Course recommendation method, device, equipment and storage medium
By updating and replacing the historical training course data, the problems of old and low quality of courses are solved, the effectiveness and efficiency of course recommendations are improved, and the accuracy and user experience of training course settings are ensured.
Patent Information
- Application Number
- CN202210606139.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-05-31
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2042-05-31
AI Technical Summary
In the prior art, when setting up training courses, due to the old, low quality or low learning volume, the effectiveness, efficiency and accuracy of artificial searching course information is low.
By obtaining historical training course data, the data that meets the update requirements are updated according to the teaching type, the updated data is used to recommend courses for users, and the replacement course screening model is used to determine the replacement courses, and the recommended course sample data is optimized.
It improves the effectiveness and efficiency of course recommendations, enhances the accuracy of course settings, and ensures the quality and user experience of recommended courses.
Smart Images

Figure CN114971799B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a course recommendation method, device, equipment and storage medium. Background Art
[0002] In the era of intelligence, with the popularization of the Internet, people's lives and learning methods have changed greatly. Online teaching has become popular, and the method of customizing and recommending online courses according to the personalized needs of users has been increasingly widely used.
[0003] In the prior art, a training administrator manually searches for course information from a database to set up courses.
[0004] However, since the courses are old, low-quality or have low learning volume, they are difficult to identify intuitively. Therefore, the effectiveness, efficiency and accuracy of the existing technology of manually searching for course information for course setting are low. Summary of the invention
[0005] The present application provides a course recommendation method, device, equipment and storage medium, which are used to solve the technical problem that the effectiveness, efficiency and accuracy of course setting by manually searching for course information are low.
[0006] In a first aspect, the present application provides a course recommendation method, comprising:
[0007] Acquire historical training course data, wherein the historical training course data includes: teaching type;
[0008] Updating the historical training course data that meets the update requirements according to the teaching type to obtain updated historical training course data;
[0009] Use updated historical training course data to recommend courses to users.
[0010] Optionally, updating the historical training course data that meets the update requirement according to the teaching type to obtain updated historical training course data includes:
[0011] Determine historical training course data that meets the update requirements according to the course types;
[0012] Using the corresponding replacement course screening model to determine the corresponding replacement course;
[0013] Historical training course data that meets the update requirements is updated using replacement courses.
[0014] Optionally, the determining, according to the teaching type, the historical training course data that meets the updating requirement includes:
[0015] If it is determined that the teaching type is offline teaching, a first to-be-updated course screening model is obtained, and the first to-be-updated course screening model is used to determine historical training course data that meets the update requirements;
[0016] If it is determined that the teaching type is online teaching, a second screening model for courses to be updated is obtained, and the second screening model for courses to be updated is used to determine historical training course data that meets the update requirements.
[0017] Optionally, the step of using the first to-be-updated course screening model to determine the historical training course data that meets the update requirements includes:
[0018] Determine a first to-be-updated course screening indicator corresponding to the historical training course data, wherein the first to-be-updated course screening indicator includes: the latest teaching time, the number of teaching times within a preset time range, and the teaching score;
[0019] Inputting the first to-be-updated course screening indicator into the first to-be-updated course screening model;
[0020] The first to-be-updated course screening model is used to screen out historical training course data that meets the update requirements.
[0021] Optionally, the step of using the second to-be-updated course screening model to determine the historical training course data that meets the update requirements includes:
[0022] Determine a second to-be-updated course screening indicator corresponding to the historical training course data, wherein the second to-be-updated course screening indicator includes: the number of learners, the number of learning times, and the learning duration within a preset time range;
[0023] inputting the second to-be-updated course screening indicator into the second to-be-updated course screening model;
[0024] The second to-be-updated course screening model is used to screen out historical training course data that meets the update requirements.
[0025] Optionally, if the teaching type is offline teaching, the adopting a corresponding replacement course screening model to determine a corresponding replacement course includes:
[0026] Obtaining a first replacement course screening model and multiple alternative training course data;
[0027] Determine the first replacement course screening indicator corresponding to each candidate training course data; the first replacement course screening indicator includes: the latest teaching time, lecturer activity and course rating within a preset time range;
[0028] inputting the first replacement course screening indicator into the first replacement course screening model;
[0029] The first replacement course screening model is used to screen out replacement courses.
[0030] Optionally, if the teaching type is online teaching, the adopting a corresponding replacement course screening model to determine a corresponding replacement course includes:
[0031] Obtaining a second replacement course screening model and multiple alternative training course data;
[0032] Determine the second replacement course screening index corresponding to each candidate training course data; the second replacement course screening index includes: course online time, number of learners, number of learning times and learning time;
[0033] inputting the second replacement course screening indicator into the second replacement course screening model;
[0034] The second replacement course screening model is used to screen out replacement courses.
[0035] Optionally, the adopting updated historical training course data to recommend courses to users includes:
[0036] receiving a course recommendation request sent by a user terminal, wherein the course recommendation request includes a training employee type and a course keyword;
[0037] Using a trained recommendation model to determine recommended courses based on the training employee type and course keywords; the trained recommendation model is obtained by training using updated historical training course data;
[0038] The recommended courses are sent to the user terminal so that the user terminal displays the recommended courses on a recommendation interface.
[0039] In a second aspect, the present application provides a course recommendation device, comprising:
[0040] An acquisition module is used to acquire historical training course data, wherein the historical training course data includes: teaching type;
[0041] An updating module, used for updating the historical training course data that meets the updating requirements according to the teaching type to obtain updated historical training course data;
[0042] The recommendation module is used to recommend courses to users using updated historical training course data.
