Grouping exercise recommendation method, system and device, storage medium and program product

Abstract

The invention discloses a grouping exercise recommendation method, system and device, a storage medium and a program product, and relates to the technical field of intelligent exercise watchs.The method comprises the steps that a grouping exercise request of a first user is received; acquiring motion data of the first user and other users, and extracting motion features of the first user and other users; according to the motion characteristics of the first user and the other users, respectively calculating physical ability levels of the first user and the other users; based on the physical ability levels of the first user and the other users, calculating the motion similarity between the first user and the other users; and on the basis of the motion similarities, pushing a grouping motion request to the users meeting the grouping requirements in the other users. According to the scheme, the physical fitness level of each user is calculated according to the exercise features, the users with similar exercise hobbies and physical fitness levels are mined, the users are helped to find exercise partners with similar exercise interests and physical fitness levels, and the exercise experience of the users is improved.

Description

Technical Field

[0001] The present application relates to the technical field of smart sports watches, and in particular to group sports recommendation methods, systems, devices, storage media and program products. Background Art

[0002] Traditional social networking platforms such as WeChat and QQ allow users to create groups to communicate and organize sports-related activities. However, this method requires manually inviting friends to join, which is a cumbersome process, and the members who are pulled into the group may not be interested in or suitable for the proposed sports. In addition, this method lacks precision and cannot ensure that members in the group have similar interests and sports levels, thus affecting the quality and participation of team activities.

[0003] Although existing smart sports watches can collect detailed personal sports data, most manufacturers have not yet fully utilized this data for in-depth analysis to identify and connect user groups with the same interests and similar exercise habits. Current data analysis often focuses on simple indicators, fails to fully explore information in multiple dimensions such as exercise types and interest tags, and cannot make intelligent recommendations based on users' exercise intensity and physical fitness levels. Summary of the invention

[0004] The main purpose of this application is to provide a group exercise recommendation method, system, device, storage medium and program product, aiming to solve the technical problem of how to provide users with more intelligent and accurate group exercise recommendations.

[0005] To achieve the above objectives, the present application proposes a group exercise recommendation method, the method comprising:

[0006] receiving a group exercise request from a first user;

[0007] Acquire motion data of the first user and other users, and extract motion features of the first user and other users;

[0008] Calculating the physical fitness levels of the first user and the other users respectively according to the motion characteristics of the first user and the other users;

[0009] Calculating the motion similarity between the first user and the other users based on the physical fitness levels of the first user and the other users;

[0010] Based on the movement similarities, the group movement request is pushed to users among the other users who meet the group movement requirement.

[0011] In one embodiment, the step of respectively calculating the physical fitness levels of the first user and the other users according to the motion characteristics of the first user and the other users comprises:

[0012] Calculating the physical fitness scores of the first user and the other users respectively by using a random forest algorithm according to the motion characteristics of the first user and the other users;

[0013] The physical fitness levels of the first user and the other users are divided according to the physical fitness scores.

[0014] In one embodiment, the step of respectively calculating the physical fitness scores of the first user and the other users by using a random forest algorithm according to the motion characteristics of the first user and the other users comprises:

[0015] For each user, based on the random forest algorithm, regression prediction is performed on the motion characteristics of the user to obtain a prediction result of each decision tree;

[0016] Calculate the average value of all decision trees according to the prediction results of each decision tree;

[0017] The average value of all decision trees is taken as the final physical fitness score.

[0018] In one embodiment, the step of calculating the motion similarity between the first user and the other users based on the fitness levels of the first user and the other users comprises:

[0019] Obtaining basic user information of each user, wherein the basic user information includes at least location area, age, and exercise time;

[0020] Based on the basic information of each user and the physical fitness level corresponding to each user, the movement similarity between the first user and the other users is calculated.

