Course recommendation method and device, storage medium and electronic device

Abstract

The present disclosure relates to the field of computer technology, and relates to a course recommendation method and device, storage medium and electronic device. The method comprises: collecting course behavior data, wherein the course behavior data comprises data generated by all users interacting with the course; calculating the basic score of each course according to the interactive behavior generated by each course and the time complexity factor corresponding to the interactive behavior, wherein the time complexity factor is used to identify the impact value of the interactive behavior on the degree of course audience; updating the user data of multiple dimensions of the current user according to the course learning content of the current user, and calculating the target score of each course corresponding to the current user in combination with the basic score of each course, the updated user data and the preset weight factor; determining the target course set to recommend to the current user according to the target score. The present disclosure can recommend courses to users in combination with active tendency guidance, course audience degree and user preference, and the accuracy of course recommendation is high.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and more specifically, to a course recommendation method, a course recommendation device, a computer storage medium, and an electronic device. Background Art

[0002] With the development of computer technology, online learning has become a mainstream learning method. Users can flexibly choose the location, time and content for learning. Users can download learning software through the terminal or log in to the web version to learn. In order to meet the learning needs of various users, learning software or platforms will recommend courses to users. Therefore, how to improve the accuracy of course recommendations has become one of the issues that cannot be underestimated in online learning.

[0003] The course recommendation method in the related art usually recommends courses according to the course library corresponding to the result of the user's course selection. That is, the course is strongly related to the user's choice, so that the recommended courses meet the public's preferences. However, the recommended courses may not be truly suitable for the current user. The course recommendation accuracy is low, resulting in invalid recommendations, thereby causing user loss.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the present disclosure is to provide a course recommendation method and device, a computer storage medium and an electronic device, thereby improving the accuracy of course recommendations at least to a certain extent.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to one aspect of the present disclosure, a course recommendation method is provided, comprising: collecting course behavior data, the course behavior data including data generated by all users' interaction behaviors with the course; calculating a basic score for each course according to the interaction behavior corresponding to each course and a time complexity factor corresponding to the interaction behavior, the time complexity factor being used to identify the degree of influence of the interaction behavior on the course audience; updating user data with multiple dimensions of the current user according to the course learning content of the current user, and calculating a target score for each course corresponding to the current user in combination with the basic score of each course, the updated user data and a preset weight factor; and determining a target course set to recommend to the current user according to the target score.

[0008] In an exemplary embodiment of the present disclosure, the interactive behavior includes sub-behaviors of multiple dimensions; before calculating the basic score of each course based on the interactive behavior corresponding to each course and the time complexity factor corresponding to the interactive behavior, the method also includes: determining the target operability factors corresponding to the types of multiple sub-behaviors of each course based on the correspondence between the sub-behavior type and the operability factor; and using the target operability factor as the time complexity factor corresponding to each sub-behavior.

[0009] In an exemplary embodiment of the present disclosure, the method further includes: for each of the courses, obtaining a target time decay factor corresponding to each of the sub-behaviors, and updating a time complexity factor of the corresponding sub-behavior according to the target time decay factor; wherein, obtaining the target time decay factor corresponding to each of the sub-behaviors includes: for each course, obtaining the time length from the execution time of each of the sub-behaviors to the current time, and obtaining the probability that the time length is greater than a time threshold, wherein the probability is the ratio of the number of time lengths corresponding to each of the sub-behaviors that are greater than the time threshold to the number of executions; determining the target time decay factor according to the correspondence between the probability interval and the time decay factor.

[0010] In an exemplary embodiment of the present disclosure, the basic score of each course is calculated based on the interactive behavior corresponding to each course and the time complexity factor corresponding to the interactive behavior, including: obtaining the number of executions of each of the sub-behaviors; calculating the basic score of each course based on the number of executions of each of the sub-behaviors and the corresponding time complexity factor.

[0011] In an exemplary embodiment of the present disclosure, the user data of multiple dimensions of the current user include the interaction behavior data, user attribute data and business data of the current user; updating the user data of multiple dimensions of the current user according to the course learning content of the current user, and calculating the target score of each course corresponding to the current user in combination with the basic score of each course, the updated user data and the preset weight factor, includes: determining the type of course of interest of the current user according to the course learning content, and updating the data associated with the type of course of interest in the interaction behavior data of the current user; calculating the course interaction score of each course according to the basic score of each course and the preset course interaction weight factor, the preset course interaction weight factor being included in the preset weight factor; calculating the user score of each course corresponding to the current user in combination with the basic score of each course, the user attribute data, the business data, the updated interaction behavior data, and the preset weight factor; for each course, calculating the target score according to the corresponding course interaction score and user score.

[0012] In an exemplary embodiment of the present disclosure, the user score of each course corresponding to the current user is calculated by combining the basic score of each course, user attribute data, business data, updated interaction behavior data, and a preset weight factor, including: obtaining interest tags from the user attribute data, business data, and updated interaction behavior data; determining whether there is a target course corresponding to the target interest tag, and if so, calculating the score of the target course corresponding to the target data dimension based on the weight corresponding to the target data dimension to which the target interest tag belongs and the basic score corresponding to the target course; for each course, obtaining the sum of the scores corresponding to each data dimension as the user score of each course corresponding to the current user.

[0013] In an exemplary embodiment of the present disclosure, before calculating the score of the target course corresponding to the target data dimension based on the weight corresponding to the target data dimension to which the target interest tag belongs and the basic score corresponding to the target course, the method also includes: obtaining the occurrence frequency of the target interest tag in the target data dimension to which it belongs; and adjusting the weight corresponding to the target data dimension according to the occurrence frequency.

[0014] In an exemplary embodiment of the present disclosure, when the target data dimension to which the target interest tag belongs includes business data, the score of the target course corresponding to the target data dimension is calculated according to the weight corresponding to the target data dimension to which the target interest tag belongs and the basic score corresponding to the target course, including: evaluating and determining the business capability dimension of the current user based on the business data of the current user; if the business capability dimension reaches a preset capability dimension, adding a negative sign to the score of the target course corresponding to the business data dimension of the current user.

