Online course learning path recommendation method and device

By calculating the sequence scores and classification sorting between courses, the optimized online course learning path is recommended, which solves the problem of poor recommendation results of learning paths in the existing technology, and improves the learning effect and user experience.

WO2024250373A1PCT designated stage expired Publication Date: 2024-12-12GUO RUNQI
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2023/106077
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-06-06
Filing Date
2023-07-06
Publication Date
2024-12-12

AI Technical Summary

Technical Problem

The existing online course platform is difficult to effectively recommend learning paths, which leads to users who need to decide on the learning order by themselves, and the recommendation effect is poor.

Method used

By determining the user's learning objectives and completed courses, obtaining course learning paths for reference objects with the same learning objectives, calculating the order scores between courses, and classifying and sorting courses to recommend optimized learning paths.

Benefits of technology

It improves the effect of learning path recommendation, enables users to study courses in the order of recommendation, improves learning effect, and reduces the burden of users to decide on the learning order by themselves.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2023106077_12122024_PF_FP_ABST
    Figure CN2023106077_12122024_PF_FP_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of networks, and provides an online course learning path recommendation method and device. The method comprises: determining a learning objective and completed courses of an object waiting for recommendation; determining a set of reference objects which have the same learning objective as the object waiting for recommendation and have achieved the learning objective; acquiring a course learning path of each reference object in the set of reference objects, and according to each course in the course learning path of each reference object, determining a course set corresponding to the learning objective; determining a sequence score between any two courses in the course set; classifying each course in the course set according to course content to obtain multiple categories; sorting the multiple categories in sequence according to the sequence score and the completed courses; and according to a category sorting result, determining a subsequent learning path recommended for the object waiting for recommendation on the basis of the completed courses. The present solution can recommend a learning path having a learning sequence and improve the recommendation effect.
Need to check novelty before this filing date? Find Prior Art

Description

Online course learning path recommendation method and device Technical Field

[0001] The embodiments of the present invention relate to the field of network technology, and in particular to a method and device for recommending an online course learning path. Background Art

[0002] With the rapid development and widespread application of internet technology, online courses have gradually become a focus of attention. Users can select the online courses they want to study on online course platforms. Existing online course platforms can recommend multiple online courses based on their learning goals. However, this recommendation is ineffective as users are required to decide the order in which to study.

[0003] Summary of the Invention

[0004] The embodiments of the present invention provide a method and device for recommending an online course learning path, which can recommend a learning path with a learning sequence and improve the recommendation effect.

[0005] In a first aspect, an embodiment of the present invention provides a method for recommending an online course learning path, comprising:

[0006] Determine the learning objectives of the subject to be recommended and the completed courses aimed at the learning objectives;

[0007] Determining a set of reference subjects that have the same learning goal as the subject to be recommended and achieve the learning goal;

[0008] Obtaining a course learning path for each reference object in the reference object set, and determining a course set corresponding to the learning objective based on each course in the course learning path of each reference object;

[0009] Determine, based on the course learning path of each reference object, a sequence score between any two courses in the course set; the sequence score is used to indicate the order in which one course follows another;

[0010] Classifying each course in the course set according to course content to obtain a plurality of categories; each category includes at least one course;

[0011] sorting the multiple categories in order of priority based on the priority scores and the completed courses;

[0012] A subsequent learning path recommended for the recommended subject based on the completed course is determined according to the classification and sorting results; the courses on the subsequent learning path are all located in the course set.

[0013] Preferably, determining the sequence score between any two courses in the course set based on the course learning path of each reference object includes:

[0014] For a first course and a second course in the course set, determining, in a course learning path of each reference object, a first course learning path in which the second course is located after the first course, and a second course learning path in which the first course is located after the second course;

[0015] Determine the number of interval courses between the first course and the second course in each first course learning path, and multiply the sum of the quantitative values ​​corresponding to the number of interval courses by the number of first course learning paths to determine the order score of the second course after the first course;

[0016] Determine the number of interval courses between the first course and the second course in each second course learning path, and multiply the sum of the quantitative values ​​corresponding to the number of interval courses by the number of second course learning paths to determine the sequence score of the first course after the second course.

[0017] Preferably, the step of sorting the multiple categories in order of priority based on the priority scores and the completed courses includes:

[0018] determining whether there is a non-reference course that does not belong to the course set among the completed courses;

[0019] If so, deleting the non-reference course and determining the completed categories and unfinished categories in the multiple categories based on the categories to which the remaining completed courses belong;

[0020] performing a first sorting of the completed categories according to the order of the remaining completed courses;

[0021] The unfinished categories are sorted for the second time according to the first sorting result and the sequence scores.

