Recommended method, device, electronic equipment and storage medium

Abstract

The application provides a recommendation method and device, electronic equipment and a storage medium. The method comprises: obtaining course customization information of a user, wherein the course customization information comprises at least one of course category information, course keyword information and reference object information; determining an initial target course and historical learning data of the initial target course according to the course customization information, wherein the historical learning data comprises historical learning time and historical learning duration of each time of learning the initial target course; determining a target course in the initial target course according to the historical learning data of the initial target course; and generating course recommendation information according to the target course, and displaying the course recommendation information in a display interface of a learning platform after the user logs in the learning platform. The method improves the accuracy of recommended courses.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and particularly relates to a recommendation method and device, electronic equipment and storage medium. BACKGROUND

[0002] The learning platform is based on internet technology, adopts an open online learning platform mode, takes learning resources as a core, meets various training scene needs of enterprises, constructs an enterprise internal training ecological system, and helps enterprises to realize talent leading. With popularization and deep application of the internet, the enterprise online learning platform has become an important way for internal education and knowledge sharing.

[0003] At present, when the existing learning platform pushes a course, the existing learning platform generally pushes a related course to a user according to click quantity of other users within a period of time or attribute information of the user.

[0004] However, when the existing learning platform pushes a course, the existing learning platform has the problem of low accuracy of related course pushing. SUMMARY

[0005] The present application provides a recommendation method and device, electronic equipment and storage medium, to solve the problem of low accuracy of course pushing.

[0006] In a first aspect, the present application provides a recommendation method, comprising:

[0007] obtaining course customization information of a user, wherein the course customization information comprises at least one of course category information, course keyword information and reference object information;

[0008] determining an initial target course and historical learning data of the initial target course according to the course customization information, wherein the historical learning data comprises historical learning time and historical learning duration of each time of learning the initial target course;

[0009] determining a target course in the initial target course according to the historical learning data of the initial target course;

[0010] generating course recommendation information according to the target course, so as to display the course recommendation information in a display interface of a learning platform after the user logs in the learning platform.

[0011] In the present application, the course customization information comprises course category information, and the target course in the initial target course is determined according to the historical learning data of the initial target course, comprising:

[0012] determining activity information of the initial target course according to the historical learning data of the initial target course, wherein the activity information represents activity of learning the initial target course;

[0013] According to the activity information of the initial target course, a target course in the initial target course is determined.

[0014] In the present application, according to the historical learning data of the initial target course, the activity information of the initial target course is determined, comprising:

[0015] The current time is obtained.

[0016] According to the current time, the historical learning time segment is determined.

[0017] According to the historical learning data of the initial target course, the learning times and the learning duration are determined, the learning times being the total learning times of the initial target course in the historical learning time segment, and the learning duration being the total learning duration of the initial target course in the historical learning time segment.

[0018] According to the relationship between the historical learning time segment, the learning times and the preset learning times threshold, and the relationship between the learning duration and the preset learning duration threshold, the activity information of the initial target course is determined.

[0019] In the present application, when the historical learning time segment is more than two, according to the relationship between the historical learning time segment, the learning times and the preset learning times threshold, and the relationship between the learning duration and the preset learning duration threshold, the activity information of the initial target course is determined, comprising:

[0020] According to the relationship between the historical learning time segment, the learning times and the preset learning times threshold, and the relationship between the learning duration and the preset learning duration threshold, the initial activity information of the initial target course in each historical learning time segment is determined.

[0021] The initial activity information is weighted and summed to obtain the activity information of the initial target course.

[0022] In the present application, the course customization information is the course keyword information, according to the historical learning data of the initial target course, a target course in the initial target course is determined, comprising:

[0023] According to the historical learning data of the initial target course, the time limit information of the initial target course is determined, the time limit information representing the effective time limit for learning the initial target course.

[0024] According to the time limit information of the initial target course, a target course in the initial target course is determined.

[0025] In the present application, according to the historical learning data of the initial target course, the time limit information of the initial target course is determined, comprising:

[0026] According to the historical learning data of the initial target course, total learning times, total learning duration, and average learning time points of each learning of the initial target course are determined.

[0027] According to the relationship between the total learning times and the preset learning times threshold, the relationship between the total learning duration and the preset learning duration threshold, and the average learning time points, time limit information of the initial target course is determined.

[0028] In the present application, according to the historical learning data of the initial target course, total learning times, total learning duration, and average learning time points of each learning of the initial target course are determined, including:

[0029] According to the historical learning data of the initial target course, learning time of each learning of the initial target course, total learning times and total learning duration of learning the initial target course are determined.

[0030] The time difference between the learning time of each learning of the initial target course and the current time is determined.

[0031] According to the total learning times, the time difference is weighted and averaged to obtain the average learning time points.

[0032] In the present application, the course customization information is the reference object information, and according to the course customization information, the initial target course and the historical learning data of the initial target course are determined, including:

[0033] According to the course customization information, the reference object and the historical record data of the reference object are determined.

[0034] According to the historical record data of the reference object, the initial target course and the historical learning data of the initial target course are determined.

[0035] In the present application, according to the historical learning data of the initial target course, the target course in the initial target course is determined, including:

[0036] According to the historical learning data of the initial target course, the online time, learning times, learning duration, and total learning times and total learning duration of the initial target course are determined, the learning times are the total learning times of the initial target course in the historical learning time segment, and the learning duration is the total learning duration of the initial target course in the historical learning time segment.

[0037] According to the online time, learning times, learning duration, and total learning times and total learning duration of the initial target course, the target course in the initial target course is determined.