[0015] In an exemplary embodiment of the present disclosure, before determining the target course set to recommend to the current user based on the target score, the method further includes: obtaining playback information of each course in the target course set; adjusting the sorting method of the courses in the target course set based on the playback information, and recommending the target course set to the current user according to the adjusted sorting method.

[0016] According to one aspect of the present disclosure, a course recommendation device is provided, the device comprising:

[0017] A data collection module is used to collect course behavior data, and the course behavior data includes data generated by all users' interaction with the course; a basic score calculation module is used to calculate the basic score of each course according to the interaction behavior corresponding to each course and the time complexity factor corresponding to the interaction behavior, and the time complexity factor is used to identify the impact of the interaction behavior on the audience of the course; a target score calculation module is used to update the user data of the current user with multiple dimensions according to the course learning content of the current user, and calculate the target score of each course corresponding to the current user in combination with the basic score of each course, the updated user data and the preset weight factor; a course recommendation module is used to determine the target course set to recommend to the current user according to the target score.

[0018] According to one aspect of the present disclosure, a computer storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, any one of the above-mentioned course recommendation methods is implemented.

[0019] According to one aspect of the present disclosure, there is provided an electronic device, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement a course recommendation method as described in any one of the above items.

[0020] The course recommendation method in the exemplary embodiment of the present disclosure first calculates the basic score of each course according to the interactive behavior data generated by each course and the corresponding time complexity factor; then updates the user data of multiple dimensions of the current user according to the course learning content of the current user, so as to combine the basic score of each course, the updated user data and the preset weight factor to calculate the target score of each course corresponding to the current user; finally, the target course set is determined and recommended to the current user according to the target score. On the one hand, the weight factors of the user data of multiple dimensions are configurable, which can be used to guide users to learn in different dimensions and realize the configuration management of user learning; on the other hand, the interactive behavior generated by each course is based on the interactive data of all users, so that the recommended courses meet the public preferences. On this basis, combined with the user data of multiple dimensions, it is also ensured that the recommended courses meet the personalized needs of the current user and improve the acceptability of the course recommendation; on the other hand, when calculating the basic score of each course, the time complexity factor corresponding to the interactive behavior is taken into account, and the influence of the user-course interactive behavior on the course audience over time is used as the parameter factor for calculating the basic score of each course, so as to avoid the accuracy of the course recommendation being affected by the decay of the interactive behavior data over time.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which:

[0023] Figure 1 A flow chart showing a course recommendation method according to an exemplary embodiment of the present disclosure is shown;

[0024] Figure 2 A flow chart of obtaining a target time attenuation factor according to an exemplary embodiment of the present disclosure is shown;

[0025] Figure 3 A flowchart of calculating a basic score for each course according to an exemplary embodiment of the present disclosure is shown;

[0026] Figure 4 A flowchart of calculating a target score for each course corresponding to a current user according to an exemplary embodiment of the present disclosure is shown;

[0027] Figure 5 A flowchart is shown for calculating the user score of each course corresponding to the current user by combining the basic score of each course, user attribute data, business data, updated interaction behavior data, and a preset weight factor according to an exemplary embodiment of the present disclosure;

[0028] Figure 6 A flow chart showing the application of the course recommendation method according to an exemplary embodiment of the present disclosure to a specific application scenario;

[0029] Figure 7 A schematic diagram showing the structure of a course recommendation device according to an exemplary embodiment of the present disclosure is shown;

[0030] Figure 8 A schematic diagram showing a storage medium according to an exemplary embodiment of the present disclosure; and

[0031] Fig. 9 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown.

[0032] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0033] The exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present disclosure will be more comprehensive and complete and the concepts of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the figures represent the same or similar structures, and thus their detailed description will be omitted.

[0034] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known structures, methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0035] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or these functional entities or parts of functional entities may be implemented in one or more software hardened modules, or these functional entities may be implemented in different networks and / or processor devices and / or microcontroller devices.

[0036] Online learning is an important means of personal learning, school and corporate training. It is favored by more and more people due to its freedom of space and time. Users with different professions, positions or hobbies have their own learning demands. At the same time, the popularity of each course is different. However, in the existing online learning process, course recommendations cannot combine the course audience with the user's personalized needs, resulting in the recommended courses being unable to meet the user's needs and the low course completion rate, resulting in a waste of course resources and user time and energy, reducing user experience and affecting the user retention rate of online learning platforms.

[0037] Based on this, in an exemplary embodiment of the present disclosure, a course recommendation method is first provided. Figure 1 As shown, the course recommendation method includes the following steps:

[0038] Step S110: Collecting course behavior data, which includes data generated by all users' interaction with the course;

[0039] Step S120: Calculate the basic score of each course according to the interactive behavior corresponding to each course and the time complexity factor corresponding to the interactive behavior, where the time complexity factor is used to identify the influence of the interactive behavior on the course audience level;

[0040] Step S130: updating the user data of multiple dimensions of the current user according to the course learning content of the current user, and calculating the target score of each course corresponding to the current user in combination with the basic score of each course, the updated user data and the preset weight factor;

[0041] Step S140: Determine a target course set to recommend to the current user based on the target score.

[0042] According to the course recommendation method in this example embodiment, the weight factors of user data in multiple dimensions are configurable, which can be used to guide users to learn in different dimensional directions and realize user learning configuration management; the interactive behavior generated by each course is based on the interactive data of all users, so that the recommended courses meet the public's preferences. On this basis, combined with user data in multiple dimensions, it is also ensured that the recommended courses meet the current user's personalized needs and improve the acceptability of course recommendations; when calculating the basic score of each course, the time complexity factor corresponding to the interactive behavior is taken into account, and the impact of the user's interactive behavior with the course on the degree of course audience over time is used as a parameter factor for calculating the basic score of each course, so as to avoid the accuracy of course recommendations being affected by the decay of interactive behavior data over time.

[0043] Combine the following Figure 1 A course recommendation method in an exemplary embodiment of the present disclosure is described.

