A big data-based user weight intelligent management method and device

Abstract

The present application relates to the technical field of intelligent weight management, and specifically discloses a user weight intelligent management method and device based on big data, which can accurately quantify the user intelligent weight management trend, provide personalized intervention, and realize systematic analysis process. The method comprises the following steps: S1, collecting user weight management data through an intelligent health management device; S2, screening target users and their weight management score parameters according to the user weight management data, generating a screening strategy according to the weight management score parameters of the target users, and screening and obtaining a weight management state coefficient of the target users under the current weight management score parameters according to the screening strategy; S3, analyzing the weight management state coefficient of the target users and predicting weight management project information of the target users; and S4, generating corresponding reminder information according to the weight management project information of the target users, and outputting the reminder information to the users.

Description

Technical Field

[0001] This invention relates to the field of intelligent weight management technology, specifically to a user weight intelligent management method and device based on big data. Background Technology

[0002] With social development and improved living standards, weight management has become one of the core needs of public health management. Effective weight management not only helps to shape a healthy body shape, but is also a key means to prevent obesity-related chronic diseases (such as hypertension and diabetes). Traditional weight management often relies on manual recording of weight data, subjective assessment of diet and exercise, or the use of basic wearable devices for simple step and heart rate monitoring. This approach has limitations such as fragmented data, single analysis dimensions, high dependence on user self-discipline, and difficulty in providing personalized and forward-looking guidance.

[0003] In recent years, the application of big data and artificial intelligence technologies in the health field has become increasingly in-depth, providing new solutions for weight management. Among existing technologies, some systems have attempted to provide general suggestions by collecting data such as users' exercise duration and diet logs, combined with simple algorithms. However, these methods usually fail to deeply quantify users' long-term psychological tendencies and behavioral compliance with specific weight management behaviors (such as fat loss and muscle gain), and also lack dynamic assessment of the impact of users' non-management time (i.e., the time period when no active weight management behavior is carried out) on health management. This results in a lack of targeted management strategies, which are usually judged only based on the user's recorded results after weight management, leading to limited prediction accuracy and making it difficult to achieve timely prediction and weight management based on users' weight management habits.

[0004] Therefore, how to utilize big data technology to deeply integrate user behavioral data and psychological tendency parameters to build a weight management analysis model that can accurately quantify user status, intelligently predict management trends, and provide personalized intervention has become a technical problem that needs to be solved. Summary of the Invention

[0005] The purpose of this invention is to provide a user weight intelligent management method and device based on big data, which solves the technical problems of low personalization, inaccurate trend prediction, and delayed intervention in existing weight management programs.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A big data-based intelligent user weight management method, the method includes:

[0008] S1. Collect user weight management data through intelligent health management devices. User weight management data includes weight management time and non-weight management time.

[0009] S2. Filter target users and their weight management rating parameters based on user weight management data.

[0010] A filtering strategy is generated based on the target user's weight management rating parameters; and the weight management status coefficient of the target user under the current weight management rating parameters is obtained according to the filtering strategy; the weight management rating parameters are obtained by comprehensively statistically analyzing the rating values ​​of the user's weight management items, and are used to quantify the target user's tendency to choose weight management items;

[0011] S3. Analyze the weight management status coefficient of the target user and predict the weight management program information of the target user. The weight management program information includes weight loss management program, muscle gain management program and routine management program.

[0012] S4. Generate corresponding reminder information based on the target user's weight management program information and output the reminder information to the user.

[0013] Preferably, the filtering strategy is generated in the following way:

[0014] Monitor the dynamic changes in users' weight management time and non-weight management time over a period of time to obtain users' weight management habits;

[0015] Based on the user's weight management habits, set the frequency of weight management and the frequency of weight management score statistics.

[0016] Preferably, the weight management scoring parameters are obtained in the following way:

[0017] Based on the user's historical weight management data, extract features from multiple weight management programs;

[0018] The system analyzes the characteristics of multiple weight management items using a pre-defined scoring model and outputs the user's score for each weight management item.

[0019] The weight management score is calculated by combining and weighting the scores of each weight management item to obtain the weight management score parameters.

[0020] Preferably, the screening method of the screening strategy is as follows:

[0021] By using a filtering strategy, we can obtain the execution time and effect data of the weight management project within the time period corresponding to each update of the user's weight management rating parameters;

[0022] Statistically analyze the execution time and effect data of weight management projects corresponding to all weight management rating parameters of this user, and match them to obtain the user's weight management habit elements and health goal elements;

[0023] Based on the weight management habit elements and health goal elements, a weight management compliance score is generated for this user.

