Application type education course matching method based on behavior analysis

Abstract

The invention relates to the technical field of curriculum matching recommendation, in particular to an application type education curriculum matching method based on behavior analysis, and the method comprises the steps: obtaining all dimension indexes of a student to be subjected to curriculum matching under each preset dimension in a current time period, and obtaining a historical similar student set corresponding to the student to be subjected to curriculum matching; determining the current stable correlation of the student to be subjected to course matching under each preset dimension, and obtaining the historical stable correlation of each historical student under each preset dimension; determining learning stability credibility and interest learning stability degree under each preset dimension; judging whether the student to be subjected to course matching is a stable learning student; and if the student to be subjected to course matching is not the stable learning student, correcting the historical similar student set, and performing application type education course matching based on the corrected historical similar student set. According to the invention, the application type education course matching is realized, and the reasonability of application type education course matching recommendation for students is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of course matching recommendation, and in particular to an applied education course matching method based on behavior analysis. Background Art

[0002] Applied courses refer to applied courses that use industry-education integration and school-enterprise cooperation as teaching models, and emphasize and highlight applied and practical courses. In order to facilitate students' learning of applied education courses, it is often necessary to match and recommend suitable applied education courses for students. At present, when recommending objects to users, the method usually used is to recommend objects to users based on a set of similar users stored historically.

[0003] However, when recommending applied education courses to students based on a historically stored set of similar students, the following technical problems often arise: Since students' learning situations often change dynamically, that is, the learning situations of some students are often unstable, the students in the historically stored similar student set may no longer be students with similar learning situations to the students to be recommended for courses at the current stage. At this time, if applied education course matching recommendations are made to students based on the historically stored similar student set, the rationality of applying education course matching recommendations to students may be poor. Summary of the invention

[0004] In order to solve the technical problem of poor rationality in recommending applied education courses for students, the present invention proposes an applied education course matching method based on behavior analysis.

[0005] In a first aspect, the present invention provides an applied education course matching method based on behavior analysis, the method comprising: Obtain all dimension indicators of the students to be matched with the course under each preset dimension in the current time period as the current dimension indicators, and obtain the set of historically similar students corresponding to the students to be matched with the course; According to the distribution changes of all current dimension indicators under each preset dimension, determine the current stable correlation of the students to be matched with the course under each preset dimension. Similarly, obtain the historical stable correlation of each historical student under each preset dimension. Determine the learning stability credibility under each preset dimension based on the historical stability correlation of all history students under each preset dimension; According to the current stable relevance and learning stability credibility under each preset dimension, determine the interest learning stability of the students to be matched with the course under each preset dimension; According to the interest and learning stability of the students to be matched with courses in all preset dimensions, it is judged whether the students to be matched with courses are stable students; If the student to be matched with a course is a stable student, then the applied education course matching is performed based on a set of historically similar students; If the student to be matched with a course is not a stable student, the set of historically similar students is revised, and applied education course matching is performed based on the revised set of historically similar students.

[0006] In combination with the first aspect above, in a possible implementation, determining the current stable correlation of the students to be matched with the course in each preset dimension according to the distribution change of all current dimension indicators in each preset dimension includes: All current dimension indicators under each preset dimension form a current dimension indicator sequence under each preset dimension; The autocorrelation coefficient of the current dimension indicator sequence under each preset dimension at a preset time interval is determined as the current autocorrelation coefficient of the student to be matched with the course under each preset dimension; According to the current autocorrelation coefficient under each preset dimension and the range of the current dimension indicator sequence under it, the current stable correlation of the students to be matched with the course under each preset dimension is determined.

[0007] In combination with the first aspect above, in a possible implementation, determining the current stable correlation of the students to be matched with the course in each preset dimension according to the current autocorrelation coefficient in each preset dimension and the range of the current dimension indicator sequence thereunder includes: Determine the range of the current dimension indicator sequence under each preset dimension as the current range under each preset dimension; According to the current range under each preset dimension, the current local stability factor under each preset dimension is determined, wherein the current range is negatively correlated with the current local stability factor; The product of the current autocorrelation coefficient and the current local stability factor under each preset dimension is determined as the current stable correlation of the students to be matched with the course under each preset dimension.

[0008] In combination with the first aspect above, in a possible implementation, determining the learning stability credibility under each preset dimension according to the historical stability correlation of all history students under each preset dimension includes: The information entropy of the historical stability correlation of all history students under each preset dimension is determined as the chaotic change factor under each preset dimension; According to the chaos change factor under each preset dimension, the learning stability credibility under each preset dimension is determined, wherein the chaos change factor is negatively correlated with the learning stability credibility.