[0022] Preferably, the first sorting of the completed categories according to the order of the remaining completed courses includes:

[0023] If there are multiple completed courses belonging to the same category among the remaining completed courses, the position of any one of the multiple completed courses belonging to the same category will be used as the position in the order of the category to which they belong.

[0024] Preferably, performing a second sorting on the unfinished categories according to the first sorting result and the sequence scores includes:

[0025] Determine the possible sorting combinations for the unfinished classification;

[0026] Adding each sorting combination to the first sorting result to form a new sorting combination;

[0027] For each new ranking combination, determine the average score of the order in which the latter category is located after the former category between each two adjacent categories in the new ranking combination, and determine the sum of the average scores of each order as the total order score of the new ranking combination;

[0028] The sorting combination corresponding to the maximum total score of the order in each new sorting combination is determined as the second sorting result of the incomplete classification.

[0029] Preferably, determining the subsequent learning path recommended to the recommended subject based on the completed course according to the classification and sorting results includes:

[0030] Selecting a course from each of the unfinished categories and forming a recommended path according to the second sorting result to obtain a recommended path set;

[0031] According to the recommended path set, a subsequent learning path recommended for the subject to be recommended based on the completed course is determined.

[0032] Preferably, it also includes:

[0033] When it is determined that the subject to be recommended has not selected a course according to the subsequent learning path, the completed course is updated, and a subsequent learning path recommended to the subject to be recommended based on the completed course is re-determined.

[0034] In a second aspect, an embodiment of the present invention further provides an online course learning path recommendation device, comprising:

[0035] A first determining unit is used to determine the learning objectives of the recommended subject and the completed courses for the learning objectives;

[0036] A second determining unit is configured to determine a set of reference objects that have the same learning goal as the object to be recommended and achieve the learning goal;

[0037] a third determining unit, configured to obtain a course learning path for each reference object in the reference object set, and determine a course set corresponding to the learning objective based on each course in the course learning path of each reference object;

[0038] A fourth determining unit is configured to determine a sequence score between any two courses in the course set based on the course learning path of each reference object; the sequence score is used to indicate the order in which one course follows another course;

[0039] a classification unit, configured to classify each course in the course set according to course content to obtain a plurality of categories; each category includes at least one course;

[0040] A sorting unit, configured to sort the multiple categories in order according to the order scores and the completed courses;

[0041] The recommendation unit is used to determine a subsequent learning path recommended to the recommended object based on the completed course according to the classification and sorting results; the courses on the subsequent learning path are all located in the course set.

[0042] In a third aspect, an embodiment of the present invention further provides a computing device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in any embodiment of this specification is implemented.

[0043] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, enables the computer to execute the method described in any embodiment of this specification.

[0044] The embodiment of the present invention provides a method and device for recommending online course learning paths. Since the learning objectives of each reference object in the reference object set are the same as the learning objectives of the object to be recommended, and each reference object has achieved the learning objective, it can be seen that the course set formed by each course in the course learning path of the reference object has more reference value for the recommended object. The courses in the course set almost cover all course stages that can achieve the learning objectives. By classifying each course in the course set according to the course content, the multiple classifications obtained correspond to the various course stages that can achieve the learning objectives. In addition, each course in the course learning path of each reference object has a sequence, and the sequence between any two courses in the course set can be determined. Value, the sequence score is used to indicate the order of one course after another, that is, there is a certain learning order when studying multiple courses. Compared with studying in the order of randomly selecting courses, studying in a certain learning order can make the learning effect better. Therefore, the sequence scores between courses can be used to sort multiple categories to obtain the learning order of multiple course stages; in addition, since the recommended objects have completed courses, it is necessary to use the completed courses and the sorting results to recommend subsequent learning paths for the recommended objects, so that the recommended objects can study the courses in the order of the courses on the recommended subsequent learning path without having to decide the learning order by themselves, thereby improving the recommendation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] FIG1 is a flow chart of a method for recommending an online course learning path according to an embodiment of the present invention;

[0047] FIG2 is a flow chart of a classification and sorting method provided by one embodiment of the present invention;

[0048] FIG3 is a hardware architecture diagram of a computing device provided by an embodiment of the present invention;

[0049] FIG4 is a structural diagram of an online course learning path recommendation device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0051] Referring to FIG1 , an embodiment of the present invention provides a method for recommending an online course learning path, the method comprising:

[0052] Step 100: Determine the learning goals of the recommended subject and the completed courses for the learning goals;

[0053] Step 102: Determine a set of reference objects that have the same learning goal as the object to be recommended and achieve the learning goal;

[0054] Step 104: Obtain a course learning path for each reference object in the reference object set, and determine a course set corresponding to the learning objective based on each course in the course learning path of each reference object;

[0055] Step 106: Determine a precedence score between any two courses in the course set based on the course learning path of each reference object; the precedence score is used to indicate the order in which one course follows another.