[0024] Based on the user's weight management compliance score, identify the target user and the target user's weight management status, and obtain the target user's weight management status coefficient.

[0025] Preferably, the method for generating the user's weight management compliance score based on weight management habit elements and health goal elements is as follows:

[0026] Through formula Calculate and obtain the user's weight management compliance score. ;in, For weight management compliance scoring, an index function is used. For weight management habit parameters, For health target parameters; Standard parameters for weight management habits, Standard parameters for health goals; The first preset weighting coefficient, The second preset weighting coefficient, and , All are greater than 0;

[0027] Judgment when If the weight exceeds the preset standard threshold, the current user is confirmed as the target user, and their weight management effect is excellent.

[0028] Judgment when If the weight loss is below the preset threshold, the current user is identified as a non-target user or a potential target user, and their weight management effectiveness needs to be improved.

[0029] Preferably, the weight management status coefficient of the target user is calculated as follows:

[0030] Through formula Calculate and obtain the target user's weight management status coefficient ;in, The total number of updates to the target user's weight management rating parameters, and ∈ ; The third preset weighting coefficient, and >0; For the first The latest updated weight management scoring parameters; For the first The latest updated weight management scoring criteria parameters.

[0031] Preferably, the method for analyzing the weight management status coefficient of the target user is as follows:

[0032] Weight management status coefficient of target users Weight management status coefficient threshold range of preset standard target users Compare:

[0033] like ∈ If so, it is determined that the target user's weight management status is stable;

[0034] like < If so, it is determined that the target user's weight management status needs to be strengthened and the management strategy needs to be adjusted;

[0035] like > If so, it can be determined that the target user's weight management status is excellent, achieving the ideal management effect.

[0036] Preferably, the method for predicting the target user's weight management program information is as follows:

[0037] pass Calculate and obtain the target user's weight management trend value; where, This represents the total weight management time for the target users within the statistical period. This represents the total amount of time spent on non-weight management activities by the target users within the statistical period. The weighting factor is determined by the impact of management time. The weighting coefficients for non-management time influence are as follows: > >0; and ∈ .

[0038] Preferably, the target user's weight management status coefficient is used. Weight management status value of the target user Compare:

[0039] like > If so, it can be determined that the target user is involved in a weight loss or muscle gain program.

[0040] like ≤ If so, it can be determined that the target user has a tendency towards negative routine management projects.

[0041] A big data-based intelligent health management device for user weight, which executes the user weight management process based on a big data-based intelligent user weight management method, includes:

[0042] The data collection module is used to collect user weight management data through smart health management devices. User weight management data includes weight management time and non-weight management time.

[0043] The data processing module is used to filter target users and their weight management rating parameters based on user weight management data, generate a filtering strategy based on the target users' weight management rating parameters, and obtain the weight management status coefficient of the target users under the current weight management rating parameters based on the filtering strategy. Among them, the weight management rating parameters are obtained by comprehensively statistically analyzing the rating values ​​of user weight management items, and are used to quantify the target users' tendency to choose weight management items.

[0044] The analysis and prediction module is used to analyze the weight management status coefficient of the target user and predict the weight management program information of the target user, including weight loss management program, muscle gain management program and routine management program.

[0045] The information output module is used to generate corresponding reminder information based on the target user's weight management program information and output the reminder information to the user.

[0046] The beneficial effects of this invention are:

[0047] By constructing weight management scoring parameters, the inherent acceptance, preference, and long-term adherence potential of different weight management programs for users are quantified. Furthermore, by combining weight management adherence scores, a quantitative model integrating user psychological and behavioral data on this type of weight management is created. This ensures that more personalized user health management strategies are developed based on dynamic monitoring of recent user habits and through the generation of screening strategies and the setting of data collection and evaluation frequencies. It not only accurately assesses and classifies the user's current overall status through a weight management status coefficient but also calculates weight management trend values ​​using recent behavioral data. By comparing long-term historical status with recent dynamic changes, it intelligently predicts the types of weight management programs users are more likely to favor in the future, improving the user experience of intelligent health management devices and enhancing the application effectiveness of intelligent weight management methods.