[0021] In one embodiment, the step of calculating the motion similarity between the first user and the other users based on the basic information of each user and the physical fitness level corresponding to each user includes:

[0022] Based on the basic information of each user and the physical fitness level corresponding to each user, construct a first feature vector of the first user and a second feature vector of the other users respectively;

[0023] Calculating the covariance and standard deviation of the first eigenvector and each of the second eigenvectors;

[0024] The motion similarity between the first user and the other users is calculated using the covariances and the standard deviations using a correlation coefficient formula.

[0025] In one embodiment, the step of pushing the group exercise request to the other users who meet the group exercise requirements based on the exercise similarity includes:

[0026] Determining whether the similarities of the movements meet the group formation requirements;

[0027] If the movement similarity meets the group requirement, the group movement request is pushed to the users among the other users who meet the group requirement.

[0028] In one embodiment, the user motion data is collected by a smart sports watch during the user's exercise and uploaded to a client, and the client transmits the user motion data to a server for storage.

[0029] In addition, to achieve the above purpose, the present application also proposes a group exercise push system, the group exercise push system comprising:

[0030] A receiving module, configured to receive a group exercise request from a first user;

[0031] An extraction module, used to obtain the motion data of the first user and other users, and extract the motion features of the first user and other users;

[0032] a physical fitness level calculation module, used to calculate the physical fitness levels of the first user and the other users respectively according to the motion characteristics of the first user and the other users;

[0033] a similarity calculation module, configured to calculate the motion similarity between the first user and the other users based on the fitness levels of the first user and the other users;

[0034] A push module is used to push the group exercise request to the users among the other users who meet the group exercise requirement based on the similarities of the respective exercises.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a group sports pushing device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the group sports pushing method described above.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the group movement push method described above are implemented.

[0037] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the group movement push method as described above.

[0038] The embodiment of the present application provides a group exercise recommendation method, system, device, storage medium and program product, the method comprising: receiving a group exercise request from a first user; obtaining exercise data of the first user and other users, and extracting exercise features of the first user and the other users; calculating the physical fitness levels of the first user and the other users respectively according to the exercise features of the first user and the other users; calculating the exercise similarity between the first user and the other users based on the respective physical fitness levels of the first user and the other users; and pushing a group exercise request to other users who meet the group requirements based on the respective exercise similarities. The solution analyzes and counts the collected exercise data, calculates the physical fitness level of each user, and mines users with similar sports hobbies and similar physical fitness levels to conduct group exercise, providing users with more intelligent and accurate group exercise recommendations, helping users find exercise partners with similar sports interests and physical fitness levels, and improving users' sports experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application.

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1 A flowchart of the first embodiment of the group exercise recommendation method of the present application is provided;

[0042] Figure 2 A schematic diagram of the business data flow of the group exercise recommendation method provided in Example 1 of the present application;

[0043] Figure 3 A schematic diagram of a brief process of the group exercise recommendation method provided in Example 1 of the present application;

[0044] Figure 4 This is a schematic diagram of the module structure of the group exercise recommendation system according to an embodiment of the present application;

[0045] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the group exercise recommendation method in the embodiment of the present application.

[0046] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0048] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0049] The main solution of the embodiment of the present application is: receiving a group exercise request from a first user; obtaining exercise data of the first user and other users, and extracting exercise features of the first user and the other users; calculating the fitness levels of the first user and the other users respectively according to the exercise features of the first user and the other users; calculating the exercise similarity between the first user and the other users based on the fitness levels of the first user and the other users; and pushing the group exercise request to other users who meet the group exercise requirements based on the exercise similarities.

[0050] In the current data age, sports health applications such as Gudong and Yuedongquan have become widely popular and have become an important platform for the public to record and share personal sports achievements. These applications usually provide a variety of sports mode options, but they mainly focus on relatively single projects such as running, and there are no strict restrictions on the identity conditions of participants, such as age, height, weight, etc. However, although these applications provide users with basic social functions, such as publishing event information or achievements, they do not make in-depth use of users' sports data to promote deeper social interactions.

