Application type education learning behavior data mining method and system based on action logic

Abstract

The invention relates to the technical field of data mining, in particular to an action logic-based application type education learning behavior data mining method and system, and the method comprises the steps: obtaining the learning behavior data of a student group for a target course for the target course, and the learning behavior data comprises a plurality of learning plans; according to the learning behavior data, obtaining preference indexes of the student group for a plurality of learning plans; according to the preference index of the student group for the learning plan, obtaining a learning interest factor of a target student individual; acquiring a learning behavior characteristic factor of the target student individual according to the learning interest factor of the target student individual; and according to the learning behavior characteristic factor of the target student individual, customizing a learning plan for the target student individual. According to the embodiment of the invention, personalized teaching and tutoring of the target student individual can be realized, and the teaching quality and the teaching effect of the teaching system are improved.

Description

Technical Field

[0001] The present application belongs to the field of data mining technology, and specifically relates to an applied education learning behavior data mining method and system based on action logic. Background Art

[0002] With the rapid development of information technology, a large number of digital tools and platforms have gradually been introduced into the field of education, such as online learning systems, smart classrooms, learning management systems (LMS), etc. These tools have not only changed the traditional teaching methods, but also generated a large amount of log data of student learning behaviors, providing a rich data source for data mining.

[0003] In traditional applied education learning behavior data mining methods, since student behavior is usually dynamically changing, traditional methods are usually difficult to accurately capture the dynamic changing characteristics of student behavior, such as changes in learning interests, adjustments to learning plans, etc., which leads to reduced real-time and reliability of prediction and analysis results of traditional static model methods; therefore, how to effectively capture students' dynamic behavioral changes and provide students with personalized educational strategies is an important issue currently faced. Summary of the invention

[0004] In order to solve the above problems, according to a first aspect of an embodiment of the present application, a method for mining applied education learning behavior data based on action logic is provided, the method comprising: For a target course, obtaining learning behavior data of a student group for the target course, wherein the learning behavior data includes a plurality of learning plans; According to the learning behavior data, obtaining the preference index of the student group for the plurality of learning plans; Obtaining a learning interest factor of a target student individual according to the preference index of the student group for the learning plan; According to the learning interest factor of the target student individual, obtaining the learning behavior characteristic factor of the target student individual; A learning plan is tailored for the target student individual based on the learning behavior characteristic factors of the target student individual.

[0005] Optionally, obtaining the preference index of the student group for the plurality of learning plans includes: According to the learning behavior data, obtaining the learning completion degree of the student group for the target learning plan; According to the learning behavior data, obtaining the selection prominence of the target learning plan by the student group; According to the learning completion degree and the selection prominence, the preference index of the student group for the plurality of learning plans is obtained.

[0006] Optionally, obtaining the learning completion degree of the student group for the target learning plan includes: Taking the time between two adjacent learning assessment nodes as the learning time window, obtaining the adjacent first learning time window and the second learning time window; Counting a first total number of students in the student group who select the target learning plan in the first learning time window, and a second total number of students who select the target learning plan in the second learning time window; The degree of learning completion of the target learning plan by the student group is obtained based on the first total number of people and the second total number of people.

[0007] Optionally, obtaining the learning completion degree of the student group for the target learning plan includes: Obtaining the sum of the first total number of people and the second total number of people; The ratio of the sum to the first total number of people is used as the learning completion degree of the student group for the target learning plan.

[0008] Optionally, obtaining the selection prominence of the target learning plan by the student group includes: Obtaining a frequency of occurrence of the target learning plan in a first learning plan set in a target region, where the first learning plan set is a set of all learning plans in the target region; Obtaining an average of the frequencies of occurrence of learning plans in a second learning plan set in the first learning plan set, wherein the second learning plan set is a set of all learning plans in the target region except the target learning plan; According to the frequency and the mean, the selection prominence of the target learning plan by the student group is obtained.

[0009] Optionally, obtaining the preference index of the student group for the plurality of learning plans according to the learning completion degree and the selection prominence degree includes: The product of the learning completion degree and the selection prominence is used as the preference index of the student group for the multiple learning plans.

[0010] Optionally, obtaining the learning interest factor of the target student individual according to the preference index of the student group for the learning plan includes: Obtain the information entropy of the target student's individual choice of study plan; The learning interest factor of the target student individual is obtained according to the information entropy of the selected learning plan of the target student individual and the preference indexes of the plurality of learning plans.

[0011] Optionally, obtaining the learning behavior characteristic factor of the target student individual according to the learning interest factor of the target student individual includes: Obtaining the degree of correlation between the learning plans of the target students; The learning behavior characteristic factor of the target student individual is obtained according to the product of the association degree and the learning interest factor.

[0012] Optionally, obtaining the correlation between the target student individual learning plans includes: Obtaining the probability of any one of all the learning plans of the target individual student being selected by the student group; According to the probability, obtaining the joint probability of any two study plan combinations among all study plans of the target individual student being selected in the student group; Using the distribution of the joint probability as the joint entropy of the learning plan combination; According to the joint entropy of the combination of learning plans, the degree of association between the learning plans of the target individual students is obtained.