[0048] Of course, any product implementing this invention does not necessarily need to achieve all the advantages described above at the same time. Attached Figure Description

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a flowchart illustrating the steps of a user weight intelligent management method based on big data according to the present invention.

[0051] Figure 2This is a schematic diagram of the structure of a user weight intelligent health management device based on big data according to the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] Please see Figure 1 As shown, a user weight intelligent management method based on big data specifically includes:

[0054] S1. Collect user weight management data through intelligent health management devices. User weight management data includes weight management time and non-weight management time.

[0055] S2. Filter target users and their weight management rating parameters based on user weight management data.

[0056] A filtering strategy is generated based on the target user's weight management rating parameters; and the weight management status coefficient of the target user under the current weight management rating parameters is obtained according to the filtering strategy; the weight management rating parameters are obtained by comprehensively statistically analyzing the rating values ​​of the user's weight management items, and are used to quantify the target user's tendency to choose weight management items;

[0057] S3. Analyze the weight management status coefficient of the target user and predict the weight management program information of the target user. The weight management program information includes weight loss management program, muscle gain management program and routine management program.

[0058] S4. Generate corresponding reminder information based on the target user's weight management program information and output the reminder information to the user.

[0059] In the above technical solution, firstly, the smart health management device in step S1 typically includes wearable smartphones, wearable smartwatches or bracelets, mobile smart health management devices, etc., which continuously collect raw data. After processing, this data is classified into two categories: weight management time (e.g., periods of continuous exercise for more than 30 minutes, and periods of careful recording of three meals) and non-weight management time (e.g., periods of prolonged sitting, periods of no food or exercise recording). These two types of time data together constitute the basic dataset for analyzing user behavior patterns.

[0060] Then, step S2 performs a preliminary analysis of all users' long-term data. Based on preset rules such as activity level and data integrity, it filters out target user groups that meet the conditions for in-depth analysis. For target users, the system extracts multiple weight management project features related to different weight management projects (such as high-intensity interval training - HIIT for fat loss, strength training for muscle gain, and balanced nutrition maintenance) from their historical data. These features include project execution frequency, average duration of each session, and heart rate target achievement rate. The system then uses a pre-trained scoring model (such as a model based on logistic regression or a neural network) to analyze these features and outputs the user's score for each project. By comprehensively weighting and statistically analyzing these scores (such as weighted average), the system obtains the user's unique weight management score parameter. The value of this parameter reflects the user's overall tendency to perform weight management projects.

[0061] By monitoring the dynamic changes in the target user's weight management time and non-weight management time in the past week, their recent weight management habits can be obtained. Based on these weight management habits, the frequency of data collection and the statistical frequency of recalculating scoring parameters are dynamically set to form the current screening strategy. By applying this screening strategy, more refined calculations can be performed.

[0062] Next, step S3 compares the calculated weight management status coefficient with a preset threshold range determined through a large amount of sample data. Based on the comparison results, a qualitative judgment is made on the user's current status to achieve data-driven management of the target user's weight health. This is achieved by predicting and determining weight management project information. The weight management project information includes weight loss management projects, muscle gain management projects, and routine management projects. Weight loss management projects are classified according to information on various weight loss exercises to determine that the main purpose of the exercise is weight loss. Muscle gain management projects are classified according to information on various muscle gain exercises to determine that the main purpose of the exercise is muscle gain. Routine management projects are classified according to the main purpose of relatively slow walking, stretching, and other routine joint movement patterns. This design only informs the user that the weight management project of the device is a data-driven prediction classification of whether there is a trend of weight loss or muscle gain. Therefore, the weight loss project predicted by the weight management device reflects the user's main weight management project, while muscle gain and routine exercise are behavioral information other than the main weight management project.

[0063] Finally, step S4 enables the timely transmission and output of weight management program information for the target user. Through a reminder template library corresponding to various program information, specific, encouraging, or guiding reminder messages are automatically generated. For example, for users who are inclined towards weight loss, a reminder such as "Your recent persistence has yielded significant results. It is recommended to continue maintaining the frequency of aerobic exercise. You can try adding one high-intensity interval training session this week!" may be generated. This reminder message is output to the user through the device's screen, speaker, or push notifications from the associated mobile app.

[0064] As one embodiment of the present invention, the filtering strategy is generated in the following way:

[0065] Monitor the dynamic changes in users' weight management time and non-weight management time over a period of time to obtain users' weight management habits;

[0066] Based on the user's weight management habits, set the frequency of weight management and the frequency of weight management score statistics.