[0038] In the present application, the target course in the initial target course is determined according to the online time of the initial target course, the learning times, the learning time length, and the total learning times and the total learning time length, and includes:

[0039] The first score is determined according to the relationship between the learning times and the preset learning times threshold;

[0040] The second score is determined according to the relationship between the learning time length and the preset learning time length threshold;

[0041] The third score is determined according to the relationship between the total learning times and the preset total learning times threshold;

[0042] The fourth score is determined according to the relationship between the total learning time length and the preset total learning time length threshold;

[0043] The target course in the initial target course is determined according to the online time of the initial target course, the first score, the second score, the third score and the fourth score.

[0044] In the present application, the target course in the initial target course is determined according to the online time of the initial target course, the first score, the second score, the third score and the fourth score, and includes:

[0045] The target course to be screened in the initial target course is determined according to the online time of the initial target course, the first score, the second score, the third score and the fourth score;

[0046] The target reference object and the attribute data of the target reference object are determined according to the target course to be screened;

[0047] The target course in the target course to be screened is determined according to the attribute data of the target reference object and the user attribute data of the user.

[0048] In a second aspect, the present application provides a recommendation device, which includes:

[0049] The acquisition module is configured to acquire the course customization information of the user, wherein the course customization information includes at least one of the course category information, the course keyword information and the reference object information;

[0050] The first determination module is configured to determine the initial target course and the historical learning data of the initial target course according to the course customization information, wherein the historical learning data includes the historical learning time and the historical learning time length of each time of learning the initial target course;

[0051] The second determination module is configured to determine the target course in the initial target course according to the historical learning data of the initial target course;

[0052] The generating module is configured to generate course recommendation information according to the target course, so as to display the course recommendation information in a display interface of the learning platform after the user logs in the learning platform.

[0053] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory connected with the processor in communication;

[0054] The memory stores computer execution instructions.

[0055] The processor executes the computer execution instructions stored in the memory to implement the recommendation method of the present application.

[0056] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the recommendation method of the present application.

[0057] The recommendation method, device, electronic device and storage medium provided by the present application can obtain the course learning intention of the user, obtain the initial target course, and determine the final target learning course according to the historical learning data of the initial target course, so as to achieve the effect of accurately recommending courses. BRIEF DESCRIPTION OF DRAWINGS

[0058] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the present application.

[0059] Figure 1 The flowchart of the recommendation method provided by the embodiment of the present application is shown in the figure.

[0060] Figure 2 The flowchart of another recommendation method provided by the embodiment of the present application is shown in the figure.

[0061] Figure 3 The structure diagram of the recommendation device provided by the embodiment of the present application is shown in the figure.

[0062] Figure 4 The structure diagram of the electronic device provided by the embodiment of the present application is shown in the figure.

[0063] The specific embodiments of the application have been shown and described in the above drawings and the following description. These drawings and description are not meant to limit the scope of the inventive concept in any way but are merely meant to illustrate the inventive concept to one skilled in the art by reference to particular embodiments. DETAILED DESCRIPTION

[0064] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The same numbers are used in different drawings to represent the same or similar elements. The following detailed description is not meant to limit the application in any way but is merely meant to illustrate the application with respect to particular embodiments.

[0065] At present, when a learning platform makes course recommendation, it generally recommends courses according to the click volume of the courses in the adjacent time period, which may result in that the recommended courses are not in accordance with the user's demand, thereby reducing the accuracy of course recommendation.

[0066] To solve the above problem, the application provides a recommendation method, which can acquire course customization information of a user, thereby acquiring an initial target course from a learning platform according to the user's demand, and then acquiring historical learning data of the initial target course, and determining a target course of the initial target course according to the historical learning data, thereby achieving the effect of accurately recommending courses.

[0067] The technical solutions of the application and how the technical solutions solve the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the application will be described below with reference to the drawings.

[0068] The execution subject of the recommendation method provided by the embodiments of the application can be a server. The server can be a mobile phone, a tablet computer, a computer or the like. The embodiments of the application do not particularly limit the implementation of the execution subject, as long as the execution subject can acquire course customization information of a user, wherein the course customization information includes at least one of course category information, course keyword information and reference object information; determine an initial target course and historical learning data of the initial target course according to the course customization information, wherein the historical learning data includes historical learning time and historical learning duration of each time of learning the initial target course; determine a target course in the initial target course according to the historical learning data of the initial target course; and generate course recommendation information according to the target course, so as to display the course recommendation information in a display interface of a learning platform after the user logs in the learning platform.

[0069] Machine Learning (ML) is a multi-disciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, computational complexity theory, etc. Machine Learning is the core of artificial intelligence and the fundamental approach to making computers intelligent. It is applied in various fields of artificial intelligence. Machine Learning and Deep Learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and teaching learning.

[0070] Figure 1 A flowchart of a recommendation method provided by the embodiments of the present application is shown. The execution subject of the method can be a server or other server, and the embodiments are not particularly limited here, such as the method shown in Figure 1 The method can include:

[0071] S101, obtaining course customization information of a user, wherein the course customization information includes at least one of course category information, course keyword information, and reference object information.

[0072] The course customization information can refer to customization information input by the user according to his / her own needs in response to the learning platform. The course customization information can include course category information, course keyword information, and reference object information, wherein the course category information can refer to the specific category of the course, such as the course category information input by the user, which can be a course of scientific and technological innovation, or a course of network construction, etc. The course keyword information can refer to the keyword of the course, such as the course keyword information input by the user, which can be keywords such as network optimization or data mining. The reference object information can be the learning content of a specific group of users that the user wants to refer to in the learning process, such as the reference object information input by the user, which can be users in the same professional position or users in a certain department.

