Method and device for pushing fat reduction content

Abstract

The invention is suitable for the technical field of prediction data processing, and provides a fat reduction content pushing method and device, and the method comprises the steps: obtaining user basic information and body data collected by a body fat scale; matching a user group tag according to the user basic information; matching target push content according to the user group tag and the body data; the target push content comprises product information and course information. According to the scheme, dynamic adjustment can be carried out according to the real-time data of the user, and it is ensured that the pushed content always adapts to the current physical condition of the user. By utilizing an intelligent matching technology and combining personal body data and group labels, precise pushing of fat reduction content is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of predictive data processing, and in particular, relates to a method and device for pushing fat-reducing content. Background Art

[0002] As people's living standards continue to improve, health management and weight control have gradually received widespread attention. As a common home health monitoring device, body fat scales can measure the user's body composition data, such as body fat percentage, muscle mass, bone mass, visceral fat level, etc., through bioelectrical impedance analysis (BIA) technology. These data provide an important reference for users to understand their own health status and develop fat loss or fitness plans.

[0003] However, the body fat scale products currently on the market are mainly limited to data collection and simple display, and lack the ability to push in-depth content based on user personalized characteristics. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method and device for pushing fat-reducing content to solve the technical problem that traditional body fat scales lack the ability to push deep content based on user personalized characteristics.

[0005] A first aspect of an embodiment of the present invention provides a method for pushing fat-reducing content, the method for pushing fat-reducing content being applied to a body fat scale, and the method for pushing fat-reducing content comprising: Obtaining basic user information and body data collected by a body fat scale; the basic information includes age, gender, height and weight, and the types of body data include body fat percentage, muscle mass, bone mass and visceral fat level; Matching user group tags according to the user basic information; According to the user group tag and the physical data, target push content is matched; the target push content includes product information and course information.

[0006] Furthermore, the step of matching user group tags according to the user basic information includes: Constructing the user basic information into a basic information vector; Obtaining a plurality of pre-stored sample information vectors and standard labels corresponding to the plurality of sample information vectors; Calculating a first similarity between the basic information vector and the sample information vector; The standard label corresponding to the sample information vector corresponding to the maximum first similarity is used as the user group label.

[0007] Furthermore, the step of matching target push content according to the user group tag and the physical data includes: Get the normal value range corresponding to each type of physical data; The type of body data that exceeds the normal value range is regarded as an abnormal type; the abnormal type includes abnormal body fat, abnormal muscle, abnormal bone mass and abnormal visceral fat; Matching a plurality of first purchase preference tags corresponding to the abnormal type; Matching a plurality of second purchase preference tags corresponding to the user group tag; Combining a plurality of the first purchase preference labels and a plurality of the second purchase preference labels to obtain a total preference label; In the push content set, target push content is matched according to the total preference tag; the push content set includes a product set and / or a course set, and the target push content includes a target product and / or a target course.

[0008] Furthermore, the step of combining the plurality of the first purchase preference labels and the plurality of the second purchase preference labels to obtain a total preference label includes: extracting repeated tags from a plurality of the first purchase preference tags and a plurality of the second purchase preference tags; Using the first preset weight as the weight of the repeated label; The second preset weight is used as the weight of the non-repeated label; The repeated label, the first preset weight corresponding to the repeated label, the non-repeated label, and the second preset weight corresponding to the non-repeated label are used as the total preference label.

[0009] Furthermore, the step of matching the target pushed content in the pushed content set according to the total preference tag includes: Get multiple preset tags corresponding to each pushed content in the pushed content collection; Calculating a preference score corresponding to each pushed content according to the multiple purchase preference tags in the total preference tags, the preset weights corresponding to the multiple purchase preference tags, and the multiple preset tags; The push content corresponding to the maximum preference score is used as the target push content.

[0010] Furthermore, the step of calculating the preference score corresponding to each pushed content according to the multiple purchase preference tags in the total preference tags, the preset weights corresponding to the multiple purchase preference tags, and the multiple preset tags includes: Count the number of identical tags among multiple purchase preference tags and multiple preset tags; The preference score corresponding to each pushed content is calculated according to the total number of the plurality of preset tags, the number of the same tags and the preset weights corresponding to the purchase preference tags.

[0011] Furthermore, the step of calculating the preference score corresponding to each pushed content according to the total number of the plurality of preset tags, the number of the same tags and the preset weight corresponding to the purchase preference tag includes: Calculate the proportion of the number of identical tags in the total number; Adding the preset weight values ​​corresponding to the same tag in multiple purchase preference tags to obtain a total weight value; Calculate the average value of preset weight values ​​corresponding to multiple identical tags; Adjust the proportion value by a first adjustment coefficient to obtain a first value; Adjust the total weight value by a second adjustment coefficient to obtain a second value; Adjust the average value by a third adjustment coefficient to obtain a third value; The first value, the second value, and the third value are added to obtain the preference score.