[0009] In combination with the first aspect above, in a possible implementation, determining the interest learning stability of the students to be matched with the course in each preset dimension according to the current stability correlation and learning stability credibility in each preset dimension includes: The product of the current stability correlation and the learning stability credibility under each preset dimension is normalized to obtain the interest learning stability of the students to be matched with the course under each preset dimension.

[0010] In combination with the first aspect above, in a possible implementation, judging whether the student to be matched with a course is a stable student in terms of interest learning stability of the student to be matched with a course in all preset dimensions includes: According to the stability of the interest learning of the students to be matched with the course in each preset dimension, determine whether each preset dimension is the current variable dimension; If the proportion of the current change dimension in all preset dimensions is greater than the preset change proportion, it is determined that the student to be matched with the course is not a stable student; If the proportion of the current change dimension in all preset dimensions is less than or equal to the preset change proportion, the student to be matched with the course is determined to be a stable learning student.

[0011] In combination with the first aspect above, in a possible implementation, judging whether each preset dimension is a current variable dimension according to the interest learning stability of the students to be matched with the course in each preset dimension includes: Any preset dimension is determined as a marked dimension. If the degree of interest learning stability of the students to be matched with the course under the marked dimension is less than or equal to a preset stability threshold, the marked dimension is determined as the current variable dimension.

[0012] In combination with the first aspect above, in a possible implementation, the modifying the set of students with similar history includes: Get all dimension indicators of each history student under each preset dimension in the historical period time period; The mean of all dimension indicators of each history student under each preset dimension during the historical period is determined as the dimension representative indicator of each history student under each preset dimension; The mean of all current dimension indicators of the students to be matched with the course in each preset dimension is determined as the dimension representative indicator of the students to be matched with the course in each preset dimension; According to the dimension representative indicators of all historical students in all preset dimensions and the dimension representative indicators of the students to be matched with the courses in all preset dimensions, a revised set of historical similar students is obtained.

[0013] In combination with the first aspect above, in a possible implementation, obtaining a revised set of historical similar students according to the dimension representative indicators of all historical students in all preset dimensions and the dimension representative indicators of the students to be matched with the courses in all preset dimensions includes: According to the dimension representative indicators of all historical students in all preset dimensions and the dimension representative indicators of the students to be matched with the courses in all preset dimensions, a collaborative filtering matrix is ​​constructed as the target collaborative filtering matrix; According to the target collaborative filtering matrix, the collaborative filtering algorithm is used to screen out historical students who match the students to be matched with the course from all historical students to form a revised set of similar historical students.

[0014] In combination with the above first aspect, in a possible implementation manner, the preset dimension is a single learning dimension or a fusion learning dimension, and the fusion learning dimension is a fusion of at least two single learning dimensions.

[0015] In a second aspect, the present invention provides an applied education course matching system based on behavior analysis, the system comprising: The data acquisition module is used to obtain all dimension indicators of the students to be matched with the course under each preset dimension in the current time period as the current dimension indicators, and obtain the historical similar student set corresponding to the students to be matched with the course; The stable correlation determination module is used to determine the current stable correlation of the students to be matched with the course in each preset dimension according to the distribution changes of all current dimension indicators in each preset dimension. Similarly, the historical stable correlation of each historical student in each preset dimension is obtained; A learning stability credibility determination module is used to determine the learning stability credibility under each preset dimension according to the history stability correlation of all history students under each preset dimension; The interest learning stability determination module is used to determine the interest learning stability of the students to be matched with the course in each preset dimension according to the current stability correlation and learning stability credibility in each preset dimension; A module for judging students with stable learning is used to judge whether the students to be matched with courses are stable students according to their interest and learning stability in all preset dimensions; An applied education course matching module is used to match applied education courses based on a set of historically similar students if the student to be matched with the course is a stable student; The set correction course matching module is used to correct the set of historically similar students if the student to be matched with the course is not a stable student, and to match the applied education courses based on the corrected set of historically similar students.

[0016] In a third aspect, a server is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the method in the first aspect or any possible implementation of the first aspect.

[0017] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0018] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect.

