratio value can be 1 / 5, which is 10 days; it can also be 1 / 2, which is 25 days; or it can be 1 / 3, which is about 17 days. The preset ratio value can be set based on the validity of the historical data, so that the shortened first cycle can maintain the reference value of the original data, and will not be too short to reflect the changes in the body's response.

[0078] This approach avoids an excessively long first cycle, thus preventing it from losing the reference value of historical health data monitoring cycles. This ensures that subsequent adjustments to exercise intensity and calorie deficits are always supported by reliable data, effectively preventing health risks from spiraling out of control due to excessively long cycles and ensuring the continuous stability of health risks during weight loss. It also prevents the first cycle from becoming disconnected from historical health data monitoring cycles, maintaining the connection between weight loss plan adjustments and the original data reference system. This standardizes the cycle setting criteria when extending the weight loss cycle, preventing cycle setting confusion and ensuring the continuity and scientific nature of the weight loss plan adjustment process.

[0079] In some implementations, the above method further includes: when a user extends their weight loss cycle to the first cycle, obtaining the remaining total exercise intensity of the current weight loss plan, determining the ratio of the remaining total exercise intensity to the preset total exercise intensity, and using this ratio as an adjustment factor. The exercise intensity is adjusted by multiplying the exercise intensity by the adjustment factor, and the calorie deficit is also adjusted by multiplying the calorie deficit by the adjustment factor. Specifically, if the remaining total exercise intensity is less than the preset total exercise intensity, the adjusted exercise intensity value must not be lower than the baseline exercise intensity.

[0080] In this implementation, when a user extends the fat loss cycle to the first cycle, the remaining total exercise intensity of the current fat loss plan can be obtained, and the ratio of the remaining total exercise intensity to the preset total exercise intensity can be determined as the adjustment ratio value. Then, this adjustment ratio value can be multiplied by the exercise intensity to adjust the exercise intensity, and this value can also be multiplied by the calorie deficit to adjust the calorie deficit.

[0081] It should be noted that the remaining total exercise intensity is less than the preset total exercise intensity, and the adjusted exercise intensity cannot be lower than the baseline exercise intensity.

[0082] It should be noted that the preset total exercise intensity and preset total calorie deficit can be determined based on the user's physiological characteristics.

[0083] For example, the preset total exercise intensity can be determined by using an experience value table, combined with the user's age, gender, maximum heart rate, muscle mass, and other physiological characteristics. For example, for young users with high muscle mass, the preset total exercise intensity can be set slightly higher. The preset total calorie deficit can be determined by using an experience value table, based on the user's basal metabolic rate and body fat percentage. For example, for users with a high basal metabolic rate, the preset total calorie deficit can be appropriately increased.

[0084] It should be noted that the preset total exercise intensity and preset total calorie deficit can also be determined using the user's historical data.

[0085] For example, the user's exercise intensity record over the past 3 months can be referenced to take the average total exercise intensity per week as the preset total exercise intensity; the preset total calorie deficit can be referenced to the average total calorie deficit during the user's past successful fat loss period without health problems, so that the preset total calorie deficit is more in line with the user's exercise and metabolic habits.

[0086] In some implementations, the above method further includes: when a user shortens their weight loss cycle to the second cycle, obtaining the remaining total calorie deficit of the current weight loss plan, determining the ratio of the preset total calorie deficit to the remaining total calorie deficit as an adjustment ratio value. The exercise intensity is adjusted by multiplying the exercise intensity by the adjustment ratio value, and the calorie deficit is adjusted by multiplying the calorie deficit by the adjustment ratio value. Specifically, the preset total calorie deficit is less than the remaining total calorie deficit, and the adjusted calorie deficit does not exceed the calorie deficit limit.

[0087] In this implementation, when a user shortens the fat loss cycle to the second cycle, the remaining total calorie deficit of the current fat loss plan can be obtained, and the ratio of the preset total calorie deficit to the remaining total calorie deficit can be determined as the adjustment ratio value. The exercise intensity and calorie deficit can be adjusted separately by adjusting the adjustment ratio value.

[0088] It should be noted that the preset total calorie deficit is less than the remaining total calorie deficit, and the adjusted calorie deficit cannot exceed the calorie deficit limit.