[0044] In step S110 , course behavior data is collected.

[0045] In an exemplary embodiment of the present disclosure, course behavior data is strongly associated with the course, including data generated by all users' interactive behaviors with the course, and the interactive behaviors include multiple sub-dimensions, including but not limited to user's likes, dislikes, comments, forwarding and downloading of the course, and other operation sub-dimensions that can generate interactive data. Among them, each sub-behavior has a corresponding time complexity factor, and the time complexity factor is used to identify the impact value of each sub-behavior on the audience level of the course, wherein the audience level of the course refers to the popularity of the course, the higher the audience level, the higher the popularity of the course, on the contrary, the lower the audience level, the lower the popularity of the course; optionally, the larger the time complexity factor, the higher the impact value of the corresponding sub-behavior on the audience level of the course; optionally, the smaller the time complexity factor, the higher the impact value of the corresponding sub-behavior on the audience level of the course. Of course, the correlation between the size of the time complexity factor and the impact value of the corresponding sub-behavior on the audience level of the course can be determined according to actual needs, and the present disclosure does not make special restrictions on this.

[0046] In some possible implementations, before calculating the basic score of each course based on the interactive behaviors corresponding to each course and the time complexity factors corresponding to the interactive behaviors, it is also possible to determine the target operability factors corresponding to the types of multiple sub-behaviors of each course based on the correspondence between the sub-behavior types and the operability factors, and use the obtained target operability factors as the time complexity factors corresponding to each sub-behavior.

[0047] Specifically, due to the different operational complexities of different sub-behaviors, the corresponding operability factors are different. For example, "Course Forwarding" needs to first trigger the forwarding, then select the forwarding address, and finally trigger and confirm the forwarding instruction, while "Course Like" only requires one click operation. It can be seen that the operational complexity of "Course Forwarding" is higher than that of "Course Like", and the corresponding operability factors of the two are different. Therefore, the target operability factors corresponding to different types of sub-behaviors are determined according to the correspondence between the sub-behavior type and the operability factor. The correspondence between the sub-behavior type and the operability factor can be pre-configured. Optionally, the higher the operational complexity of the sub-behavior type, the larger the corresponding operability factor; optionally, the higher the operational complexity of the sub-behavior type, the smaller the corresponding operability factor. Of course, the present disclosure can select the association between the operability factor and the sub-behavior type (operation complexity) according to actual needs, and there is no special limitation on this.

[0048] In some possible implementations, it is also possible to obtain a target time decay factor corresponding to each sub-behavior for each course, and update the time complexity factor of the corresponding sub-behavior according to the target time decay factor.

[0049] Specifically, see Figure 2 , the target time decay factor corresponding to each sub-behavior can be obtained as follows:

[0050] In step S210, for each course, the time length from the execution time of each sub-behavior to the current time is obtained, and the probability that the time length is greater than the time threshold is obtained. In this exemplary embodiment, the execution time of each sub-behavior is obtained, and the time length from the execution time of each execution operation to the current time is obtained, and for any sub-behavior, the number of execution operations with a time length greater than the time threshold is counted, and the ratio of the number to the number of executions of the corresponding sub-behavior is obtained to obtain the probability that the time length is greater than the time threshold.

[0051] In step S220, the target time decay factor corresponding to the summary of any sub-behavior is determined based on the correspondence between the probability interval and the time decay factor. In an exemplary embodiment of the present disclosure, the target time decay factor corresponding to any sub-behavior is obtained based on the correspondence between the preset probability interval and the time decay factor. Optionally, the greater the probability, the greater the corresponding time decay factor; optionally, the greater the probability, the smaller the corresponding time decay factor. Of course, the correlation between the two can also be selected according to actual needs, and the present disclosure does not make any special limitation on this.

[0052] Furthermore, after obtaining the target time decay factor corresponding to each sub-behavior, the time complexity factor of the corresponding sub-behavior is updated by the target time decay factor, that is, the target operability factor of the corresponding sub-behavior is updated. Optionally, the target time decay factor can be multiplied by the target operability factor to obtain an updated time complexity factor; optionally, the time complexity factor can be updated by the following formula: time complexity factor = target operability factor e 目标时间衰减因子 ,Of course, the specific method to update the time complexity factor can be selected according to actual needs.

[0053] Tables 1 and 2 respectively show the correspondence between sub-behavior types and operability factors and the correspondence between probability intervals and time decay factors. The following is a specific example of obtaining the updated time complexity factor corresponding to any sub-behavior in combination with Tables 1 and 2.

[0054] Table 1

[0055]

[0056]

[0057] Table 2

[0058] Probability (%) [85,100] [70,85) [60,70) [50,60) [40,50) [30,40) [0,30) Time decay factor 0.8 0.7 0.6 0.5 0.4 0.3 0.2

[0059] Referring to Table 1, based on the correspondence between the sub-behavior types and the manipulability factors, the manipulability factor corresponding to the sub-behavior "Like" is 0.1, the manipulability factor corresponding to the "Comment" is 0.1, and so on. In the present disclosure, a negative sign can also be added to the obtained manipulability factor according to the negative behavioral effects of the sub-behavior types. For example, "Like", "Comment", "Download" and "Forward" have positive behavioral effects or have no obvious positive or negative behavioral effects, so no processing is done. However, "Dislike" has an obvious negative effect, so a negative sign can be added before the manipulability factor corresponding to "Dislike", that is, "-0.1". In this way, the behavioral result effects of different sub-behavior types are reflected in the manipulability factor, which can fully reflect the user's attitude towards the course when calculating the basic score of each course, making the course basic score more representative of the user.