[0019] The present invention has the following beneficial effects: The applied education course matching method based on behavior analysis of the present invention realizes applied education course matching, solves the technical problem of poor rationality of applied education course matching recommendation for students, and improves the rationality of applied education course matching recommendation for students. Compared with recommending applied education course matching for students based on a set of similar students stored historically, the present invention quantifies multiple features related to students' learning situations by analyzing dimensional indicators that characterize different learning behaviors of students, such as current stable correlation, historical stable correlation, learning stable credibility, and interest learning stability, thereby judging whether the student to be matched with the course is a stable learning student. If the student to be matched with the course is not a stable learning student, the set of historical similar students is corrected, which improves the rationality of similar students who subsequently participate in the applied education course matching recommendation to a certain extent, thereby improving the rationality of applying education course matching recommendation for students. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A flowchart of the applied education course matching method based on behavior analysis of the present invention; Figure 2It is a schematic diagram of the composition structure of the applied education course matching system based on behavior analysis of the present invention; Figure 3 The figure is a schematic diagram of the structure of a computer device of the present invention. DETAILED DESCRIPTION

[0022] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the technical solutions proposed by the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0023] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0024] refer to Figure 1 , shows the process of some embodiments of the application-oriented education course matching method based on behavior analysis according to the present invention. The application-oriented education course matching method based on behavior analysis includes the following steps: Step S1, obtaining all dimension indicators of the students to be matched with the course under each preset dimension in the current time period as the current dimension indicators, and obtaining the historical similar student set corresponding to the students to be matched with the course.

[0025] Among them, the students to be matched with courses are students who are to be recommended for applied education course matching. The current time period can be a period of time with the current moment as the end moment. The students in the historical similar student set corresponding to the students to be matched with courses can be students with similar past learning situations to the students to be matched with courses. The preset dimension can be a single learning dimension or a fusion learning dimension set in advance. The fusion learning dimension can be a fusion of at least two single learning dimensions, that is, it can be a fusion of multiple learning-related dimensions. A single learning dimension can be a single learning-related dimension. The dimensional indicator under the preset dimension can be a numerical value corresponding to the dimensional data under the preset dimension, that is, if the dimensional data is a numerical value, the dimensional data can be used as a dimensional indicator. If the dimensional data is not a numerical value, the dimensional data can be converted into a numerical value, and the converted numerical value can be used as a dimensional indicator. Dimension indicators can characterize students' learning behavior to a certain extent.

[0026] A single learning dimension may be, but is not limited to: a test score dimension of a single subject, a homework completion rate dimension of a single subject, a homework accuracy rate dimension of a single subject, a study time dimension of a single subject, a study period dimension of a single subject, a knowledge point mastery dimension of a single subject, a learning resource usage dimension of a single subject, and a course absence rate dimension of a single subject. For example, a dimensional indicator under the test score dimension of a single subject may be the average of all test scores of a student for a single subject within a preset unit time. The preset unit time may be a unit time whose corresponding duration is less than the duration corresponding to the current time period, which may be 1 day. A dimensional indicator under the homework completion rate dimension of a single subject may be a student's homework completion rate for a single subject within a preset unit time. A dimensional indicator under the homework accuracy rate dimension of a single subject may be a student's homework accuracy rate for a single subject within a preset unit time. A dimensional indicator under the study time dimension of a single subject may be a student's study time for a single subject within a preset unit time. The dimensional data under the learning period dimension of a single subject can be morning, afternoon or evening, which means that students can study a single subject in the morning, afternoon or evening within a preset unit of time. Since it is not a numerical value, it can be converted into a numerical value. For example, 0000 can be used to represent the morning, 0001 can be used to represent the afternoon, and 0002 can be used to represent the evening. At this time, the dimensional indicator under the learning period dimension of a single subject can be 0000, 0001 or 0002. The dimensional indicator under the knowledge point mastery dimension of a single subject can be the teacher's score on the student's mastery of the subject. The larger the value, the higher the student's mastery of the subject. The value range can be [0, 10]. The dimensional indicator under the learning resource usage dimension of a single subject can be different numerical values ​​used to represent different types of learning resources, where different types of learning resources can include: video, text and interactive exercises. The dimensional indicator under the course absence rate dimension of a single subject can be the course absence rate.

[0027] The fusion learning dimension may be, but is not limited to, the learning input dimension of a single subject, the learning outcome dimension of a single subject, and the learning habit dimension of a single subject. The learning input dimension of a single subject may be a fusion of the learning time dimension and the homework completion rate dimension of a single subject. The learning outcome dimension of a single subject may be a fusion of the test score dimension and the homework accuracy dimension of a single subject. The learning habit dimension of a single subject may be a fusion of the learning time period dimension and the learning resource usage dimension of a single subject. The method for obtaining the dimensional indicators under the fusion learning dimension may be: the dimensional indicators under all the single learning dimensions contained in the fusion learning dimension of the same student within a preset unit time constitute a target vector under the fusion learning dimension, classify all the target vectors under the fusion learning dimension, and represent the different categories obtained at this time with different numerical values, and record the numerical values ​​corresponding to the categories to which the target vector belongs as the dimensional indicators under the fusion learning dimension. Among them, the algorithm for implementing classification may be, but is not limited to, a decision tree algorithm, a logistic regression algorithm, a K-Means clustering algorithm, and a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm. For example, a method for obtaining dimensional indicators under the learning input dimension of a single subject may include: using the dimensional indicators of all single learning dimensions contained in the learning input dimension of the same student within a preset unit time to form a target vector under the learning input dimension, classifying all target vectors under the learning input dimension through the DBSCAN algorithm, and representing the different categories obtained at this time with different numerical values, and recording the numerical value corresponding to the category to which the target vector under the learning input dimension belongs as the dimensional indicator under the learning input dimension.