[0089] This implementation first obtains the remaining total exercise intensity of the current weight loss plan when the user extends the weight loss cycle to the first cycle. The ratio of this remaining intensity to the preset total exercise intensity is calculated as an adjustment ratio. This ratio is then multiplied by the exercise intensity and calorie deficit to obtain the adjusted data. When the cycle is shortened to the second cycle, the remaining total calorie deficit is obtained. The ratio of this remaining deficit to the preset total calorie deficit is calculated as an adjustment ratio, and the adjusted data is calculated. This provides a precise quantitative basis for adjusting exercise intensity and calorie deficit, significantly reducing adjustment deviations and ensuring stable health risks and weight loss efficiency during weight loss. The adjusted weight loss plan is highly compatible with the user's current weight loss status, preventing slowdowns due to excessively low exercise intensity and health risks due to excessively high calorie deficits, thus improving the adaptability and safety of the weight loss plan.

[0090] Figure 3 A flowchart illustrating the second method for analyzing health risks related to weight loss based on multi-data fusion provided in this application embodiment is shown below. Figure 3 As shown, in some implementations, the above method also includes S210 to S220, which will be described in detail below.

[0091] S210. Obtain the user's real-time health data and determine the weight loss health risk coefficient based on the real-time health data. The real-time health data includes weight change rate, body fat percentage, metabolic indicators, and exercise volume data. The weight loss health risk coefficient is determined by weighting the weight change trend, body fat fluctuation rate, and metabolic abnormality index.

[0092] Figure 4 A schematic diagram of the workflow for the second method of weight loss health risk analysis based on multi-data fusion provided in this application embodiment is shown below. Figure 4 As shown, in this implementation, the user's real-time health data can be obtained, including weight change rate, body fat percentage, metabolic indicators and exercise data. Then, the weight change trend, body fat fluctuation rate and metabolic abnormality index can be weighted and calculated to determine the weight loss health risk coefficient.

[0093] It's important to note that a weight loss goal is a specific expectation set by the user. For example, a user might set a goal like "to lose 5 kg in 2 months" or "to reduce body fat percentage by 3% in 1 month." For instance, if a user's historical health data shows a stable monthly weight loss of 0.5 kg, then setting a weight loss goal of "losing 1 kg per month" will adjust the dynamic risk threshold based on historical data. The more aggressive the goal, the lower the threshold may be, in order to identify potential risks earlier.

[0094] S220. Determine a dynamic risk threshold based on the user's historical health data and weight loss goals. When the weight loss health risk coefficient is greater than or equal to the dynamic risk threshold, generate a weight loss risk warning signal and determine the difference between real-time health data and baseline health data. Determine the risk level based on the difference between real-time health data and baseline health data, and obtain the corresponding weight loss intervention plan.

[0095] In this implementation, a dynamic risk threshold can be determined based on the user's historical health data and the user's set weight loss goals. When the weight loss health risk coefficient is greater than or equal to the dynamic risk threshold, a weight loss risk warning signal can be generated, and the difference between real-time health data and baseline health data can be calculated.

[0096] After determining the difference between real-time health data and baseline health data, the risk level can be determined using this difference, and then a weight loss intervention plan corresponding to the risk level can be obtained.

[0097] It should be noted that the difference between real-time health data and baseline health data is a quantitative difference between the real-time status and the user's basic status.

[0098] For example, if a user's baseline weight change rate is 0.3% per week and their real-time weight change rate is 1.2% per week, the difference between the two is 0.9%.

[0099] For example, the baseline metabolic index can be the average resting metabolic rate in the user's historical health data. If the real-time resting metabolic rate is 100 kcal lower than the average, the difference is 100 kcal, which intuitively reflects the degree to which the real-time status deviates from the baseline.

[0100] It should be noted that the risk level is divided into different levels based on the difference between real-time and baseline health data.

[0101] For example, a difference of 0-5% from the baseline health data is considered low risk, 5%-15% is considered medium risk, and more than 15% from the baseline health data is considered high risk.

[0102] For example, if a user's real-time heart rate is 12 beats per minute higher than their baseline heart rate, the risk level corresponding to the difference is medium risk, and an intervention plan that adjusts the diet can be matched; if the difference exceeds 20 beats per minute, it is considered high risk, and it can be recommended to reduce the intensity of exercise and increase the rest time.

[0103] This approach first acquires real-time user health data, including weight change rate, body fat percentage, metabolic indicators, and exercise volume. A weighted calculation of weight change trends, body fat fluctuation rate, and metabolic abnormality index determines the weight loss health risk coefficient. Then, based on the user's historical health data, weight loss goals, and physiological characteristics, a dynamic risk threshold is determined. This ensures that risk assessment is aligned with both real-time status and individual circumstances, accurately capturing health risks during weight loss and avoiding misjudgments due to single data points, thus improving the accuracy of weight loss health risk assessment. Furthermore, it allows weight loss plans to dynamically adjust to the user's physical condition, breaking the limitations of fixed plans and ensuring the plan always adapts to changes in the user's body. This guarantees health and safety during weight loss while preventing rigid plans from affecting weight loss efficiency.