[0056] Step 108: Classify each course in the course set according to the course content to obtain multiple categories; each category includes at least one course;

[0057] Step 110, sorting the multiple categories in order of priority based on the priority scores and the completed courses;

[0058] Step 112: Determine a subsequent learning path recommended for the recommended subject based on the completed course according to the classification and sorting results; all courses on the subsequent learning path are located in the course set.

[0059] In the embodiment of the present invention, since the learning objectives of each reference object in the reference object set are the same as the learning objectives of the object to be recommended, and each reference object has achieved the learning objectives, it can be seen that the course set formed by each course in the course learning path of the reference object has more reference value for the recommended object. The courses in the course set almost cover all course stages that can achieve the learning objectives. By classifying each course in the course set according to the course content, the multiple classifications obtained correspond to the various course stages that can achieve the learning objectives; and each course in the course learning path of each reference object has a sequence, and the sequence score between any two courses in the course set can be determined. The sequence score is used In other words, there is a certain learning order when studying multiple courses. Compared with studying in the order of randomly selecting courses, studying in a certain learning order can make the learning effect better. Therefore, the order scores between courses can be used to sort multiple categories to obtain the learning order of multiple course stages. In addition, since the recommended objects have completed courses, it is necessary to use the completed courses and the sorting results to recommend subsequent learning paths for the recommended objects, so that the recommended objects can study the courses in the order of the courses on the recommended subsequent learning path without having to decide the learning order by themselves, thereby improving the recommendation effect.

[0060] The following describes how to execute each step shown in FIG1 .

[0061] First, step 100 "determining the learning objectives of the object to be recommended and the completed courses for the learning objectives" and step 102 "determining a set of reference objects that have the same learning objectives as the object to be recommended and have achieved the learning objectives" are explained simultaneously.

[0062] The learning goal can be entered by the subject when filling out the questionnaire when initially registering on the online course learning platform, or can be entered by the subject when searching for courses on the online course learning platform using the learning goal as a search criterion. For example, the learning goal could be "CET-4" or "IELTS".

[0063] In specific applications, the embodiments of the present invention can be applied in a server. The object (i.e., the user who needs to learn online courses) can log in to the online course learning platform on the terminal and initiate a learning path recommendation request to the server based on the learning goal. The terminal sends the object attribute information and the learning goal to the server, and the server recommends a learning path for the object based on the learning goal.

[0064] When the recommended object initiates a learning path recommendation request to the server, it may have previously studied some courses for the learning goal; or it may not have studied any courses for the learning goal, that is, the number of completed courses is 0.

[0065] In one embodiment of the present invention, a set of reference objects that have the same learning goal as the object to be recommended and have achieved the learning goal can be determined. Since each reference object in the reference object set has achieved the learning goal, the course learning paths of these reference objects are very valuable for reference. Recommending learning paths based on the course learning paths of these reference objects can greatly improve the recommendation effect.

[0066] Wherein, achieving the learning goal may include: passing the grade, the grade to total score ratio exceeding a set ratio, etc. In this embodiment, whether the subject has achieved the learning goal can be determined through feedback on the learning effect.

[0067] Next, step 104 of "obtaining a course learning path for each reference object in the reference object set, and determining a course set corresponding to the learning objective based on each course in the course learning path of each reference object" is described.

[0068] The server stores the records of each reference subject's course learning for the learning objective, and based on the records, a course learning path for the reference subject can be formed. All courses on the course learning path are conducted for the learning objective.

[0069] In one embodiment of the present invention, since these reference objects achieve the learning objectives after completing the study of each course according to the corresponding course learning path, these courses and the order of learning the courses have very great reference value for achieving the learning objectives. All courses in the course learning path of each reference object can be added to the course set corresponding to the learning objective to improve the coverage of the reference courses.

[0070] Furthermore, when each reference subject is studying a course, some of the selected courses may not be of much use in achieving their learning objectives. Therefore, in one embodiment of the present invention, several courses with the lowest course duplication rate can be deleted from the course set obtained above to obtain a processed course set. By eliminating courses with low reference value, course redundancy is reduced, thereby reducing the computational complexity of subsequent processes.

[0071] Next, for step 106, "determine the sequence score between any two courses in the course set based on the course learning path of each reference object; the sequence score is used to represent the sequence relationship of one course after another course."