[0028] It should be noted that the number of preset dimensions can be preset. Generally speaking, the more the number of preset dimensions, the more reasonable the students who are similar to the learning situation of the students to be matched with the courses finally screened by the embodiment of the present invention are, and the more reasonable the applied education courses that are currently matched by the students to be matched with the courses are. Secondly, the missing data can be filled with the mean, median or mode. For example, if a student does not take a test in a certain subject on a certain day, the mean of all test scores of the student for the subject in the week of that day can be used to represent the student's average test score on that day, which can be used to represent the dimensional index of the student's test score dimension for the subject on that day. If a student does not use any learning resources to study a certain subject on a certain day, the numerical value corresponding to the type of learning resource that the student uses most for the subject in the week of that day can be used to represent the dimensional index of the student's use of learning resources for the subject on that day.

[0029] As an example, this step may include the following steps: The first step is to obtain the dimension indicators of each preset dimension of the students to be matched with the course in each preset unit time; the dimension indicators of the students to be matched with the course in the same preset dimension in all preset unit times in the current time period are combined to form all the dimension indicators of the students to be matched with the course in the same preset dimension in the current time period; and the dimension indicators in the current time period are used as the current dimension indicators.

[0030] In the second step, similarly, all dimension indicators of the students to be matched with the course under each preset dimension in the historical time period are obtained, and all dimension indicators of each historical student under each preset dimension in the historical cycle time period are obtained.

[0031] Among them, the historical time period can be a time period before the current time period, and the end time of the historical time period can be the start time of the current time period. The historical cycle time period can include the time stage corresponding to the historical time period and the time stage corresponding to the current time period. For example, if the student to be matched with the course is a third-grade student in elementary school and has been studying for 6 weeks, the historical time period can be the first 2 weeks of the third-grade student to be matched with the course, the current time period can be the last 4 weeks of the third-grade student to be matched with the course, and the historical cycle time period can be the entire period of the historical student's third-grade study.

[0032] The third step is to determine the mean of all dimensional indicators of the students to be matched with the course under each preset dimension in the historical time period as the overall historical dimension indicator of the students to be matched with the course under each preset dimension.

[0033] The fourth step is to determine the mean of all dimensional indicators of each history student under each preset dimension during the historical cycle time period as the overall historical dimension indicator of each history student under each preset dimension.

[0034] The fifth step is to obtain the historically similar student set corresponding to the students to be matched with the course.

[0035] For example, based on the overall historical dimension indicators of the students to be matched with the course in each preset dimension, and the overall historical dimension indicators of each history student in each preset dimension, a collaborative filtering matrix can be constructed as a historical collaborative filtering matrix. Based on the historical collaborative filtering matrix, through the collaborative filtering algorithm, historical students whose learning situations are similar to those of the students to be matched with the course can be screened out from all history students to form a set of historically similar students.

[0036] Step S2, according to the distribution changes of all current dimension indicators under each preset dimension, determine the current stable correlation of the students to be matched with the course under each preset dimension. Similarly, obtain the historical stable correlation of each historical student under each preset dimension.

[0037] As an example, according to the distribution changes of all current dimension indicators under each preset dimension, determining the current stable correlation of the students to be matched with the course under each preset dimension may include the following steps: The first step is to combine all current dimension indicators under each preset dimension into a current dimension indicator sequence under each preset dimension.

[0038] The current dimension indicator sequence may be a time series, and the earlier the current dimension indicator is in the current dimension indicator sequence, the earlier the collection time corresponding to the current dimension indicator may be.

[0039] In the second step, the autocorrelation coefficient of the current dimension indicator sequence under each preset dimension at the preset time interval is determined as the current autocorrelation coefficient of the students to be matched with the course under each preset dimension.

[0040] The preset time interval may be a pre-set time interval, which may be 7 days.

[0041] It should be noted that in actual situations, the larger the autocorrelation coefficient of a sequence is, the more likely it is that the current value is highly correlated with the past value, and the more likely it is that the change trend of the sequence is regular or stable. Therefore, the larger the current autocorrelation coefficient of the students to be matched with courses in a certain preset dimension is, the more likely it is that the learning behavior of the students to be matched with courses related to the preset dimension is more stable, and the more likely it is that the learning situation of the students to be matched with courses in the preset dimension is more stable.