[0060] Continuing to refer to Table 1, the ratio of the number of time lengths corresponding to the sub-behavior "Like" that is greater than the time threshold to the number of execution times is 25 / 30=83%, that is, the probability corresponding to the sub-behavior "Like" is 83%. Referring to the corresponding relationship between the probability interval and the time decay factor in Table 2, the target time decay factor corresponding to the sub-behavior "Like" is 0.7. Correspondingly, the target time decay factor corresponding to the sub-behavior "Dislike" is 0.2, indicating that in this course, the sub-behavior "Like" has a high degree of decay over time, and the sub-behavior "Like" may have little effect on the current user's choice. On the contrary, the sub-behavior "Dislike" has a low degree of decay over time, and the sub-behavior "Dislike" may have a large impact on the current user's choice. Based on this, the updated time complexity factor corresponding to the sub-behavior "Like" is 0.1 0.7 , the updated time complexity factor corresponding to the sub-behavior "Like" is -0.1 0.2 , the other sub-behaviors obtain the updated time complexity factors in the same way, which will not be repeated here.

[0061] It should be noted that the specific values ​​in Tables 1 and 2 and the methods used to update the time complexity factors are only exemplary. The specific values ​​in Tables 1 and 2 and the methods used to update the time complexity factors can also be adjusted according to actual needs. All sub-behaviors that decay to a high degree over time and whose time complexity factors after being updated based on the time decay factor show a decreasing trend to varying degrees are within the scope of protection of the present disclosure.

[0062] In an exemplary embodiment of the present disclosure, since sub-behaviors decay over time, the farther the execution time of a sub-behavior is from the current time, the smaller the impact of the sub-behavior on the current user. Therefore, by obtaining the probability that the time length from the execution time of any sub-behavior to the current time is greater than the time threshold, and based on the correspondence between the probability interval and the time decay factor, the target time decay factor corresponding to any sub-behavior is obtained, so that when considering the audience level of the course, the time decay of the sub-behavior is used as an influencing factor, so that the basic score of each course obtained is more in line with the user preferences at the current time, thereby improving the accuracy of subsequent course recommendations based on the basic score of each course.

[0063] In step S120, the basic score of each course is calculated according to the interactive behavior corresponding to each course and the time complexity factor corresponding to the interactive behavior.

[0064] In the exemplary embodiment of the present disclosure, the basic score of each course reflects the interest of all users in the course. The larger the basic score, the higher the audience of the course. As can be seen from step S110, the interactive behavior corresponding to each course includes multiple sub-behaviors, see Figure 3 A flowchart of calculating the basic score of each course according to an exemplary embodiment of the present disclosure is shown. Figure 3It can be seen that the process includes: in step S310, obtaining the number of executions of each sub-behavior; in step S320, calculating the basic score of each course according to the number of executions of each sub-behavior and the corresponding time complexity factor.

[0065] In some possible implementations, the basic score of each course can be calculated by the following formula:

[0066] A=M1×n1+M2×n2+M3×n3+……M m ×n m

[0067] Among them, A is the basic score of each course, M1 is the number of executions of sub-behavior 1 corresponding to course A, n1 is the time complexity factor corresponding to sub-behavior 1, M2 is the number of executions of sub-behavior 2 corresponding to course A, n2 is the time complexity factor corresponding to sub-behavior 2, M3 is the number of executions of sub-behavior 3 corresponding to course A, n3 is the time complexity factor corresponding to sub-behavior 3, M m is the number of executions of sub-behavior m corresponding to course A, n m is the time complexity factor corresponding to sub-behavior m, where m corresponds to the number of sub-behaviors corresponding to course A.

[0068] Through the exemplary embodiments of the present disclosure, for each course, the sub-behaviors corresponding to each course and the corresponding time complexity factor are weighted and summed to obtain the basic score of each course, which not only reflects the interest level of all users in each course, but also reflects the impact of different user behaviors on the course audience as time decays.

[0069] In step S130, the user data with multiple dimensions of the current user is updated according to the course learning content of the current user, and the target score of each course corresponding to the current user is calculated in combination with the basic score of each course, the updated user data and the preset weight factor.

[0070] In an exemplary embodiment of the present disclosure, the user data of the current user with multiple dimensions includes the interactive behavior data, user attribute data and business data of the current user. Among them, the interactive behavior data is the data that identifies the interactive correlation between the user and the course, including but not limited to interactive behaviors such as likes, comments, forwarding, sharing, stepping on, and collection. From the interactive behavior data, the user's favorite course type (or favorite course label) can be obtained, reflecting the user's interest in the course; the user attribute data is the user's personal basic information data, including but not limited to job level, subordinate personnel, position, etc.; the business data is the user's business capability data, including but not limited to business direction, business level, number of customers, business completion volume, etc.

[0071] The interest tags of the current user can be obtained through the user data with multiple dimensions. For example, if the current user clicks on a large number of courses related to the "law" type in the interactive behavior data, the interest tag of the current user "law" can be obtained; if the current user is an "administrator", "efficient management" and other data in the user attribute data, the interest tags of the current user are "management", "efficiency" and so on, and the interest tags of the current user are "health insurance", "order issuance", "number of customers" and so on in the user business data, the interest tag of the current user is "health insurance". In other words, interest tags that reflect the current needs of the user can be obtained from the interactive behavior data, user attribute data and business data of the current user.

[0072] Figure 4 A flowchart of calculating the target score of each course corresponding to the current user according to an exemplary embodiment of the present disclosure is shown. Figure 4 As shown, the process includes:

[0073] In step S410, the type of course of interest to the current user is determined according to the course learning content, and the data associated with the type of course of interest in the interactive behavior data of the current user is updated.

[0074] In an exemplary embodiment of the present disclosure, new interactive behavior data is often generated during the current user's participation in learning, which continues to affect subsequent course recommendations. Therefore, the interest course type is first determined based on the current user's course learning content, and the data associated with the interest course type in the current user's interactive behavior data is updated.

[0075] For example, the course learning content within a preset time period before the current time can be obtained; for another example, all the course learning content generated after the last update of the current user's interactive behavior data can be obtained. Subsequently, the current user's interest course type is obtained from the obtained course learning content. For example, if the current user has watched Basic Law-related videos in the obtained course learning content, the current user's interest course type is obtained as "law" and "Basic Law", and the data associated with "law" and "Basic Law" in the user's interactive behavior data is updated. If such related data does not originally exist in the user's interactive behavior data, the newly added "law" and "Basic Law" interactive data can be directly added to the current user's interactive behavior data. If there is "law" and "Basic Law" related data in the user's interactive behavior data, the newly added "law" and "Basic Law" interactive data can be directly added to the current user's interactive behavior data, and the associated data and the interactive data whose time length from the current time exceeds the time threshold can also be replaced to ensure that the current user's interactive behavior data is in line with the current user's interests and personalized data at the current moment.