[0051] On the other hand, traditional social networking platforms such as WeChat and QQ also allow users to create groups to communicate and organize sports-related activities. However, this method requires manually inviting friends to join, which is a cumbersome process, and the members who are pulled into the group may not be interested in or suitable for the proposed sports. In addition, this method lacks precision and cannot ensure that members in the group have similar interests and sports levels, thus affecting the quality and sense of participation in team activities.

[0052] Although existing smart sports watches can collect detailed personal sports data, most manufacturers have not yet fully utilized this data for in-depth analysis to identify and connect user groups with the same interests and similar exercise habits. Current data analysis often focuses on simple indicators, fails to fully explore information in multiple dimensions such as exercise types and interest tags, and cannot make intelligent recommendations based on users' exercise intensity and physical fitness levels.

[0053] This application provides a solution that can support more than 30 sports, and each sport can collect multiple sports indicators such as heart rate, exercise duration, speed, etc. Through the integrated learning algorithm, the system can calculate the user's physical fitness level based on the user's heart rate, speed and exercise duration when running. Furthermore, the system will calculate the similarity between users based on their sports hobbies, physical fitness levels and cities, and recommend users with high similarity to participate in group sports. Compared with sports apps and social apps, this solution uses detailed sports data collected by smart sports watches for in-depth analysis and precise recommendations, ensuring the authenticity and reliability of the recommendation results, enhancing the user's sports experience, and improving the quality of social interaction.

[0054] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a smart sports watch, a mobile phone, etc., or an electronic device capable of realizing the above functions, etc. The following takes a mobile phone as an example to illustrate this embodiment and the following embodiments.

[0055] Based on this, the present application embodiment provides a group exercise recommendation method, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the group exercise recommendation method of the present application.

[0056] In this embodiment, the group exercise recommendation method includes steps S10 to S40:

[0057] Step S10, receiving a group exercise request from a first user;

[0058] It should be noted that the first user refers to the user who sends a group exercise request to the server.

[0059] Specifically, the first user actively sends a group exercise request to the server through the APP client. The server obtains the user's corresponding exercise data by receiving the group exercise request sent by the first user, which is used to calculate the physical fitness level of each user and the exercise similarity between users.

[0060] Step S20, acquiring motion data of the first user and other users, and extracting motion features of the first user and other users;

[0061] Specifically, the embodiment of the present application provides a smart sports watch, which supports more than 30 sports items such as indoor walking, outdoor walking, indoor running, outdoor running, outdoor cycling, indoor swimming, outdoor swimming, and rope skipping. For different sports, the smart sports watch can collect the wearer's sports data and extract key sports feature indicators from it, such as exercise time, calorie consumption, heart rate, exercise speed, and maximum oxygen uptake. During the data collection process, the smart sports watch not only records the user's sports data in real time, but also pushes these data to the supporting APP client at regular intervals, and finally the APP client stores these sports data in the back-end server for further analysis and use. For example, when a runner wears a smart sports watch for running, the smart sports watch will focus on collecting and analyzing the runner's maximum heart rate, 90% of the maximum heart rate, 80% of the maximum heart rate, exercise time, exercise speed, height, weight, age, and gender, and use these data as user sports features.

[0062] Through the above steps, the smart sports watch can provide detailed sports data analysis for each user, ensuring that the extracted sports features are comprehensive and accurate. These data not only help to evaluate the user's physical fitness level, but also can be used to calculate the sports similarity between users, so as to recommend other users with the same interests and similar physical fitness levels to participate in group sports.

[0063] Step S30, calculating the physical fitness levels of the first user and the other users respectively according to the motion characteristics of the first user and the other users;

[0064] It should be noted that the physical fitness level refers to a comprehensive assessment of the user's current physical condition and athletic ability based on a series of key sports indicators and physiological parameters. This level reflects the user's physical fitness level in a specific period of time and serves as an important basis for personalized exercise recommendations and group matching.

[0065] In a feasible embodiment, step S30 may further include steps S31 to S32:

[0066] Step S31, calculating the physical fitness scores of the first user and the other users respectively by using a random forest algorithm according to the motion characteristics of the first user and the other users;

[0067] It should be noted that the random forest algorithm is an algorithm that integrates multiple trees through the idea of ​​ensemble learning, and its basic unit is the decision tree.