[0042] The third step is to determine the current stable correlation of the students to be matched with the course in each preset dimension according to the current autocorrelation coefficient in each preset dimension and the range of the current dimension indicator sequence under it, which may include the following sub-steps: In the first sub-step, the range of the current dimension indicator sequence under each preset dimension is determined as the current range under each preset dimension.

[0043] The second sub-step is to determine the current local stability factor under each preset dimension according to the current range under each preset dimension.

[0044] Among them, the current range can be negatively correlated with the current local stability factor.

[0045] In the third sub-step, the product of the current autocorrelation coefficient and the current local stability factor under each preset dimension is determined as the current stable correlation of the students to be matched with the course under each preset dimension.

[0046] For example, the formula for determining the current stable correlation of students to be matched with courses under the preset dimensions can be: ;in, is the current stable correlation of the students to be matched with the course under the i-th preset dimension. i is the serial number of the preset dimension. It is the current autocorrelation coefficient of the students to be matched with the course under the i-th preset dimension. It is the maximum value in the current dimension indicator sequence under the i-th preset dimension. It is the minimum value in the current dimension indicator sequence under the i-th preset dimension. is a natural exponential function. is the current range under the i-th preset dimension. is the current local stability factor under the i-th preset dimension.

[0047] It should be noted that when When the value is larger, it often indicates that the learning behavior of the students to be matched with the course related to the i-th preset dimension is more likely to be stable, and it often indicates that the learning situation of the students to be matched with the course under the i-th preset dimension is more likely to remain stable. The smaller it is, the smaller the fluctuation of the dimension index of the students to be matched with the course in the i-th preset dimension is. This often means that the learning situation of the students to be matched with the course in the i-th preset dimension is more likely to change smoothly. This often means that the learning situation of the students to be matched with the course in the i-th preset dimension is more likely to remain stable. Therefore, when When it is larger, it often means that the learning situation of the students to be matched with the course in the i-th preset dimension is more likely to remain stable, and it often means that the learning behavior in the i-th preset dimension is more likely not to change significantly.

[0048] As another example, obtaining the historical stability correlation of each history student in each preset dimension may include the following steps: The first step is to combine all dimensional indicators of each history student under each preset dimension during the historical cycle time period to form a historical dimension indicator sequence for each history student under each preset dimension.

[0049] The historical dimension indicator sequence may be a time series, and the earlier the dimension indicator is in the historical dimension indicator sequence, the earlier the collection time corresponding to the dimension indicator may be.

[0050] In the second step, the autocorrelation coefficient of the historical dimension indicator sequence of each history student in each preset dimension at a preset time interval is determined as the historical autocorrelation coefficient of each history student in each preset dimension.

[0051] The third step is to determine the historical stability correlation of each history student in each preset dimension according to the historical autocorrelation coefficient of each history student in each preset dimension and the range of the historical dimension indicator sequence under it, which may include the following sub-steps: In the first sub-step, the range of the historical dimension indicator sequence of each history student in each preset dimension is determined as the historical range of each history student in each preset dimension.

[0052] The second sub-step is to determine the historical local stability factor of each history student in each preset dimension based on the historical extreme value of each history student in each preset dimension.

[0053] Among them, the historical extremes can be negatively correlated with the historical local stability factors.

[0054] In the third sub-step, the product of the historical autocorrelation coefficient and the historical local stability factor of each history student in each preset dimension is determined as the historical stability correlation of each history student in each preset dimension.

[0055] Step S3, determining the learning stability credibility under each preset dimension according to the historical stability correlation of all history students under each preset dimension.

[0056] As an example, this step may include the following steps: In the first step, the information entropy of the historical stability correlation of all history students in each preset dimension is determined as the chaotic change factor in each preset dimension.

[0057] The second step is to determine the learning stability credibility under each preset dimension based on the chaos change factor under each preset dimension.

[0058] Among them, the chaotic change factor can be negatively correlated with the learning stability credibility.

[0059] For example, the formula for determining the learning stability credibility under the preset dimension can be: ;in, is the learning stability credibility under the i-th preset dimension. i is the serial number of the preset dimension. is the chaotic change factor under the i-th preset dimension.

[0060] It should be noted that when The larger the value, the easier it is for different students to change their learning behaviors under the i-th preset dimension. The larger it is, the less likely different students' learning behaviors in the i-th preset dimension are to change. This often means that the learning behaviors in the i-th preset dimension are more likely to be common learning behaviors. This often means that the learning behaviors in the i-th preset dimension are more common and stable.