[0076] In step S420, the course interaction score of each course is calculated according to the basic score of each course and the preset course interaction weight factor.

[0077] In an exemplary embodiment of the present disclosure, the preset course interaction weight factor is included in the preset weight factor, which is used to identify the degree of influence of the course interaction of each course on the target score of the course. The course interaction score of each course can be determined by multiplying the basic score of each course by the corresponding interaction weight factor. For example, if the basic score of a course A is 70 points and the preset course interaction weight factor is 30%, the course interaction score corresponding to course A is 21=70×30%.

[0078] In step S430, the user score of each course corresponding to the current user is calculated by combining the basic score of each course, user attribute data, business data, updated interaction behavior data, and preset weight factors.

[0079] In an exemplary embodiment of the present disclosure, in addition to the preset course interaction weight factor described in step 420, the preset weight factors may also include attribute weight factors corresponding to user attribute data, business weight factors corresponding to business data, and interaction weight factors corresponding to updated interaction behavior data. Including the preset course interaction weight factor, the preset weight factors may be adjusted according to actual recommendation needs. For example, in order to fully consider user attributes, user business, and user interaction behavior in recommending courses, and to weaken the impact of courses on recommended courses, the preset course interaction weight factor may be lowered, and several other preset weight factors may be increased accordingly. That is, the preset weight factors tend to be configurable and can guide user learning. For example, as a user supervisor, different preset weight factors may be configured according to the specific actual situation of the subordinates under his jurisdiction, so as to guide the subordinates to learn.

[0080] Furthermore, Figure 5 A flowchart is shown of calculating the user score of each course corresponding to the current user by combining the basic score of each course, user attribute data, business data, updated interaction behavior data, and preset weight factors according to an exemplary embodiment of the present disclosure, as shown in FIG. Figure 5 As shown, the process includes:

[0081] In step S510, interest tags are obtained from user attribute data, business data, and updated interaction behavior data.

[0082] In an exemplary embodiment of the present disclosure, interest tags reflecting the current needs of the user, such as "law", "health insurance" and "management", etc., can be obtained from the user attribute data, business data and updated interaction behavior data of the current user.

[0083] In step S520, it is determined whether there is a target course corresponding to the target interest tag. If so, the score of the target course corresponding to the target data dimension is calculated based on the weight corresponding to the target data dimension to which the target interest tag belongs and the basic score corresponding to the target course.

[0084] In an exemplary embodiment of the present disclosure, after obtaining the interest tags of the current user in step S510, it is determined in turn whether each tag has a corresponding associated course. If so, the score corresponding to the target data dimension to which the interest tag belongs is increased for the corresponding associated course. In other words, the increased score is determined based on the weight of the target data dimension to which the interest tag belongs and the basic score of the course.

[0085] For example, the target interest tag "Law" comes from the interactive behavior data dimension, and there are associated target courses A, target course B and target course C. The scores corresponding to the interactive behavior data dimension are respectively increased for these three courses, where the scores are determined based on the interactive weight factor corresponding to the interactive behavior data dimension (contained in the preset weight factor) and the basic score of each course. For example, the basic score of target course A is 70, the basic score of target course B is 75, and the basic score of target course C is 60, and the interactive weight factor corresponding to the interactive behavior data dimension is 30%. The increased scores of target course A, target course B and target course C are 70×30%=21, 75×30%=22.5, and 60×30%=18, respectively, and so on. Different courses can obtain different increased scores based on the association relationship of user interest tags.

[0086] In some possible implementations, when the target data dimension to which the target interest tag belongs includes business data, when calculating the score of the target course corresponding to the target data dimension based on the weight corresponding to the target data dimension to which the target interest tag belongs and the basic score corresponding to the target course, the business capability dimension of the current user can also be evaluated and determined based on the business data of the current user. If the business capability dimension reaches the preset capability dimension, a negative sign is added to the score of the target course corresponding to the business data dimension of the current user.

[0087] Specifically, since the score of the business data dimension reflects the current user's demand for this business-related course, if it is determined based on the current user's business data evaluation that the current user's business ability dimension reaches the preset ability dimension, the recommendation of this type of target course can be reduced. Therefore, by adding a negative sign to the score of the target course corresponding to the current user's business data dimension, the sum of the scores of each business data dimension is reduced. Correspondingly, if the current user's business ability does not reach the preset ability dimension, the recommendation of this type of target course is maintained. Therefore, the score of the target course corresponding to the current user's business data dimension is not negatively added. Therefore, by adding a negative sign or not, the possibility of the target course being recommended can be reduced or increased, thereby achieving the effect of "strengthening strengths and avoiding weaknesses".

[0088] In step S530, for each course, the sum of the scores corresponding to each data dimension is calculated as the user score of each course corresponding to the current user.

[0089] In an exemplary embodiment of the present disclosure, for each course, the sum of the scores corresponding to each data dimension is calculated as the user score of each course corresponding to the current user.

[0090] Taking Course A as an example, the basic score of Course A is 70, and the attribute weight factor corresponding to the preset user attribute data dimension is 20%, the business weight factor corresponding to the business data dimension is 20%, and the interaction weight factor corresponding to the updated interaction behavior data is 30%. Then, through step S520, it can be obtained that the score of Course A corresponding to the user attribute data dimension is 70×20%=14, the score of Course A corresponding to the business data dimension is 70×20%=14, and the score of Course A corresponding to the updated interaction behavior data dimension is 70×30%=21. Then, the user score of Course A corresponding to the current user is 14+14+21=49.