[0012] A second aspect of an embodiment of the present invention provides a device for pushing fat-reducing content, including: An acquisition unit, used to acquire basic information of the user and body data collected by a body fat scale; the basic information includes age, gender, height and weight, and the types of body data include body fat percentage, muscle mass, bone mass and visceral fat level; A first matching unit, configured to match user group labels according to the user basic information; The second matching unit is used to match target push content according to the user group tag and the physical data; the target push content includes product information and course information.

[0013] A third aspect of an embodiment of the present invention provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps in the method for pushing fat reduction content described in the first aspect are implemented.

[0014] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the method for pushing fat loss content described in the first aspect are implemented.

[0015] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: by obtaining the basic information of the user (such as age, gender, height and weight) and the body data collected by the body fat scale (such as body fat percentage, muscle mass, bone mass and visceral fat level), the present invention can accurately match the user group label according to the specific situation of the user. Through this process, the pushed content can not only meet the actual needs of the user, but also achieve a high degree of personalization of the content, avoiding the universality problem in the traditional push method. Based on the user group label and body data, the present invention can more accurately match the target push content for the user, including customized product information and course information. This precise matching technology can effectively improve the user's acceptance and interest in the pushed content, and encourage the user to actively participate in health management activities such as fat loss and fitness, thereby helping the user to achieve more significant health goals. By pushing fat loss content that is highly related to the user's physical condition and personal characteristics (such as a specific fat loss course or a suitable health product), the present invention can enhance the user's recognition and dependence on the product or service. This personalized push can not only improve the user experience, but also help to improve user stickiness, thereby increasing the platform's activity and customer loyalty. Unlike traditional health management methods, the present invention uses the data provided by the body fat scale for scientific analysis, making fat loss suggestions and product recommendations more scientific and accurate. It can dynamically adjust according to the user's real-time data to ensure that the pushed content is always adapted to the user's current physical condition, thereby helping users achieve more scientific and sustainable fat loss and health management. In short, the present invention uses intelligent matching technology, combined with personal body data and group tags, to achieve accurate push of fat loss content. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A schematic flow chart of a method for pushing fat-reducing content provided by the present invention is shown; Figure 2 A schematic diagram showing a device for pushing fat-reducing content provided by an embodiment of the present invention; Figure 3 A schematic diagram of a terminal device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0018] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0019] The embodiments of the present invention provide a method and device for pushing fat-reducing content, so as to solve the technical problem that the traditional body fat scale lacks the ability to push deep content based on the personalized characteristics of the user.

[0020] First, the present invention provides a method for pushing fat loss content. Figure 1 , Figure 1 FIG. 1 is a schematic flow chart of a method for pushing fat-reducing content provided by the present invention. Figure 1 As shown, the method for pushing fat-reducing content may include the following steps: Step 101: Obtain basic information of the user and body data collected by a body fat scale; the basic information includes age, gender, height and weight, and the types of body data include body fat percentage, muscle mass, bone mass and visceral fat level; The user's age, gender and height information is collected through the terminal device. The body weight, body fat percentage, muscle mass, bone mass and visceral fat level are collected through the body fat scale. Among them, age can help determine physiological characteristics such as metabolic rate and hormone levels, which can affect fat loss goals and methods. At the gender level, men and women have differences in body fat distribution, metabolic rate and muscle growth. Gender information helps to develop personalized fat loss plans. Height and weight can be combined to calculate the body mass index (BMI), which helps to understand the user's overall health. The user's weight directly affects their fat loss goals. By understanding the weight, the system can infer the need and priority for fat loss. Body fat percentage is the proportion of body fat in total weight, which directly reflects the user's body fat level. Muscle mass reflects the user's muscle development. The amount of muscle mass usually affects the basal metabolic rate. People with higher muscle mass consume more calories and the fat loss process will be different. Bone mass is helpful for estimating the user's weight and health level. It is related to the goal of weight loss during fat loss. Visceral fat has a greater impact on health. High levels of visceral fat may mean that more attention needs to be paid to the fat loss process.

[0021] Step 102: Matching user group tags according to the user basic information; This step is to classify user groups or label matching based on the acquired user information. Through comprehensive analysis of basic data such as age, gender, height, weight, etc., the system can classify users into different group labels.

[0022] Specifically, step 102 specifically includes steps 1021 to 1024: Step 1021: construct the user basic information into a basic information vector; Standardize each basic information to ensure that they are comparable in value. For example, height, weight, and age have different dimensions and need to be normalized or standardized (for example, convert height and weight into standardized numbers).