[0072] What's valuable for achieving learning goals isn't just the courses the subject has already taken, but also the order in which they took them. Because courses are interconnected, they need to be studied in a specific order. Completing the courses first provides a theoretical foundation for subsequent courses, allowing for a better understanding and learning of them, which in turn helps achieve learning goals.

[0073] In the embodiment of the present invention, the order score can be used to represent the order relationship between two courses. The larger the order score, the more the two courses need to be sorted according to the order.

[0074] In one embodiment of the present invention, step 106 can determine the order scores between the two courses in at least one of the following ways, which includes steps S61-S63:

[0075] S61. For the first course and the second course in the course set, determine, in the course learning paths of each reference object, a first course learning path in which the second course follows the first course, and a second course learning path in which the first course follows the second course.

[0076] There are two kinds of order relationships between two courses: one is that the second course is placed after the first course, and the other is that the first course is placed after the second course. Therefore, in this embodiment, it is necessary to determine the order scores for the two order relationships respectively.

[0077] Since different reference objects choose to study different courses, and there are cases where a reference object does not select both the first course and the second course, in this embodiment, a course learning path that includes both the first course and the second course can be first determined in the course learning path of each reference object. Then, a first course learning path in which the second course is located after the first course in the course learning path, and a second course learning path in which the first course is located after the second course can be further determined.

[0078] S62. Determine the number of interval courses between the first course and the second course in each first course learning path, and multiply the sum of the quantitative values ​​corresponding to the number of interval courses by the number of first course learning paths to determine the sequence score of the second course after the first course.

[0079] In an embodiment of the present invention, the more interval courses there are between the first course and the second course, the greater the need for their order. Therefore, the quantitative value corresponding to the number of interval courses can be positively correlated with the number of interval courses. For example, if the first course is adjacent to the second course, the number of interval courses is 0, and the quantitative value of the interval course number of 0 is taken as the basic quantitative value, such as the basic quantitative value is 1. Then, as the number of interval courses gradually increases, the quantitative value also gradually increases. For example, the relationship between the quantitative value of the number of interval courses and the basic quantitative value can be: n =A0*(n+1). Where A n It is the quantitative value corresponding to the number of interval courses being n (n is an integer not less than 0), and A0 is the basic quantitative value.

[0080] In each first-course learning path, the number of courses between the first and second courses can be determined, and the above formula can be used to calculate the quantitative value of the number of courses between them. In this embodiment, the sum of the quantitative values ​​of each first-course learning path multiplied by the number of first-course learning paths is used as the ranking score for the second course after the first course.

[0081] S63. Determine the number of interval courses between the first course and the second course in each second course learning path, and multiply the sum of the quantitative values ​​corresponding to the number of interval courses by the number of second course learning paths to determine the order score of the first course after the second course.

[0082] This step S63 is similar to step S62. Please refer to the relevant description of step S62 for details. This embodiment will not be repeated here.

[0083] It should be noted that in addition to the above-mentioned method for calculating the precedence score, other calculation methods can also be used. For example, only the course learning paths of the first and second courses that are adjacent to each other can be used as the first course learning path or the second course learning path for calculating the precedence score. Then, the number of first course learning paths or the number of second course learning paths divided by the total number of course learning paths that are adjacent to each other can be used as the precedence score for the second course after the first course, or the precedence score for the first course after the second course.

[0084] The following describes step 108 of "classifying the courses in the course set according to the course content to obtain a plurality of categories; each category includes at least one course" and step 110 of "sorting the plurality of categories in order of priority based on the priority scores and the completed courses."

[0085] Since the course collection covers almost all the course stages for achieving the learning goal, in order to ensure that the recommended subjects can complete the courses corresponding to the above-mentioned course stages and increase the probability of achieving the learning goal, the courses in the course collection can be classified according to the course content, and each classification corresponds to a course stage.

[0086] In an embodiment of the present invention, an online course learning platform generally provides a textual introduction to the course content for the subject to refer to and decide whether to study the course. Therefore, when determining the course content, the server can obtain detailed course information and use the detailed course information as the course content.

[0087] In the embodiment of the present invention, a clustering algorithm may be used to classify the courses in the course set, such as KNN algorithm, Kmeans, density clustering, hierarchical clustering, etc.

[0088] In an embodiment of the present invention, the K value of the number of categories may be determined in an adaptive manner, or the mean, median or mode of the number of courses included in the course learning path of each reference object may be determined as the K value of the number of categories.

[0089] Since there is a sequence relationship between courses, after classifying them according to course content, there is also a sequence relationship between the categories.

[0090] Referring to FIG. 2 , the embodiment of the present invention can implement sorting of multiple categories through at least the following steps:

[0091] S20. Determine whether there is any non-reference course in the completed courses that does not belong to the course set; if so, execute S21; if not, execute step S22.