[0043] In a third aspect, the present application provides an electronic device, including:
[0044] A processor, and a memory, an input device, and an output device communicatively connected to the processor;
[0045] The memory stores computer-executable instructions; the input device is used to receive data input by a user; the output device is used to output courses recommended for the user;
[0046] The processor executes the computer-executable instructions stored in the memory to implement the method as described in any one of the first aspects.
[0047] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method as described in any one of the first aspects.
[0048] The present application provides a course recommendation method, device, equipment and storage medium, which obtains historical training course data, wherein the historical training course data includes: teaching type. The historical training course data that meets the update requirements is updated according to the teaching type to obtain the updated historical training course data. The updated historical training course data is used to recommend courses for users. Considering that there are old courses or courses are removed from the shelves, if these courses are used as the output results of the neural network model, the recommendation value of the training course will be reduced. Therefore, the present application optimizes the recommended course sample data and improves the effectiveness of course recommendation by updating the historical training course data that meets the update requirements. By recommending courses to users, the efficiency of corporate training course setting is improved. And when updating the recommended course sample data, since the judgment conditions for whether different teaching types meet the update requirements are different, when updating the recommended course sample data, it is updated according to the teaching type, which improves the accuracy of updating the historical training course data. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0050] Figure 1 An application scenario diagram of the training course recommendation method provided in an embodiment of the present application;
[0051] Figure 2 A method flow chart of a training course recommendation method provided in Example 1 of the present application;
[0052] Figure 3 A method flow chart of a training course recommendation method provided in Example 2 of the present application;
[0053] Figure 4 A method flow chart of a training course recommendation method provided in Example 3 of the present application;
[0054] Figure 5A method flow chart of a training course recommendation method provided in Example 4 of the present application;
[0055] Figure 6 A method flow chart of a training course recommendation method provided in Example 5 of the present application;
[0056] Figure 7 A method flow chart of a training course recommendation method provided in Example 6 of the present application;
[0057] Figure 8 A method flow chart of a training course recommendation method provided in Embodiment 7 of the present application;
[0058] Fig. 9 A method flow chart of a training course recommendation method provided in Example 8 of the present application;
[0059] Fig.10 A schematic diagram of the structure of a course recommendation device provided in Example 1 of the present application;
[0060] Fig.11 A schematic diagram of the structure of an electronic device provided in Example 1 of the present application. DETAILED DESCRIPTION
[0061] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0062] In order to clearly understand the technical solution of the present application, the solution of the prior art is first introduced in detail.
[0063] The existing technology sets training courses by manually searching for suitable course information, but historical course data is outdated and of low quality. Therefore, this method has the problem of low effectiveness and efficiency in setting courses.
[0064] Based on the fact that the existing technology cannot solve the problem of the effectiveness and low efficiency of training course settings, the inventor of the present application has discovered through creative research that as long as the old and low-quality courses in the history courses are updated and replaced with similar high-quality courses, the value of course recommendations can be effectively improved and the effectiveness and efficiency of course settings can be improved. At the same time, due to different teaching types, the conditions for updating and replacing are also different. Therefore, as long as the courses are updated according to the teaching type, the accuracy of updating the history course samples can be improved.
[0065] The following is an introduction to the network architecture and application scenarios of the training course recommendation method provided by this application.
[0066] Figure 1 Application scenario diagram of the training course recommendation method provided in the present application. The network structure corresponding to the training course recommendation method provided in the embodiment of the present application may include: database 1, electronic device 2, and user terminal 3. Historical course data is stored in database 1. Electronic device 2 can be a server, providing background services for the course recommendation method. Historical training course data is optimized and updated regularly. The front-end interface of the user terminal 3 displays the front-end page of the course recommendation method, and provides a course setting function for the training administrator. When the training administrator clicks on the course setting function, enters the training population and / or training course keywords, and triggers the course recommendation component, the electronic device 2 receives the course recommendation request, and after the matching degree is calculated, the recommended course information is pushed on the front-end interface of the user terminal 3. For example, Figure 1 As shown, in the front-end page of the course recommendation method carried by the user terminal, the training group input by the user is "new employee induction training", and three courses are recommended on the front-end interface, namely "enterprise system training", "enterprise production operation process training" and "promotion system".
[0067] The training course recommendation method provided in this application can be specifically applied to corporate training course setting or teaching and training course setting. For example, an enterprise needs to offer induction training courses for new employees. When the training administrator enters the new employee induction training field and clicks the course recommendation button, the background service receives the input information and matches the course samples according to the input population and course keywords, and selects a preset number of new employee induction training courses with the highest matching degree, sorts them, and then returns to the user interface to display them to the training administrator.
[0068] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are 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 repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0069] Embodiment 1
[0070] Figure 2A method flow chart of a training course recommendation method provided in Example 1 of the present application. This embodiment provides a training course recommendation method to address the problems of low course recommendation value, low setting efficiency and low accuracy in training course setting. The method in this embodiment is applied to a course recommendation device, which can be located in an electronic device. The electronic device can be a digital computer in various forms. Such as cellular phones, smart phones, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Figure 2 As shown, the training course recommendation method of the embodiment of the present application includes the following steps:
[0071] Step S101: Acquire historical training course data, where the historical training course data includes: teaching type.
[0072] Historical training course data is the training course information accumulated from past training sessions. Course information mainly includes teaching type, course name, keywords, etc.
