A sports training course recommendation method and system

Abstract

The present invention discloses a sports training course recommendation method and system, the method comprising: S1. presetting initial recommendation parameters of each sports training course; S2. obtaining the initial heat of each sports training course according to the initial recommendation parameters of each sports training course and performing heat sorting, which is used as the initial recommendation sorting of each sports training course; S3. real-time recording of user behavior and obtaining the user access volume and course page display duration data of each sports training course, and calculating the interactive heat of each sports training course accordingly; S4. calculating the final heat of each sports training course according to the initial heat and interactive heat of each sports training course, and re-sorting each sports training course according to the final heat to obtain the final recommendation sorting of each sports training course. The present invention can quickly and accurately recommend relevant sports training courses to users, and improve the efficiency of user rush purchase.

Description

Technical Field

[0001] The present invention belongs to the technical field of sports training course recommendation, and in particular relates to a sports training course recommendation method and system. Background Art

[0002] The existing market-oriented youth sports training model is mostly a way for sports training institutions to sell training services directly to students and parents. Through a combination of online and offline means, it is relatively convenient to realize the closed loop of youth sports training-related businesses. However, young students are still in the initial stage of trying and cultivating sports interests in various sports training programs. Their interest in a certain sport is not yet solid. There is a certain threshold for young students to pay for long-term sports training services, which limits the cultivation of young people's sports interests. The youth sports training service mode under the public welfare service model solves this problem very well, providing young people with free experience opportunities for a variety of sports, better stimulating their interest in sports and improving their physical health.

[0003] However, in this innovative youth sports training service model, the rush to buy training places is very popular, and the speed and success rate of users' rush to buy are highly correlated with the accuracy of course recommendations. Compared with the traditional market-oriented youth sports training service sales model with normalized low-frequency transactions, the calculation method and influencing factors of the course recommendation algorithm in this new public welfare model must be different. Therefore, in order to better meet actual needs, it is urgent to develop a new course recommendation method. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the prior art. The present invention provides a sports training course recommendation method and system. The present invention is based on the interpretation and calculation of relevant influencing factors in the process of snapping up sports training course places, and forms a universal sports training course recommendation algorithm to solve the problem of course recommendation accuracy in the process of snapping up free youth sports training course places, optimize the course recommendation exposure rules based on user needs, and try to shorten the time for users to locate target sports training courses during the course snapping up process, so as to assist users to quickly complete the snapping up of sports training course places.

[0005] In order to achieve the expected effect, the present invention adopts the following technical solutions:

[0006] The present invention discloses a sports training course recommendation method, comprising:

[0007] S1. Preset the initial recommended parameters for each sports training course;

[0008] S2. Obtaining the initial popularity of each sports training course according to the initial recommendation parameters of each sports training course and ranking the popularity, which serves as the initial recommendation ranking of each sports training course;

[0009] S3. Record user behavior in real time and obtain the user visits and course page display time data of each sports training course, and calculate the interaction heat of each sports training course based on this;

[0010] S4. The final heat of each sports training course is calculated according to the initial heat and interactive heat of each sports training course, and each sports training course is re-sorted according to the final heat to obtain the final recommended sorting of each sports training course.

[0011] Furthermore, the initial recommendation parameters of each sports training course include: each class location of each sports training course, the start time and end time of the course registration phase, the threshold of remaining places for course recommendation, and at least one of the number of sports training courses that the current user is interested in.

[0012] Furthermore, during the course registration stage, the initial popularity of each sports training course at each class location is calculated respectively, and the courses are sorted from high to low to obtain an initial recommended ranking of each sports training course.

[0013] Furthermore, the calculation step of the initial recommended ranking of each sports training course specifically includes:

[0014] S21. Get the preset class location data;

[0015] S22. Obtain the quota Q of each sports training course in the history of a single activity at the preset class location and the rush purchase time T1 of the preset number of quotas M, the number of registered students, the number of signed-in students, and the number of full-attendance students;

[0016] S22. Calculate the attendance rate p of each sports training course in the historical single activity at the preset class location, where the attendance rate p = number of students who signed up / number of students who registered*100%;

[0017] S23. Calculate the full attendance rate f of each sports training course in the historical single activity at the preset class location, where the full attendance rate f = number of full attendance students / number of signed-in students*100%;

[0018] S24. Calculate the popularity of each sports training course in a single historical activity at the preset class location, where the popularity of any target sports training course in a single activity = (M / T1)*A+p*B+f*C, where A, B, and C are custom weighted coefficients;

[0019] S25. Calculate the initial heat Hc of each sports training course in the current activity at the preset class location, where the initial heat Hc of the target sports training course in a single activity = (Hc1+Hc2+…+HcN) / N, Hc1, Hc2,…, HcN are the corresponding heats of the target sports training course in N activities calculated in S24.