[0013] According to a second aspect of an embodiment of the present application, there is provided an applied education learning behavior data mining system based on action logic, the system comprising a server, the server comprising: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of any one of the methods in the first aspect.

[0014] In summary, the embodiment of the present application provides an applied education learning behavior data mining method based on action logic, the method comprising: for a target course, obtaining the learning behavior data of a student group for the target course, the learning behavior data comprising a plurality of learning plans; based on the learning behavior data, obtaining the preference index of the student group for the plurality of learning plans; based on the preference index of the student group for the learning plan, obtaining the learning interest factor of the target individual student; based on the learning interest factor of the target individual student, obtaining the learning behavior characteristic factor of the target individual student; based on the learning behavior characteristic factor of the target individual student, tailoring a learning plan for the target individual student. The embodiment of the present application obtains the learning behavior characteristic factor of the target individual student by mining the learning behavior data of the student group and the learning behavior data of the individual student, and tailors a learning plan for the target individual student based on the learning behavior characteristic factor, thereby realizing personalized teaching and tutoring for the target individual student and improving the teaching quality and teaching effect of the teaching system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the implementation scheme of the present application, the drawings required for use in the implementation scheme will be briefly introduced below. It should be understood that the drawings only show certain implementation schemes of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on the drawings without paying creative work.

[0016] Figure 1 It is a flowchart of an applied education learning behavior data mining method based on action logic according to an exemplary embodiment.

[0017] Figure 2 The present invention is a flowchart showing a method for obtaining a preference index of a student group for multiple learning plans according to an exemplary embodiment.

[0018] Figure 3 The present invention is a flowchart of a method for obtaining the learning completion degree of a student group for a target learning plan according to an exemplary embodiment.

[0019] Figure 4 The flowchart is another method for obtaining the learning completion degree of a student group for a target learning plan according to an exemplary embodiment.

[0020] Figure 5 The present invention is a flowchart showing a method for obtaining the selection prominence of a student group for a target learning plan according to an exemplary embodiment.

[0021] Figure 6 The flowchart of another method for obtaining the preference index of a student group for multiple learning plans is shown according to an exemplary embodiment.

[0022] Figure 7 The present invention is a flowchart of a method for obtaining a learning interest factor of a target student according to an exemplary embodiment.

[0023] Figure 8 It is a flow chart showing a method for obtaining learning behavior characteristic factors of a target student individual according to an exemplary embodiment.

[0024] Fig. 9 The present invention is a flowchart showing a method for obtaining the degree of association between individual learning plans of target students according to an exemplary embodiment.

[0025] Fig.10 It is a block diagram of an applied education learning behavior data mining system based on action logic according to an exemplary embodiment.

[0026] Fig.11 It is a block diagram of a server according to an exemplary embodiment. DETAILED DESCRIPTION

[0027] In order to clearly illustrate the technical features of the present solution, the present application is described in detail below through specific implementation methods and in conjunction with the accompanying drawings.

[0028] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0029] It should be understood that the various steps described in the method implementation of the present application can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0030] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0031] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0032] It should be noted that the modifications of "one" and "multiple" mentioned in this application are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more". In the description of this application, unless otherwise specified, "multiple" means two or more than two, and other quantifiers are similar; "at least one item", "one or more items" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one item a can represent any number of a; for another example, one or more items of a, b and c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple; "and / or" is a kind of association relationship that describes the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural.

[0033] Although the operations or steps are described in a specific order in the drawings in the embodiments of the present application, it should not be understood that it is required to perform these operations or steps in the specific order shown or in a serial order, or to perform all the operations or steps shown to obtain the desired results. In the embodiments of the present application, these operations or steps can be performed in series; these operations or steps can also be performed in parallel; or some of these operations or steps can be performed.

[0034] At the same time, it is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0035] First, the application scenario of this application is explained. The applied education learning behavior data mining method and system based on action logic is a technical means to analyze various specific behavioral data generated by students in the learning process, reveal their learning habits, cognitive processes and potential problems, thereby providing a scientific basis for educational decision-making, and thus improving the quality and effectiveness of education.

[0036] This case aims at the fact that traditional applied education learning behavior data mining methods are unable to capture the dynamic changes in student behavior. This case proposes an applied education learning behavior data mining method and system based on action logic. Based on the differences in learning behaviors among different individual students and their different adaptability to different learning plans, by collecting and analyzing the selection and feedback data of all students in the target area on different learning plans, the overall appeal of different learning plans to the student group can be obtained, and the popularity and effectiveness of specific learning plans in general can be identified; then, for the target individual students, their historical learning plan information is analyzed to understand the student's past learning behavior, preferences and effects; finally, by continuously collecting and analyzing individual student learning data, teaching strategies are adjusted in real time to adapt to the dynamic changes in student behavior, thereby avoiding the disadvantages of static assumptions in traditional methods.