[0068] Each decision tree is constructed based on different training samples and feature subsets. During the construction process, information gain is used to select the best features for node splitting. The information gain is calculated as follows:

[0069]

[0070] IG(Y|X)=H(Y)-H(Y|X)

[0071] Where X represents the input feature; Y is the target variable; H(Y): entropy of the target variable Y; x i represents the classification label; p(x i ) represents the category x i The probability of occurrence in the data set; H(X) represents the entropy of the set; IG(Y|X) represents the information gain; I(x i ) indicates that the feature X takes the value x i The amount of information is defined as -log2p(x i ).

[0072] Specifically, before calculating the user's physical fitness score through the random forest algorithm, the random forest needs to be trained. The random forest uses the resampling technology to repeatedly randomly extract k samples (k is generally the same as N) from the original training sample set N with replacement to generate a new training sample set, and then generates n classification trees based on the self-help sample set to form a random forest. Feature selection randomly selects some features from all features, and then compares the errors generated in different situations by training the tree model (decision trees use information gain to select features). It can detect the number of selected features determined by the intrinsic estimation error, classification ability and correlation.

[0073] Random forests are composed of multiple decision trees. The classification ability of a single tree may be very small, but after randomly generating a large number of decision trees, a test sample can select the most likely classification through the classification results of each tree after statistics. Assuming that the input sample size is N, then the sampling sample size is also N. In this way, the input samples of each tree during training are not all samples, and it is relatively less likely to overfit. Then column sampling is performed to select m features from M features (m< <M)。

[0074] After that, the sampled data is completely split to build a decision tree. In this way, a leaf node of the decision tree is either unable to continue to split, or all the samples in it point to the same category. By resampling and randomly selecting the input user movement features into the random forest, a group of decision trees with average prediction results can be combined into a random forest to achieve better prediction results (for example, each decision tree is an expert in a narrow field). In this way, there are many experts in different fields in the random forest, and the prediction results are better by referring to their comprehensive opinions. The prediction result of each decision tree is a value of 0-100. The output value of each decision tree is soft voted (averaging the prediction results) to calculate the average output of each decision tree. The average output of each decision tree is used as the size of the user's physical fitness score.

[0075] In summary, step S31 not only realizes the in-depth analysis of the user's motion characteristics through the random forest algorithm, but also provides accurate and reliable physical fitness score evaluation, thereby enhancing the user experience and sports fun.

[0076] Step S32: classifying the physical fitness levels of the first user and the other users according to the user physical fitness scores.

[0077] Specifically, after calculating the physical fitness scores of the first user and other users by the random forest algorithm in step S31, the respective physical fitness scores are divided to obtain the physical fitness levels of the first user and other users. For example, users with a physical fitness score in the range of 10-20 points are evaluated as novices, users with a physical fitness score in the range of 20-30 points are evaluated as beginners, users with a physical fitness score in the range of 30-40 points are evaluated as sports enthusiasts, users with a physical fitness score in the range of 40-65 points are evaluated as advanced athletes, and users with a physical fitness score in the range of 65-80 points are evaluated as elite athletes.

[0078] Through the above steps, the system can divide the first user and other users into different physical fitness levels according to their physical fitness scores, help users find sports partners with similar levels to themselves, promote group sports and social interaction, and thus enhance the overall sports experience.

[0079] Step S40, calculating the exercise similarity between the first user and the other users based on the physical fitness levels of the first user and the other users;

[0080] It should be noted that exercise similarity refers to the degree of similarity between exercise characteristics and habits of different users based on the user's physical fitness level.

[0081] It is worth noting that in order to identify user groups with similar sports abilities and interests, step S40 is performed to provide users with more accurate social interaction and sports partner matching recommendations.