[0104] This method derives a weight loss health risk coefficient and compares it with a dynamic risk threshold. When the coefficient is greater than or equal to the threshold, a weight loss risk warning signal is generated. Then, the deviation between real-time health data and baseline health data is calculated to determine the risk level. Finally, a corresponding weight loss intervention plan is matched, ensuring that the intervention measures and risk levels are accurately matched. This avoids the problems of insufficient or excessive intervention, making the weight loss intervention plan more adaptable, effectively reducing the probability of health risks escalating during the weight loss process, and ensuring the safe progress of weight loss.

[0105] In some implementations, the above method further includes: when the duration for which the weight loss health risk coefficient is greater than or equal to the dynamic risk threshold reaches a preset duration, determining the ratio of the weight loss health risk coefficient to the dynamic risk threshold as an intervention adjustment ratio. The intervention adjustment period is then multiplied by this ratio to adjust the intervention plan's adjustment period.

[0106] In this implementation, the duration of the comparison between the weight loss health risk coefficient and the dynamic risk threshold can be monitored. When the duration for which the weight loss health risk coefficient is greater than or equal to the dynamic risk threshold reaches a preset duration, the ratio of the weight loss health risk coefficient to the dynamic risk threshold is calculated as the intervention adjustment ratio, and then this ratio is multiplied by the adjustment cycle of the intervention plan for adjustment.

[0107] For example, if the preset duration is 7 days, the risk coefficient is 1.2, the dynamic risk threshold is 1.0, and the intervention adjustment ratio is calculated to be 1.2, then when the original adjustment period is 10 days, the adjusted period will be 12 days.

[0108] In some implementations, the above method further includes: when the duration for which the weight loss health risk coefficient is less than the dynamic risk threshold reaches a preset duration, determining the ratio of the weight loss health risk coefficient to the dynamic risk threshold as an intervention adjustment ratio. This intervention adjustment ratio is then multiplied by the adjustment period of the intervention plan to adjust the adjustment period of the intervention plan.

[0109] In this implementation, when the duration for which the weight loss health risk coefficient is less than the dynamic risk threshold reaches a preset duration, the ratio of the risk coefficient to the dynamic risk threshold can be calculated as the intervention adjustment ratio, and this ratio can be multiplied by the adjustment cycle of the intervention plan to adjust it.

[0110] For example, if the preset duration is 7 days, the dynamic risk threshold is 1.0, the weight loss health risk coefficient is 0.8, the intervention adjustment ratio is 0.8, and the original adjustment cycle is 8 days, the adjustment cycle of the adjusted intervention plan is 6.4 days.

[0111] This implementation method sets corresponding intervention adjustment ratio calculation methods for different scenarios with varying health risk levels during weight loss. The ratio is then multiplied by the adjustment cycle of the intervention plan to achieve cycle adjustment, ensuring that the adjustment cycle of the intervention plan corresponds to the duration of risk. This avoids the rigidity of a fixed adjustment cycle and allows the adjustment cycle to adapt to different risk durations, enhancing the flexibility and targeting of weight loss intervention plans.

[0112] This approach first monitors the comparison between the weight loss health risk coefficient and the dynamic risk threshold for a set period of time. Once the preset duration is reached, the ratio is calculated to obtain the intervention adjustment ratio. The adjustment cycle of the intervention plan is then adjusted proportionally, rather than through sudden, temporary adjustments. This avoids significant changes in the adjustment cycle of the intervention plan, ensures a smooth transition in the weight loss intervention process, reduces the interference of sudden changes in the adjustment cycle on the user's weight loss rhythm, and maintains the continuity of the weight loss plan.

[0113] Figure 5 A flowchart illustrating the third method for analyzing weight loss health risks based on multi-data fusion provided in this application embodiment is shown below. Figure 5 As shown, in some implementations, the above method also includes S310 to S320, which will be described in detail below.

[0114] S310. Based on physiological response data and health risk scores, determine multiple intervention strategies. Send the intervention strategies to the user terminal, and the user executes the multiple intervention strategies sequentially. Obtain real-time feedback data of the user executing the multiple intervention strategies sequentially. Each intervention strategy corresponds to a specific exercise intensity, dietary adjustment plan, and rest recommendations. The real-time feedback data includes exercise completion rate and changes in the user's physiological indicators. The execution cycle of the intervention strategy is shorter than the execution cycle of the fat loss plan.