[0023] The basic information of each user is represented as a numerical vector by normalization, combination or one-hot encoding. These numerical vectors can be understood as the position of the user in a multidimensional space, where each dimension represents a basic information feature. This basic information vector is the key to the subsequent steps, and it will serve as the basis for subsequent similarity calculations and label matching.

[0024] Step 1022: Acquire multiple pre-stored sample information vectors and standard labels corresponding to the multiple sample information vectors; The system needs to prepare multiple sample information vectors and the standard labels corresponding to these sample information vectors in advance. The sample information vector comes from known user data or group data, and each sample information vector contains a vector representation of the basic information of different users. The standard label is the group label corresponding to each sample information vector (for example, "young-male group-medium weight-medium height", "middle-aged-female group-medium weight-medium height", etc.).

[0025] These pre-stored sample information vectors and their standard labels will serve as a “reference” dataset for comparison and matching with the basic information vectors of new users.

[0026] Step 1023: Calculate a first similarity between the basic information vector and the sample information vector; This step is the core matching process, and its purpose is to find the most similar sample by comparing the similarity between the user's basic information vector and multiple pre-stored sample information vectors. This similarity calculation will obtain a value that reflects the degree of similarity between the user and each sample. A "first similarity" is calculated for each sample information vector and the user's basic information vector.

[0027] Step 1024: Use the standard label corresponding to the sample information vector corresponding to the maximum first similarity as the user group label.

[0028] The system will select the maximum value from all calculated similarities and determine the user's group label based on the standard label of the sample information vector corresponding to the maximum similarity. That is, if a pre-stored sample information vector has the highest similarity with the user's basic information vector, the user will be classified as the group label represented by the sample information vector.

[0029] For example, if the user's basic information has the highest similarity to the sample information vector of "young-male group-medium weight-medium height", then the user is classified as "young-male group-medium weight-medium height".

[0030] In the embodiment corresponding to step 1021 to step 1024, through the above steps, the user's basic information vector and the pre-stored sample information vector are similarly calculated, and the group label to which the user belongs is determined based on the maximum similarity. This method can efficiently divide users into different groups and provide an accurate basis for subsequent personalized push.

[0031] Step 103: Match target push content according to the user group tag and the physical data; the target push content includes product information and course information.

[0032] After matching the user group tag, the system will further personalize the recommended target push content based on the user's physical data (such as body fat percentage, muscle mass, visceral fat level, etc.). At this time, the push content is not just universal information, but customized based on the user's current physical condition and group tag.

[0033] Push content is divided into two categories: Product information includes but is not limited to fat-reducing products (such as slimming drinks, protein powder, sports equipment, etc.) or health-supporting products (such as smart sports equipment, nutritional supplements, etc.). Through the push of product information, users can choose suitable fat-reducing products according to their needs to help improve fat-reducing effects.

[0034] Course information includes but is not limited to targeted fat loss training courses, diet adjustment plans, healthy lifestyle suggestions, etc. These courses can be videos, online tutorials, graphic tutorials, etc. Users can choose to learn and participate according to their own circumstances.

[0035] Specifically, step 103 specifically includes steps 1031 to 1036: Step 1031: Obtain the normal value range corresponding to each type of body data; The system needs to preset or obtain the normal value range of each body data (such as body fat percentage, muscle mass, bone mass, visceral fat level) from medical research data. These value ranges can be defined according to health standards, medical guidelines or industry standards. For example: Body fat percentage: The normal body fat percentage for men is usually between 10%-20%, and for women it is between 20%-30%.

[0036] Muscle mass: The normal range of muscle mass varies depending on your weight-to-height ratio.

[0037] Bone mass: The normal range of bone mass generally depends on age and sex.

[0038] Visceral fat: Normal visceral fat levels are usually 1-9, and levels outside this range are considered abnormal.

[0039] These normal value ranges will be used in subsequent steps to determine whether the physical data is normal.

[0040] Step 1032: The type of body data that exceeds the normal value range is regarded as an abnormal type; the abnormal type includes abnormal body fat, abnormal muscle, abnormal bone mass and abnormal visceral fat; When a user's physical data exceeds these normal ranges, it is considered "abnormal". Abnormal types are mainly divided into: Abnormal body fat: If the body fat percentage is too high or too low, it indicates that the user may need to lose fat or increase body fat. Abnormal muscle: Too low muscle mass may mean that the muscles need to be strengthened, while too high muscle mass may mean that the muscles need to be maintained or controlled. Abnormal bone mass: Too low bone mass may indicate insufficient bone density, requiring nutritional supplements or bone training. Abnormal visceral fat: Too high a visceral fat level indicates that the user has health risks, such as cardiovascular disease.

[0041] Through this step, the system can identify abnormalities in certain physical data of the user.