[0082] In a feasible embodiment, step S40 may include steps S41 to S42:

[0083] Step S41, obtaining basic user information of each user, wherein the basic user information at least includes location area, age, and exercise time;

[0084] Specifically, basic information of users is collected through smart sports watches, including but not limited to location area (geographic location information of the user, such as city, province, etc.), age (such as teenagers, adults, and the elderly), exercise time (such as daily exercise frequency (how many times a week), duration of each exercise, and specific exercise time of the day), etc.

[0085] Step S42: calculating the movement similarity between the first user and the other users based on the basic information of each user and the physical fitness level corresponding to each user.

[0086] Specifically, the Pearson correlation coefficient is used to represent the exercise similarity of two athletes by combining the location area, age, running time period of each user and the physical fitness level of each user calculated in step S30:

[0087]

[0088] Where X is input variable 1 (a vector consisting of the first user's fitness level, location area, age, and exercise time); Y is input variable 2 (a vector consisting of other users' fitness level, location area, age, and exercise time); cov(X, Y) is the covariance of X and Y; μ x is the mean of X; μ y is the mean of Y; σ x is the standard deviation of X; x is the standard deviation of Y; ρx,y is the Pearson correlation coefficient.

[0089] After obtaining the final similarity value through the above formula, the user is judged whether it is suitable for group exercise according to the preset threshold M. The higher the similarity value ρx,y is, the greater the similarity between the two users in terms of exercise characteristics and habits is, and the more suitable they are for exercising together; otherwise, it means that the differences between them are large and they are not suitable for group exercise.

[0090] In addition, to further improve the accuracy of recommended group formation, the system dynamically adjusts the similarity threshold M according to user feedback and actual results to adapt to different sports types and user needs. By analyzing the actual response of users, the system can continuously optimize the threshold M to ensure more accurate and effective push. This not only improves the quality of group matching but also better meets the personalized needs of users.

[0091] Through the above steps S41 and S42, not only can the understanding of users' sports behaviors be deepened, but also a solid foundation can be laid for building a more active and personalized sports community. At the same time, this method also enables users to more easily find like-minded sports partners and enjoy a more diverse sports experience.

[0092] Step S50: Based on each of the sports similarities, push the group sports request to the users among the other users who meet the group formation requirements.

[0093] Specifically, after obtaining the sports similarity value between the first user and other users, it is determined whether the sports similarity value ρx,y between the first user and other users is greater than or equal to M (a preset threshold). If ρx,y≥M, it means that the sports similarity value between the two is relatively high, that is, it is confirmed that the user meets the group formation requirements. Therefore, the system pushes the group sports request initiated by the user wearing the smart sports watch (i.e., the first user) to the users among the other users who meet the above group sports requirements. The push notification can include detailed information such as the personal information of the initiator, the recommended sports type, time, and location. And the receiving user can choose to click "Agree" or "Reject". If the receiver clicks "Agree", they join the group sports and the group formation is successful; if they click "Reject" or do not respond, the group formation fails. If ρx,y<M, it means that the sports similarity value between the two is relatively low, that is, the user does not meet the group formation requirements. Therefore, the system does not push the group sports request to this user.

[0094] Through the above step S40, not only can targeted group sports requests be pushed according to the sports similarities of users, but also the interaction frequency and quality between users can be improved, thus bringing a more diverse sports experience to users.

[0095] The above-mentioned embodiment method specifically includes receiving a group exercise request from the first user; obtaining the exercise data of the first user and other users, and extracting the exercise features of the first user and other users; calculating the fitness levels of the first user and other users respectively according to the exercise features of the first user and other users; calculating the exercise similarity between the first user and other users based on the fitness levels of the first user and other users; and pushing the group exercise request to other users who meet the group requirements based on the exercise similarities. The solution uses an integrated learning algorithm to calculate the user's fitness level based on the collected user exercise data, and then calculates the similarity based on the sports hobbies, fitness levels, and cities, and recommends participating groups with high similarity. It provides users with more intelligent and accurate group exercise recommendations, helps users find sports partners with similar sports interests, and enhances users' sports experience.