[0073] Obtaining the course customization information of the user can be that the learning platform shows an information input interface to the user, and the user inputs at least one of the course category information, the course keyword information, and the reference object information according to his / her own needs in the information input interface. Thus, in response to the input of the user, the learning platform obtains the course customization information of the user.

[0074] S102, determining an initial target course and historical learning data of the initial target course according to the course customization information, wherein the historical learning data includes historical learning time and historical learning duration of each time of learning the initial target course.

[0075] The initial target course can be an initial target course selected from the courses stored in the learning platform according to the course customization information. For example, when the course customization information is course category information, the initial target course can be a course belonging to the course category information; when the course customization information is course keyword information, the initial target course can be a course containing the course keyword information; and when the course customization information is reference object information, the initial target course can be a course learned by the reference object.

[0076] The historical learning data can be data of each time when the initial target course is learned, and the historical learning data includes historical learning time and historical learning duration of each time when the initial target course is learned. For example, the historical learning data of the initial target course can be {x year y month z day, a time-b time}.

[0077] In S103, a target course in the initial target course is determined according to the historical learning data of the initial target course.

[0078] The target course can refer to a target course selected from the initial target course according to the historical learning data. In some embodiments, a course with a large amount of learning and close to the current time can be selected from the learning platform according to the time of the historical learning data.

[0079] In the embodiments of the present application, the course customization information includes course category information, and the method of determining the target course in the initial target course according to the historical learning data of the initial target course can include:

[0080] According to the historical learning data of the initial target course, the activity information of the initial target course is determined, and the activity information represents the activity of learning the initial target course.

[0081] According to the activity information of the initial target course, the target course in the initial target course is determined.

[0082] The activity information can represent the activity of learning the initial target course. The higher the activity is, the greater the amount of learning of the initial target course close to the current time is, and the more likely the course is a course that the user needs to learn.

[0083] After the activity information is determined, the target course in the initial target course can be determined according to whether the activity of the initial target course meets a preset activity condition or according to the activity sorting of the initial target course.

[0084] In the embodiments of the present application, the method of determining the activity information of the initial target course according to the historical learning data of the initial target course can include:

[0085] The current time is obtained.

[0086] Based on the current time, determine the time segments for historical learning;

[0087] Based on the historical learning data of the initial target course, the number of learning sessions and the learning duration are determined. The number of learning sessions is the total number of times the initial target course is learned within the historical learning time segments, and the learning duration is the total learning duration of the initial target course within the historical learning time segments.

[0088] Based on the relationship between historical learning time segments, the number of learning sessions and the preset learning session threshold, and the relationship between learning duration and the preset learning duration threshold, the activity information of the initial target course is determined.

[0089] The historical learning time segmentation can be a time period divided based on the current time and the historical learning time. In this embodiment, after determining the current time and the historical learning time, several time points T0, T1, T2, ..., T can be selected from the earliest historical learning time and the current time. j ... T J Where T0 can be the current time point, T1 can be the time point closest to the current time point T0, and T... J This can be the time point furthest from the current time point T0. Historical learning time segments can be T1, T2, ..., T... j ... T J The time segment is T0. In some embodiments, the historical learning time segment can be a time segment from T0 to T1.

[0090] The number of learning sessions can refer to the sum of all learning sessions within a historical learning time segment.

[0091] Learning duration can refer to the sum of all learning durations within a historical learning time segment.

[0092] The relationship between the number of learning sessions and a preset learning session threshold can be the ratio of the number of learning sessions to the preset learning session threshold. The relationship between the learning duration and a preset learning duration threshold can be the ratio of the learning duration to the preset learning duration threshold. In this embodiment, when there are two or more historical learning time segments, the method for determining the activity information of the initial target course based on the historical learning time segments, the relationship between the number of learning sessions and the preset learning session threshold, and the relationship between the learning duration and the preset learning duration threshold may include:

[0093] Based on the relationship between historical learning time segments, the number of learning sessions and the preset learning session threshold, and the relationship between learning duration and the preset learning duration threshold, the initial activity information of the initial target course within each historical learning time segment is determined.

[0094] The initial activity information is weighted and summed to obtain the initial target course activity information.

[0095] In the embodiments of the present application, the initial target course activity information is determined according to the historical learning time segment, the relationship between the learning frequency and the preset learning frequency threshold, and the relationship between the learning time length and the preset learning time length threshold, which can be determined by the formula:

[0096]

[0097] A j may be an adjustment coefficient, which can be set to 1 in the embodiments of the present application;

[0098] LT i，j may be the learning time length of the initial target course within the historical learning time segment [T j , T0];

[0099] LN i，j may be the learning frequency of the initial target course within the historical learning time segment [T j , T0];

[0100] LT 0，j may be the preset learning time length threshold within the historical learning time segment [T j , T0];

[0101] LN 0，j may be the preset learning frequency threshold within the historical learning time segment [T j , T0]. Through , the closer to the current time the historical learning time segment is, the higher the proportion is, and thus the more recent the learning time is, and the higher the proportion is, thereby improving the recommendation effect.

[0102] In the embodiments of the present application, after obtaining the initial target course activity information, the target course can be determined from the initial target course according to whether the activity information meets the preset activity condition. Alternatively, the initial target courses can be sorted according to the activity information, and the target course with a high ranking can be selected.

[0103] In the embodiments of the present application, the course customization information is course keyword information, and the method for determining the target course from the initial target course according to the historical learning data of the initial target course can include:

[0104] According to the historical learning data of the initial target course, the time effectiveness information of the initial target course is determined, and the time effectiveness information represents the effective time effectiveness of learning the initial target course;

[0105] According to the time effectiveness information of the initial target course, the target course in the initial target course is determined.