[0091] In some possible implementations, user behavior data may not exist, that is, the current user does not have any interactive data with the course. In this case, the weight corresponding to the updated interactive behavior data is empty. Optionally, the weight corresponding to the data dimension can be evenly distributed to other data dimensions and the course interaction weight factor. Taking course A as an example, the weight corresponding to the updated interactive behavior data is 30% and evenly distributed to other data dimensions and the course interaction weight factor. Then, the attribute weight factor corresponding to the user attribute data dimension is 30%, the business weight factor corresponding to the business data dimension is 30%, and the course interaction weight factor is changed from the original 30% to 40%. Optionally, the weight corresponding to the data dimension can also be evenly distributed to other data dimensions without adjusting the course interaction weight factor.

[0092] In some possible implementations, the score of each course corresponding to different data dimensions may be based on the course interaction score of the course. For example, if the course interaction weight factor of Course A is 30%, then the score of Course A corresponding to the business data dimension is 70×30%×20%=4.2, and the score of Course A corresponding to the updated interactive behavior data dimension is 70×30%×30%=6.3. Based on this, the score of Course A corresponding to each data dimension is determined on the basis of the course interaction score, so that the score takes into account both the course itself and the personalized interest needs of the current user.

[0093] Through this exemplary embodiment, a user score corresponding to each course of the current user is obtained, which reflects the user's personalized interests. A high user score indicates that the current user has a high degree of interest in the course. On the contrary, a low user score indicates that the current user has a low degree of interest in the course.

[0094] In some possible implementations, before calculating the score of the target course corresponding to the target data dimension based on the weight corresponding to the target data dimension to which the target interest tag belongs and the basic score corresponding to the target course, the frequency of occurrence of the target interest tag in the target data dimension can also be obtained, and the weight corresponding to the target data dimension can be adjusted according to the frequency of occurrence. For example, for user A, the interest tag "law" appears 5 times in the updated interaction behavior data dimension, and for user B, the interest tag "law" appears 1 time in the updated interaction behavior data dimension. Then, the weight corresponding to the updated interaction behavior data dimension of user A is adjusted to be greater than the weight of the updated interaction behavior data dimension of user B. In other words, the updated interaction behavior data dimension has a higher impact on user A than on user B. The weight of this dimension of user A is increased. Based on the adjustment of the weight of this data dimension, for each course, the score of the same data dimension is different for different users. Even if different users have the same interest tags and the target courses corresponding to the interest tags are also the same, due to the different frequencies of occurrence of the interest tags, the scores of different users are also different, thereby distinguishing the score of each course from the user dimension again.

[0095] In step S440, for each course, a target score is calculated based on the corresponding course interaction score and user score.

[0096] In an exemplary embodiment of the present disclosure, for each course, after obtaining the course interaction score and user score of the current user, the sum of the course interaction score and the user score can be calculated as the target score of each current user. Based on this, the target score of each course corresponding to the current user combines the interactive impact of the course itself with the personalized interest needs of the current user.

[0097] In some possible implementations, the target scores may be sorted in descending order to form a sequence, and the first N courses in the sequence may be obtained to form a target course set to be recommended to the current user, where N is a positive integer.

[0098] In some possible implementations, before determining the target course set to recommend to the current user based on the target score, the playback information of each course in the target course set can also be obtained, and the sorting method of the courses in the target course set can be adjusted according to the playback information, and the target course set can be recommended to the current user according to the adjusted sorting method. Among them, the playback information includes but is not limited to the completion rate of the video course (the playback completion rate of the video, that is, the number of users who have watched the video / the number of users who clicked to watch the video), the proportion of viewing time (that is, the viewing progress, the ratio of the length of the video watched by the user at the current time point to the total length of the course), the number of replays, etc. Based on this, it is possible to recommend courses with higher acceptance to the current user based on the playback information of the video course, improve the accuracy of the recommended courses, and increase the user retention of the course.

[0099] The course recommendation method disclosed in the present invention is described below in combination with specific application scenarios. Figure 6 A flowchart showing the course recommendation method disclosed in the present invention is applied to a specific application scenario, such as Figure 6 First, the administrator is the manager of the current user. For example, in the insurance industry, the administrator manages different agents. The administrator can guide agents to learn courses by configuring preset weight factors and adjusting the tendency of course recommendations. The process specifically includes:

[0100] In step S610, course behavior data is collected and stored; in step S620, user attribute data of the current user is collected; in step S630, interaction behavior data of the current user is collected, and in step S640, business data of the current user is collected; in step S650, the administrator configures a preset weight factor; wherein, the execution order of steps S610 to S650 is not executed according to the step number, but can also be flexibly adjusted, or executed simultaneously, and the present disclosure does not make any special limitation on this.

[0101] In step S660, based on the course recommendation method disclosed in the present invention and the course behavior data and user data collected in steps S610 to S650 and the preset weight factors, the target score of each course corresponding to the current user is calculated, and the courses are sorted according to the target scores to form a sequence and recommended to the current user; in step S670, the current user studies according to the course recommendation and generates new interaction behavior data; in step S680, the interaction behavior data is updated according to the learning content of the current user so as to be applied to step S660 to readjust the course recommendation results, so that the target course set recommended to the current user is the best at the current moment.

[0102] In the process of recommending course sets to users, they can be in the form of a feed stream (an interface for receiving updates from information sources) so that current users can learn continuously.

[0103] According to the course recommendation method in this example embodiment, the weight factors of user data in multiple dimensions are configurable, which can be used to guide users to learn in different dimensional directions and realize user learning configuration management; the interactive behavior generated by each course is based on the interactive data of all users, so that the recommended courses meet the public's preferences. On this basis, combined with user data in multiple dimensions, it is also ensured that the recommended courses meet the current user's personalized needs and improve the acceptability of course recommendations; when calculating the basic score of each course, the time complexity factor corresponding to the interactive behavior is taken into account, and the impact of the user's interactive behavior with the course on the degree of course audience over time is used as a parameter factor for calculating the basic score of each course, so as to avoid the accuracy of course recommendations being affected by the decay of interactive behavior data over time.