[0096] For example, to help understand the implementation process of the group exercise recommendation method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 2 , Figure 2 A business data flow diagram of a group exercise recommendation method is provided, specifically:

[0097] This embodiment provides a group exercise recommendation system, including but not limited to a smart sports watch (a smart watch used to collect user exercise data), an APP client (the software name on Android phones and Apple phones) and a server.

[0098] In this embodiment, user 1 first initiates a group exercise request through the APP. The system server calculates the exercise similarity S between the first user and other users based on the user's physical fitness level and location area, and determines whether the similarity exceeds the preset threshold M. If the calculated similarity S is greater than or equal to the set threshold M, it is confirmed that the user meets the group requirements, so the system will send the group exercise request to the user. When the user who meets the group requirements receives the group exercise request and clicks "Agree to Join", they can successfully form a group to exercise together.

[0099] In order to ensure good results from group exercise, the similarity of users is particularly important. In particular, the athletic abilities of two sports enthusiasts should be relatively consistent, and their running time periods should be the same, so that they can be more coordinated and enjoyable when exercising together. The system calculates the similarity of exercise based on the user's past exercise data, such as heart rate, exercise duration, exercise speed and other features, and uses a random forest algorithm to evaluate the user's physical fitness level. Subsequently, the system combines factors such as physical fitness level, location area, age, etc., and uses the Pearson correlation coefficient to calculate the exercise similarity between at least two users, thereby achieving accurate matching.

[0100] Through the above-mentioned embodiment method, through the user group recommendation algorithm and dynamic optimization mechanism with high similarity in sports hobbies, not only the effect of group sports and user experience are significantly improved, but also group requests can be efficiently pushed according to the users' sports similarity, thereby improving the success rate of group sports and user satisfaction.

[0101] For example, to help understand the implementation process of the group exercise recommendation method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 3 , Figure 3 A brief flowchart of a group exercise recommendation method is provided, specifically:

[0102] With the rise of night running, running groups and other sports trends, as well as the rapid development of smart watch technology, more and more users choose to wear smart watches to exercise. This trend not only promotes the popularization of personal health management, but also gives rise to a new model of group exercise. By collecting and analyzing users' exercise data through smart watches, the system can accurately match users with similar exercise habits and abilities, thereby improving the effect of group exercise and user experience.

[0103] Among them, smart sports watches support the collection of more than 30 sports including indoor walking, outdoor walking, indoor running, outdoor running, outdoor cycling, indoor swimming, outdoor swimming, rope skipping, etc. Depending on the sport, the collected data indicators are not exactly the same. For example, smart sports watches can record the specific duration of each exercise, monitor the energy consumed during exercise, and monitor heart rate changes in real time, especially the heart rate interval distribution during high-intensity exercise (such as maximum heart rate, 90% of maximum heart rate, 80% of maximum heart rate), and record the user's pace or speed in sports with a clear concept of speed such as running and cycling, or record the user's maximum oxygen uptake during exercise. Smart sports watches will save these exercise data, and then push the saved data to the APP client at a regular interval, usually after the exercise ends or according to a set time interval (such as once an hour)

[0104] When a user initiates a group exercise in the APP, the system server will analyze the exercise data of the user and other sports enthusiasts collected by the smart sports watch to extract relevant exercise features, such as exercise time, calorie consumption, heart rate, exercise speed, and maximum oxygen uptake. Then, based on the user's past exercise data, the random forest algorithm is used to calculate the user's physical fitness level. Among them, the random forest algorithm integrates multiple decision trees through the idea of ​​ensemble learning, and each tree is built based on different training samples and feature subsets. Information gain is used to select the optimal split feature to ensure that the model can effectively capture the pattern in the data.