[0067] In the above technical solution, an initial monitoring period is first selected, such as the last 7 days, 14 days, or 30 days. During this period, the system continuously and with high granularity records and analyzes sequence data of user weight management time (i.e., time spent on activities actively performed and recorded by users that are clearly related to weight management goals, such as structured exercise, diet tracking, and specialized training courses) and non-weight management time (i.e., time periods during which the above-mentioned active management behaviors were not monitored, excluding physiologically necessary time such as sleep). Through time-series analysis algorithms, key characteristics in user behavior patterns are identified, such as: time distribution patterns, behavioral fluctuations, behavioral continuity, and concentration of management time. These key characteristics are analyzed and summarized to obtain user weight management habits, which are then tagged with corresponding weight management habit labels, such as "regular," "intermittently concentrated," "loosely distributed," or "fluctuating and exploratory." Based on the identified habits, a dynamic generation and application of filtering strategies is performed, mainly reflected in the personalized setting of two key operation frequencies. The settings include: first, setting the weight management frequency to actively trigger data collection or send interactive prompts to users; second, setting the statistical frequency of weight management scoring parameters to quantify the time interval of weight management scoring parameters.

[0068] As one embodiment of the present invention, the weight management scoring parameters are obtained as follows:

[0069] Based on the user's historical weight management data, extract features from multiple weight management programs;

[0070] The system analyzes the characteristics of multiple weight management items using a pre-defined scoring model and outputs the user's score for each weight management item.

[0071] The weight management score is calculated by combining and weighting the scores of each weight management item to obtain the weight management score parameters.

[0072] The above technical solution first retrieves the target user's accumulated historical weight management data over a historical period, such as the past 30 or 90 days. From this time-series data, for several pre-set weight management projects (e.g., Project A "Aerobic Fat Loss", Project B "Strength Building", Project C "Diet Control", Project D "Routine Sleep Patterns"), it extracts multiple weight management project features that characterize user participation, completion quality, and adherence. These weight management project features include project execution frequency, average duration per session, intensity achievement rate, and completion score. Then, the extracted multi-dimensional feature vector is input into a pre-set scoring model. This model is a machine learning model (e.g., based on logistic regression, random forest, or lightweight) pre-trained using a large amount of labeled user behavior and effect data. This model (constructed using a hierarchical neural network for classification or regression) learns the contribution weights of different features to the effectiveness of different management programs and analyzes them accordingly. It outputs a score between 0 and 1 (or within a set score range) for each weight management program. The comprehensive weighted calculation of each weight management program's score reflects the potential effect tendency and behavioral fit based on the user's historical behavioral data when executing the corresponding program. Finally, the user's scores for each weight management program are comprehensively weighted. The weights are dynamically adjusted according to the user's long-term health goals (e.g., primary goal is weight loss). If the user's primary goal is weight loss, the scores for "aerobic fat loss" and "diet control" programs have a higher weighting in the weighted calculation. The result of the weighted calculation is the user's weight management score parameter.

[0073] Weighted calculations are typically performed using a linear weighted sum, i.e.:

[0074] The weight management score parameter is the sum of the product of the score value corresponding to a certain item type and the weight of that item over time. The resulting weight management score parameter is a comprehensive scalar that integrates the user's historical performance and tendencies across all key weight management dimensions. It provides accurate quantitative input for subsequent user segmentation, development of personalized screening strategies, and calculation of weight management status coefficients.

[0075] As one embodiment of the present invention, the screening method of the screening strategy is as follows:

[0076] By using a filtering strategy, we can obtain the execution time and effect data of the weight management project within the time period corresponding to each update of the user's weight management rating parameters;

[0077] Statistically analyze the execution time and effect data of weight management projects corresponding to all weight management rating parameters of this user, and match them to obtain the user's weight management habit elements and health goal elements;

[0078] Based on the weight management habit elements and health goal elements, a weight management compliance score is generated for this user.

[0079] Based on the user's weight management compliance score, identify the target user and the target user's weight management status, and obtain the target user's weight management status coefficient.

[0080] In the above technical solution, firstly, based on the currently effective screening strategy (which has set the frequency of data collection and evaluation intervals), at the update point of each weight management scoring parameter, the corresponding statistical period (e.g., the past week) is traced back; detailed execution time of weight management projects (e.g., the specific start and end times and total duration of the user's "strength training") and effect data (e.g., the user's average strength load, number of sets completed, or related resting heart rate changes, sleep quality data, etc.) are obtained within that statistical period; thus, each update of the weight management scoring parameter is associated with a specific and detailed behavioral history and a short-term effect snapshot.