[0106] The timeliness information can refer to a relationship between a starting learning time point of the initial target course and a current time. When the starting learning time point of the initial target course is closer to the current time, the timeliness of the initial target course is better. Thus, when the course is recommended, the course whose starting learning time is closer to the current time can be preferentially recommended.

[0107] In the embodiments of the present application, the method for determining the timeliness information of the initial target course according to the historical learning data of the initial target course can include:

[0108] The total learning times, the total learning duration, and the average learning time point of the initial target course are determined according to the historical learning data of the initial target course.

[0109] The timeliness information of the initial target course is determined according to the relationship between the total learning times and the preset learning times threshold, the relationship between the total learning duration and the preset learning duration threshold, and the average learning time point.

[0110] The total learning times can refer to all learning times of the initial target course. In the embodiments of the present application, the total learning times can be determined by counting the historical learning time in each learning historical learning data.

[0111] The total learning duration can refer to the total learning duration of the initial target course. In the embodiments of the present application, the total learning times can be obtained by counting the historical learning time and the historical learning duration of each learning initial target course.

[0112] The average learning time point can refer to an average time point of the time point of learning the initial target course relative to the current time.

[0113] In the embodiments of the present application, the method for determining the total learning times, the total learning duration, and the average learning time point of the initial target course according to the historical learning data of the initial target course can include:

[0114] The learning time of each learning initial target course, and the total learning times and the total learning duration of learning the initial target course are determined according to the historical learning data of the initial target course.

[0115] A time difference set is obtained according to the learning time of each learning initial target course and the current time. The time difference set includes a plurality of time differences.

[0116] The time difference between the learning time of each learning initial target course and the current time is determined.

[0117] The average learning time point is obtained by weightedly averaging the time differences according to the total learning times.

[0118] The formula for obtaining the average learning time point can be:

[0119]

[0120] K can be the total number of learning times of the initial target course; t i，k may be the time of each learning of the initial target course.

[0121] In the embodiments of the present application, the method for determining the timeliness information of the initial target course can be through the formula:

[0122]

[0123] LN i may be the total number of learning times of the initial target course;

[0124] LT i may be the total learning time of the initial target course;

[0125] LN0may be the preset learning time threshold of the initial target course;

[0126] LT0may be the preset learning time threshold of the initial target course.

[0127] When E(t) is larger, the average learning time point is farther away from the current time point, and the timeliness represented by the timeliness information is poorer. Therefore, when the total learning time of the initial target course is longer and the number of learning times is more, the average learning time point is closer to the current time, and the initial target course is more recommended.

[0128] In the embodiments of the present application, after obtaining the timeliness information of the initial target course, the target course can be determined from the initial target course according to whether the timeliness information meets the preset timeliness condition. Or the initial target course can be sorted according to the timeliness information, and the target course with a high ranking can be selected

[0129] In the embodiments of the present application, the course customization information is the reference object information, and the method for determining the initial target course and the historical learning data of the initial target course according to the course customization information can include:

[0130] According to the course customization information, the reference object and the historical record data of the reference object are determined;

[0131] According to the historical record data of the reference object, the initial target course and the historical learning data of the initial target course are determined.

[0132] The historical record data can include data of course learning of the reference object in a certain time period, for example, the historical record data can be course data learned in two years and time of learning the course. In the embodiment of the application, the historical record data can also include attribute information of the reference object, for example, the historical record data X1 of the reference object = {Zhang San, new employee, communication engineering major, 24 years old, master, wireless communication post, March 30, 2021, 9:00-10:00, cloud computing technology course ID}. When a reference object includes multiple courses, multiple pieces of historical record data can be generated for one reference object.

[0133] After obtaining the historical record data of all reference objects, the course ID in the historical record data can be extracted to determine the initial target course.

[0134] In the embodiment of the application, the method for determining the target course in the initial target course according to the historical learning data of the initial target course can include:

[0135] According to the historical learning data of the initial target course, the online time, the learning times, the learning time length, the total learning times and the total learning time length of the initial target course are determined, the learning times are the total learning times of the initial target course in the historical learning time segment, and the learning time length is the total learning time length of the initial target course in the historical learning time segment.

[0136] According to the online time, the learning times, the learning time length, the total learning times and the total learning time length of the initial target course, the target course in the initial target course is determined.

[0137] The online time can refer to the time when the initial target course is uploaded to the learning platform.

[0138] The target course in the initial target course can be screened through the online time, the learning times, the learning time length, the total learning times and the total learning time length.

[0139] In the embodiment of the application, the method for determining the target course in the initial target course according to the online time, the learning times, the learning time length, the total learning times and the total learning time length of the initial target course can include:

[0140] According to the relationship between the learning times and the preset learning times threshold, a first score is determined.

[0141] According to the relationship between the learning time length and the preset learning time length threshold, a second score is determined.

[0142] According to the relationship between the total learning times and the preset total learning times threshold, a third score is determined.

[0143] The fourth score is determined according to a relationship between the total learning duration and a preset total learning duration threshold;

[0144] The target course in the initial target course is determined according to the online time of the initial target course, the first score, the second score, the third score, and the fourth score.

[0145] The first score can refer to whether the number of learning times of the initial target course in the historical learning time segment is too small. The second score can refer to whether the learning duration of the initial target course in the historical learning time segment is too short. The third score can refer to whether the total number of learning times of the initial target course is too small. The fourth score can refer to whether the total learning duration of the initial target course is too short.