[0042] Step 1033: Match multiple first purchase preference tags corresponding to the abnormal type; Each abnormality type is associated with a different purchase preference label (for example, users with abnormal body fat may prefer to buy fat-reducing products, and users with abnormal muscle may prefer to buy muscle-building products). These first purchase preference labels are set based on the characteristics of the abnormal data. For example: Abnormal body fat: fat-reducing products, sports equipment, low-calorie foods, etc.

[0043] Muscle abnormalities: muscle-building powder, protein supplements, strength training courses, etc.

[0044] Abnormal bone mass: calcium supplements, bone density increasing courses, bone strengthening training, etc.

[0045] Abnormal visceral fat: Products that help reduce visceral fat (such as specific fat reduction products), exercise classes, dietary adjustments, etc.

[0046] Step 1034: Matching a plurality of second purchase preference tags corresponding to the user group tag; In addition to the abnormal types of physical data, users' group labels also affect their purchasing preferences. Group labels are usually classified based on users' age, gender, lifestyle and other characteristics. For example: Male group: may be more inclined to buy fitness equipment, muscle-building products, etc.

[0047] Female group: may be more concerned about healthy eating, fat-reducing products, yoga classes, etc.

[0048] Young people: may purchase high-intensity training courses and body shaping courses.

[0049] Elderly people: may tend to choose low-intensity exercise classes, joint health products, etc.

[0050] These preference labels reflect the consumption habits and needs of different groups.

[0051] Step 1035: merging a plurality of the first purchase preference labels and a plurality of the second purchase preference labels to obtain a total preference label; In this step, the system combines multiple purchase preference labels from abnormal types and user group labels to form a total preference label. This total preference label contains the purchase preferences formed by the user due to physical data abnormalities and group characteristics. For example: Abnormal body fat of a user may lead the system to recommend fat-reducing products or courses, but the young female group label to which the user belongs may be more inclined to push body shaping and yoga courses.

[0052] Abnormal visceral fat in users may lead to product push notifications aimed at improving health, while their group labels may affect the types of products or brands recommended.

[0053] Combining these tags helps the system identify user needs more accurately and provide more personalized push notifications.

[0054] Specifically, step 1035 specifically includes steps A1 to A4: Step A1: extracting repeated tags from a plurality of the first purchase preference tags and a plurality of the second purchase preference tags; The system needs to compare the first purchase preference tag with the second purchase preference tag to find the same (duplicate) tags in the two. For example: If the first purchase preference tag has the tag "fat reduction products" and the second purchase preference tag also has the tag "fat reduction products", this is a duplicate tag.

[0055] The system needs to compare the contents of the two tag sets, identify which tags appear in both sets, and extract these duplicate tags.

[0056] Step A2: using the first preset weight as the weight of the repeated label; For these repeated tags, the system will give them a specific weight, which is determined by the first preset weight. The "first preset weight" here is usually a numerical value that represents the importance of these repeated tags.

[0057] Repeated tags indicate that the user's needs are consistent between the two tag sets, so these tags may be more important. By giving them higher weights, the system can prioritize the impact of these tags on the total preferred tags. For example, if a user is very interested in "fat loss products", if this tag exists in multiple tag sets, it means that the user's needs are relatively strong, and the system will give this tag a higher weight.

[0058] Step A3: using the second preset weight as the weight of the non-repeated label; Next, the system needs to process those tags that appear only once in the first purchase preference tag and the second purchase preference tag, that is, non-duplicate tags. For these tags, the system assigns them the second preset weight. Compared with the first preset weight, the second preset weight is usually lower, indicating that the non-duplicate tag is relatively less important in the combined total preference tag.

[0059] Non-repeated tags represent that users' preferences in some aspects do not completely overlap. Although these tags can also provide certain preference information, their "importance" may be lower than those repeated tags that appear between multiple tag sets. Therefore, assigning lower weights to these non-repeated tags can better balance the effectiveness of the total preference tags.

[0060] Step A4: The repeated label, the first preset weight corresponding to the repeated label, the non-repeated label and the second preset weight corresponding to the non-repeated label are used as the total preference label.

[0061] All these tags and their corresponding weights are combined to form a comprehensive total preference tag, which reflects the user's purchase preferences in many aspects and distinguishes the relative importance of each tag through weights.

[0062] In the embodiment corresponding to step A1 to step A4, through these steps, the system can effectively process the purchase preference tags from different sources, and assign different weights according to the degree of repetition of these tags, and finally form a comprehensive and personalized total preference tag. The total preference tag not only includes the user's preferences, but also reflects the relative importance between tags. This process can ensure that the content that best meets the user's needs is given priority in the final push content.

[0063] Step 1036: In the push content set, target push content is matched according to the total preference tag; the push content set includes a product set and / or a course set, and the target push content includes a target product and / or a target course.