[0081] The system compiles a dataset of behaviors and effects corresponding to all historical rating parameter updates for the user. By aggregating and analyzing this time-series data spanning multiple periods and performing pattern recognition (e.g., using cluster analysis and sequence pattern mining algorithms), the system can transcend the limitations of a single period and identify two core elements that profoundly reflect the user's intrinsic characteristics: weight management habits and health goals. Weight management habits are quantified by extracting parameters from aspects such as the regularity of behavior time, preference sequences in project selection, and typical recovery patterns after interruption. These parameters are used to determine whether the user's behavior is positive, negative, or average; a larger quantified parameter indicates a more positive behavior. Health goals are quantified by extracting parameters from aspects such as the long-term alignment between effect data and the user's set goals (e.g., weight loss speed, muscle gain), and the user's sensitivity to feedback from different projects (e.g., if weight decreases after performing a project, should the frequency of subsequent project executions be increased). These parameters are used to determine whether the user's health goals are positive, average, or negative; a larger quantified parameter indicates a more positive behavior.

[0082] The quantitative parameters of the weight management habit elements and health goal elements obtained from the above matching are input into a preset calculation model or formula (e.g., a function that combines the stability coefficient of weight management habits with the closeness to the achievement of health goals) to generate a comprehensive weight management compliance score. The level of this weight management compliance score further reflects the degree of consistency between the user's long-term behavior pattern and their stated or implicit health goals, and it is the core indicator for predicting whether they can adhere to an effective management plan in the future.

[0083] Finally, the target user information is determined by comparing the calculated weight management compliance score of the user with a threshold. If the score is higher than the threshold, the user is confirmed as a high-potential target user, and their weight management status is determined to be an object that can be optimized or stabilized. Based on the weight management compliance score, the weight management status coefficient of the target user is obtained through comprehensive calculation for advanced analysis and trend prediction.

[0084] As one embodiment of the present invention, the method for generating the user's weight management compliance score based on weight management habit elements and health goal elements is as follows:

[0085] Through formula Calculate and obtain the user's weight management compliance score. ;in, For weight management compliance scoring, an index function is used. For weight management habit parameters, For health target parameters; Standard parameters for weight management habits, Standard parameters for health goals; The first preset weighting coefficient, The second preset weighting coefficient, and , All are greater than 0;

[0086] Judgment when If the weight exceeds the preset standard threshold, the current user is confirmed as the target user, and their weight management effect is excellent.

[0087] Judgment when If the weight loss is below the preset threshold, the current user is identified as a non-target user or a potential target user, and their weight management effectiveness needs to be improved.

[0088] In the above technical solution, the method for obtaining the target user's weight management compliance score in this embodiment relies on the user's weight management habit elements (such as exercise regularity) and health goal elements (such as expected weight loss rate) for calculation. This involves data normalization processing and parameter selection. This design uses a calculation formula... It can obtain the user's weight management adherence score. Based on weight management compliance scores, it determines whether users are inclined to use smart health management devices. Users who are inclined to use the device are identified as target users, and their information can be obtained to confirm health behavior monitoring and management, ensuring real-time monitoring of their health status. For those who are not inclined to use the device, other measures are taken, typically including weakening the device's health monitoring function and emphasizing other functions, such as time reminders, note-taking, and other modes, to improve the device's usage efficiency and expand the application scenarios of smart health management devices.

[0089] Among them, the weight management compliance score related index function Its function is to perform a nonlinear transformation on the linear terms after weighted synthesis, ensuring the output weight management compliance score. It always remains a positive number, meets the scoring data requirements, and amplifies the differences between high-performing and average users. It ensures that both weight management habit elements and health goal elements meet or exceed certain standards, guaranteeing that the exponential function highlights adherence evidence, and that the weight management adherence score is related to the exponential function. This design is based on a comprehensive survey of users' historical awareness of weight management and historical database information. Data was collected through the survey and historical database methods, analyzed using fuzzy set qualitative comparative analysis, and then used to simulate a model to obtain the relevant index function for weight management adherence scoring; and the standard parameters for weight management habits were also determined. and health target standard parameters First preset weighting coefficient Second preset weighting coefficient These settings were all selected and configured based on historical experience data, and will not be detailed here.