[0073] Among them, the teaching types include online teaching and offline teaching. When the teaching type is offline teaching, the historical training course data can also include teaching time, teaching lecturer, teaching score, etc. When the teaching type is online teaching, the historical training course data also includes course online time, number of learners, number of learning times, learning time, etc.
[0074] Specifically, the electronic device obtains all historical training course data from the database.
[0075] Step S102: Update the historical training course data that meets the update requirements according to the teaching type to obtain updated historical training course data.
[0076] Specifically, according to the teaching type, different preset update requirements are used to filter out courses that meet the update requirements. For example, if the teaching type is offline teaching, old, low-quality or low-learning courses can be filtered out based on the teaching time, teaching score and number of teaching. If the teaching type is online teaching, old courses can be filtered out based on the course launch time, or courses with low learning volume can be filtered out based on the number of learning times, learning time or number of learners.
[0077] Specifically, according to the teaching type, different preset replacement conditions are used to screen and find replacement courses that meet the replacement requirements. For example, if the teaching type is offline teaching, recent courses or high-quality courses can be screened out as high-quality face-to-face courses that meet the replacement requirements based on the teaching time, teaching rating or number of teaching. If the teaching type is online teaching, hot courses with high learning volume can be screened out as high-quality online courses that meet the replacement requirements based on the number of learning times, learning time or number of learners.
[0078] Among them, when updating historical training course data that meets the update requirements, the original old and low-quality course file path can be replaced by the found high-quality course file path.
[0079] Among them, the preset screening conditions and the preset replacement conditions are not specifically limited.
[0080] Step S103: Use the updated historical training course data to recommend courses to the user.
[0081] The electronic device regularly updates historical training course samples and trains the course recommendation model through the updated historical training course samples.
[0082] When the training administrator sets up a course, he / she inputs the applicable population and course keywords. The electronic device obtains the input data, uses the course recommendation model to match the updated historical training course sample set, and selects a preset number of matching courses. The courses are sorted by matching degree and returned to the front-end page to provide a reference for the training administrator to set up courses.
[0083] In an embodiment of the present application, historical training course data is obtained. The historical training course data that meets the update requirements is updated according to the teaching type to obtain updated historical training course data. The updated historical training course data is used to recommend courses to users. The present application optimizes the recommended course sample data and improves the effectiveness of course recommendations by updating the historical training course data that meets the update requirements. By recommending courses to users, the efficiency of corporate training course setting is improved. And when updating the recommended course sample data, since the judgment conditions for whether different teaching types meet the update requirements are different, when updating the recommended course sample data, it is updated according to the teaching type, thereby improving the accuracy of updating the historical training course data.
[0084] Embodiment 2
[0085] Figure 3 The flow chart of the training course recommendation method provided in the fourth embodiment of the present application is as follows: Figure 3As shown, based on the above embodiments, the embodiment of the present application involves a specific implementation method of updating the historical training course data that meets the update requirements according to the teaching type in step S102 to obtain the updated historical training course data. In the training course recommendation method provided by the present application, the historical training course data that meets the update requirements is updated according to the teaching type to obtain the updated historical training course data, including the following steps:
[0086] Step S201: determine historical training course data that meets the update requirements according to the teaching type.
[0087] Optionally, according to the teaching type, the preset update requirements corresponding to the teaching type are filtered to find courses that meet the update requirements. For example, if the teaching type is offline teaching, courses with low comprehensive scores for offline teaching can be filtered out according to at least one of the teaching time, teaching score, and number of teachings. If the teaching type is online teaching, courses with low comprehensive scores for online teaching can be filtered out according to at least one of the course online time, number of learning times, learning time, and number of learners.
[0088] Step S202: using a corresponding replacement course screening model to determine a corresponding replacement course.
[0089] Among them, the replacement course screening model refers to the model that meets the course replacement screening requirements.
[0090] Specifically, according to the teaching type, different replacement course screening models are used to screen and find replacement courses that meet the replacement requirements. For example, if the teaching type is offline teaching, courses with higher comprehensive scores can be screened out as replacement courses that meet the replacement requirements based on at least one of the teaching time, teaching score, and number of teachings. If the teaching type is online teaching, hot courses with higher learning volume can be screened out as replacement courses that meet the replacement requirements based on at least one of the number of learning times, learning time, or number of learners.
[0091] Step S203: Use replacement courses to update historical training course data that meets the update requirements.
[0092] Among them, when replacing courses to update historical training course data that meets the update requirements, the original old and low-quality course file path is replaced with the found high-quality course file path, so that when the course is obtained through the path, the original old and low-quality course files are no longer obtained, but high-quality course files are obtained.
[0093] In an embodiment of the present application, historical training course data that meets the update requirements is determined according to the teaching type. The corresponding replacement courses are determined using a corresponding replacement course screening model. The historical training course data that meets the update requirements is updated using replacement courses. According to different teaching types and update requirements, the courses that need to be updated are accurately screened out. At the same time, different replacement course screening models are used for different teaching types, which can accurately screen out high-quality courses that can be replaced, and the historical training course data that meets the update requirements is updated. The updated historical training course data can be used to recommend courses to users, further improving the recommendation value of the course recommendation samples.
[0094] Embodiment 3
[0095] Figure 4 The flow chart of the training course recommendation method provided in the fourth embodiment of the present application is as follows: Figure 4 As shown, based on the content of Example 2, the embodiment of the present application involves a specific implementable method of determining historical training course data that meets the update requirements according to the teaching type in step S201. In the training course recommendation method provided by the present application, determining historical training course data that meets the update requirements according to the teaching type includes the following steps:
[0096] Step 301, determine whether the course type is offline teaching.