[0104] In addition, in an exemplary embodiment of the present disclosure, a course recommendation device is also provided. Figure 7 As shown, the course recommendation device 700 may include a data collection module 710, a basic score calculation module 720, a target score calculation module 730, and a course recommendation module 740. Specifically,

[0105] The data collection module 710 is used to collect course behavior data, which includes data generated by all users' interaction with the course;

[0106] A basic score calculation module 720 is used to calculate the basic score of each course according to the interactive behavior corresponding to each course and the time complexity factor corresponding to the interactive behavior, where the time complexity factor is used to identify the influence of the interactive behavior on the degree of course audience;

[0107] The target score calculation module 730 is used to update the user data of the current user with multiple dimensions according to the course learning content of the current user, and calculate the target score of each course corresponding to the current user in combination with the basic score of each course, the updated user data and the preset weight factor;

[0108] The course recommendation module 740 is used to determine a target course set according to the target score and recommend it to the current user.

[0109] In an exemplary embodiment of the present disclosure, the interactive behavior includes sub-behaviors of multiple dimensions; the course recommendation device 700 of the present disclosure may also include:

[0110] A target operability factor determination module is used to determine the target operability factors corresponding to the types of multiple sub-behaviors of each course according to the corresponding relationship between the sub-behavior types and the operability factors;

[0111] The time complexity factor determination module is used to use the target operability factor as the time complexity factor corresponding to each sub-behavior.

[0112] In an exemplary embodiment of the present disclosure, the course recommendation device 700 of the present disclosure may further include:

[0113] The time complexity factor updating module is used to obtain the target time decay factor corresponding to each sub-behavior for each course, and update the time complexity factor of the corresponding sub-behavior according to the target time decay factor;

[0114] Wherein, the time complexity factor updating module may also include:

[0115] A probability acquisition unit is used to obtain the time length from the execution time of each sub-behavior to the current time for each course, and obtain the probability that the time length is greater than the time threshold, which is the ratio of the number of time lengths corresponding to each sub-behavior greater than the time threshold to the number of executions;

[0116] The target time decay factor determination unit is used to determine the target time decay factor corresponding to the probability of each sub-behavior according to the corresponding relationship between the probability interval and the time decay factor.

[0117] In an exemplary embodiment of the present disclosure, the basic score calculation module 720 may include:

[0118] An execution count acquisition unit is used to acquire the execution count of each sub-behavior;

[0119] The basic score calculation unit is used to calculate the basic score of each course according to the number of executions of each sub-behavior and the corresponding time complexity factor.

[0120] In an exemplary embodiment of the present disclosure, the user data of the current user with multiple dimensions includes the interaction behavior data, user attribute data and business data of the current user; the target score calculation module 730 may include:

[0121] A data updating unit, used to determine the type of course of interest to the current user according to the course learning content, and to update the data associated with the type of course of interest in the interactive behavior data of the current user;

[0122] A course interaction score calculation unit, used to calculate the course interaction score of each course according to the basic score of each course and a preset course interaction weight factor, wherein the preset course interaction weight factor is included in the preset weight factor;

[0123] A user score calculation unit, used to calculate the user score of each course corresponding to the current user by combining the basic score of each course, user attribute data, business data, updated interaction behavior data, and a preset weight factor;

[0124] The target score calculation unit is used to calculate the target score for each course based on the corresponding course interaction score and user score.

[0125] In an exemplary embodiment of the present disclosure, the target score calculation module 730 may further include:

[0126] An interest tag acquisition unit, used to acquire interest tags from user attribute data, business data, and updated interaction behavior data;

[0127] A data dimension score calculation unit is used to determine whether there is a target course corresponding to the target interest tag. If so, the score of the target course corresponding to the target data dimension is calculated according to the weight corresponding to the target data dimension to which the target interest tag belongs and the basic score corresponding to the target course;

[0128] The user score calculation unit is also used to obtain the sum of the scores corresponding to each data dimension for each course as the user score of each course corresponding to the current user.

[0129] In an exemplary embodiment of the present disclosure, the target score calculation module 730 may further include:

[0130] A frequency acquisition unit, used to acquire the occurrence frequency of the target interest tag in the corresponding target data dimension;

[0131] The weight adjustment unit is used to adjust the weight corresponding to the target data dimension according to the frequency of occurrence.

[0132] In an exemplary embodiment of the present disclosure, the target score calculation module 730 may further include:

[0133] A business capability dimension evaluation unit, used to evaluate and determine the business capability dimension of the current user based on the business data of the current user;

[0134] The data processing unit is used to add a negative sign to the score of the business data dimension of the target course corresponding to the current user if the business capability dimension reaches the preset capability dimension.

[0135] In an exemplary embodiment of the present disclosure, the course recommendation device of the present disclosure may further include:

[0136] The playback information acquisition module is used to obtain the playback information of each course in the target course set;

[0137] The sorting adjustment module is used to adjust the sorting method of the courses in the target course set according to the playback information, and recommend the target course set to the current user according to the adjusted sorting method.

[0138] Since the functional modules of the course recommendation device of the exemplary embodiment of the present disclosure are the same as those in the above-mentioned course recommendation method in the inventive embodiment, they will not be described in detail here.

[0139] It should be noted that, although several modules or units of the course recommendation device are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0140] In addition, in the exemplary embodiment of the present disclosure, a computer storage medium capable of implementing the above method is also provided. A program product capable of implementing the above method of this specification is stored thereon. In some possible embodiments, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to perform the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of this specification.

[0141] refer to Figure 8 As shown, a program product 800 for implementing the above method according to an exemplary embodiment of the present disclosure is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0142] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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.

[0143] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0144] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0145] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0146] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided. It will be appreciated by those skilled in the art that various aspects of the present disclosure may be implemented as a system, method, or program product. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which may be collectively referred to herein as a "circuit", "module", or "system".

[0147] Refer to the following Fig. 9 hereinafter describes an electronic device 900 according to such an embodiment of the present disclosure. Fig. 9 The electronic device 900 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0148] like Fig. 9As shown, the electronic device 900 is in the form of a general computing device. The components of the electronic device 900 may include, but are not limited to: the at least one processing unit 910, the at least one storage unit 920, a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910), and a display unit 940.