[0090] As one embodiment of the present invention, the weight management status coefficient of the target user is calculated as follows:

[0091] Through formula Calculate and obtain the target user's weight management status coefficient ;in, The total number of updates to the target user's weight management rating parameters, and ∈ ; The third preset weighting coefficient, and >0; For the first The latest updated weight management scoring parameters; For the first The latest updated weight management scoring criteria parameters;

[0092] The method for analyzing the weight management status coefficient of the target user is as follows:

[0093] Weight management status coefficient of target users Weight management status coefficient threshold range of preset standard target users Compare:

[0094] like ∈ If so, it is determined that the target user's weight management status is stable;

[0095] like < If so, it is determined that the target user's weight management status needs to be strengthened and the management strategy needs to be adjusted;

[0096] like > If so, it can be determined that the target user's weight management status is excellent, achieving the ideal management effect.

[0097] In the above technical solution, the weight management compliance score calculated through the aforementioned steps Achieving alignment between users' long-term behavioral habits and health goals can represent the consistency of users' ability to maintain stability and manage weight, and this value... The state coefficients are calculated relatively consistently each time (in one cycle) and can be used as the base values ​​for superposition. As a short-term tendency to fluctuate, among which It is the first The updated weight management scoring parameters reflect the user's overall preference for various management items within a specific statistical period; It is the threshold corresponding to the first The updated weight management scoring criteria parameters are typically preset at the time of the update or based on baseline values ​​from the performance of the user group during the same period; the ratio standardizes the relative level of the current scoring parameters. Greater than This indicates that if the user's tendency is higher than the set benchmark during the period, a positive gain is generated; conversely, if it is lower, a negative impact is generated; the third preset weighting coefficient , No. The latest updated weight management scoring criteria parameters All of these data were obtained by fitting historical experience data, which will not be detailed here. Furthermore, the total number of updates to the target user's weight management score parameters was pre-set based on the user's weight management score for different usage cycles of the smart health management device within the monitoring period.

[0098] By summing the results of each update cycle and accumulating the contributions of all historical cycles, a comprehensive reflection of weight management status can be obtained. This allows for the assessment of the target user's weight management status coefficient. The larger the value, the better the long-term compliance of the target user, and when... With threshold range When making comparisons, the quantitative results can reflect the weight management status of the target user. As the lower limit of the threshold interval, The upper limit of the threshold range forms a numerical range representing the normal and stable performance of the target user group. By comparing whether the current weight management status coefficient of the target user falls within the range, if it does, it indicates that the user's overall status coefficient falls within the typical range of most successful users. That is, the results achieved through the combined effect of the current weight management model, behavioral compliance, and short-term tendencies are effective and sustainable, and no strategy adjustment is required. However, if the user's overall status coefficient is lower than the lower limit of the normal and stable range, it is judged that the target user's weight management status needs to be strengthened and needs to be adjusted in the near future. This is also reflected in the long-term decline in compliance, which requires adjustment of the management system and health goal settings. For cases that exceed the upper limit and reach an excellent level, higher-level challenging goals can be recommended or exercise recommendations to maintain stability can be provided.

[0099] As one embodiment of the present invention, the method for predicting the target user's weight management program information is as follows:

[0100] pass Calculate and obtain the target user's weight management trend value ;in, This represents the total weight management time for the target users within the statistical period. This represents the total amount of time spent on non-weight management activities by the target users within the statistical period. The weighting factor is determined by the impact of management time. The weighting coefficients for non-management time influence are as follows: > >0; and ∈ ;

[0101] Weight management status coefficient of target users Weight management status value of the target user Compare:

[0102] like > If so, it can be determined that the target user is involved in a weight loss or muscle gain program.

[0103] like ≤ If so, it can be determined that the target user has a tendency towards negative routine management projects.