[0115] Figure 6 A schematic diagram of the workflow for the third method of weight loss health risk analysis based on multi-data fusion provided in the embodiments of this application is shown below. Figure 6As shown, in this implementation, multiple intervention strategies can be determined based on the user's physiological response data and health risk score. Each intervention strategy corresponds to a specific exercise intensity, dietary adjustment plan, and rest recommendation. These intervention strategies can be sent to the user terminal, and the user can execute multiple intervention strategies in sequence.

[0116] For example, when determining multiple intervention strategies based on a user's physiological response data and health risk score, multiple intervention strategies can be directly determined using an empirical value table based on the user's physiological response data and health risk score.

[0117] During the execution of multiple intervention strategies by the user, real-time feedback data can be obtained as the user executes multiple intervention strategies in sequence. The real-time feedback data includes exercise completion rate and changes in the user's physiological indicators. The execution cycle of the intervention strategy is shorter than the execution cycle of the fat loss plan.

[0118] It should be noted that intervention strategies can be determined by combining users' physiological response data (such as weight changes, fatigue levels, and heart rate indicators) and health risk scores.

[0119] For example, if a user's physiological response data shows high fatigue and their health risk score is close to the threshold, an intervention strategy of "reducing exercise intensity, increasing protein intake, and extending rest time" can be determined; if a user's weight change is as expected and their health risk score is low, an intervention strategy of "maintaining current exercise intensity, adjusting dietary fiber ratio, and maintaining the original rest rhythm" can be determined.

[0120] It should be noted that different combinations of physiological response data and health risk scores will correspond to different intervention strategies. For example, when a user's heart rate index is consistently high and their health risk score is rising, an intervention strategy of "reducing aerobic exercise, increasing resting recovery time, and adjusting dietary calorie distribution" can be generated to ensure that the intervention strategy is appropriate for the user's actual physical condition.

[0121] It should be noted that exercise intensity can refer to the duration, frequency, or difficulty of each exercise session. For example, brisk walking for 30 minutes three times a week is considered moderate intensity, while HIIT for 20 minutes four times a week is considered high intensity. Dietary adjustment plans can refer to adjusting the daily intake ratio of carbohydrates, protein, and fat. For example, reducing the proportion of carbohydrates from 50% to 45% while increasing the proportion of protein to 30%. Rest recommendations can refer to the required daily sleep time or the recovery rest time after exercise. For example, it is recommended to sleep 7-8 hours a day or rest for 15 minutes after exercise before the next activity.

[0122] It should be noted that the exercise intensity, dietary adjustment plan and rest recommendations in each intervention strategy are coordinated with each other. For example, an intervention strategy may require "moderate exercise intensity (3 times a week for 40 minutes of jogging), high protein diet (daily intake of 1.2g of protein per kg of body weight), and 30 minutes of stretching and rest after exercise", so as to adjust the user's fat loss status through the synergistic effect of the three.

[0123] It should be noted that the implementation period of an intervention strategy is shorter than that of a weight loss program. The implementation period of an intervention strategy can be a shorter time period, such as 3 or 5 days, while the implementation period of a weight loss program can be 2 or 4 weeks.

[0124] For example, if the weight loss plan is implemented over a period of 4 weeks, the intervention strategy can be implemented over a period of 3 days. The user implements a set of intervention strategies every 3 days, and then adjusts them based on feedback. Or, if the weight loss plan is implemented over a period of 2 weeks, the intervention strategy can be implemented over a period of 5 days, ensuring that the intervention strategy can be adjusted multiple times within the weight loss plan period.

[0125] It should be noted that the intervention strategy has a relatively short execution cycle. In order to obtain user feedback data in a timely manner, exercise completion rate and physiological indicator changes can be collected every 3 days. This allows for rapid response to changes in the user's status and adjustment of subsequent intervention strategies.

[0126] S320. When real-time feedback data indicates that a change in user status leads to an increased health risk, the priority of the intervention strategy corresponding to the real-time feedback data should be reduced. When real-time feedback data indicates that a change in user status leads to a decreased health risk, the priority of the intervention strategy corresponding to the real-time feedback data should be increased.

[0127] In this implementation, when real-time feedback data indicates that a change in user status leads to an increased health risk, the priority of the intervention strategy corresponding to the real-time feedback data can be reduced; conversely, when real-time feedback data indicates that a change in user status leads to a decreased health risk, the priority of the intervention strategy corresponding to the real-time feedback data can be increased.

[0128] It should be noted that the priority of intervention strategies refers to the order of execution or the degree of recommendation of intervention strategies. For example, intervention strategies with higher priority will be recommended to users for execution first, or will be ranked at the top of the user's intervention list.

[0129] For example, if an intervention strategy has a "high" priority, it will be placed at the top of the intervention list on the user's terminal, prompting the user to execute it first; if the priority is "medium", it will be placed in the middle; and if the priority is "low", it will be placed at the end.