[0064] After obtaining the total preference tags, the system will search in the push content collection to match the content that best matches these preference tags. The push content collection can include two types of content: Product collection: Push corresponding health products based on user preferences, such as nutritional supplements, sports equipment, fat-reducing products, etc.

[0065] Course collection: Push corresponding fitness courses, diet plans, fat loss training, etc. according to user needs.

[0066] The targeted push content is the product and course that best matches the user's preferences. Ultimately, based on the overall preference tag, the system will push the most suitable product and / or course to the user. These push contents will be accurately matched to the user's physical data abnormalities, group tags, purchase preferences and other comprehensive needs, thereby improving user engagement and satisfaction.

[0067] Specifically, step 1036 specifically includes step B1 to step B3: Step B1: obtaining multiple preset tags corresponding to each push content in the push content set; The system needs to define multiple preset tags for each item in the push content collection (whether it is a product or a course). These tags describe the characteristics, applicable groups, or main functions of the push content. For example, the preset tags for a fat loss training course may be: "Fat Loss", "High Intensity", "Women's Only", "Home Fitness". The preset tags for a protein powder may be: "Muscle Gain", "Sports Supplement", "Suitable for Men", "High Protein".

[0068] The purpose of this step is to lay the foundation for subsequent tag matching and scoring, ensuring that each pushed content has rich descriptive tags for comparison.

[0069] Step B2: calculating a preference score corresponding to each pushed content according to the multiple purchase preference tags in the total preference tags, the preset weights corresponding to the multiple purchase preference tags, and the multiple preset tags; Next, the system needs to score each pushed content based on the total preference label generated previously.

[0070] Specifically, step B2 specifically includes step B21 to step B22: Step B21: Counting the number of identical tags among the multiple purchase preference tags and the multiple preset tags; The system needs to compare the purchase preference tags with the preset tags and find out how many tags are the same between them.

[0071] For example, if a user's purchase preference tag includes "fat loss" and a push content's preset tag also includes "fat loss", then this is a same tag. If a user's purchase preference tag includes "women's only", and a push content's preset tag also includes "women's only", this is also a same tag.

[0072] Step B21: Calculate the preference score corresponding to each pushed content according to the total number of the plurality of preset tags, the number of the same tags and the preset weight corresponding to the purchase preference tag.

[0073] After obtaining the number of identical tags, the next step is to calculate the push content preference score based on these identical tags.

[0074] The total number of the multiple preset tags is the total number of tags for each pushed content, indicating all the characteristics described by the pushed content.

[0075] The number of identical tags is the number calculated in the previous step, indicating the number of matches between the user's purchase preference tags and the preset tags of the pushed content.

[0076] The preset weight corresponding to the purchase preference tag is a preset weight for each purchase preference tag, indicating the importance of the tag. For example, the weight of "fat loss" may be 5, while the weight of "women only" may be 3.

[0077] Specifically, step B21 specifically includes steps B221 to B227: Step B221: Calculate the proportion of the number of identical tags in the total number; The system needs to calculate the proportion of the same tags in the total number of preset tags in the pushed content. A percentage value is obtained to reflect how many tags in the pushed content match the user's purchase preference tags. The higher the percentage value, the more the pushed content matches the user's interests.

[0078] Step B222: Adding the preset weight values ​​corresponding to the same tag in multiple purchase preference tags to obtain a total weight value; Next, the system adds up the weights of each matching purchase preference tag to get the total weight value. Each purchase preference tag has a corresponding preset weight (for example, the weight of "fat loss" may be 5, and the weight of "high intensity" may be 3). If the preset tag of a push content matches multiple purchase preference tags, the system adds up the weights of all matching tags. Get the weighted total value of all matching tags. This total weight value reflects the degree of consistency between the push content and the user's preference tags. If the total weight value is high, it means that the push content is highly consistent with the user's needs and interests.

[0079] Step B223: Calculate the average value of preset weight values ​​corresponding to multiple identical tags; At this point, the system calculates the average weight of all matching tags. The purpose of this step is to remove the excessive influence of the weight of a single tag on the score, and to avoid an imbalance in the score caused by a tag with too high a weight. By averaging the weight values, a more balanced score is obtained. This value reflects the combined influence of all matching tags, rather than the bias of a single tag.

[0080] Step B224: adjusting the proportion value by a first adjustment coefficient to obtain a first value; Step B225: adjusting the total weight value by a second adjustment coefficient to obtain a second value; Step B226: adjusting the average value by a third adjustment coefficient to obtain a third value; Step B227: Add the first value, the second value and the third value to obtain the preference score.