[0104] In the above technical solution, by predicting the target user's weight management program information, it is possible to further determine the momentum and trend of the target user's recent behavioral patterns, whether it is trending towards positive or negative weight management (negative weight management is not aimed at weight loss or muscle gain, but rather at routine warm-up exercises, walking, or stretching without significant weight loss needs); specifically through formulas... Calculate and obtain the target user's weight management trend value , This represents the cumulative interval of the target user's weight management time within the statistical period, symbolizing the total duration of all proactive management behaviors; This represents the cumulative interval of non-weight management time for the target user within the same statistical period, signifying the total duration of all periods without proactive weight management; it also obtains the target user's weight management status value. Used to simulate the cumulative contribution effect of recent behavior on managerial potential; when the cumulative term is positive, i.e. The larger the value, the longer the management behavior lasts, and the greater its marginal contribution per unit time to building a positive management trend; conversely, the smaller the value, the smaller its marginal contribution per unit time. The management time affects the weighting coefficient. Weighting coefficients for non-management time influence All settings are based on historical data and experience; > A value greater than 0 indicates that establishing positive health behaviors is more difficult than overcoming inertia or interruptions; therefore, the positive weight of positive behaviors is greater than the negative weight of negative behaviors. This also makes... It is more sensitive to continuous management efforts, while having a certain buffer against short-term management deficiencies;

[0105] On the other hand, the weight management status coefficient, which represents the user's long-term and historical overall performance, will be used to... Weight management status values ​​(trends) of target users driven by recent behaviors. Compare the sizes, and when > When this occurs, it indicates that the current user has a long-term exercise habit and tends towards active weight loss or muscle gain management programs; conversely, when this occurs, it indicates that the user does not. ≤ This indicates that users have recently become lax in their weight management and need to resume exercise or break out of their negative state. The transition can be facilitated through regular management programs to ensure that weight management dynamically adapts to user habits.

[0106] Please see Figure 2As shown, a user weight intelligent health management device based on big data executes the user weight management process based on a big data-based user weight intelligent management method. The device includes:

[0107] The data collection module is used to collect user weight management data through smart health management devices. User weight management data includes weight management time and non-weight management time.

[0108] The data processing module is used to filter target users and their weight management rating parameters based on user weight management data, generate a filtering strategy based on the target users' weight management rating parameters, and obtain the weight management status coefficient of the target users under the current weight management rating parameters based on the filtering strategy. Among them, the weight management rating parameters are obtained by comprehensively statistically analyzing the rating values ​​of user weight management items, and are used to quantify the target users' tendency to choose weight management items.

[0109] The analysis and prediction module is used to analyze the weight management status coefficient of the target user and predict the weight management program information of the target user, including weight loss management program, muscle gain management program and routine management program.

[0110] The information output module is used to generate corresponding reminder information based on the target user's weight management program information and output the reminder information to the user.

[0111] In the above technical solution, the intelligent health management device is a software system integrated into a server or cloud platform. The data collection module is responsible for communicating with various external intelligent health management devices, receiving and preprocessing raw data according to a set protocol, and extracting structured weight management time and non-weight management time data. Then, it connects to the data collection module through a data processing module, which includes data storage, computing units, and a strategy engine. It executes a series of core algorithms, including user screening, scoring model invocation, parameter calculation (scoring parameters, compliance score Com, status coefficients, etc.), and dynamic screening strategy generation. The analysis and prediction module connects to the data processing module, receiving the calculated coefficients and, through built-in comparison logic and trend prediction algorithms (such as algorithms for calculating the target user's weight management status value), is responsible for completing status analysis and project trend prediction. The information output module connects to the analysis and prediction module, matching or generating personalized text, voice, or graphic reminder information from the system library based on the received prediction project information, and controlling the communication interface to send it to the user terminal. Through the communication connections between these modules, the entire process from data collection to the completion of the prediction process and the generation of health management reminder signals is completed collaboratively.

[0112] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, and therefore described more simply; relevant parts can be referred to the descriptions of the method embodiments.

[0113] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended documents. In some cases, the actions or steps described in this application may be performed in a different order than that shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0114] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in this application, they should all fall within the protection scope of the present invention.