[0130] It should be noted that the priority adjustment is based on real-time feedback data from users. For example, if after an intervention strategy is implemented, the user's physiological indicators show that their heart rate returns to normal and their fatigue level decreases, thus reducing health risks, then the priority of the intervention strategy will be increased from "medium" to "high". If, after implementation, the user's fatigue level increases and their heart rate remains high, thus increasing health risks, then the priority of the intervention strategy will be decreased from "high" to "medium".

[0131] This approach determines multiple intervention strategies, including specific exercise intensities, dietary adjustment plans, and rest recommendations, based on physiological response data and health risk scores. These strategies are then sent to the user's terminal for sequential execution. Simultaneously, real-time feedback data during the execution process is acquired, ensuring that the intervention strategies closely align with the user's physical condition during weight loss. This effectively adapts to individual user circumstances and guarantees that the user remains healthy throughout the weight loss process.

[0132] With this approach, the execution cycle of the weight loss plan is shorter than the detection cycle corresponding to historical health data, and the execution cycle of the intervention strategy is shorter than the execution cycle of the weight loss plan. This ensures that weight loss-related interventions are always accurately matched to the user's physical condition in different execution cycles, enabling the user to adjust their weight loss strategy in a timely manner to advance the weight loss process while ensuring their health.

[0133] This implementation method identifies the impact of user status changes on health risks based on real-time feedback data of user intervention strategies. If the user status change increases health risks, the priority of the corresponding intervention strategy is reduced; if it decreases health risks, the priority of the corresponding intervention strategy is increased. This method can adapt to fluctuations in user status in a timely manner, effectively avoid the problem of increased health risks during weight loss, and help improve the rationality and adaptability of the weight loss process.

[0134] Figure 7 A flowchart illustrating the fourth method for analyzing health risks related to weight loss based on multi-data fusion provided in this application is shown below. Figure 7 As shown, in some implementations, the above method also includes S410 to S420, which will be described in detail below.

[0135] S410. Based on physiological response data, health risk scores, fat loss goals, and constraints, establish a personalized intervention path optimization model. The objective function of this model is to maximize health benefits, which are determined by a weighted calculation of fat loss effectiveness and user satisfaction. Constraints include user compliance limits and physiological indicator safety limits.

[0136] In this implementation, a personalized intervention path optimization model can be built by combining physiological response data, health risk scores, fat loss goals and constraints. The goal of the personalized intervention path optimization model is to maximize health benefits, which can be obtained by weighted calculation of fat loss effect and user satisfaction.

[0137] Meanwhile, personalized intervention path optimization models can take into account user compliance limits, such as the upper limit of the exercise duration that users can maintain daily, as well as safety limits for physiological indicators, such as the safe range that heart rate should not exceed.

[0138] It should be noted that the construction of a personalized intervention path optimization model can begin by clearly defining the input parameters, such as weight changes and fatigue levels in physiological response data, health risk scores, the user's weight loss goals (e.g., losing 10 pounds in 3 months), and the constraints such as the user's adherence requirement of exercising for 30 minutes per day and the physiological safety limit of blood pressure not exceeding 130 / 85. The objective function can be determined to maximize health benefits. Then, the constraints can be transformed into mathematical expressions, such as exercise duration ≤ 30 minutes / day and heart rate ≤ 150 beats / minute. These elements are then integrated to form a complete model structure.

[0139] It's important to clarify that maximizing health benefits can be understood as improving fat loss while ensuring the user's health, and simultaneously increasing user satisfaction with the intervention program. For example, an intervention program that helps a user consistently lose 2 pounds per month (good fat loss effect) and that the user finds the exercise intensity and diet plan easy to stick to (high satisfaction) will have higher health benefits than another program that, while resulting in faster weight loss, is difficult for the user to maintain. Furthermore, if a user wants to lose fat while maintaining muscle mass, a program with high health benefits will reduce fat while preserving muscle, and the user will also be satisfied with the taste of the food and the enjoyment of the exercise.

[0140] It's important to note that when calculating health benefits by weighting weighted results based on weight loss effectiveness and user satisfaction, you can first assign weights to each, for example, weight loss effectiveness with a weight of 0.6 and user satisfaction with a weight of 0.4. Weight loss effectiveness is quantified by the ratio of actual weight loss to target weight loss. For example, if the target weight loss is 2 pounds in one month and the actual weight loss is 1.8 pounds, the weight loss effectiveness score is 0.9. User satisfaction is calculated using the average ratings for exercise and diet. For example, if a user rates exercise 4 out of 5 and diet 3.5, the average is 3.75. The health benefit would then be 0.9 × 0.6 and 3.75 × 0.4 = 2.04. As another example, another plan might have a weight loss effectiveness score of 0.8 and a user satisfaction score of 4, resulting in a health benefit of 0.8 × 0.6 and 4 × 0.4 = 2.08. This plan offers a higher health benefit.