[0146] The target course in the initial target course can be determined by the formula:

[0147]

[0148] TT can be a threshold value of the online time of the initial target course;

[0149] CT m may be the online time of the initial target course;

[0150] CT0 can be the current time;

[0151] LN m，j may be the number of learning times of the initial target course in the historical learning time segment [T j , T0];

[0152] LT m，j may be the learning duration of the initial target course in the historical learning time segment [T j , T0];

[0153] LN 0，j may be a threshold value of the number of learning times of the initial target course in the historical learning time segment [T j , T0];

[0154] LT 0，j may be a threshold value of the learning duration of the initial target course in the historical learning time segment [T j , T0];

[0155] LN i may be the total number of learning times of the initial target course;

[0156] LN0 can be the total learning duration of the initial target course;

[0157] LT i may be a threshold value of the total number of learning times;

[0158] The LT0 can be a learning total time threshold.

[0159] The score of the initial target course can be determined by whether the online time of the initial target course is too long, whether the learning time in stages of the initial target course and the total learning time are too short, and whether the learning times in stages of the initial target course and the total learning times are too few. The low-efficiency course with a lower score can be deleted from the initial target course according to the size of the score, so that the target course can be determined. For example, when f3 m When f3 < 2, the initial target course is the low-efficiency course with a lower score.

[0160] In the embodiments of the present application, when the course customization information includes two or more of the course category information, the course keyword information, and the reference object information, the de-duplication operation can be performed on the target course corresponding to each obtained course customization information, so that the corresponding target course is obtained.

[0161] In the embodiments of the present application, the method for determining the target course in the initial target course according to the online time, the first score, the second score, the third score, and the fourth score of the initial target course can include:

[0162] The target course to be screened is determined according to the online time, the first score, the second score, the third score, and the fourth score of the initial target course.

[0163] The target reference object and the attribute data of the target reference object are determined according to the target course to be screened.

[0164] The target course in the target course to be screened is determined according to the attribute data of the target reference object and the user attribute data of the user.

[0165] The target course to be screened can refer to a course determined from the initial target course according to the online time, the first score, the second score, the third score, and the fourth score. For example, when f3 m When f3 ≥ 2, the initial target course is the target course to be screened.

[0166] The target reference object can refer to a user who has learned the target course to be screened in the reference object.

[0167] The attribute data of the target reference object can refer to attributes of the target reference object, for example, the attributes can include positions, professions, ages, and educational backgrounds, etc.; the user attribute data of the user can refer to attributes of the user. In the embodiments of the present application, the attribute data of the target reference object and the user attribute data of the user can be pre-stored in the learning platform. It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for the user to choose authorization or refusal.

[0168] Determining the target course in the to-be-screened target courses can refer to determining the target course from the to-be-screened target courses according to the similarity or matching degree between the attribute data of the target reference object and the user attribute data of the user.

[0169] S104, generating course recommendation information according to the target course, so as to display the course recommendation information in the display interface of the learning platform after the user logs in the learning platform.

[0170] The course recommendation information can be recommendation information generated according to the target course, and the course recommendation information can be displayed in the form of a chart or a list in the display interface of the learning platform after the user logs in the learning platform.

[0171] The recommendation method provided in the present application can obtain the course learning intention of the user, obtain the initial target course, and determine the final target learning course according to the historical learning data of the initial target course, so as to realize the effect of accurately recommending courses.

[0172] Figure 2 The flowchart of another recommendation method provided in the embodiments of the present application, the execution subject of the method can be a computer, and the embodiments are not particularly limited here, for example, as shown in the figure, the method can include: Figure 2

[0173] S201, in response to the input operation of the student, obtaining the customized demand of the student, wherein the customized demand includes at least one type of demand in course category, course keyword and reference object.

[0174] The customized demand obtaining module of the learning platform provides a demand obtaining window to the student, in which the student can select or fill in the customized demand content, including three types of demands of course category, course keyword and reference object.

[0175] ​S202. When the customization requirement is a requirement for a course category, multiple first courses belonging to the customized course category are searched from the course database of the learning platform.

[0176] S203, Obtain the activity value of the first course;

[0177] S204. Based on the activity value of the first course, determine the first target course in the first course.

[0178] The course category customization recommendation module of the learning platform can receive customization requests for course categories sent by the customization request acquisition module.

[0179] The course category customization recommendation module searches the learning platform's course database for courses belonging to a customized course category and stores the course list in collection D1, where D1 = {class ID1}. i}, i=1, 2, 3,..., I1.

[0180] After storing the course list in collection D1, retrieve the course class ID1 from the learning record data of the learning platform. i The activity-related information includes the number of times the course was studied, the duration of study, and the time spent studying.

[0181] After obtaining activity-related information, use the formula:

[0182]

[0183] Calculate the course class ID1 i Activity value.

[0184] Based on the activity level, select the first target course from the first course.

[0185] S205. When the customization requirement is a requirement for course keywords, multiple second courses belonging to the customized course keywords are searched from the course database of the learning platform.

[0186] S206. Obtain the timeliness value of the second course;

[0187] S207. Based on the timeliness value of the second course, determine the second target course in the second course.

[0188] Among them, the course category customization recommendation module of the learning platform can receive customization requests sent by the customization request acquisition module, which are requests for course keywords.

[0189] The course category customization recommendation module searches in the course database of the learning platform for courses matching the customized keywords within a preset time, and stores the course list in set D2, D2 = {class ID2 i}, i = 1, 2, 3, …, I2.

[0190] After storing the course list in set D2, the relevant learning information of course class ID2 i is obtained from the learning record data of the learning platform, including course learning times, learning duration, and learning timeliness, etc.

[0191] After obtaining the relevant learning information, the relevant learning information of course class ID2 i is calculated by the formula:

[0192]

[0193]

[0194] According to the relevant learning information, a second target course is selected from the second course.