[0097] If yes, execute step 302, otherwise execute step 303.
[0098] Step S302: Obtain a first screening model for courses to be updated, and use the first screening model for courses to be updated to determine historical training course data that meets the update requirements.
[0099] Among them, the first course screening model to be updated refers to a model that meets the update screening requirements for corresponding courses with the course type being offline teaching.
[0100] Specifically, first determine the input data of the course screening model to be updated, and determine it as the course screening index of the course corresponding to the offline face-to-face teaching. Obtain multiple screening indexes of the courses corresponding to the offline face-to-face teaching. Then, input the obtained course screening index of each course corresponding to the offline face-to-face teaching into the first course screening model to be updated, and calculate the value of each course corresponding to the offline face-to-face teaching through the first course screening model to be updated. The value is used to determine whether the update requirements are met. If the update requirements are met, the course corresponding to the offline face-to-face teaching is determined as a course that needs to be updated.
[0101] Step S303: Obtain a second screening model for courses to be updated, and use the second screening model for courses to be updated to determine historical training course data that meets the update requirements.
[0102] The second course screening model to be updated refers to a model that meets the update screening requirements for courses whose teaching type is online teaching.
[0103] Specifically, firstly, the input data of the course screening model to be updated is determined, and the input data is determined as the screening index of the courses corresponding to the online courses. The screening indexes of the courses corresponding to the online courses are obtained.
[0104] Then, the screening indicators of each online course corresponding to the obtained course are input into the second screening model for courses to be updated. The second screening model for courses to be updated is used to calculate a value that can characterize whether the online course corresponding to the course meets the update requirements. Whether the update requirements are met is determined based on the value. When the update requirements are met, the online course corresponding to the course is determined to be a course that needs to be updated.
[0105] In an embodiment of the present application, if the teaching type is determined to be offline teaching, a first course screening model to be updated is obtained, and the first course screening model to be updated is used to determine the historical training course data that meets the update requirements. If the teaching type is determined to be online teaching, a second course screening model to be updated is obtained, and the second course screening model to be updated is used to determine the historical training course data that meets the update requirements. Different course screening models to be updated are used for different teaching types, so that historical training courses that meet different update conditions can be screened out more specifically, making the screened historical training courses that meet the update conditions more accurate.
[0106] Embodiment 4
[0107] Figure 5 The flow chart of the training course recommendation method provided in the fourth embodiment of the present application is as follows: Figure 5 As shown, based on the content of Example 3, the embodiment of the present application involves a specific implementable method of using the first to-be-updated course screening model to determine the historical training course data that meets the update requirements in step S301. In the training course recommendation method provided by the present application, the first to-be-updated course screening model is used to determine the historical training course data that meets the update requirements, including the following steps:
[0108] Step S401: Determine the first course screening indicator to be updated corresponding to the historical training course data. The first course screening indicator to be updated includes: the latest teaching time, the number of teaching times within a preset time range, and the teaching score.
[0109] Specifically, obtain multiple face-to-face courses CC k , k = 1, 2, 3, ... K, K is the number of face-to-face courses. Get face-to-face courses CC k The latest teaching time CCNTime k , the number of classes within the preset time range CCN k and CCSk The above information is determined as the first selection index for the courses to be updated. The preset time range is not limited and can be within one year.
[0110] Step S402: input the first to-be-updated course screening indicator into the first to-be-updated course screening model.
[0111] The first model to be updated can be expressed as:
[0112] f1=f11+∧(∨(CCN k -CCN0,0),1)+∧(∨(CCS k -CCS0,0),1)
[0113] in,
[0114] Among them, CCN0 is the threshold of the number of lectures, CCS0 is the threshold of the lecture score, T0 is the current time, and TV1 is the threshold of the number of days from the current time to the latest lecture time of the same course. Each threshold is greater than 0 and can be set as needed. ∨ is a large symbol, and ∧ is a small symbol. The course indicators obtained in step S401 are input into the first model to be updated.
[0115] Step S403: Use the first to-be-updated course screening model to screen out historical training course data that meets the update requirements.
[0116] When f1=0, face-to-face courses CC k Meet the update conditions. f1=0 The meaning of a course meeting the update conditions is: when the number of course lectures and the teaching score do not reach the preset threshold, and the number of days from the latest teaching time to the current time exceeds the preset threshold, the course needs to be updated. When f1=1, the face-to-face course CC k The update condition is not met. f1=1 The course does not meet the update condition means that when the number of course lectures or the teaching score reaches the preset threshold, or the number of days from the latest teaching time to the present does not exceed the preset threshold, the course does not need to be updated.
[0117] In an embodiment of the present application, a first course screening indicator to be updated corresponding to the historical training course data is determined. The first course screening indicator to be updated includes: the latest teaching time, the number of teachings within a preset time range, and the teaching score, and the first course screening indicator to be updated is input into the first course screening model to be updated. The first course screening model to be updated is used to filter out historical training course data that meets the update requirements. For face-to-face courses, the first course screening model to be updated is used to screen the courses by determining the screening indicators. Since the first course screening model to be updated comprehensively considers the influence of the latest teaching time, the number of teachings within a preset time range, and the teaching score, it is possible to accurately screen out historical training courses that meet the update conditions of face-to-face courses.