[0020] Furthermore, the specific steps of calculating the interaction heat of each sports training course are as follows:

[0021] S31. Obtain the total number of user visits Na and the total display time of the course page for each sports training course T2;

[0022] S32. Calculate the interaction heat Hm of each sports training course, where the interaction heat Hm=Na / T2.

[0023] Furthermore, the method further comprises:

[0024] S5. Combined with the positioning data of the target user, and based on the preset first recommendation distance threshold, second recommendation distance threshold, initial recommendation parameters of each sports training course and final popularity of each sports training course, popular sports training courses are recommended and ranked to obtain the ranking of sports training courses recommended to the user.

[0025] Furthermore, the S5 specifically includes the following steps:

[0026] S51. Obtaining a preset first recommended distance threshold and a second recommended distance threshold for recommending sports training courses;

[0027] S52. Based on the positioning data of the target user, the sports training courses within the first recommended distance threshold are prioritized and ranked according to the final popularity from high to low for sports training course recommendation;

[0028] S53. After the sports training courses within the first recommended distance threshold are recommended, the sports training courses within the second recommended distance threshold are ranked in descending order according to the final popularity;

[0029] S54. Then, the final popularity of the remaining sports training courses outside the second recommended distance threshold range is ranked from high to low for sports training course recommendation;

[0030] The first recommended distance threshold range includes all locations whose distances to the location of the target user are less than or equal to the first recommended distance threshold;

[0031] The second recommended distance threshold range includes all locations whose distances from the target user's location are greater than the first recommended distance threshold and less than or equal to the second recommended distance threshold.

[0032] Furthermore, the method further comprises:

[0033] S6. During the course registration stage, the order of sports training course recommendations is optimized in real time through a popular sports training course recommendation algorithm, taking into account the real-time interactive popularity of each sports training course.

[0034] Furthermore, the S6 specifically includes the following steps:

[0035] S61. Obtain the number of times the current user visits each sports training course No and the length of time T3 that the user stays on the course page, and calculate the current user's attention K to each sports training course, where attention K = T3 / No;

[0036] S62. Obtain the number of sports training courses that the current user is interested in, sort the current user's attention to each sports training course from high to low, and recommend them in order according to the preset number of sports training courses that the current user is interested in;

[0037] S63. The popular sports training course recommendation list first recommends the sports training courses that the current user is interested in according to the preset number of sports training courses that the current user is interested in, and then recommends sports training courses according to the recommendation order in S4.

[0038] The present invention also discloses a sports training course recommendation system, comprising:

[0039] A collection module, used for collecting various data for recommending sports training courses;

[0040] The recommendation module is used to recommend sports training courses according to any of the sports training course recommendation methods described above.

[0041] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention provides a sports training course recommendation method and system. The present invention is based on the interpretation and calculation of relevant influencing factors in the process of rushing to buy places, and forms a universal course recommendation algorithm to solve the problem of course recommendation accuracy in the process of rushing to buy places for free youth sports training courses. The present invention optimizes the course recommendation exposure rules based on user needs, shortens the time for users to locate target sports training courses in the process of rushing to buy courses as much as possible, and assists users to quickly complete the process of rushing to buy places for training courses. Compared with the existing market-oriented youth sports training service model, the present invention can effectively solve the problem of low effectiveness of course recommendation in the process of rushing to buy places for youth sports training services under the public welfare service model, and can quickly and accurately recommend relevant sports training courses to users, thereby improving the efficiency of user rushing to buy. The present invention can help the application of innovative models of youth sports training, help youth sports training activities to be carried out stably and orderly, further explore and cultivate youth sports interests, improve youth training effects, and promote the healthy growth of youth. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention 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, 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 paying creative work.

[0043] Figure 1 It is a flow chart of a sports training course recommendation method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] See also Figure 1 The present invention discloses a sports training course recommendation method, comprising:

[0046] S1. Preset the initial recommendation parameters for each sports training course; preferably, the initial recommendation parameters for each sports training course include: the class location of each sports training course, the start time and end time of the course registration phase, the threshold for the remaining places for course recommendation, and at least one of the number of sports training courses that the current user is interested in.