Claims

1. A user weight intelligent management method based on big data, characterized in that, The method includes: S1. Collect user weight management data through intelligent health management devices, wherein the user weight management data includes weight management time and non-weight management time; S2. Filter target users and their weight management rating parameters based on user weight management data. A filtering strategy is generated based on the target user's weight management rating parameters; and the weight management status coefficient of the target user under the current weight management rating parameters is obtained according to the filtering strategy; the weight management rating parameters are obtained by comprehensive statistics based on the rating values ​​of the user's weight management items, and are used to quantify the target user's tendency to select weight management items; S3. Analyze the weight management status coefficient of the target user and predict the weight management project information of the target user, wherein the weight management project information includes weight loss management project, muscle gain management project and routine management project; S4. Generate corresponding reminder information based on the target user's weight management project information, and output the reminder information to the user; The filtering method of the filtering strategy is as follows: The filtering strategy is used to obtain the execution time and effect data of the weight management project within the time period corresponding to each update of the user's weight management rating parameters; Statistically analyze the execution time and effect data of weight management projects corresponding to all weight management rating parameters of this user, and match them to obtain the user's weight management habit elements and health goal elements; Based on the weight management habit elements and health goal elements, a weight management compliance score is generated for the user. Based on the user's weight management compliance score, identify the target user and the target user's weight management status, and obtain the target user's weight management status coefficient; The method for generating the user's weight management compliance score based on the aforementioned weight management habit elements and health goal elements is as follows: Through formula Calculate and obtain the user's weight management compliance score. ;in, For weight management compliance scoring, an index function is used. For weight management habit parameters, For health target parameters; Standard parameters for weight management habits, Standard parameters for health goals; The first preset weighting coefficient, The second preset weighting coefficient, and , All are greater than 0; Judgment when If the weight exceeds the preset standard threshold, the current user is confirmed as the target user, and their weight management effect is excellent. Judgment when If the weight loss is less than the preset standard threshold, the current user is identified as a non-target user or a potential target user, and the effectiveness of their weight management needs to be improved. The weight management status coefficient of the target user is calculated as follows: Through formula Calculate and obtain the target user's weight management status coefficient ;in, The total number of updates to the target user's weight management rating parameters, and ∈ ; The third preset weighting coefficient, and >0; For the first The latest updated weight management scoring parameters; For the first The latest updated weight management scoring criteria parameters.

2. The user weight intelligent management method based on big data according to claim 1, characterized in that, The filtering strategy is obtained as follows: Monitor the dynamic changes in users' weight management time and non-weight management time over a period of time to obtain users' weight management habits; Based on the user's weight management habits, set the weight management frequency and the statistical frequency of weight management score parameters.

3. The user weight intelligent management method based on big data according to claim 2, characterized in that, The weight management scoring parameters are obtained as follows: Based on the user's historical weight management data, extract features from multiple weight management programs; The features of the multiple weight management items are analyzed using a preset scoring model, and the user's score for each weight management item is output. The weight management score parameters are obtained by comprehensively and weightedly calculating the scores of each weight management item.

4. The user weight intelligent management method based on big data according to claim 1, characterized in that, The method for analyzing the weight management status coefficient of the target user is as follows: Weight management status coefficient of target users Weight management status coefficient threshold range of preset standard target users Compare: like ∈ If so, it is determined that the target user's weight management status is stable; like < If so, it is determined that the target user's weight management status needs to be strengthened and the management strategy needs to be adjusted; like > If so, it can be determined that the target user's weight management status is excellent, achieving the ideal management effect.

5. The user weight intelligent management method based on big data according to claim 4, characterized in that, The method for predicting the target user's weight management program information is as follows: pass Calculate and obtain the target user's weight management trend value; where, This represents the total weight management time for the target users within the statistical period. This represents the total amount of time spent on non-weight management activities by the target users within the statistical period. The weighting factor is determined by the impact of management time. The weighting coefficients for non-management time influence are as follows: > >0; and ∈ .

6. The user weight intelligent management method based on big data according to claim 5, characterized in that, Weight management status coefficient of target users Weight management status value of the target user Compare: like > If so, it can be determined that the target user is involved in a weight loss or muscle gain program. like ≤ If so, it can be determined that the target user has a tendency towards negative routine management projects.

7. A smart health management device for user weight based on big data, characterized in that, The device performs a user weight management process based on a big data-based intelligent user weight management method according to any one of claims 1-6, and the device includes: The data collection module is used to collect user weight management data through intelligent health management devices, including weight management time and non-weight management time. The data processing module is used to filter target users and their weight management rating parameters based on user weight management data, generate a filtering strategy based on the target users' weight management rating parameters, and obtain the weight management status coefficient of the target users under the current weight management rating parameters according to the filtering strategy; wherein, the weight management rating parameters are obtained by comprehensively statistically analyzing the rating values ​​of user weight management items, and are used to quantify the target users' tendency to choose weight management items; The analysis and prediction module is used to analyze the weight management status coefficient of the target user and predict the weight management program information of the target user, which includes weight loss management program, muscle gain management program and routine management program. The information output module is used to generate corresponding reminder information based on the target user's weight management program information and output the reminder information to the user.

Images