[0118] Embodiment 5
[0119] Figure 6 The flowchart of the training course recommendation method provided in Example 5 of this application is as follows: Figure 6 As shown, based on the content of Example 3 or Example 4, the embodiment of the present application involves a specific implementable method of using the second to-be-updated course screening model to determine the historical training course data that meets the update requirements in step S302. In the training course recommendation method provided by the present application, the second to-be-updated course screening model is used to determine the historical training course data that meets the update requirements, including the following steps:
[0120] Step S501: Determine the second to-be-updated course screening indicator corresponding to the historical training course data, where the second to-be-updated course screening indicator includes: the number of learners, the number of learning times and the learning duration within a preset time range.
[0121] Specifically, get the online course CC' k , k = 1, 2, 3, ... T, T is the number of online courses. Then get the online course CC' from the database k Learning volume information, including the number of learners within the preset time range CCS1 k 、Number of learning times CCS2 k and study time CCS3 k The above information is determined as the second selection index for the courses to be updated. The preset time range is not limited and can be within one year.
[0122] Step S502: input the second to-be-updated course screening index into the second to-be-updated course screening model.
[0123] Among them, the second to-be-updated course screening model can be expressed in two formulas:
[0124] a. The absolute value method formula can be expressed as:
[0125] f2=∧(∨(CCS1k -A1,0),1)+∧(∨(CCS2 k -A2,0),1)+∧(∨(CCS3 k -A3, 0), 1)
[0126] Among them, A1, A2, and A3 are thresholds corresponding to each indicator, and each threshold is greater than 0 and can be set as needed.
[0127] b. The relative value method formula can be expressed as:
[0128] f3=∧(∨(CCS1 k / AVG1-B1,0),1)+∧(∨(CCS2 k / AVG2-B2,0),1)+∧(∨(CCS3 k / AVG3-B3,0),1)
[0129] Among them, AVG1, AVG2, and AVG3 are the average values of the number of learners, the number of learning times, and the length of learning time. B1, B2, and B3 are the thresholds of the corresponding indicators, and each threshold is greater than 0 and can be set as needed.
[0130] Step S503: Use the second to-be-updated course screening model to screen out historical training course data that meets the update requirements.
[0131] If function f2=0 or f3=0, it is considered that course CC' k Satisfy the update conditions. Function f2=0 or f3=0, the course satisfies the update conditions means: when the relative values of the number of learners, number of learning times and learning time cannot reach the preset threshold, the course is an inactive course and needs to be updated. Function f2>0 or f3>0, the course does not need to be updated. Function f2>0 or f3>0 The course does not need to be updated means that any relative value of the number of learners, number of learning times and learning time of the online course reaches the preset threshold, the course is an active course and does not need to be updated.
[0132] In an embodiment of the present application, a second course screening indicator to be updated corresponding to the historical training course data is determined. The second course screening indicator to be updated includes: the number of learners, the number of learning times and the length of learning time within a preset time range. The second course screening indicator to be updated is input into the second course screening model to be updated. The second course screening model to be updated is used to screen out historical training course data that meets the update requirements. For online courses, by determining the screening indicators, the second course screening model to be updated is used to screen the courses. Since the second course screening model to be updated comprehensively considers the influence of the number of learners, the number of learning times and the length of learning time within a preset time range, it is possible to accurately screen out historical training courses that meet the online course update conditions.
[0133] Embodiment 6
[0134] Figure 7 The flow chart of the training course recommendation method provided in the fourth embodiment of the present application is as follows: Figure 7 As shown, based on the content of any one of the embodiments from Embodiment 2 to Embodiment 5, the embodiment of the present application involves a specific implementation method of step S202, in which if the teaching type is offline teaching, a corresponding replacement course screening model is used to determine a corresponding replacement course. In the training course recommendation method provided by the present application, if the teaching type is offline teaching, a corresponding replacement course screening model is used to determine a corresponding replacement course, including the following steps:
[0135] Step S601: Obtain a first replacement course screening model and a plurality of candidate training course data.
[0136] Among them, the first replacement course screening model refers to a model that meets the replacement screening requirements for corresponding courses with offline teaching types.
[0137] Specifically, get the course CC k Keywords CCW k , find similar courses based on keyword information as alternative training course data CC s , s = 1, 2, 3, … S, S is the number of alternative training courses corresponding to the face-to-face courses.
[0138] The first replacement course screening model is expressed as: f4 = f(CCNTime s ,TN s ,CCS s ), where CCNTime s It is an alternative training course CC S Latest class schedule for TN S It is an alternative training course CC S The activity of the lecturer can be expressed by the number of lectures given within a preset time range. S It is an alternative training course CC S Teaching ratings.
[0139] Step S602: Determine the first replacement course screening index corresponding to each candidate training course data. The first replacement course screening index includes: the latest teaching time, lecturer activity and course rating within a preset time range.
[0140] Specifically, the first replacement course screening index corresponding to each candidate training course data is determined according to the input data of the first replacement course screening model, including the latest teaching time, lecturer activity and course rating within a preset time range.
[0141] Step S603: input the first replacement course screening index into the first replacement course screening model.
[0142] Specifically, the first replacement course screening index of each candidate training course is input into the first replacement course screening model for calculation.
[0143] The first replacement course screening model can be expressed as:
[0144]
[0145] Among them, T0 is the current time, TN0 is the reference value of the instructor's activity, and CCS0 is the reference value of the course score. The reference value is not limited to a range and can be set as needed. For example, TN0 can be 5 and CCS0 can be 85%. CCNTime S TN S and CCS S As model input data, the specific meaning is as described above.
[0146] Step S604: Use the first replacement course screening model to screen out replacement courses.
[0147] Among them, for courses with f4>0, the f4 values are sorted in descending order. The f4 value is proportional to the instructor activity, teaching score, and latest teaching time of the candidate training courses. That is, the higher the instructor activity and teaching score, the larger the f4 value; the closer the latest teaching time is to the present, the larger the f4 value. Therefore, the first 1 to 2 courses with larger f4 values are selected as the course CC k Replacement courses.