[0141] S420. Using a personalized intervention path optimization model, an initial intervention path is obtained by prioritizing the combination of intervention actions with the highest health benefits according to a greedy strategy. An improved genetic algorithm is then used to optimize and solve the initial intervention path, resulting in a personalized fat loss intervention path. The improved genetic algorithm includes selection, crossover, and mutation operations. The initial intervention path is generated using a greedy strategy to accelerate convergence. The personalized fat loss intervention path includes a daily exercise plan, dietary recommendations, and fat loss progress monitoring points.

[0142] In this implementation, a greedy strategy can be used to select the initial intervention path, that is, to prioritize the combination of intervention actions that currently provide the highest health benefits. For example, when selecting the intervention actions for the first day, the combination of exercise plan A (health benefit 2.5) and dietary advice B (health benefit 2.2) is chosen because these two currently provide the highest benefits.

[0143] In this implementation, the initial path can be optimized by improving the genetic algorithm. The improved genetic algorithm includes selection, crossover and mutation operations. The initial population of the initial intervention path is generated using a greedy strategy, so that the quality of the initial population is higher and a good solution can be found faster. The personalized fat loss intervention path obtained after optimization can include specific daily exercise plans, dietary recommendations and fat loss progress monitoring points.

[0144] It's important to note that a greedy strategy involves choosing the best option at each step. For example, when selecting an intervention, it chooses the one with the highest current health benefit. For instance, when choosing an intervention for the next day, it might select a combination of exercise plan C (health benefit 2.3) and dietary recommendation D (health benefit 2.1).

[0145] It should be noted that the improved genetic algorithm is based on the traditional genetic algorithm. It uses a greedy strategy to generate the initial population, then selects and retains good individuals, combines the good parts of two individuals through crossover, and randomly mutates some parts to obtain a better path. For example, each individual in the initial population represents an intervention path selected by the greedy strategy. After several rounds of genetic operations, the resulting path has a higher health benefit than the initial path.

[0146] It should be noted that the daily exercise plan can be a specific arrangement of time periods and types of exercise, such as doing 20 minutes of HIIT at 8 am on Tuesday and taking a 40-minute walk at 6 pm; the dietary recommendations can be specific types and portions of food, such as eating oatmeal with eggs for breakfast and chicken breast salad for lunch; the weight loss progress monitoring points can be fixed time points or indicator tests, such as measuring weight and waist circumference every Friday evening, measuring body fat percentage every two weeks, and conducting a health risk assessment every month, so that users know what to do every day and can keep track of their weight loss progress in a timely manner.

[0147] Through this implementation, the personalized intervention path optimization model takes maximizing health benefits as the objective function. The health benefits are calculated by weighting the fat loss effect and user satisfaction. The constraints cover user compliance limits and physiological safety limits. The resulting path includes a daily exercise plan, dietary recommendations, and fat loss progress monitoring points. It can accurately adapt to the individual user's situation, meet the user compliance and physiological safety requirements, and fully satisfy the personalized fat loss intervention needs of different users.

[0148] This implementation method clearly guides users to perform weight loss actions, and sets up weight loss progress monitoring points to facilitate timely monitoring of weight loss status. This improves the standardization of users' weight loss intervention, ensures weight loss results and user satisfaction, and effectively enhances the controllability and reliability of the weight loss intervention process.

[0149] In some implementations, the above method further includes: when the duration for which the weight loss health risk coefficient is less than the dynamic risk threshold reaches a preset first duration, reducing the initial intervention path length corresponding to the preset first duration according to a preset path adjustment ratio, thereby adjusting the initial intervention path length. Different preset first durations correspond to different initial intervention path lengths.

[0150] In this implementation, the duration for which the weight loss health risk coefficient is less than the dynamic risk threshold can be monitored. When the duration reaches a preset first duration, the length of the initial intervention path corresponding to the preset first duration can be obtained, and then the length of the initial intervention path can be adjusted. Different preset first durations correspond to different initial intervention path lengths, and the two have a pre-set correspondence.

[0151] It should be noted that the preset first duration is a pre-set reference duration used to determine the duration of a user's low health risk state, such as 3 days, 5 days, or 7 days; the initial intervention path length is the length of the intervention path corresponding to different preset first durations, and the length of the intervention path corresponds to a different number of fat loss progress monitoring points.

[0152] For example, the adjustment ratio according to the preset path can be 0.5, 0.8 or 0.9.