[0092] S21. Delete non-reference courses and execute S22.

[0093] Because the recommended object may have studied randomly selected courses before requesting the server to recommend a learning path, and these completed courses may belong to the course set, or there may be non-reference courses that do not belong to the course set. Non-reference courses have low reference value for achieving learning goals. Therefore, non-reference courses can be deleted and not included as courses on the learning path that needs to be recommended.

[0094] It should be noted that the number of completed courses may also be 0. When the number of completed courses is 0, multiple categories can be determined as unfinished categories for the second sorting.

[0095] S22. Determine completed categories and unfinished categories in the multiple categories based on the categories to which the remaining completed courses belong.

[0096] After deleting non-reference courses, each remaining completed course corresponds to one of the multiple categories. Therefore, the category to which each remaining completed course belongs can be determined by similarity calculation.

[0097] For example, there are multiple categories, namely categories 1 to 10, and there are currently 3 remaining completed courses, namely courses 1 to 3. Among them, course 1 and course 3 belong to category 1, and course 2 belongs to category 2. Then it can be determined that the completed categories among the 10 categories are category 1 and category 2, and the unfinished categories are categories 3 to 10.

[0098] S23. Perform a first sorting of the completed categories according to the order of the remaining completed courses.

[0099] Since the course stages corresponding to the completed categories have been completed, the courses of the completed categories can no longer be recommended to the recommended objects. However, the order of the completed categories has a certain impact on the recommendation of subsequent learning paths. Therefore, the order of the completed categories needs to be determined.

[0100] Specifically, in one embodiment of the present invention, it is possible to determine whether there are multiple completed courses in the remaining completed courses that belong to the same category. If so, the position of any one of the multiple completed courses belonging to the same category is used as the position of the category in the order of precedence; otherwise, the position of the completed course is used as the position of the category in the order of precedence.

[0101] Continuing with the example in the above steps, if the order of courses 1 to 3 is course 1 → course 2 → course 3, then the order of category 1 and category 2 can be: category 1 → category 2, or category 2 → category 1.

[0102] In addition to the above methods for sorting completed categories, you can also use other methods to sort completed categories. For example, you can determine the order of completed courses based on the order of their categories. Continuing with the above example, if the order of courses 1 to 3 is course 1 → course 2 → course 3, the order of completed categories would be category → category 2 → category 1.

[0103] S24. Perform a second sorting on the unfinished categories according to the first sorting result and the sequence scores.

[0104] In this step, if there is a first sorting result, the unfinished classification is second sorted using the first sorting result and the sequence scores between courses; if there is no first sorting result, the unfinished classification is directly second sorted using the sequence scores between courses.

[0105] In one embodiment of the present invention, the second sorting of the unfinished categories can be performed by at least one of the following implementation processes:

[0106] S241. Determine the achievable sorting combinations for the unfinished classification.

[0107] S242: Add each sorting combination to the first sorting result to form a new sorting combination.

[0108] For example, for the sorting combination of category 3 → category 4 → category 5 → category 6 → category 7 → category 8 → category 9 → category 10, add it to the first sorting result category 1 → category 2 to form a new sorting combination: category 1 → category 2 → category 3 → category 4 → category 5 → category 6 → category 7 → category 8 → category 9 → category 10.

[0109] S243. For each new sorting combination, determine the average score of the sequence in which the latter category is located after the former category between each two adjacent categories in the new sorting combination, and determine the sum of the average scores of the sequence as the total score of the sequence of the new sorting combination.

[0110] For example, consider two adjacent categories, category 3 and category 4. Category 3 includes courses 31, 32, and 33, while category 4 includes courses 41 and 42. The average score of the courses in category 4 that follow category 3 can be calculated in one of the following ways:

[0111] For each course in the latter category 4, perform the following steps: calculate the sequence score of the course after each course in the former category 3, and calculate the sum of the sequence scores of the courses;

[0112] Add up the sum of the sequence scores of each course in the next category 4, divide it by the product of the number of courses in the next category 4 and the number of courses in the previous category 3, and use the resulting quotient as the average sequence score of the next category 4 after the previous category 3.

[0113] The average scores of the order of each two adjacent categories are added together to obtain the total score of the order of the new sorting combination. The larger the total score of the order of the new sorting combination, the more accurate the order of the new sorting combination.

[0114] S244: Determine the sorting combination corresponding to the maximum total score of the order in each new sorting combination as the second sorting result for the unfinished classification.

[0115] Illustratively, the second sorting result is: category 8 → category 4 → category 6 → category 10 → category 3 → category 5 → category 9 → category 7.