[0148] In an embodiment of the present application, a first replacement course screening model and multiple alternative training course data are obtained. The first replacement course screening indicators corresponding to each alternative training course data are determined. The first replacement course screening indicators include: the latest teaching time, lecturer activity and course rating within a preset time range. The first replacement course screening indicators are input into the first replacement course screening model. The first replacement course screening model is used to screen out replacement courses. For face-to-face courses, the alternative training course data are determined by keywords, and the replacement course screening indicators are determined at the same time. Since the first replacement course screening model comprehensively considers the impact of the latest teaching time, lecturer activity and course rating within a preset time range on screening replacement courses of offline teaching types, it is possible to accurately determine the replacement courses corresponding to the face-to-face courses that need to be updated.
[0149] Embodiment 7
[0150] Figure 8 The flow chart of the training course recommendation method provided in the fourth embodiment of the present application is as follows: Figure 8As shown, based on the content of any one of the embodiments from Embodiment 2 to Embodiment 6, the embodiment of the present application involves a specific implementation method of step 202, if the teaching type is online teaching, then the corresponding replacement course screening model is used to determine the corresponding replacement course. In the training course recommendation method provided by the present application, if the teaching type is online teaching, the corresponding replacement course screening model is used to determine the corresponding replacement course, including the following steps:
[0151] Step S701: Obtain a second replacement course screening model and a plurality of candidate training course data.
[0152] Among them, the second replacement course screening model refers to a model that meets the replacement screening requirements for courses corresponding to online teaching types.
[0153] Specifically, get the online course CC' k Keywords CCW k , find similar courses based on keyword information as alternative training course data CC q , q=1,2,3,…Q, Q is the number of alternative training courses corresponding to the online courses.
[0154] The second replacement course screening model is expressed as: f5 = f(T q ,CCS1 q ,CCS2 q ,CCS3 q ), where T q Yes Course CC q Course launch time, CCS1 q ,CCS2 q ,CCS3 q CC q The number of learners, number of learning times and duration of learning.
[0155] Step S702: Determine the second replacement course screening index corresponding to each candidate training course data. The second replacement course screening index includes: course online time, number of learners, number of learning times and learning duration.
[0156] Specifically, the second replacement course screening indicators corresponding to each candidate training course data are determined according to the input data of the second replacement course screening model, including the course online time, the number of learners, the number of learning times and the learning duration.
[0157] Step S703: input the second replacement course screening index into the second replacement course screening model.
[0158] Specifically, the second replacement course screening index of each candidate training course is input into the second replacement course screening model for calculation.
[0159] The second replacement screening course can be expressed as:
[0160]
[0161]
[0162] Among them, T0 is the current time, AVG1, AVG2, and AVG3 are the average values of the number of students, number of learning times, and learning time of all online courses. q ,CCS1 q ,CCS2 q ,CCS3 q is the input data of the model, and its specific meaning is as described above. The α value is used as the basis for whether it can be used as an alternative training course. q When the number of learners, number of learning times and learning duration of the online course do not reach the average value of the corresponding indicators of the online course, α = 0, and the alternative training course CC q Cannot be used as a replacement course. α=1, alternative training course CC q Can be used as an alternative course.
[0163] Step S704: Use the second replacement course screening model to screen out replacement courses.
[0164] For courses with f5>0, the f5 values are sorted in descending order. Since the f5 value is proportional to the number of learners, number of learning times, learning time, and course launch time of the candidate training courses, that is, the more learners, the more times of learning, and the longer the learning time, the larger the f5 value; the closer the course launch time is to the present, the larger the f5 value. Therefore, the first 1 to 2 courses with larger f5 values are selected as the course CC' k Replacement courses.
[0165] In an embodiment of the present application, a second replacement course screening model and multiple alternative training course data are obtained. The second replacement course screening indicators corresponding to each alternative training course data are determined. The second replacement course screening indicators include: course online time, number of learners, number of learning times and learning duration. The second replacement course screening indicators are input into the second replacement course screening model. The second replacement course screening model is used to screen out replacement courses. For online courses, the alternative training course data are determined by keywords, and the replacement course screening indicators are determined at the same time. Since the second replacement course screening model comprehensively considers the influence of the number of learners, number of learning times, learning duration and course online time, it is possible to accurately determine the replacement courses corresponding to the online courses that need to be updated.
[0166] Embodiment 8
[0167] Fig. 9 The flow chart of the training course recommendation method provided in the fourth embodiment of the present application is as follows: Fig. 9 As shown, based on the content of any one of the embodiments 1 to 7, the embodiment of the present application relates to a specific implementation method of step S103 using updated historical training course data to recommend courses to users. In the training course recommendation method provided by the present application, using updated historical training course data to recommend courses to users includes the following steps:
[0168] Step S801: receiving a course recommendation request sent by a user terminal, wherein the course recommendation request includes a training employee type and a course keyword.
[0169] Specifically, when the training administrator sets a course in the user terminal, he inputs the training staff type and course keyword information, and the user terminal sends a course recommendation request to the electronic device. The electronic device receives the course recommendation request sent by the user terminal, and the request includes the input training staff type and course keyword information.
[0170] Among them, the course keyword can be the type of course. For example, in the course training of the enterprise technology department, the course keyword can be: artificial intelligence, cloud computing, intelligent transportation, etc.