[0061] Step S4, determining the interest learning stability of the students to be matched with the course in each preset dimension according to the current stability correlation and learning stability credibility in each preset dimension.

[0062] As an example, the product of the current stability relevance and the learning stability credibility under each preset dimension can be normalized to obtain the interest learning stability of the students to be matched with the course under each preset dimension.

[0063] For example, the formula for determining the stability of interest learning of students to be matched with courses under the preset dimensions can be: ;in, It is the stability of the students’ interest in learning under the i-th preset dimension. i is the serial number of the preset dimension. is a normalization function. It is the current stable correlation of the students to be matched with the course under the i-th preset dimension. is the learning stability credibility under the i-th preset dimension.

[0064] It should be noted that Can be used as When When the value is larger, it often means that the learning situation of the students to be matched with the course in the i-th preset dimension is more likely to remain stable, and it often means that the learning behavior in the i-th preset dimension is more likely to not change significantly. When the value is larger, it often means that the learning behavior of different students in the i-th preset dimension is less likely to change, and it often means that the learning behavior in the i-th preset dimension is more generally stable. The larger it is, the more stable the learning situation of the students to be matched with the course is in the i-th preset dimension.

[0065] Step S5, judging whether the student to be matched with the course is a stable learning student according to the degree of interest learning stability of the student to be matched with the course in all preset dimensions.

[0066] As an example, this step may include the following steps: The first step is to determine whether each preset dimension is the current variable dimension based on the stability of the students' interest in learning in each preset dimension.

[0067] For example, any preset dimension can be determined as a marked dimension, and if the interest learning stability of the course-matched student under the marked dimension is less than or equal to a preset stability threshold, the marked dimension is determined as the current variable dimension. The preset stability threshold can be a preset threshold, which can be 0.5.

[0068] It should be noted that the current change dimension can represent the preset dimension in which the learning behavior corresponding to the students to be matched with the course changes greatly.

[0069] In the second step, if the proportion of the current change dimension in all preset dimensions is greater than the preset change proportion, it is determined that the student to be matched with the course is not a stable learning student.

[0070] Among them, the proportion of the current changing dimension in all preset dimensions can be expressed as: ; Wherein, q is the number of current change dimensions. Q is the number of preset dimensions. The preset change ratio may be a preset ratio, which may be 0.4.

[0071] It should be noted that the more current changing dimensions there are, the more preset dimensions that represent the corresponding changes in the learning behaviors of the students to be matched with courses. This often means that more learning behaviors of the students to be matched with courses may have changed. This often means that the learning situations of students in the historically stored set of similar students are more likely to be dissimilar to the current learning situations of the students to be matched with courses. This often means that when making course recommendations for the students to be matched with courses, it is more necessary to correct the set of similar historical students.

[0072] In the third step, if the proportion of the current change dimension in all preset dimensions is less than or equal to the preset change proportion, the student to be matched with the course is determined to be a stable learning student.

[0073] Step S6: If the student to be matched with a course is a stable student, then matching applied education courses is performed based on a set of historically similar students.

[0074] As an example, if the student to be matched with a course is a stable student, then the applied education courses for history students in the set of students with similar history can be recommended to the student to be matched with a course.

[0075] Step S7: If the student to be matched with a course is not a stable student, the set of historically similar students is modified, and applied education course matching is performed based on the modified set of historically similar students.

[0076] As an example, this step may include the following steps: The first step is to obtain all dimension indicators of each history student under each preset dimension during the historical period.

[0077] In the second step, the mean of all dimensional indicators of each history student under each preset dimension during the historical period is determined as the dimensional representative indicator of each history student under each preset dimension.

[0078] The third step is to determine the mean of all current dimension indicators of the students to be matched with the course in each preset dimension as the dimension representative indicator of the students to be matched with the course in each preset dimension.

[0079] The fourth step is to obtain the revised set of historical similar students based on the dimension representative indicators of all historical students in all preset dimensions and the dimension representative indicators of the students to be matched with the courses in all preset dimensions.

[0080] For example, obtaining a corrected historically similar student set may include the following sub-steps: In the first sub-step, a collaborative filtering matrix is ​​constructed as the target collaborative filtering matrix based on the dimension representative indicators of all historical students in all preset dimensions and the dimension representative indicators of the students to be matched with the courses in all preset dimensions.

[0081] In the second sub-step, according to the target collaborative filtering matrix, through the collaborative filtering algorithm, historical students matching the students to be matched with the course are screened out from all historical students to form a revised set of similar historical students.

[0082] The historical students who match the students to be matched with the courses may be students whose current learning situations are similar to those of the students to be matched with the courses.