[0116] It should be noted that in addition to the above-mentioned classification sorting method, other sorting methods can also be used. For example, without considering the sorting of completed categories, the unfinished categories can be directly sorted, and the sorting results of the unfinished categories can be used to recommend subsequent learning courses for the recommended objects, so as to reduce the amount of calculation and improve the recommendation efficiency.

[0117] Finally, for step 112, a subsequent learning path recommended for the recommended object based on the completed course is determined according to the classification and sorting results; the courses on the subsequent learning path are all located in the course set.

[0118] In an embodiment of the present invention, when determining the subsequent learning path, it can include: selecting a course from each of the unfinished categories to form a recommended path according to the second sorting result, and obtaining a recommended path set; based on the recommended path set, determining the subsequent learning path recommended for the recommended object based on the completed course.

[0119] The number of courses in each subsequent learning path in the recommended path set is the same as the number of unfinished categories, and is obtained one-to-one from each unfinished category according to the second sorting result.

[0120] In one embodiment, at least one subsequent learning path in the recommended path set may be used as the subsequent learning path recommended for the object to be recommended.

[0121] In another embodiment, a subsequent learning path with the largest sum of sequence scores may be selected from the recommended path set as the subsequent learning path recommended for the object to be recommended.

[0122] In one embodiment of the present invention, after the server recommends a subsequent learning path for the object to be recommended, it may also include: when it is determined that the object to be recommended has not selected a course according to the subsequent learning path, updating the completed course and re-determining the subsequent learning path recommended for the object to be recommended based on the completed course.

[0123] In the embodiment of the present invention, since the learning objectives of each reference object in the reference object set are the same as the learning objectives of the object to be recommended, and each reference object has achieved the learning objectives, it can be seen that the course set formed by each course in the course learning path of the reference object has more reference value for the recommended object. The courses in the course set almost cover all course stages that can achieve the learning objectives. By classifying each course in the course set according to the course content, the multiple classifications obtained correspond to the various course stages that can achieve the learning objectives; and each course in the course learning path of each reference object has a sequence, and the sequence score between any two courses in the course set can be determined. The sequence score is used In other words, there is a certain learning order when studying multiple courses. Compared with studying in the order of randomly selecting courses, studying in a certain learning order can make the learning effect better. Therefore, the order scores between courses can be used to sort multiple categories to obtain the learning order of multiple course stages. In addition, since the recommended objects have completed courses, it is necessary to use the completed courses and the sorting results to recommend subsequent learning paths for the recommended objects, so that the recommended objects can study the courses in the order of the courses on the recommended subsequent learning path without having to decide the learning order by themselves, thereby improving the recommendation effect.

[0124] In the embodiment of the present invention, due to the different learning foundations of different objects, the course learning path of a certain reference object can only indicate that the reference object can achieve the learning goal by using the course learning path, and cannot fully indicate that other objects can achieve the learning goal by using the course learning path. Therefore, this embodiment does not use the course learning path of a certain reference object as the subsequent learning path recommended for the object to be recommended, but classifies the reference courses in the course set formed by the reference courses so that the classification covers all course stages for achieving the learning goal as much as possible, and selects one course from each classification to recommend to the object to be recommended, so that the object to be recommended can complete all course stages, which can increase the probability of achieving the learning goal.

[0125] As shown in Figures 3 and 4, an embodiment of the present invention provides an online course learning path recommendation device. The device embodiment can be implemented through software, or through hardware or a combination of software and hardware. From the hardware level, as shown in Figure 3, it is a hardware architecture diagram of a computing device where an online course learning path recommendation device provided by an embodiment of the present invention is located. In addition to the processor, memory, network interface, and non-volatile memory shown in Figure 3, the computing device where the device is located in the embodiment can generally also include other hardware, such as a forwarding chip responsible for processing messages, etc. Taking software implementation as an example, as shown in Figure 4, as a device in a logical sense, it is formed by the CPU of the computing device where it is located reading the corresponding computer program in the non-volatile memory into the memory for execution. An online course learning path recommendation device provided in this embodiment includes:

[0126] The first determining unit 401 is configured to determine a learning goal of the recommended subject and completed courses for the learning goal;

[0127] A second determining unit 402 is configured to determine a set of reference objects that have the same learning goal as the object to be recommended and achieve the learning goal;

[0128] The third determining unit 403 is configured to obtain a course learning path for each reference object in the reference object set, and determine a course set corresponding to the learning objective based on each course in the course learning path of each reference object;

[0129] A fourth determining unit 404 is configured to determine a precedence score between any two courses in the course set based on the course learning path of each reference object; the precedence score is used to indicate the order in which one course follows another.