[0195] S208, when the customization requirement is a requirement for a reference object, the historical record data of the reference object is determined from the database of the learning platform according to the reference object, the historical record data including the reference object, attribute information of the reference object, learning duration, learning time, and a third course;

[0196] S209, according to the learning duration, the learning time, and the third course, a target course to be screened in the initial learning course is determined;

[0197] S210, according to the attribute information of the reference object and the attribute information of the student, a third target course in the target course to be screened is determined.

[0198] The reference object includes: a training class student, a department employee in an organizational structure, a designated post sequence employee, and a group of self-selected students from a student list, etc.

[0199] The course category customization recommendation module of the learning platform can receive the customization requirement as a requirement for a reference object sent by the customization requirement acquisition module. Wherein, the reference object set is denoted as RS, RS = {RS1, RS2, RS3, …, RS n , …, RS N}, N is the number of reference objects, RS N represents the student ID.

[0200] After obtaining the reference object set, the historical learning data and data attributes of the reference object RS n are obtained to build an initial data set. Wherein, the reference object RS​n The historical learning data R1 and the data attribute R2 can be respectively R1={student unique identifier ID, learning time, learning course unique identifier}, and R2={student unique identifier, student attribute 1, student attribute 2, student attribute 3, …}. The data set R0={student ID, student attribute 1, student attribute 2, student attribute 3, …, learning time, learning course ID} is determined, and the initial data set X can be obtained according to the historical learning data R1 and the data attribute R2, X={X1, X2, X3, …, Xn}, for example, X1={Zhang San, new employee, communication engineering major, 24 years old, master, wireless communication post, March 30, 2021, 9:00-10:00, cloud computing technology course ID}. e i I

[0201] After obtaining the initial data set, the score of the learning course in each initial data set can be determined according to the formula:

[0202]

[0203] When the score of the learning course is less than a preset value, the initial data set can be deleted, and thus the screening data set representing high timeliness and fast learning amount of the learning course is obtained, wherein the screening data set includes a plurality of target courses to be screened.

[0204] After obtaining the screening data set, the screening data set can be sent to a data mining software (such as IBM SPSS Statistics), and the screening data set is imported according to the software prompt, wherein the independent variable is {student ID, student attribute 1, student attribute 2, student attribute 3, …, learning time}, and the dependent variable is {learning course ID}. Thus, the third target course matched with the attribute information of the reference object and the attribute information of the student can be obtained.

[0205] S211, according to the customized needs of the student, when the student logs in the learning platform, the first target course, the second target course and the third target course are recommended in the recommendation list of the learning platform.

[0206] Another recommendation method provided by the application can obtain the customized needs of the student, adopt a deep learning technology, comprehensively analyze the historical learning data of the courses on the learning platform, and automatically recommend a recommendation list of customized learning courses meeting the needs of the student, so as to provide data support for accurate operation of the learning platform and ensure the accuracy of the recommended courses.

[0207] Figure 3 The structure schematic diagram of the recommendation device provided by the embodiment of the application is shown in FIG. 1. Figure 3 ​​​As shown, the recommendation device 30 comprises an acquisition module 301, a first determination module 302, a second determination module 303, and a generation module 304. Wherein:

[0208] The acquisition module 301 is configured to acquire course customization information of the user, wherein the course customization information comprises at least one of course category information, course keyword information, and reference object information;

[0209] The first determination module 302 is configured to determine an initial target course and historical learning data of the initial target course according to the course customization information, wherein the historical learning data comprises historical learning time and historical learning duration of each time of learning the initial target course;

[0210] The second determination module 303 is configured to determine a target course in the initial target course according to the historical learning data of the initial target course;

[0211] The generation module 304 is configured to generate course recommendation information according to the target course, so as to display the course recommendation information in a display interface of a learning platform after the user logs in the learning platform.

[0212] In the embodiments of the present application, the second determination module 303 can be specifically configured to:

[0213] determine activity information of the initial target course according to the historical learning data of the initial target course, wherein the activity information represents activity of learning the initial target course;

[0214] determine the target course in the initial target course according to the activity information of the initial target course.

[0215] In the embodiments of the present application, the second determination module 303 can be specifically configured to:

[0216] acquire a current time;

[0217] determine a historical learning time segment according to the current time;

[0218] determine a learning frequency and a learning duration according to the historical learning data of the initial target course, wherein the learning frequency is a total learning frequency of the initial target course in the historical learning time segment, and the learning duration is a total learning duration of the initial target course in the historical learning time segment;

[0219] determine the activity information of the initial target course according to a relationship between the historical learning time segment, the learning frequency and a preset learning frequency threshold, and a relationship between the learning duration and a preset learning duration threshold.

[0220] In the embodiments of the present application, the second determination module 303 can be specifically configured to:

[0221] According to a relationship between the historical learning time segments, a relationship between the learning times and the preset learning time threshold, and a relationship between the learning time lengths and the preset learning time length threshold, initial activity information of the initial target course in each historical learning time segment is determined.

[0222] The initial activity information is weighted and summed to obtain the activity information of the initial target course.

[0223] In the embodiments of the present application, the second determination module 303 can be specifically used for:

[0224] According to the historical learning data of the initial target course, time effectiveness information of the initial target course is determined, the time effectiveness information representing effective time effectiveness of learning the initial target course.

[0225] According to the time effectiveness information of the initial target course, a target course in the initial target course is determined.

[0226] In the embodiments of the present application, the second determination module 303 can be specifically used for:

[0227] According to the historical learning data of the initial target course, a total learning time, a total learning time length, and an average learning time point of each time of learning the initial target course are determined.

[0228] According to a relationship between the total learning time and the preset learning time threshold, a relationship between the total learning time length and the preset learning time length threshold, and the average learning time point, the time effectiveness information of the initial target course is determined.