[0153] For example, suppose the preset first duration is set to three levels: 3 days, 5 days, and 7 days, and the corresponding initial intervention path lengths are 7 weight loss progress monitoring points, 10 weight loss progress monitoring points, and 14 weight loss progress monitoring points, respectively.

[0154] For example, when a user's weight loss health risk coefficient is less than the dynamic risk threshold for 3 days, the initial intervention path length of 10 weight loss progress monitoring points for the corresponding 3 days can be obtained. The initial intervention path length corresponding to the preset first duration can be reduced by a preset path adjustment ratio of 0.5, so that the initial intervention path length is adjusted to 5 weight loss progress monitoring points, thereby adjusting the original initial intervention path length.

[0155] This implementation first monitors the duration for which the weight loss health risk coefficient is below a dynamic risk threshold. When this duration reaches a preset first duration, the length of the initial intervention path corresponding to this preset first duration is obtained. The length of the initial intervention path is then adjusted to ensure a precise match between the initial intervention path length and the user's sustained low health risk state. This avoids adaptation problems caused by a fixed path length and improves the fit between the initial intervention path and the user's current state. This makes the adjustment more scientific and ensures that the intervention path can adapt to user needs under different durations of low risk. Furthermore, by allowing the initial intervention path to change dynamically with the user's sustained low-risk state, it avoids the mismatch problems caused by a rigid initial intervention path length.

[0156] This application also provides a weight loss health risk analysis system based on multi-data fusion, including a unit for implementing the above-mentioned weight loss health risk analysis method based on multi-data fusion.

[0157] Figure 8 A schematic diagram of the logical structure of a weight loss health risk analysis system based on multi-data fusion provided in this application embodiment is shown below. Figure 8 As shown, the system 1 of this embodiment includes a processing unit 11, a storage unit 12, and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12, and the transceiver unit 13 cooperate with each other to implement the above-described method. The beneficial effects of the embodiments of this application have been described in the above-described method and will not be repeated here.

[0158] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0159] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0160] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0161] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0162] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0163] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0164] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0165] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for analyzing health risks associated with weight loss based on multi-data fusion, characterized in that, The method includes: Acquire the user's historical health data and the user's set weight loss goals. Historical health data includes weight, BMI, diet records, and exercise intensity. Based on the historical health data and the user's set weight loss goals, determine multiple weight loss plans, each with a different calorie deficit and exercise plan. The system collects physiological response data from users during the execution cycle of each weight loss plan. This data includes weight change, fatigue level, and heart rate. Based on the physiological response data, a health risk score is determined for each weight loss plan. Multiple weight loss plans are ranked based on their health risk scores, and the plan with the lowest health risk score is selected as the optimal weight loss plan. The execution cycle of each weight loss plan is shorter than the monitoring cycle corresponding to the historical health data. During the execution cycle of the weight loss program, obtain the user's instructions for adjusting the weight loss cycle; when the user extends the weight loss cycle, reduce the exercise intensity of the optimal weight loss plan proportionally to maintain stable health risks; when the user shortens the weight loss cycle, increase the calorie deficit proportionally to maintain weight loss efficiency. The method further includes: Based on physiological response data and health risk scores, multiple intervention strategies are determined; these strategies are sent to user terminals, and users execute them sequentially; real-time feedback data on the sequential execution of these intervention strategies is obtained; each intervention strategy corresponds to a specific exercise intensity, dietary adjustment plan, and rest recommendations, and the real-time feedback data includes exercise completion rate and changes in user physiological indicators; the execution cycle of the intervention strategy is shorter than the execution cycle of the fat loss plan. When real-time feedback data indicates that changes in user status lead to increased health risks, the priority of the intervention strategy corresponding to the real-time feedback data is reduced; when real-time feedback data indicates that changes in user status lead to decreased health risks, the priority of the intervention strategy corresponding to the real-time feedback data is increased. Based on physiological response data, health risk scores, fat loss goals, and constraints, a personalized intervention path optimization model is established. The objective function of the personalized intervention path optimization model is to maximize health benefits. The health benefits are determined by weighted calculation of fat loss effect and user satisfaction. The constraints include user compliance limits and physiological indicator safety limits. The personalized intervention path optimization model selects the combination of intervention actions with the highest health benefits based on a greedy strategy to obtain the initial intervention path. The personalized fat loss intervention path is obtained by optimizing the initial intervention path through an improved genetic algorithm. The improved genetic algorithm includes selection, crossover and mutation operations. The initial intervention path is generated through a greedy strategy to accelerate convergence. The personalized fat loss intervention path includes a daily exercise plan, dietary recommendations and fat loss progress monitoring points.