[0047] S2. Obtain the initial popularity of each sports training course according to the initial recommendation parameters of each sports training course and rank the popularity, and use this as the initial recommendation ranking of each sports training course; preferably, during the course registration stage, calculate the initial popularity of each sports training course at each class location respectively, and rank them from high to low to obtain the initial recommendation ranking of each sports training course.

[0048] In a preferred embodiment, the step of calculating the initial recommended ranking of each sports training course specifically includes:

[0049] S21. Get the preset class location data;

[0050] S22. Obtain the quota Q of each sports training course in the historical single activity at the preset class location and the rush purchase time T1, the number of registered students, the number of signed-in students, and the number of fully attended students; preferably, M can be set to the first 50% of Q, or it can be set to other proportions, considering the course withdrawal situation. When calculating here, the value is taken according to the rush purchase data of the first 50% of the course to reduce the error;

[0051] S22. Calculate the attendance rate p of each sports training course in the historical single activity at the preset class location, where the attendance rate p = number of students who signed up / number of students who registered*100%;

[0052] S23. Calculate the full attendance rate f of each sports training course in the historical single activity at the preset class location, where the full attendance rate f = number of full attendance students / number of signed-in students*100%;

[0053] S24. Calculate the popularity of each sports training course in a historical single activity at the preset class location, where the popularity of any target sports training course in a single activity = (M / T1)*A+p*B+f*C; where A, B, and C are custom weighted coefficients, which can be adjusted according to actual needs. Preferably, A is set to 60%, B is set to 20%, and C is set to 20%.

[0054] S25. Calculate the initial heat Hc of each sports training course in the current activity at the preset class location, where the initial heat Hc of the target sports training course in a single activity = (Hc1+Hc2+…+HcN) / N, Hc1, Hc2,…, HcN are the corresponding heats of the target sports training course in N activities calculated in S24.

[0055] S3. Record user behavior in real time and obtain the user visits and course page display time data of each sports training course, and calculate the interaction heat of each sports training course based on this;

[0056] In a preferred embodiment, the specific steps of calculating the interaction heat of each sports training course are as follows:

[0057] S31. Obtain the total number of user visits Na and the total display time of the course page for each sports training course T2;

[0058] S32. Calculate the interaction heat Hm of each sports training course, where the interaction heat Hm=Na / T2.

[0059] S4. The final heat of each sports training course is calculated according to the initial heat and interactive heat of each sports training course, and each sports training course is re-sorted according to the final heat to obtain the final recommended sorting of each sports training course.

[0060] Specifically, the final heat H=initial heat Hc+interaction heat Hm.

[0061] In one embodiment, the method further comprises:

[0062] S5. Combined with the positioning data of the target user, and based on the preset first recommendation distance threshold, second recommendation distance threshold, initial recommendation parameters of each sports training course and final popularity of each sports training course, popular sports training courses are recommended and ranked to obtain the ranking of sports training courses recommended to the user.

[0063] Furthermore, the S5 specifically includes the following steps:

[0064] S51. Obtaining a preset first recommended distance threshold and a second recommended distance threshold for recommending sports training courses;

[0065] S52. Based on the positioning data of the target user, the sports training courses within the first recommended distance threshold are prioritized and ranked according to the final popularity from high to low for sports training course recommendation;

[0066] S53. After the sports training courses within the first recommended distance threshold are recommended, the sports training courses within the second recommended distance threshold are ranked in descending order according to the final popularity;

[0067] S54. Then, the final popularity of the remaining sports training courses outside the second recommended distance threshold range is ranked from high to low for sports training course recommendation;

[0068] The first recommended distance threshold range includes all locations whose distances to the location of the target user are less than or equal to the first recommended distance threshold;

[0069] The second recommended distance threshold range includes all locations whose distances from the target user's location are greater than the first recommended distance threshold and less than or equal to the second recommended distance threshold.

[0070] In another embodiment, the method further comprises:

[0071] S6. During the course registration stage, the order of sports training course recommendations is optimized in real time through a popular sports training course recommendation algorithm, taking into account the real-time interactive popularity of each sports training course.

[0072] Furthermore, the S6 specifically includes the following steps:

[0073] S61. Obtain the number of times the current user visits each sports training course No and the length of time T3 that the user stays on the course page, and calculate the current user's attention K to each sports training course, where attention K = T3 / No;

[0074] S62. Obtain the number of sports training courses that the current user is interested in, sort the current user's attention to each sports training course from high to low, and recommend them in order according to the preset number of sports training courses that the current user is interested in;

[0075] S63. The popular sports training course recommendation list first recommends the sports training courses that the current user is interested in according to the preset number of sports training courses that the current user is interested in, and then recommends sports training courses according to the recommendation order in S4.