[0130] The classification unit 405 is configured to classify each course in the course set according to the course content to obtain a plurality of categories, each category including at least one course;

[0131] A sorting unit 406 is configured to sort the multiple categories in order of priority based on the priority scores and the completed courses;

[0132] The recommendation unit 407 is configured to determine a subsequent learning path recommended to the recommended subject based on the completed course according to the classification and sorting results; the courses on the subsequent learning path are all located in the course set.

[0133] In one embodiment of the present invention, the fourth determination unit 404 is specifically configured to determine, for the first course and the second course in the course set, the first course learning path in which the second course is located after the first course, and the second course learning path in which the first course is located after the second course in the course learning path of each reference object; determine the number of interval courses between the first course and the second course in each first course learning path, and multiply the sum of the quantitative values ​​corresponding to the number of interval courses by the number of first course learning paths to determine the sequence score of the second course after the first course; determine the number of interval courses between the first course and the second course in each second course learning path, and multiply the sum of the quantitative values ​​corresponding to the number of interval courses by the number of second course learning paths to determine the sequence score of the first course after the second course.

[0134] In one embodiment of the present invention, the sorting unit 406 is specifically used to determine whether there are non-reference courses in the completed courses that do not belong to the course set; if so, delete the non-reference courses, and determine the completed categories and unfinished categories in the multiple categories based on the categories to which the remaining completed courses belong; perform a first sort on the completed categories based on the sequence of the remaining completed courses; and perform a second sort on the unfinished categories based on the first sort result and the sequence score.

[0135] In one embodiment of the present invention, when the sorting unit 406 performs the first sorting of the completed categories according to the order of the remaining completed courses, the steps specifically include:

[0136] If there are multiple completed courses belonging to the same category among the remaining completed courses, the position of any one of the multiple completed courses belonging to the same category will be used as the position in the order of the category to which they belong.

[0137] In one embodiment of the present invention, when the sorting unit 406 performs the second sorting of the unfinished categories according to the first sorting result and the sequence score, the steps specifically include:

[0138] Determine the possible sorting combinations for the unfinished classification;

[0139] Adding each sorting combination to the first sorting result to form a new sorting combination;

[0140] For each new ranking combination, determine the average score of the order in which the latter category is located after the former category between each two adjacent categories in the new ranking combination, and determine the sum of the average scores of each order as the total order score of the new ranking combination;

[0141] The sorting combination corresponding to the maximum total score of the order in each new sorting combination is determined as the second sorting result of the incomplete classification.

[0142] In one embodiment of the present invention, the recommendation unit 407 is specifically used to select a course from each of the unfinished categories and form a recommended path according to the second sorting result to obtain a recommended path set; based on the recommended path set, determine the subsequent learning path recommended for the recommended object based on the completed course.

[0143] In one embodiment of the present invention, the recommendation unit 407 is also used to update the completed course and re-determine the subsequent learning path recommended to the object to be recommended based on the completed course when it is determined that the object to be recommended has not selected a course according to the subsequent learning path.

[0144] It should be understood that the structure illustrated in the embodiments of the present invention does not constitute a specific limitation on an online course learning path recommendation device. In other embodiments of the present invention, an online course learning path recommendation device may include more or fewer components than illustrated, or may combine or separate certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0145] The information interaction, execution process, etc. between the modules in the above-mentioned device are based on the same concept as the embodiment of the method of the present invention. For specific contents, please refer to the description in the embodiment of the method of the present invention and will not be repeated here.

[0146] An embodiment of the present invention further provides a computing device including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, an online course learning path recommendation method according to any embodiment of the present invention is implemented.

[0147] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes a method for recommending an online course learning path according to any embodiment of the present invention.

[0148] Specifically, a system or device equipped with a storage medium can be provided, on which software program codes that implement the functions of any of the above-mentioned embodiments are stored, and a computer (or CPU or MPU) of the system or device can be enabled to read and execute the program codes stored in the storage medium.

[0149] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute part of the present invention.

[0150] Examples of storage media for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code can be downloaded from a server computer via a communication network.

[0151] In addition, it should be clear that the functions of any of the above embodiments can be achieved not only by executing the program code read by the computer, but also by enabling the operating system operating on the computer to complete part or all of the actual operations based on the instructions of the program code.

[0152] In addition, it can be understood that the program code read from the storage medium is written into a memory provided in an expansion board inserted into the computer or into a memory provided in an expansion module connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or expansion module is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above embodiments.

[0153] It should be noted that, in this article, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical factors in the process, method, article or device comprising the elements.

[0154] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk, etc. Various media that can store program codes.