[0081] The specific calculation process from step B221 to step B227 is as follows: ; in, Indicates The preference score corresponding to the pushed content, Indicates The number of identical tags corresponding to the pushed content. Indicates The total number of preset tags corresponding to the pushed content. Indicates The preset weights corresponding to the purchase preference tags are: represents the number of purchase preference tags, represents the first adjustment coefficient, represents the second adjustment coefficient, Represents the third adjustment factor.

[0082] This part measures the matching degree between the content and the user's purchase preference tags. Specifically, it indicates how many tags in the content are the user's preferred tags. Parameters can control the degree of influence of matching on the score. A larger ratio means that the content contains more tags that match user preferences, so the pushed content is more closely matched with user needs. The parameter is used to adjust the influence of this ratio. A higher value will increase the weight of the match in the score, and a lower value will reduce the impact of the match.

[0083] This part performs a weighted summation of the matching of content tags. By summing the weights of tags that are the same as the user's purchase preference tags, the combined influence of these tags can be measured. The parameter adjusts the influence of the weighted sum, with larger A higher value means that the weighted parts have a greater influence on the score.

[0084] This part calculates the average weight of all tags in the pushed content. If the pushed content contains high-weight tags, this part will increase the score, otherwise it will decrease the score. The parameter controls the influence of this part on the final score. A value of will make the overall weight of the label play a more important role in the scoring.

[0085] The above formula can finely combine the tag matching degree and tag weight, ensuring that the score of the pushed content depends not only on the matching with the user's preferred tags, but also on the importance of each tag. , , ), the scoring formula can be adjusted for different scenarios to make it more in line with the user's personalized needs and preferences. By assigning different weights to each tag and combining it with purchase preference tags, the system can implement a more refined recommendation strategy. High-weight tags will have a greater impact on the score, thereby ensuring that important tags play a decisive role in the push content preferred by users. In the formula, the number of identical tags, the weight of tags, and the balance of the number of tags are comprehensively considered. It is possible to generate accurate preference scores in the recommendation system and respond to different user needs and scenario changes by flexibly adjusting parameters. Its technical effect is that it can achieve personalization, dynamic adjustment, and refined control, thereby providing users with more accurate content push. This avoids the deviation that may be caused by a single factor (such as only looking at the degree of tag matching), thereby improving the accuracy and robustness of the recommendation system.

[0086] In the embodiment corresponding to step B221 to step B227, a preliminary score is first obtained by using the proportion and weight; then the score is finely adjusted by using multiple adjustment coefficients so that the final score is more in line with the user's preferences and actual scenario requirements; finally, the three adjusted values ​​are added together to obtain a comprehensive preference score for the selection of pushed content. This solution introduces multiple adjustment coefficients to make the score calculation more flexible and personalized, and can more accurately optimize the pushed content according to different business needs.

[0087] Step B3: The push content corresponding to the maximum preference score is used as the target push content.

[0088] Finally, the system compares the preference scores of all pushed content and finds the push content with the highest score as the target push content to be pushed to the user. The higher the preference score, the more consistent the tag of the pushed content is with the user's interest tag, and the more it meets the user's current needs or interests. This can greatly improve the relevance, click-through rate and conversion rate of the pushed content.

[0089] You can also set it to push multiple pieces of content with higher scores (such as the top 3) instead of just one; or set a minimum score threshold, and content below this score will not be pushed to ensure the quality of the push.

[0090] In the embodiment corresponding to step B1 to step B3, each pushed content is labeled, scored according to the total preference label + weight, and finally the content with the highest score is selected for push. In this way, the entire push logic becomes an accurate content recommendation based on the personalized needs of users, and because of the introduction of weights, the system can more delicately distinguish the importance of different preferences, making the recommendation more intelligent.

[0091] In the embodiment corresponding to step 1031 to step 1036, the user's purchase preference tag is accurately matched by combining the user's physical data abnormality and group tag, and personalized products and courses are pushed. In this way, the system can provide more in line with the needs of the user according to the characteristics of the user, and improve the relevance and effect of the pushed content.

[0092] In the embodiment corresponding to step 101 to step 103, by obtaining the basic information of the user (such as age, gender, height and weight) and the body data collected by the body fat scale (such as body fat percentage, muscle mass, bone mass and visceral fat level), the present invention can accurately match the user group label according to the specific situation of the user. Through this process, the pushed content can not only meet the actual needs of the user, but also achieve a high degree of personalization of the content, avoiding the universality problem in the traditional push method. Based on the user group label and body data, the present invention can more accurately match the target push content for the user, including customized product information and course information. This precise matching technology can effectively improve the user's acceptance and interest in the pushed content, prompting the user to actively participate in health management activities such as fat loss and fitness, thereby helping the user to achieve more significant health goals. By pushing fat loss content that is highly related to the user's physical condition and personal characteristics (such as a specific fat loss course or a suitable health product), the present invention can enhance the user's recognition and dependence on the product or service. This personalized push can not only improve the user experience, but also help to improve user stickiness, thereby increasing the platform's activity and customer loyalty. Unlike traditional health management methods, the present invention uses the data provided by the body fat scale for scientific analysis, making fat loss suggestions and product recommendations more scientific and accurate. It can dynamically adjust according to the user's real-time data to ensure that the pushed content is always adapted to the user's current physical condition, thereby helping users achieve more scientific and sustainable fat loss and health management. In short, the present invention uses intelligent matching technology, combined with personal body data and group tags, to achieve accurate push of fat loss content.