[0076] Preferably, the method further comprises:

[0077] S7. Obtain the threshold for the remaining places for course recommendations. The order of course recommendations should follow the principle of first recommending all courses with a number greater than the threshold for the remaining places for course recommendations, and then recommending all courses with a number less than the threshold for the remaining places for course recommendations, until the registration for the event ends.

[0078] The present invention first calculates the initial popularity of different sports courses at different training sites based on historical activity data, and then calculates the course interaction popularity of related courses in real time based on the user behavior data in the registration stage, thereby calculating the course popularity data of all courses, and then calculates the recommended ranking of popular sports training courses in the activity registration stage in real time based on the preset first recommended distance threshold and second recommended distance threshold, combined with user positioning and course popularity data. Finally, in the activity registration stage, the user attention data of the current course is calculated again in combination with the behavior data of the current user in the registration stage, the ranking of the courses that the user pays attention to is obtained, a list of courses that the user pays attention to is formed, and the ranking of the recommended list of popular sports training courses is further optimized.

[0079] Compared with the existing market-oriented youth sports training service model, the present invention can effectively solve the problem of low effectiveness of course recommendation in the process of rushing to buy youth sports training service places under the public welfare service model, and can quickly and accurately recommend relevant sports training courses to users, thereby improving the efficiency of user rushing to buy. The present invention can help the application of innovative models for youth sports training, help youth sports training activities to be carried out in a stable and orderly manner, further explore and cultivate youth sports interests, improve youth training effects, and promote the healthy growth of youth.

[0080] The present invention also discloses a sports training course recommendation system, comprising:

[0081] A collection module, used for collecting various data for recommending sports training courses;

[0082] The recommendation module is used to recommend sports training courses according to any of the sports training course recommendation methods described above.

[0083] The system embodiment and the aforementioned method embodiment can be implemented one by one, and will not be described in detail here.

[0084] Based on the same inventive concept, the present invention also discloses an electronic device, which may include: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus. The processor may call the logic instructions in the memory to execute the present invention discloses a sports training course recommendation method, including:

[0085] S1. Preset the initial recommended parameters for each sports training course;

[0086] S2. Obtaining the initial popularity of each sports training course according to the initial recommendation parameters of each sports training course and ranking the popularity, which serves as the initial recommendation ranking of each sports training course;

[0087] S3. Record user behavior in real time and obtain the user visits and course page display time data of each sports training course, and calculate the interaction heat of each sports training course based on this;

[0088] S4. The final heat of each sports training course is calculated according to the initial heat and interactive heat of each sports training course, and each sports training course is re-sorted according to the final heat to obtain the final recommended sorting of each sports training course.

[0089] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0090] On the other hand, an embodiment of the present invention further provides a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, and when the program instructions are executed by a computer, the computer can perform the above-mentioned method embodiments. The present invention discloses a sports training course recommendation method, including:

[0091] S1. Preset the initial recommended parameters for each sports training course;

[0092] S2. Obtaining the initial popularity of each sports training course according to the initial recommendation parameters of each sports training course and ranking the popularity, which serves as the initial recommendation ranking of each sports training course;

[0093] S3. Record user behavior in real time and obtain the user visits and course page display time data of each sports training course, and calculate the interaction heat of each sports training course based on this;

[0094] S4. The final heat of each sports training course is calculated according to the initial heat and interactive heat of each sports training course, and each sports training course is re-sorted according to the final heat to obtain the final recommended sorting of each sports training course.

[0095] In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the present invention discloses a sports training course recommendation method provided in the above embodiments, comprising:

[0096] S1. Preset the initial recommended parameters for each sports training course;

[0097] S2. Obtaining the initial popularity of each sports training course according to the initial recommendation parameters of each sports training course and ranking the popularity, which serves as the initial recommendation ranking of each sports training course;

[0098] S3. Record user behavior in real time and obtain the user visits and course page display time data of each sports training course, and calculate the interaction heat of each sports training course based on this;

[0099] S4. The final heat of each sports training course is calculated according to the initial heat and interactive heat of each sports training course, and each sports training course is re-sorted according to the final heat to obtain the final recommended sorting of each sports training course.