2. The method according to claim 1, characterized in that, When users extend their fat loss period, the exercise intensity of the optimal fat loss plan is reduced proportionally to maintain stable health risks; when users shorten their fat loss period, the calorie deficit is increased proportionally to maintain fat loss efficiency, including: When a user extends their fat loss cycle to the first cycle, the remaining total fat loss time is obtained, and the ratio of the remaining total fat loss time to the first cycle is determined as the adjustment ratio. The product of the adjustment ratio and the exercise intensity is determined as the adjusted exercise intensity, and the product of the adjustment ratio and the calorie deficit is determined as the adjusted calorie deficit. Among these, the first cycle is longer than the remaining total fat loss time, and the adjusted exercise intensity is not lower than the baseline exercise intensity. When a user shortens their fat loss cycle to the second cycle, the current remaining total fat loss time is obtained, and the ratio of the second cycle to the remaining total fat loss time is determined as the adjustment ratio value. The product of the adjustment ratio value and the exercise intensity is determined as the adjusted exercise intensity, and the product of the adjustment ratio value and the calorie deficit is determined as the adjusted calorie deficit. Among these, the second cycle is less than the remaining total fat loss time, and the increased calorie deficit does not exceed the calorie deficit limit.

3. The method according to claim 2, characterized in that, The method further includes: When the duration of the first cycle is greater than or equal to the detection cycle corresponding to the historical health data, the user is prompted to reduce the duration of the first cycle to a preset ratio of the detection cycle corresponding to the historical health data; wherein, the preset ratio is 1 / 5 to 1 / 2.

4. The method according to claim 1, characterized in that, The method further includes: When a user extends their weight loss cycle to the first cycle, the remaining total exercise intensity of the current weight loss plan is obtained, and the ratio of the remaining total exercise intensity to the preset total exercise intensity is determined as the adjustment ratio value. The exercise intensity is adjusted by multiplying the exercise intensity by the adjustment ratio value, and the calorie deficit is adjusted by multiplying the calorie deficit by the adjustment ratio value. Where the remaining total exercise intensity is less than the preset total exercise intensity, the adjusted exercise intensity value is not lower than the baseline exercise intensity. When a user shortens their weight loss cycle to the second cycle, the remaining total calorie deficit of the current weight loss plan is obtained. The ratio of the preset total calorie deficit to the remaining total calorie deficit is determined as an adjustment ratio value. The exercise intensity is adjusted by multiplying the exercise intensity by the adjustment ratio value, and the calorie deficit is adjusted by multiplying the calorie deficit by the adjustment ratio value. The preset total calorie deficit is less than the remaining total calorie deficit, and the adjusted calorie deficit does not exceed the calorie deficit limit.

5. The method according to claim 4, characterized in that, The method further includes: The system acquires users' real-time health data and determines the health risk coefficient for weight loss based on this data. The real-time health data includes weight change rate, body fat percentage, metabolic indicators, and exercise data. The weight change trend, body fat fluctuation rate, and metabolic abnormality index are weighted and calculated to determine the health risk coefficient for weight loss. A dynamic risk threshold is determined based on the user's historical health data and weight loss goals. When the weight loss health risk coefficient is greater than or equal to the dynamic risk threshold, a weight loss risk warning signal is generated, and the difference between real-time health data and baseline health data is determined. The risk level is determined by the difference between real-time health data and baseline health data, and a corresponding weight loss intervention plan is obtained.

6. The method according to claim 5, characterized in that, The method further includes: When the duration for which the health risk coefficient of fat loss is greater than or equal to the dynamic risk threshold reaches a preset duration, the ratio of the health risk coefficient of fat loss to the dynamic risk threshold is determined as the intervention adjustment ratio value; the adjustment period of the intervention plan is multiplied by the intervention adjustment ratio value to adjust the adjustment period of the intervention plan. When the duration for which the health risk coefficient of weight loss is less than the dynamic risk threshold reaches a preset duration, the ratio of the health risk coefficient of weight loss to the dynamic risk threshold is determined as the intervention adjustment ratio. The intervention adjustment period is then multiplied by the intervention adjustment ratio to adjust the intervention period.

7. The method according to claim 5, characterized in that, The method further includes: When the duration of the weight loss health risk coefficient being less than the dynamic risk threshold reaches the preset first duration, the length of the initial intervention path corresponding to the preset first duration is reduced according to the preset path adjustment ratio to adjust the length of the initial intervention path; different preset first durations correspond to different initial intervention path lengths.

8. A weight loss health risk analysis system based on multi-data fusion, characterized in that, Includes units for implementing the method of any one of claims 1 to 7.

Images