[0171] Step S802: using a trained recommendation model to determine recommended courses based on the training employee type and course keywords; the trained recommendation model is obtained by training using updated historical training course data.
[0172] Specifically, the recommendation model is not limited in scope. Various recommendation algorithm models can be used. This application adopts a multi-layer perceptron model. The training employee type and course keyword information are input, and the updated historical training course data is input into the trained recommendation model as a recommended course data set. After matching calculation, a preset number of recommended course information is output.
[0173] There is no limitation on the training process of the recommendation model using the updated historical training course data, and after the recommendation model is trained to convergence, a trained recommendation model is obtained.
[0174] Step S803: Send the recommended courses to the user terminal so that the user terminal displays the recommended courses on the recommendation interface.
[0175] Specifically, the electronic device sends a preset number of recommended course information to the user terminal, so that the user terminal displays the recommended course information on the recommendation interface.
[0176] In an embodiment of the present application, a course recommendation request sent by a user terminal is received, the course recommendation request including the training employee type and the course keywords. A trained recommendation model is used to determine the recommended courses based on the training employee type and the course keywords; the trained recommendation model is obtained by training with updated historical training course data. The recommended courses are sent to the user terminal so that the user terminal displays the recommended courses on the recommendation interface. This embodiment uses a trained recommendation model to recommend courses, sends the recommended courses to the user terminal, and displays the recommended courses on the recommendation interface, thereby effectively improving the efficiency of users in setting courses.
[0177] Embodiment 9
[0178] Fig.10 This is a structural diagram of the course recommendation device provided in Example 1 of the present application, such as Fig.10 As shown, the course recommendation device 80 provided in this embodiment includes: an acquisition module 81, an update module 82, and a recommendation module 83.
[0179] The acquisition module 81 is used to acquire historical training course data, which includes: teaching type.
[0180] The updating module 82 is used to update the historical training course data that meets the updating requirements according to the teaching type to obtain updated historical training course data.
[0181] The recommendation module 83 is used to recommend courses to users using the updated historical training course data. Optionally, the update module 82 is used to update the historical training course data that meets the update requirements according to the teaching type to obtain the updated historical training course data. Specifically, it is used to: determine the historical training course data that meets the update requirements according to the teaching type. Use the corresponding replacement course screening model to determine the corresponding replacement course. Use the replacement course to update the historical training course data that meets the update requirements.
[0182] Optionally, the updating module 82, in determining the historical training course data that meets the updating requirement according to the teaching type, is specifically configured to:
[0183] If the teaching type is determined to be offline teaching, the first course screening model to be updated is obtained, and the historical training course data that meets the update requirements is determined by using the first course screening model to be updated. If the teaching type is determined to be online teaching, the second course screening model to be updated is obtained, and the historical training course data that meets the update requirements is determined by using the second course screening model to be updated.
[0184] Optionally, the updating module 82, in determining the historical training course data that meets the updating requirement by using the first to-be-updated course screening model, is specifically configured to:
[0185] Determine the first to-be-updated course screening index corresponding to the historical training course data, the first to-be-updated course screening index includes: the latest teaching time, the number of teachings within a preset time range, and the teaching score. Input the first to-be-updated course screening index into the first to-be-updated course screening model. Use the first to-be-updated course screening model to screen out the historical training course data that meets the update requirements.
[0186] Optionally, the updating module 82, in determining the historical training course data that meets the updating requirement by using the second to-be-updated course screening model, is specifically configured to:
[0187] Determine the second course screening index to be updated corresponding to the historical training course data. The second course screening index to be updated includes: the number of learners, the number of learning times, and the learning duration within a preset time range. Input the second course screening index to be updated into the second course screening model to be updated. Use the second course screening model to screen out the historical training course data that meets the update requirements.
[0188] Optionally, the updating module 82, if the teaching type is offline teaching, uses the corresponding replacement course screening model to determine the corresponding replacement course, specifically for:
[0189] Obtain a first replacement course screening model and multiple candidate training course data. Determine the first replacement course screening indicators corresponding to each candidate training course data. The first replacement course screening indicators include: the latest teaching time, lecturer activity, and course ratings within a preset time range. Input the first replacement course screening indicators into the first replacement course screening model. Use the first replacement course screening model to screen out replacement courses.
[0190] Optionally, the updating module 82, if the teaching type is online teaching, adopts the corresponding replacement course screening model to determine the corresponding replacement course, specifically for:
[0191] Obtain a second replacement course screening model and multiple candidate training course data. Determine the second replacement course screening indicators corresponding to each candidate training course data. Among them, the second replacement course screening indicators include: course online time, number of learners, number of learning times and learning duration. Input the second replacement course screening indicators into the second replacement course screening model. Use the second replacement course screening model to filter out replacement courses. Optionally, the recommendation module 83, in using the updated historical training course data to recommend courses to users, is specifically used to:
[0192] Receive the employee type and course keywords entered by the user in the input box of the recommendation interface. Use the trained recommendation model to recommend courses to the user based on the employee type and course keywords. The trained recommendation model is trained using the updated historical training course data.
[0193] Embodiment 10
[0194] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Fig.11 As shown, an electronic device provided by an embodiment of the present application, the electronic device 90 includes: a processor 91, and a memory 92, an input device 93, an output device 94 and a bus 95 that are communicatively connected to the processor.
[0195] Memory 92 stores computer executable instructions.
[0196] The processor 91 executes the computer-executable instructions stored in the memory to implement the method described in any one of Embodiments 1 to 8.
[0197] The input device 93 is used to receive data input by the user.
[0198] The output device 94 is used to output the courses recommended for the user.