[0155] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for recommending learning paths for online courses, characterized in that: include: Determine the learning objectives of the subject to be recommended and the completed courses for the learning objectives; Determine a set of reference objects that have the same learning goal as the object to be recommended and achieve the learning goal; Obtaining a course learning path for each reference object in the reference object set, and determining a course set corresponding to the learning objective according to each course in the course learning path of each reference object; Determine, according to the course learning path of each reference object, a sequence score between any two courses in the course set; the sequence score is used to indicate the order relationship of one course after another course; Classifying each course in the course set according to the course content to obtain a plurality of categories; each category includes at least one course; According to the sequence scores and the completed courses, the multiple categories are sorted in sequence; A subsequent learning path recommended for the recommended object based on the completed course is determined according to the classification and sorting results; the courses on the subsequent learning path are all located in the course set.

2. The method according to claim 1, characterized in that Determining the sequence score between any two courses in the course set according to the course learning path of each reference object includes: For a first course and a second course in the course set, determining, in the course learning paths of each reference object, a first course learning path in which the second course is located after the first course, and a second course learning path in which the first course is located after the second course; Determine the number of interval courses between the first course and the second course in each first course learning path, and multiply the sum of the quantitative values ​​corresponding to the number of interval courses by the number of first course learning paths to determine the order score of the second course after the first course; Determine the number of interval courses between the first course and the second course in each second course learning path, and multiply the sum of the quantitative values ​​corresponding to the number of interval courses by the number of second course learning paths to determine the sequence score of the first course after the second course.

3. The method according to claim 1, characterized in that The step of sorting the multiple categories in order of priority according to the priority scores and the completed courses includes: determining whether there is a non-reference course that does not belong to the course set among the completed courses; If so, the non-reference course is deleted, and the completed categories and unfinished categories in the multiple categories are determined according to the categories to which the remaining completed courses belong; Performing a first sorting of the completed categories according to the order of the remaining completed courses; The unfinished categories are subjected to a second sorting according to the first sorting result and the sequence scores.

4. The method according to claim 3, characterized in that The first sorting of the completed categories according to the order of the remaining completed courses includes: If there are multiple completed courses belonging to the same category among the remaining completed courses, the position of any one of the multiple completed courses belonging to the same category will be used as the position of the category in the order of precedence.

5. The method according to claim 3 or 4, characterized in that: The second sorting of the unfinished categories according to the first sorting result and the sequence scores includes: Determine the possible sorting combinations that can be achieved by the incomplete classification; Add each sorting combination to the first sorting result to form a new sorting combination; For each new ranking combination, determine the average score of the order in which the latter category is located after the former category between each two adjacent categories in the new ranking combination, and determine the sum of the average scores of the order as the total score of the order of the new ranking combination; The sorting combination corresponding to the maximum total score of the order in each new sorting combination is determined as the second sorting result for the unfinished classification.

6. The method according to claim 3, characterized in that The determining, according to the classification and sorting results, of a subsequent learning path recommended to the recommended object based on the completed course includes: Select one course from each of the unfinished categories and form a recommended path according to the second sorting result to obtain a recommended path set; According to the recommended path set, a subsequent learning path recommended for the recommended object based on the completed course is determined.

7. The method according to any one of claims 1 to 4 and 6, characterized in that: Also includes: When it is determined that the object to be recommended has not selected a course according to the subsequent learning path, the completed course is updated, and a subsequent learning path recommended for the object to be recommended based on the completed course is re-determined.

8. An online course learning path recommendation device, characterized in that: include: A first determining unit, used to determine a learning goal of the object to be recommended and a completed course for the learning goal; A second determining unit, configured to determine a set of reference objects that have the same learning goal as the object to be recommended and achieve the learning goal; A third determining unit is used to obtain a course learning path of each reference object in the reference object set, and determine a course set corresponding to the learning goal according to each course in the course learning path of each reference object; A fourth determining unit is used to determine a sequence score between any two courses in the course set according to the course learning path of each reference object; the sequence score is used to indicate the sequence relationship of one course after another course; A classification unit, used for classifying each course in the course set according to the course content to obtain a plurality of categories; each category includes at least one course; A sorting unit, used to sort the multiple categories in order according to the order scores and the completed courses; The recommendation unit is used to determine a subsequent learning path recommended for the recommended object based on the completed course according to the classification and sorting results; the courses on the subsequent learning path are all located in the course set.

9. A computing device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute the method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Course learning path recommending method and device

    CN106023015A

  • Online course recommendation method and device and computer storage medium

    CN110990691A

  • Course recommendation method and device, equipment and storage medium

    CN112632140A

  • Knowledge graph-based learning path recommendation method and system, computer and medium

    CN114491057A

  • Online class recommendation method and system based on knowledge graph

    CN114722182A