[0229] In the embodiments of the present application, the second determination module 303 can be specifically used for:

[0230] According to the historical learning data of the initial target course, a learning time of each time of learning the initial target course, and a total learning time and a total learning time length of learning the initial target course are determined.

[0231] A time difference between the learning time of each time of learning the initial target course and the current time is determined.

[0232] According to the total learning time, the time difference is weighted and averaged to obtain the average learning time point.

[0233] In the embodiments of the present application, the second determination module 303 can be specifically used for:

[0234] According to the course customization information, a reference object and historical record data of the reference object are determined.

[0235] According to the historical record data of the reference object, the initial target course and the historical learning data of the initial target course are determined.

[0236] In the embodiments of the present application, the second determining module 303 can be specifically configured to:

[0237] According to the historical learning data of the initial target course, determine the online time, learning times, learning duration, total learning times and total learning duration of the initial target course, the learning times being the total learning times of the initial target course in the historical learning time segment, and the learning duration being the total learning duration of the initial target course in the historical learning time segment.

[0238] According to the online time, learning times, learning duration, total learning times and total learning duration of the initial target course, determine the target course in the initial target course.

[0239] In the embodiments of the present application, the second determining module 303 can be specifically configured to:

[0240] According to the relationship between the learning times and the preset learning times threshold, determine the first score;

[0241] According to the relationship between the learning duration and the preset learning duration threshold, determine the second score;

[0242] According to the relationship between the total learning times and the preset total learning times threshold, determine the third score;

[0243] According to the relationship between the total learning duration and the preset total learning duration threshold, determine the fourth score;

[0244] According to the online time, first score, second score, third score and fourth score of the initial target course, determine the target course in the initial target course.

[0245] In the embodiments of the present application, the second determining module 303 can be specifically configured to:

[0246] According to the online time, first score, second score, third score and fourth score of the initial target course, determine the target course in the initial target course.

[0247] According to the initial target course, determine the target reference object and the attribute data of the target reference object;

[0248] According to the attribute data of the target reference object and the user attribute data of the user, determine the target course in the initial target course.

[0249] It can be known from the above that the recommendation device of the embodiment comprises an acquisition module 301, configured to acquire course customization information of a user, wherein the course customization information comprises at least one of course category information, course keyword information and reference object information; a first determination module 302, configured to determine an initial target course and historical learning data of the initial target course according to the course customization information, wherein the historical learning data comprises historical learning time and historical learning duration of each time of learning the initial target course; a second determination module 303, configured to determine a target course in the initial target course according to the historical learning data of the initial target course; and a generation module 304, configured to generate course recommendation information according to the target course, and display the course recommendation information in a display interface of a learning platform after the user logs in the learning platform. Thus, the effect of accurately recommending courses can be achieved.

[0250] Figure 4 The structure schematic diagram of the electronic device provided by the embodiment of the present application is shown in the figure. Figure 4 As shown in the figure, the electronic device 40 comprises:

[0251] The electronic device 40 can comprise a processor 401 with one or more processing cores, a memory 402 with one or more computer readable storage media, a communication component 403 and the like. The processor 401, the memory 402 and the communication component 403 are connected through a bus 404.

[0252] In the specific implementation process, the at least one processor 401 executes the computer execution instructions stored in the memory 402, so that the at least one processor 401 executes the recommendation method as described above.

[0253] The specific implementation process of the processor 401 can refer to the method embodiment described above, which has similar implementation principles and technical effects, and will not be described here.

[0254] In the above Figure 4 In the embodiment shown in the figure, it should be understood that the processor can be a central processing unit (English: Central Processing Unit, for short: CPU), and can also be other general-purpose processors, digital signal processors (English: Digital Signal Processor, for short: DSP), application specific integrated circuits (English: Application Specific Integrated Circuit, for short: ASIC) and the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor and the like. The steps of the method disclosed in the application can be directly embodied as the execution of the hardware processor, or executed by the combination of hardware and software modules in the processor.

[0255] The memory can include a random access memory (RAM) and can also include a non-volatile memory (NVM), such as at least one disk memory.

[0256] The bus can be an industry standard architecture (ISA) bus, a peripheral component (PCI) bus, an extended industry standard architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, the bus in the drawings of the present application does not limit to only one bus or one type of bus.

[0257] In some embodiments, a computer program product is also provided, which includes a computer program or instructions, which, when executed by a processor, implement the steps of any of the recommendation methods described above.

[0258] The specific implementation of each operation above can refer to the previous embodiments, which will not be repeated here.

[0259] Those of ordinary skill in the art can understand that all or part of the steps of the various methods of the above embodiments can be completed by instructions, or by relevant hardware controlled by the instructions, which can be stored in a computer readable storage medium and loaded and executed by a processor.

[0260] To this end, an embodiment of the present application provides a computer readable storage medium, which stores a plurality of instructions, which can be loaded by a processor to execute the steps of any of the recommendation methods provided by the embodiments of the present application.

[0261] The storage medium can include a read only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and the like.

[0262] According to an aspect of the present application, a computer program product or a computer program is provided, which includes computer instructions stored in a computer readable storage medium.

[0263] Since the instructions stored in the storage medium can execute the steps of any of the recommendation methods provided by the embodiments of the present application, the beneficial effects that can be achieved by any of the recommendation methods provided by the embodiments of the present application can be achieved, which will be described in detail in the previous embodiments and will not be repeated here.

[0264] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the application being indicated by the following claims.

[0265] It is to be understood that the application is not limited to the precise construction herein disclosed and shown in the drawings, and that various changes in shape, size and arrangements of parts can be made without departing from the scope of the application as recited in the claims. The scope of the application is only limited by the appended claims.