[0083] Optionally, obtaining the corrected historically similar student set may further include the following sub-steps: In the first sub-step, the dimension representative indicators of each history student under all preset dimensions are used to form the overall dimension vector corresponding to each history student.

[0084] In the second sub-step, the dimension representative indicators of the students to be matched with the courses in all preset dimensions are combined to form an overall dimension vector corresponding to the students to be matched with the courses.

[0085] In the third sub-step, the overall vectors of all dimensions are clustered, and the clusters obtained by clustering at this time are used as the target clusters.

[0086] In the fourth sub-step, the historical students corresponding to all the dimensional overall vectors in the target cluster to which the dimensional overall vector corresponding to the student to be matched with the course belongs are combined to form a revised set of historical similar students.

[0087] The fifth step is to match applied education courses based on the revised historically similar student set.

[0088] For example, applied education courses for history students in the revised set of similar history students may be recommended to students to be matched with courses, so as to achieve applied education course matching based on the revised set of similar history students.

[0089] refer to Figure 2Based on the same inventive concept as the above method embodiment, the present invention provides an applied education course matching system based on behavior analysis, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the above computer program is executed by the processor, the steps of implementing an applied education course matching method based on behavior analysis may specifically include: The data acquisition module 201 is used to obtain all dimension indicators of the students to be matched with the course under each preset dimension in the current time period as the current dimension indicators, and obtain the historical similar student set corresponding to the students to be matched with the course; The stable correlation determination module 202 is used to determine the current stable correlation of the students to be matched with the course in each preset dimension according to the distribution change of all current dimension indicators in each preset dimension. Similarly, the historical stable correlation of each historical student in each preset dimension is obtained; The learning stability credibility determination module 203 is used to determine the learning stability credibility under each preset dimension according to the history stability correlation of all history students under each preset dimension; The interest learning stability determination module 204 is used to determine the interest learning stability of the students to be matched with the course in each preset dimension according to the current stability correlation and learning stability credibility in each preset dimension; The stable learning student judging module 205 is used to judge whether the student to be matched with the course is a stable learning student according to the stability of the student's interest in all preset dimensions; An applied education course matching module 206 is used to match applied education courses based on a set of historically similar students if the student to be matched with the course is a stable student; The set correction course matching module 207 is used to correct the set of historically similar students if the student to be matched with the course is not a stable student, and to perform applied education course matching based on the corrected set of historically similar students.

[0090] Figure 3 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. Figure 3 As shown, the computer device 300 includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute any one of the applied education course matching methods based on behavioral analysis introduced above.

[0091] Based on the same inventive concept as the above method embodiment, the present invention provides a server, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes any of the above-mentioned application-based education course matching methods based on behavior analysis.

[0092] Based on the same inventive concept as the above method embodiment, the present invention provides a computer program product, which includes: computer program code, when the computer program code runs on a computer, enables the computer to execute any one of the above-mentioned applied education course matching methods based on behavior analysis.

[0093] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer-readable storage medium, which stores a computer program code. When the computer program code runs on a computer, the computer executes any one of the above-mentioned applied education course matching methods based on behavior analysis.

[0094] In summary, compared with recommending applied education course matching to students based on a set of similar students stored historically, the present invention quantifies multiple features related to students' learning situations by analyzing dimensional indicators that characterize different learning behaviors of students, such as current stability correlation, historical stability correlation, learning stability credibility, and interest learning stability, thereby judging whether the student to be matched with a course is a stable learning student. If the student to be matched with a course is not a stable learning student, the set of historical similar students is corrected, which improves the rationality of similar students who subsequently participate in applied education course matching recommendations to a certain extent, thereby improving the rationality of applying education course matching recommendations to students.

[0095] 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, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for matching applied education courses based on behavioral analysis, characterized in that: The following steps are involved: Obtain all dimension indicators of the students to be matched with the course under each preset dimension in the current time period as the current dimension indicators, and obtain the set of historically similar students corresponding to the students to be matched with the course; According to the distribution changes of all current dimension indicators under each preset dimension, determine the current stable correlation of the students to be matched with the course under each preset dimension. Similarly, obtain the historical stable correlation of each historical student under each preset dimension. Determine the learning stability credibility under each preset dimension based on the historical stability correlation of all history students under each preset dimension; According to the current stable relevance and learning stability credibility under each preset dimension, determine the interest learning stability of the students to be matched with the course under each preset dimension; According to the interest and learning stability of the students to be matched with courses in all preset dimensions, it is judged whether the students to be matched with courses are stable students; If the student to be matched with a course is a stable student, then the applied education course matching is performed based on a set of historically similar students; If the student to be matched with a course is not a stable student, the set of historically similar students is revised, and applied education course matching is performed based on the revised set of historically similar students.