[0105] After the physical fitness level is determined, the user similarity is calculated based on the user's physical fitness level, location area, age, etc. The system uses the Pearson correlation coefficient to represent the exercise similarity S of two athletes. The system will first set a preset similarity threshold M to determine whether the similarity between users is high enough to recommend group exercise. If the calculated exercise similarity value S is greater than or equal to the preset threshold M, it is considered that there is a high exercise similarity between the two; if the calculated exercise similarity value S is less than the preset threshold M, it is considered that the exercise similarity between the two is low, and no group request is pushed. Past exercise data is collected through smart sports watches during user exercise, uploaded to the APP through the watch, and finally stored on the back-end server.

[0106] For users with high similarity, it means that the user meets the requirements for group formation, and the system will automatically push the group formation request to them. The push notification contains detailed information such as the initiator's personal information, the recommended exercise type, time and location. Users who receive the group formation request can choose to click "Agree" or "Reject". If the user agrees to form a group, they will join the group exercise and the group formation will be successful; if they click "Reject" or there is no response, the group formation fails.

[0107] During this period, the system also collects user feedback on push requests (such as acceptance rate, rejection reasons, etc.) in order to subsequently optimize the threshold M and push strategy to ensure that the recommendation is more accurate and effective.

[0108] Through the above-mentioned embodiment method, not only can targeted group exercise requests be pushed according to the user's exercise similarity, but also the frequency and quality of interaction between users can be improved, bringing users a richer and more diverse exercise experience. Compared with sports APPs and social APPs, based on the analysis and recommendation of data collected by smart watches, a group of people with the same interests and hobbies can exercise more realistically and enjoy the joy of exercise.

[0109] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the group exercise recommendation method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0110] This application also provides a group exercise recommendation system, please refer to Figure 4 , the group exercise recommendation system includes:

[0111] A receiving module 10, configured to receive a group exercise request from a first user;

[0112] An extraction module 20, configured to obtain motion data of a first user and other users, and extract motion features of the first user and other users;

[0113] A fitness level calculation module 30, configured to calculate the fitness levels of the first user and the other users respectively according to the motion characteristics of the first user and the other users;

[0114] A similarity calculation module 40, configured to calculate the motion similarity between the first user and the other users based on the fitness levels of the first user and the other users;

[0115] The push module 50 is configured to push the group exercise request to the users among the other users who meet the group exercise requirement based on the exercise similarities.

[0116] The group exercise recommendation system provided by the present application adopts the group exercise recommendation method in the above embodiment, which can solve the technical problem of how to provide users with more intelligent and accurate group exercise recommendations. Compared with the prior art, the beneficial effects of the group exercise recommendation system provided by the present application are the same as the beneficial effects of the group exercise recommendation method provided by the above embodiment, and other technical features of the group exercise recommendation system are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0117] The present application provides a group exercise recommendation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the group exercise recommendation method in the above-mentioned embodiment 1.

[0118] Reference below Figure 5 , which shows a schematic diagram of the structure of a group exercise recommendation device suitable for implementing the embodiment of the present application. The group exercise recommendation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The group exercise recommendation device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0119] like Figure 5As shown, the group exercise recommendation device may include a processing system 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage system 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the group exercise recommendation device are also stored. The processing system 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input system 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output system 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage system 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication system 1009. The communication system 1009 can allow the group exercise recommendation device to communicate with other devices wirelessly or by wire to exchange data. Although the group exercise recommendation device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0120] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication system, or installed from a storage system 1003, or installed from a ROM 1002. When the computer program is executed by the processing system 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0121] The group exercise recommendation device provided by the present application adopts the group exercise recommendation method in the above embodiment, which can solve the technical problem of how to provide users with more intelligent and accurate group exercise recommendations. Compared with the prior art, the beneficial effects of the group exercise recommendation device provided by the present application are the same as the beneficial effects of the group exercise recommendation method provided by the above embodiment, and the other technical features in the group exercise recommendation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0122] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0123] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0124] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the group exercise recommendation method in the above-mentioned embodiment.

[0125] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0126] The computer-readable storage medium may be included in the group exercise recommendation device; or may exist independently without being incorporated into the group exercise recommendation device.