[0199] The processor 91 , the memory 92 , the input device 93 , and the output device 94 are connected and communicate with each other via a bus 95 .
[0200] An embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the method provided by any of the above method embodiments is implemented.
[0201] An embodiment of the present application also provides a computer program product, including a computer program, which implements the method provided in any embodiment of the present application when the computer program is executed by a processor.
[0202] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.
[0203] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0204] In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional modules.
[0205] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable compliance detection device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.
[0206] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0207] In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination mode.
[0208] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.
[0209] It should be understood that the present application is not limited to the precise 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 application is limited only by the appended claims.
Claims
1. A course recommendation method, characterized in that: include: Acquire historical training course data, wherein the historical training course data includes: teaching type; Updating the historical training course data that meets the update requirements according to the teaching type to obtain updated historical training course data; Use updated historical training course data to recommend courses to users; The updating of the historical training course data that meets the updating requirements according to the teaching type to obtain updated historical training course data includes: Determine historical training course data that meets the update requirements according to the course types; Use the corresponding replacement course screening model to determine the corresponding replacement course; Update historical training course data that meets update requirements using replacement courses; If the teaching type is offline teaching, the corresponding replacement course screening model is used to determine the corresponding replacement course, including: Obtaining a first replacement course screening model and multiple alternative training course data; Determine a first replacement course screening indicator corresponding to each candidate training course data; the first replacement course screening indicator includes: the latest teaching time, instructor activity, and course rating within a preset time range; inputting the first replacement course screening indicator into the first replacement course screening model; The first replacement course screening model was used to screen out replacement courses; If the course type is online, the corresponding replacement course screening model is used to determine the corresponding replacement course, including: Obtaining a second replacement course screening model and multiple alternative training course data; Determine the second replacement course screening indicators corresponding to each candidate training course data; the second replacement course screening indicators include: course online time, number of learners, number of learning times, and learning duration; inputting the second replacement course screening indicator into the second replacement course screening model; The second replacement course screening model is used to screen out replacement courses.
2. The method according to claim 1, characterized in that The historical training course data that meets the update requirements is determined according to the teaching type, including: If it is determined that the teaching type is offline teaching, obtaining a first course screening model to be updated, and using the first course screening model to be updated to determine historical training course data that meets the update requirements; The method of using the first to-be-updated course screening model to determine historical training course data that meets the update requirements includes: Determine a first to-be-updated course screening indicator corresponding to the historical training course data, where the first to-be-updated course screening indicator includes: the latest teaching time, the number of teaching times within a preset time range, and the teaching score; Inputting the first to-be-updated course screening indicator into the first to-be-updated course screening model; Using the first to-be-updated course screening model to screen out historical training course data that meets the update requirements; If it is determined that the teaching type is online teaching, obtaining a second screening model for courses to be updated, and using the second screening model for courses to be updated to determine historical training course data that meets the update requirements; The method of using the second to-be-updated course screening model to determine the historical training course data that meets the update requirements includes: Determine a second to-be-updated course screening indicator corresponding to the historical training course data, where the second to-be-updated course screening indicator includes: the number of learners, the number of learning times, and the learning duration within a preset time range; inputting the second to-be-updated course screening indicator into the second to-be-updated course screening model; The second to-be-updated course screening model is used to screen out historical training course data that meets the update requirements.
3. The method according to any one of claims 1-2, characterized in that The updated historical training course data is used to recommend courses to users, including: receiving a course recommendation request sent by a user terminal, wherein the course recommendation request includes a training employee type and a course keyword; Determine recommended courses based on the training employee type and course keywords using a trained recommendation model; the trained recommendation model is obtained by training using updated historical training course data; The recommended courses are sent to the user terminal so that the user terminal displays the recommended courses on a recommendation interface.
4. A course recommendation device, characterized in that: include: An acquisition module is used to acquire historical training course data, wherein the historical training course data includes: teaching type; An updating module is configured to update the historical training course data that meets the updating requirements according to the teaching type to obtain updated historical training course data; the updating of the historical training course data that meets the updating requirements according to the teaching type to obtain updated historical training course data comprises: determining the historical training course data that meets the updating requirements according to the teaching type; determining the corresponding replacement course using a corresponding replacement course screening model; and updating the historical training course data that meets the updating requirements using the replacement course; The updating module is further configured to, if the teaching type is offline teaching, determine a corresponding replacement course using a corresponding replacement course screening model, including: obtaining a first replacement course screening model and a plurality of candidate training course data; determining a first replacement course screening indicator corresponding to each candidate training course data; the first replacement course screening indicator including: the latest teaching time, instructor activity, and course rating within a preset time range; inputting the first replacement course screening indicator into the first replacement course screening model; and screening out replacement courses using the first replacement course screening model; The updating module is further configured to, if the teaching type is online teaching, determine a corresponding replacement course using a corresponding replacement course screening model, including: obtaining a second replacement course screening model and a plurality of candidate training course data; determining a second replacement course screening indicator corresponding to each candidate training course data; the second replacement course screening indicator including: course online time, number of learners, number of learning times, and learning duration; inputting the second replacement course screening indicator into the second replacement course screening model; and screening out replacement courses using the second replacement course screening model; The recommendation module is used to recommend courses to users using updated historical training course data.
5. An electronic device, characterized in that: include: a processor, and a memory, an input device, and an output device communicatively connected to the processor; The memory stores computer-executable instructions; the input device is used to receive data input by a user; The output device is used to output the courses recommended for the user; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 3.
6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 3 when executed by a processor.