2. According to claim 1, a method for matching applied education courses based on behavioral analysis is characterized in that: Determining the current stable correlation of the students to be matched with the course in each preset dimension according to the distribution change of all current dimension indicators in each preset dimension includes: All current dimension indicators under each preset dimension form a current dimension indicator sequence under each preset dimension; The autocorrelation coefficient of the current dimension indicator sequence under each preset dimension at a preset time interval is determined as the current autocorrelation coefficient of the student to be matched with the course under each preset dimension; According to the current autocorrelation coefficient under each preset dimension and the range of the current dimension indicator sequence under it, the current stable correlation of the students to be matched with the course under each preset dimension is determined.

3. The method for matching applied education courses based on behavioral analysis according to claim 2 is characterized in that: Determining the current stable correlation of the students to be matched with the courses in each preset dimension according to the current autocorrelation coefficient in each preset dimension and the range of the current dimension indicator sequence thereunder includes: Determine the range of the current dimension indicator sequence under each preset dimension as the current range under each preset dimension; According to the current range under each preset dimension, the current local stability factor under each preset dimension is determined, wherein the current range is negatively correlated with the current local stability factor; The product of the current autocorrelation coefficient and the current local stability factor under each preset dimension is determined as the current stable correlation of the students to be matched with the course under each preset dimension.

4. The method for matching applied education courses based on behavioral analysis according to claim 1, characterized in that: The above-mentioned method determines the learning stability credibility under each preset dimension according to the historical stability correlation of all history students under each preset dimension, including: The information entropy of the historical stability correlation of all history students under each preset dimension is determined as the chaotic change factor under each preset dimension; According to the chaos change factor under each preset dimension, the learning stability credibility under each preset dimension is determined, wherein the chaos change factor is negatively correlated with the learning stability credibility.

5. The method for matching applied education courses based on behavioral analysis according to claim 1, characterized in that: Determining the interest learning stability of the students to be matched with the course in each preset dimension according to the current stable correlation and learning stability credibility in each preset dimension includes: The product of the current stability correlation and the learning stability credibility under each preset dimension is normalized to obtain the interest learning stability of the students to be matched with the course under each preset dimension.

6. The method for matching applied education courses based on behavioral analysis according to claim 1, characterized in that: The step of judging whether the student to be matched with a course is a stable student in terms of the stability of the student's interest in all preset dimensions includes: According to the stability of the interest learning of the students to be matched with the course in each preset dimension, determine whether each preset dimension is the current variable dimension; If the proportion of the current change dimension in all preset dimensions is greater than the preset change proportion, it is determined that the student to be matched with the course is not a stable student; If the proportion of the current change dimension in all preset dimensions is less than or equal to the preset change proportion, the student to be matched with the course is determined to be a stable learning student.

7. The method for matching applied education courses based on behavior analysis according to claim 6, characterized in that: The step of judging whether each preset dimension is a current variable dimension according to the interest learning stability of the students to be matched with the course in each preset dimension includes: Any preset dimension is determined as a marked dimension. If the degree of interest learning stability of the students to be matched with the course under the marked dimension is less than or equal to a preset stability threshold, the marked dimension is determined as the current variable dimension.

8. The method for matching applied education courses based on behavioral analysis according to claim 1, characterized in that: The correction of the historically similar student set includes: Get all dimension indicators of each history student under each preset dimension in the historical period time period; The mean of all dimension indicators of each history student under each preset dimension during the historical period is determined as the dimension representative indicator of each history student under each preset dimension; The mean of all current dimension indicators of the students to be matched with the course in each preset dimension is determined as the dimension representative indicator of the students to be matched with the course in each preset dimension; According to the dimension representative indicators of all historical students in all preset dimensions and the dimension representative indicators of the students to be matched with the courses in all preset dimensions, a revised set of historical similar students is obtained.

9. The method for matching applied education courses based on behavioral analysis according to claim 8, characterized in that: The method of obtaining a corrected set of historical similar students according to the dimension representative indicators of all historical students in all preset dimensions and the dimension representative indicators of the students to be matched with the course in all preset dimensions includes: According to the dimension representative indicators of all historical students in all preset dimensions and the dimension representative indicators of the students to be matched with the courses in all preset dimensions, a collaborative filtering matrix is ​​constructed as the target collaborative filtering matrix; According to the target collaborative filtering matrix, the collaborative filtering algorithm is used to screen out historical students who match the students to be matched with the course from all historical students to form a revised set of similar historical students.

10. The method for matching applied education courses based on behavior analysis according to claim 1, characterized in that: The preset dimension is a single learning dimension or a fusion learning dimension, and the fusion learning dimension is the fusion of at least two single learning dimensions.

Images