[0093] like Figure 2 The present invention provides a device for pushing fat-reducing content, see Figure 2 , Figure 2 A schematic diagram of a device for pushing fat-reducing content provided by the present invention is shown, Figure 2 The device for pushing fat-reducing content includes: The acquisition unit 21 is used to acquire basic information of the user and body data collected by the body fat scale; the basic information includes age, gender, height and weight, and the types of body data include body fat percentage, muscle mass, bone mass and visceral fat level; A first matching unit 22, configured to match user group labels according to the user basic information; The second matching unit 23 is used to match target push content according to the user group tag and the physical data; the target push content includes product information and course information.

[0094] The present invention provides a device for pushing fat-reducing content. By acquiring basic information of the user (such as age, gender, height and weight) and body data collected by a body fat scale (such as body fat percentage, muscle mass, bone mass and visceral fat level), the present invention can accurately match user group labels according to the specific situation of the user. Through this process, the pushed content can not only meet the actual needs of the user, but also achieve a high degree of personalization of the content, avoiding the universality problem in the traditional push method. Based on the user group label and body data, the present invention can more accurately match the target push content for the user, including customized product information and course information. This precise matching technology can effectively improve the user's acceptance and interest in the pushed content, prompting the user to actively participate in health management activities such as fat reduction and fitness, thereby helping the user to achieve more significant health goals. By pushing fat-reducing content (such as a specific fat-reducing course or a suitable health product) that is highly related to the user's physical condition and personal characteristics, the present invention can enhance the user's recognition and dependence on the product or service. This personalized push can not only improve the user experience, but also help to improve user stickiness, thereby increasing the platform's activity and customer loyalty. Unlike traditional health management methods, this invention uses the data provided by the body fat scale for scientific analysis, making fat loss suggestions and product recommendations more scientific and accurate. It can dynamically adjust according to the user's real-time data to ensure that the pushed content is always adapted to the user's current physical condition, thereby helping users achieve more scientific and sustainable fat loss and health management. In short, this invention uses intelligent matching technology, combined with personal body data and group tags, to achieve accurate push of fat loss content. Figure 3 Schematic diagram of a terminal device provided by an embodiment of the present invention. Figure 3 As shown, a terminal device 3 of this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30, such as a fat-reducing content push program. When the processor 30 executes the computer program 32, the steps in each of the above-mentioned fat-reducing content push method embodiments are implemented, such as Figure 1 Alternatively, when the processor 30 executes the computer program 32, the functions of each unit in the above-mentioned device embodiments are realized, for example, Figure 2 Function of the unit shown.

[0095] Exemplarily, the computer program 32 may be divided into one or more units, which are stored in the memory 31 and executed by the processor 30 to complete the present invention. The one or more units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 32 in the terminal device 3. For example, the computer program 32 may be divided into the following specific functions of each unit: An acquisition unit, used to acquire basic information of the user and body data collected by a body fat scale; the basic information includes age, gender, height and weight, and the types of body data include body fat percentage, muscle mass, bone mass and visceral fat level; A first matching unit, configured to match user group labels according to the user basic information; The second matching unit is used to match target push content according to the user group tag and the physical data; the target push content includes product information and course information.

[0096] The terminal device includes but is not limited to a processor 30 and a memory 31. Those skilled in the art will appreciate that Figure 3 It is only an example of a terminal device 3 and does not constitute a limitation on the terminal device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0097] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0098] The memory 31 may be an internal storage unit of the terminal device 3, such as a hard disk or memory of the terminal device 3. The memory 31 may also be an external storage device of the terminal device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 3. Further, the memory 31 may also include both an internal storage unit and an external storage device of the terminal device 3. The memory 31 is used to store the computer program and other programs and data required by the roaming control device. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0099] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0100] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0101] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by 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 embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0102] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0103] An embodiment of the present invention provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0104] If the integrated unit is implemented in the form of 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, the present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera device / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0105] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0106] Those skilled in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0107] In the embodiments provided by the present invention, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0108] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed over multiple network units.