[0100] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0101] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A sports training course recommendation method, characterized in that: include: S1. Preset the initial recommended parameters for each sports training course; S2. Obtaining the initial popularity of each sports training course according to the initial recommendation parameters of each sports training course and ranking the popularity, which serves as the initial recommendation ranking of each sports training course; S3. Record user behavior in real time and obtain the user visits and course page display time data of each sports training course, and calculate the interaction heat of each sports training course based on this; S4. Calculate the final heat of each sports training course according to the initial heat and interactive heat of each sports training course, and re-rank each sports training course according to the final heat to obtain the final recommended ranking of each sports training course; The initial recommendation parameters of each sports training course include: at least one of the class location of each sports training course, the start and end time of the course registration phase, the threshold of the remaining places for course recommendation, and the number of sports training courses that the current user is interested in; During the course registration stage, the initial popularity of each sports training course at each class location is calculated respectively, and the courses are sorted from high to low to obtain the initial recommended ranking of each sports training course; The calculation steps of the initial recommended ranking of each sports training course specifically include: S21. Get the preset class location data; S22. Obtain the quota Q of each sports training course in the history of a single activity at the preset class location and the rush purchase duration T1 of the preset number of quotas M, the number of registered students, the number of signed-in students, and the number of fully attended students; S22. Calculate the attendance rate p of each sports training course in the historical single activity at the preset class location, where attendance rate p = number of students who signed up / number of students who registered 100%; S23. Calculate the full attendance rate f of each sports training course in the historical single activity at the preset class location, where full attendance rate f = number of full attendance students / number of signed-in students 100%; S24. Calculate the heat of each sports training course in a historical single activity at the preset class location, where the heat of any target sports training course in a single activity = , where A, B, and C are custom weighted coefficients; S25. Calculate the initial heat Hc of each sports training course in the current activity at the preset class location, wherein the initial heat Hc of the target sports training course in a single activity = (Hc1 + Hc2 + ... + HcN) / N, Hc1, Hc2, ..., HcN are the corresponding heats of the target sports training course in N activities calculated in S24.

2. A sports training course recommendation method as claimed in claim 1, characterized in that: The specific steps of calculating the interaction heat of each sports training course are as follows: S31. Obtain the total number of user visits Na and the total display time data T2 of each sports training course; S32. Calculate the interaction heat Hm of each sports training course, where the interaction heat Hm=Na / T2.

3. A sports training course recommendation method as claimed in claim 1, characterized in that: The method further includes: S5. Combined with the positioning data of the target user, and based on the preset first recommendation distance threshold, second recommendation distance threshold, initial recommendation parameters of each sports training course and final popularity of each sports training course, popular sports training courses are recommended and ranked to obtain the ranking of sports training courses recommended to the user.

4. A sports training course recommendation method as claimed in claim 3, characterized in that: The S5 specifically includes the following steps: S51. Obtaining a preset first recommended distance threshold and a second recommended distance threshold for recommending sports training courses; S52. Based on the positioning data of the target user, the sports training courses within the first recommended distance threshold are prioritized and ranked according to the final popularity from high to low for sports training course recommendation; S53. After the sports training courses within the first recommended distance threshold are recommended, the sports training courses within the second recommended distance threshold are ranked in descending order according to the final popularity; S54. Then, the final popularity of the remaining sports training courses outside the second recommended distance threshold range is ranked from high to low for sports training course recommendation; The first recommended distance threshold range includes all locations whose distances to the location of the target user are less than or equal to the first recommended distance threshold; The second recommended distance threshold range includes all locations whose distances from the target user's location are greater than the first recommended distance threshold and less than or equal to the second recommended distance threshold.

5. A sports training course recommendation method as claimed in claim 1, characterized in that: The method further includes: S6. During the course registration stage, the order of sports training course recommendations is optimized in real time through a popular sports training course recommendation algorithm, taking into account the real-time interactive popularity of each sports training course.

6. A sports training course recommendation method as claimed in claim 5, characterized in that: The S6 specifically comprises the following steps: S61. Obtain the number of times the current user visits each sports training course No and the length of time T3 that the user stays on the course page, and calculate the current user's attention to each sports training course K, where attention K=T3 / No; S62. Obtain the number of sports training courses that the current user is interested in, sort the current user's attention to each sports training course from high to low, and recommend them in order according to the preset number of sports training courses that the current user is interested in; S63. The popular sports training course recommendation list first recommends the sports training courses that the current user is interested in according to the preset number of sports training courses that the current user is interested in, and then recommends sports training courses according to the recommendation order in S4.

7. A sports training course recommendation system, characterized in that: include: A collection module, used for collecting various data for recommending sports training courses; A recommendation module, used for recommending sports training courses according to a sports training course recommendation method according to any one of claims 1-6.

Images