[0149] The storage unit stores program codes, which can be executed by the processing unit 910, so that the processing unit 910 executes the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0150] The storage unit 920 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 9201 and / or a cache storage unit 9202 , and may further include a read-only storage unit (ROM) 9203 .

[0151] The storage unit 920 may also include a program / utility 9204 having a set (at least one) of program modules 9205, such program modules 9205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0152] Bus 930 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0153] The electronic device 900 may also communicate with one or more external devices 1000 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 900, and / or communicate with any device that enables the electronic device 900 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 950. Furthermore, the electronic device 900 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 960. As shown, the network adapter 960 communicates with other modules of the electronic device 900 via a bus 930. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0154] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0155] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0156] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0157] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A course recommendation method, characterized in that: include: Collecting course behavior data, which includes data generated by all users' interaction with the course; Calculate the basic score of each course according to the interactive behavior corresponding to each course and the time complexity factor corresponding to the interactive behavior, wherein the time complexity factor is used to identify the influence of the interactive behavior on the degree of course audience; Update the user data of the current user with multiple dimensions according to the course learning content of the current user, and calculate the target score of each course corresponding to the current user in combination with the basic score of each course, the updated user data and the preset weight factor; Determine a target course set according to the target score and recommend it to the current user; The user data of the current user with multiple dimensions includes the interaction behavior data, user attribute data and business data of the current user; The step of calculating the target score of each course corresponding to the current user by combining the basic score of each course, the updated user data and the preset weight factor comprises: Calculating the course interaction score of each course according to the basic score of each course and a preset course interaction weight factor, wherein the preset course interaction weight factor is included in the preset weight factor; Calculate the user score of each course corresponding to the current user by combining the basic score of each course, the user attribute data, the business data, the updated interactive behavior data, and the preset weight factor; For each course, the target score is calculated based on the corresponding course interaction score and user score.

2. The method according to claim 1, characterized in that The interactive behavior includes sub-behaviors in multiple dimensions; Before calculating the basic score of each course according to the interactive behavior corresponding to each course and the time complexity factor corresponding to the interactive behavior, the method further includes: According to the correspondence between sub-behavior types and manipulability factors, the target manipulability factors corresponding to the types of multiple sub-behaviors of each course are determined; The target operability factor is used as the time complexity factor corresponding to each sub-behavior.

3. The method according to claim 2, characterized in that The method further comprises: for each of the courses, obtaining a target time decay factor corresponding to each of the sub-behaviors, and updating a time complexity factor of the corresponding sub-behavior according to the target time decay factor; Wherein, obtaining the target time attenuation factor corresponding to each of the sub-behaviors includes: For each course, obtain the time length from the execution time of each sub-behavior to the current time, and obtain the probability that the time length is greater than the time threshold, where the probability is the ratio of the number of time lengths corresponding to each sub-behavior greater than the time threshold to the number of executions; According to the corresponding relationship between the probability interval and the time decay factor, the target time decay factor corresponding to the probability of each sub-behavior is determined.

4. The method according to claim 2, characterized in that: Calculating the basic score of each course according to the interactive behavior corresponding to each course and the time complexity factor corresponding to the interactive behavior includes: Get the number of executions of each of the sub-behaviors; The basic score of each course is calculated according to the number of executions of each sub-behavior and the corresponding time complexity factor.

5. The method according to claim 1, characterized in that The updating of the user data of multiple dimensions of the current user according to the course learning content of the current user includes: The type of course of interest to the current user is determined according to the course learning content, and data associated with the type of course of interest in the interactive behavior data of the current user is updated.

6. The method according to claim 5, characterized in that The calculating the user score of each course corresponding to the current user by combining the basic score of each course, the user attribute data, the business data, the updated interaction behavior data, and the preset weight factor includes: Obtaining interest tags from the user attribute data, business data, and updated interaction behavior data; Determine whether there is a target course corresponding to the target interest tag. If so, calculate the score of the target course corresponding to the target data dimension according to the weight corresponding to the target data dimension to which the target interest tag belongs and the basic score corresponding to the target course; For each course, the sum of the scores corresponding to each data dimension is calculated as the user score of each course corresponding to the current user.

7. The method according to claim 6, characterized in that When the target data dimension to which the target interest tag belongs includes business data, calculating the score of the target course corresponding to the target data dimension according to the weight corresponding to the target data dimension to which the target interest tag belongs and the basic score corresponding to the target course includes: Evaluate and determine the business capability dimension of the current user according to the business data of the current user; If the business capability dimension reaches the preset capability dimension, a minus sign is added to the score of the target course corresponding to the business data dimension of the current user.

8. A course recommendation device, characterized in that: The course recommendation device comprises: A data collection module is used to collect course behavior data, wherein the course behavior data includes data generated by all users' interaction with the course; A basic score calculation module, used to calculate the basic score of each course according to the interactive behavior corresponding to each course and the time complexity factor corresponding to the interactive behavior, wherein the time complexity factor is used to identify the influence of the interactive behavior on the degree of course audience; A target score calculation module is used to update the user data of the current user with multiple dimensions according to the course learning content of the current user, and calculate the target score of each course corresponding to the current user in combination with the basic score of each course, the updated user data and a preset weight factor; A course recommendation module, used to determine a target course set according to the target score and recommend it to the current user; The user data of the current user with multiple dimensions includes the interaction behavior data, user attribute data and business data of the current user; The target score calculation module is configured to execute: Calculating the course interaction score of each course according to the basic score of each course and a preset course interaction weight factor, wherein the preset course interaction weight factor is included in the preset weight factor; Calculate the user score of each course corresponding to the current user by combining the basic score of each course, the user attribute data, the business data, the updated interactive behavior data, and the preset weight factor; For each course, the target score is calculated based on the corresponding course interaction score and user score.

9. A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the course recommendation method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the course recommendation method as described in any one of claims 1 to 7.

Images