[0109] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0110] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0111] As used in the present specification and the appended claims, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to monitoring, depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is monitored" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is monitored" or "in response to monitoring [described condition or event]", depending on the context.

[0112] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0113] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0114] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for pushing fat-reducing content, characterized in that: The method for pushing fat-reducing content is applied to a body fat scale, and the method for pushing fat-reducing content includes: Obtaining basic user information and body data collected by a body fat scale; the basic information includes age, gender, height and weight, and the types of body data include body fat percentage, muscle mass, bone mass and visceral fat level; Matching user group tags according to the user basic information; According to the user group tag and the physical data, target push content is matched; the target push content includes product information and course information.

2. The method for pushing fat-reducing content according to claim 1, characterized in that: The step of matching user group tags according to the user basic information includes: Constructing the user basic information into a basic information vector; Obtaining a plurality of pre-stored sample information vectors and standard labels corresponding to the plurality of sample information vectors; Calculating a first similarity between the basic information vector and the sample information vector; The standard label corresponding to the sample information vector corresponding to the maximum first similarity is used as the user group label.

3. The method for pushing fat-reducing content according to claim 1, characterized in that: The step of matching target push content according to the user group tag and the physical data comprises: Get the normal value range corresponding to each type of physical data; The type of body data that exceeds the normal value range is regarded as an abnormal type; the abnormal type includes abnormal body fat, abnormal muscle, abnormal bone mass and abnormal visceral fat; Matching a plurality of first purchase preference tags corresponding to the abnormal type; Matching a plurality of second purchase preference tags corresponding to the user group tag; Combining a plurality of the first purchase preference labels and a plurality of the second purchase preference labels to obtain a total preference label; In the push content set, target push content is matched according to the total preference tag; the push content set includes a product set and / or a course set, and the target push content includes a target product and / or a target course.

4. The method for pushing fat-reducing content according to claim 3, characterized in that: The step of combining the plurality of the first purchase preference tags and the plurality of the second purchase preference tags to obtain a total preference tag comprises: extracting repeated tags from a plurality of the first purchase preference tags and a plurality of the second purchase preference tags; Using the first preset weight as the weight of the repeated label; The second preset weight is used as the weight of the non-repeated label; The repeated label, the first preset weight corresponding to the repeated label, the non-repeated label, and the second preset weight corresponding to the non-repeated label are used as the total preference label.

5. The method for pushing fat-reducing content according to claim 3, characterized in that: The step of matching the target pushed content in the pushed content set according to the total preference tag comprises: Get multiple preset tags corresponding to each pushed content in the pushed content collection; Calculating a preference score corresponding to each pushed content according to the multiple purchase preference tags in the total preference tags, the preset weights corresponding to the multiple purchase preference tags, and the multiple preset tags; The push content corresponding to the maximum preference score is used as the target push content.

6. The method for pushing fat-reducing content according to claim 5, characterized in that: The step of calculating the preference score corresponding to each pushed content according to the multiple purchase preference tags in the total preference tags, the preset weights corresponding to the multiple purchase preference tags, and the multiple preset tags includes: Count the number of identical tags among multiple purchase preference tags and multiple preset tags; The preference score corresponding to each pushed content is calculated according to the total number of the plurality of preset tags, the number of the same tags and the preset weights corresponding to the purchase preference tags.

7. The method for pushing fat-reducing content according to claim 6, characterized in that: The step of calculating the preference score corresponding to each pushed content according to the total number of the plurality of preset tags, the number of the same tags and the preset weight corresponding to the purchase preference tag comprises: Calculate the proportion of the number of identical tags in the total number; Adding the preset weight values ​​corresponding to the same tag in multiple purchase preference tags to obtain a total weight value; Calculate the average value of preset weight values ​​corresponding to multiple identical tags; Adjust the proportion value by a first adjustment coefficient to obtain a first value; Adjust the total weight value by a second adjustment coefficient to obtain a second value; Adjust the average value by a third adjustment coefficient to obtain a third value; The first value, the second value, and the third value are added to obtain the preference score.

8. A device for pushing fat-reducing content, characterized in that: The device for pushing the fat-reducing content comprises: An acquisition unit, used to acquire basic information of the user and body data collected by a body fat scale; the basic information includes age, gender, height and weight, and the types of body data include body fat percentage, muscle mass, bone mass and visceral fat level; A first matching unit, configured to match user group labels according to the user basic information; The second matching unit is used to match target push content according to the user group tag and the physical data; the target push content includes product information and course information.

9. A terminal device, characterized in that: The terminal device includes: a memory, a processor, and a fat-reduction content push program stored in the memory and executable on the processor, wherein the fat-reduction content push program is configured to implement the steps in the fat-reduction content push method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps in the method for pushing fat-reducing content as claimed in any one of claims 1 to 7 are implemented.

Images