[0127] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the group exercise recommendation device, the group exercise recommendation device enables the following: to receive a group exercise request from a first user; to obtain exercise data of the first user and other users, and to extract exercise features of the first user and other users; to calculate the physical fitness levels of the first user and other users respectively according to the exercise features of the first user and other users; to calculate the exercise similarity between the first user and other users based on the physical fitness levels of the first user and other users; and to push the group exercise request to users among other users who meet the group exercise requirements based on the exercise similarities.

[0128] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0129] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0130] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0131] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned group exercise recommendation method, and can solve the technical problem of how to provide users with more intelligent and accurate group exercise recommendations. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the group exercise recommendation method provided in the above-mentioned embodiment, and will not be repeated here.

[0132] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned group exercise recommendation method when executed by a processor.

[0133] The computer program product provided in this application can solve the technical problem of how to provide users with more intelligent and accurate group exercise recommendations. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the group exercise recommendation method provided in the above embodiment, which will not be repeated here.

[0134] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A group exercise recommendation method, characterized in that: The method comprises: receiving a group exercise request from a first user; Acquire motion data of the first user and other users, and extract motion features of the first user and other users; Calculating the physical fitness levels of the first user and the other users respectively according to the motion characteristics of the first user and the other users; Calculating the motion similarity between the first user and the other users based on the physical fitness levels of the first user and the other users; Based on the movement similarities, the group movement request is pushed to users among the other users who meet the group movement requirement.

2. The method according to claim 1, characterized in that The step of respectively calculating the physical fitness levels of the first user and the other users according to the motion characteristics of the first user and the other users comprises: Calculating the physical fitness scores of the first user and the other users respectively by using a random forest algorithm according to the motion characteristics of the first user and the other users; The physical fitness levels of the first user and the other users are divided according to the physical fitness scores.

3. The method according to claim 2, characterized in that The step of respectively calculating the physical fitness scores of the first user and the other users by using a random forest algorithm according to the motion characteristics of the first user and the other users comprises: For each user, based on the random forest algorithm, regression prediction is performed on the motion characteristics of the user to obtain a prediction result of each decision tree; Calculate the average value of all decision trees according to the prediction results of each decision tree; The average value of all decision trees is taken as the final physical fitness score.

4. The method according to claim 1, characterized in that The step of calculating the motion similarity between the first user and the other users based on the fitness levels of the first user and the other users comprises: Obtaining basic user information of each user, wherein the basic user information includes at least location area, age, and exercise time; Based on the basic information of each user and the physical fitness level corresponding to each user, the movement similarity between the first user and the other users is calculated.

5. The method according to claim 4, characterized in that The step of calculating the movement similarity between the first user and the other users based on the basic information of each user and the physical fitness level corresponding to each user comprises: Based on the basic information of each user and the physical fitness level corresponding to each user, construct a first feature vector of the first user and a second feature vector of the other users respectively; Calculating the covariance and standard deviation of the first eigenvector and each of the second eigenvectors; The motion similarity between the first user and the other users is calculated using the covariances and the standard deviations using a correlation coefficient formula.

6. The method according to any one of claims 2 to 5, characterized in that The step of pushing the group exercise request to the users among the other users who meet the group exercise requirements based on the exercise similarities comprises: Determining whether the similarities of the movements meet the group formation requirements; If the movement similarity meets the group requirement, the group movement request is pushed to the users among the other users who meet the group requirement.

7. A group sports push system, characterized in that: The system comprises: A receiving module, configured to receive a group exercise request from a first user; An extraction module, used to obtain the motion data of the first user and other users, and extract the motion features of the first user and other users; a physical fitness level calculation module, used to calculate the physical fitness levels of the first user and the other users respectively according to the motion characteristics of the first user and the other users; a similarity calculation module, configured to calculate the motion similarity between the first user and the other users based on the fitness levels of the first user and the other users; A push module is used to push the group exercise request to the users among the other users who meet the group exercise requirement based on the similarities of the respective exercises.

8. A group movement pushing device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the group sports push method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the group sports pushing method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the group sports pushing method according to any one of claims 1 to 6 are implemented.

Images