Claims

1. A recommendation method, characterized in that, Applied to a learning platform, the method includes: Obtain user's course customization information, wherein the course customization information includes at least one of course category information, course keyword information, and reference object information; Based on the course customization information, an initial target course is determined, as well as the historical learning data of the initial target course, including the historical learning time and duration of each learning session of the initial target course; Based on the historical learning data of the initial target course, the target courses in the initial target course are determined; Based on the target course, course recommendation information is generated so that the course recommendation information can be displayed on the display interface of the learning platform after the user logs in; The course customization information includes the course category information, and the step of determining the target course within the initial target course based on the historical learning data of the initial target course includes: Based on the historical learning data of the initial target course, the activity information of the initial target course is determined, and the activity information represents the activity level of learning the initial target course; Based on the activity information of the initial target courses, determine the target courses within the initial target courses; The course customization information is course keyword information. The step of determining the target course within the initial target course based on the historical learning data of the initial target course includes: Based on the historical learning data of the initial target course, the timeliness information of the initial target course is determined, and the timeliness information represents the effective timeliness of learning the initial target course; Based on the timeliness information of the initial target courses, determine the target courses within the initial target courses; The course customization information is reference object information. The process of determining the initial target course and its historical learning data based on the course customization information includes: Based on the course customization information, determine the reference objects and the historical data of the reference objects; Based on the historical data of the reference object, an initial target course and the historical learning data of the initial target course are determined.

2. The method according to claim 1, characterized in that, The step of determining the activity information of the initial target course based on the historical learning data of the initial target course includes: Get the current time; Based on the current time, determine the historical learning time segments; Based on the historical learning data of the initial target course, the number of learning sessions and the learning duration are determined. The number of learning sessions is the total number of times the initial target course is learned within the historical learning time segment, and the learning duration is the total learning duration of the initial target course within the historical learning time segment. The activity information of the initial target course is determined based on the relationship between the historical learning time segments, the number of learning sessions and the preset learning session threshold, and the learning duration and the preset learning duration threshold.

3. The method according to claim 2, characterized in that, When there are two or more historical learning time segments, determining the activity information of the initial target course based on the relationship between the historical learning time segments, the number of learning sessions and a preset learning session threshold, and the relationship between the learning duration and a preset learning duration threshold includes: Based on the relationship between the historical learning time segments, the number of learning sessions and the preset learning session threshold, and the relationship between the learning duration and the preset learning duration threshold, the initial activity information of the initial target course within each historical learning time segment is determined. The initial activity information is weighted and summed to obtain the activity information of the initial target course.

4. The method according to claim 1, characterized in that, The step of determining the timeliness information of the initial target course based on the historical learning data of the initial target course includes: Based on the historical learning data of the initial target course, determine the total number of times the initial target course is studied, the total study time, and the average study time point for each study of the initial target course; Based on the relationship between the total number of learning sessions and the preset learning session threshold, the relationship between the total learning duration and the preset learning duration threshold, and the average learning time point, the timeliness information of the initial target course is determined.

5. The method according to claim 4, characterized in that, The step of determining the total number of learning sessions, total learning duration, and average learning time for each session of the initial target course based on historical learning data includes: Based on the historical learning data of the initial target course, determine the learning time for each learning session of the initial target course, as well as the total number of learning sessions and the total learning duration of the initial target course; Determine the time difference between the learning time for each time the initial target course is studied and the current time; The average learning time point is obtained by weighting and averaging the time differences based on the total number of learning iterations.

6. The method according to claim 1, characterized in that, The step of determining the target courses in the initial target courses based on the historical learning data of the initial target courses includes: Based on the historical learning data of the initial target course, the online time, number of times of learning, learning duration, total number of times of learning and total learning duration of the initial target course are determined. The number of times of learning is the total number of times the initial target course is learned within the historical learning time segment, and the learning duration is the total learning duration of the initial target course within the historical learning time segment. The target courses in the initial target courses are determined based on the launch time, number of times studied, study duration, total number of times studied, and total study duration of the initial target courses.

7. The method according to claim 6, characterized in that, The step of determining the target courses within the initial target courses based on the launch time, number of times studied, study duration, and total number of times studied and total study duration of the initial target courses includes: The first score is determined based on the relationship between the number of learning attempts and the preset learning attempt threshold. The second score is determined based on the relationship between the learning duration and the preset learning duration threshold; The third score is determined based on the relationship between the total number of learning attempts and the preset threshold for the total number of learning attempts; The fourth score is determined based on the relationship between the total learning time and the preset total learning time threshold; The target courses in the initial target courses are determined based on the launch time of the initial target courses, the first rating, the second rating, the third rating, and the fourth rating.

8. The method according to claim 7, characterized in that, The step of determining the target course within the initial target course based on the initial target course's launch time, the first rating, the second rating, the third rating, and the fourth rating includes: Based on the online time of the initial target courses, the first rating, the second rating, the third rating, and the fourth rating, the target courses to be screened in the initial target courses are determined; Based on the target courses to be screened, determine the target reference objects and the attribute data of the target reference objects; Based on the attribute data of the target reference object and the user attribute data of the user, the target courses in the target courses to be screened are determined.

9. A recommended device, characterized in that, include: The acquisition module is used to acquire the user's course customization information, wherein the course customization information includes at least one of course category information, course keyword information, and reference object information; The first determining module is used to determine an initial target course and historical learning data of the initial target course based on the course customization information. The historical learning data includes the historical learning time and historical learning duration of each time the initial target course is studied. The second determining module is used to determine the target courses in the initial target courses based on the historical learning data of the initial target courses; The generation module is used to generate course recommendation information based on the target course, so as to display the course recommendation information on the display interface of the learning platform after the user logs in.

10. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the recommended method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the recommended method as described in any one of claims 1 to 8.

Images