[0037] Since students' learning interests, learning plans, knowledge mastery levels, etc. will change over time, this application aims to solve the problem that the static model in the traditional method cannot update and adjust the learning behavior characteristics of students in a timely manner, resulting in the system's prediction and analysis results of students' learning behavior being lagging and inaccurate. It proposes a data mining method and system that can effectively capture the changes in students' dynamic learning behavior, thereby improving the teaching quality and teaching effect. The application is described below in conjunction with specific embodiments.

[0038] Figure 1 FIG. 1 is a flow chart of a method for mining applied education learning behavior data based on action logic according to an exemplary embodiment. Figure 1 As shown, the embodiment of the present application provides an applied education learning behavior data mining method based on action logic, and the method may include the following steps: In step S10, for a target course, learning behavior data of a student group for the target course is obtained, and the learning behavior data includes a plurality of learning plans.

[0039] In this step, for the target course, the learning behavior data of the student group for the target course is obtained, and the learning behavior data includes multiple learning plans. For example, for a specific course, the duration of all learning behaviors of the student group of the target institution and the students' personal learning plans are collected, such as daily reading time, daily question-solving time, and daily after-class review time.

[0040] According to the work process systematic curriculum development paradigm, students' learning behaviors are divided into six different dimensions of behavioral performance: "information-planning-decision-implementation-checking-evaluation", learning declarative knowledge, procedural knowledge, strategic knowledge, operational skills, mental skills and intellectual skills.

[0041] In step S20, the preference index of the student group for the plurality of learning plans is obtained according to the learning behavior data.

[0042] In this step, the preference index of the student group for multiple learning plans is obtained based on the learning behavior data. For example, the learning completion of the student group for the target learning plan can be obtained based on the learning behavior data, and then the selection prominence of the student group for the target learning plan can be obtained based on the learning behavior data, and then the preference index of the student group for multiple learning plans can be obtained based on the learning completion and the selection prominence.

[0043] By collecting and analyzing the selection and feedback data of all students in the target area on different learning plans, we can obtain the attractiveness of different learning plans to student groups and identify the general preference index of student groups for specific learning plans. We can analyze the historical learning plan information of individual target students and understand the historical learning behavior characteristics of the students. Finally, the system continuously collects and analyzes the learning data of individual students, adjusts the teaching strategies in real time, and adapts to the dynamic changes in student behavior, thereby avoiding the drawbacks of static assumptions in traditional methods.

[0044] In step S30, the learning interest factor of the target student individual is obtained according to the preference index of the student group for the learning plan.

[0045] In this step, the learning interest factor of the target student is obtained according to the preference index of the student group for the learning plan. Exemplarily, the information entropy of the target student's choice of learning plan can be obtained first, and then the learning interest factor of the target student can be obtained according to the information entropy of the target student's choice of learning plan and the preference index of multiple learning plans.

[0046] In step S40, the learning behavior characteristic factor of the target student individual is obtained according to the learning interest factor of the target student individual.

[0047] In this step, the learning behavior characteristic factor of the target student is obtained according to the learning interest factor of the target student. Exemplarily, the correlation between the learning plans of the target student can be obtained first, and then the learning behavior characteristic factor of the target student can be obtained according to the product of the correlation and the learning interest factor.

[0048] In step S50, a learning plan is tailored for the target individual student according to the learning behavior characteristic factors of the target individual student.

[0049] In this step, a learning plan is tailored for the target student according to the learning behavior characteristic factors of the target student. Exemplarily, a learning plan is tailored for each student according to the learning behavior characteristic factors of the target student, and personalized assessment tasks and standards are set to provide students with targeted feedback and suggestions to help them continuously improve their learning methods and strategies. Through personalized education strategies, students' learning needs can be better met and their learning effects and satisfaction can be improved. At the same time, personalized education strategies can also enhance the pertinence and effectiveness of teaching, so that educational resources can be used more reasonably and effectively.

[0050] In summary, the embodiment of the present application provides an applied education learning behavior data mining method based on action logic, the method comprising: for a target course, obtaining the learning behavior data of a student group for the target course, the learning behavior data comprising a plurality of learning plans; based on the learning behavior data, obtaining the preference index of the student group for the plurality of learning plans; based on the preference index of the student group for the learning plan, obtaining the learning interest factor of the target individual student; based on the learning interest factor of the target individual student, obtaining the learning behavior characteristic factor of the target individual student; based on the learning behavior characteristic factor of the target individual student, tailoring a learning plan for the target individual student. The embodiment of the present application obtains the learning behavior characteristic factor of the target individual student by mining the learning behavior data of the student group and the learning behavior data of the individual student, and tailors a learning plan for the target individual student based on the learning behavior characteristic factor, thereby realizing personalized teaching and tutoring for the target individual student and improving the teaching quality and teaching effect of the teaching system.

[0051] Figure 2 FIG. 1 is a flow chart showing a method for obtaining a preference index of a student group for multiple learning plans according to an exemplary embodiment. Figure 2 As shown, obtaining the preference index of the student group for the plurality of learning plans may include the following steps: In step S201, the learning completion degree of the student group for the target learning plan is obtained based on the learning behavior data.

[0052] In this step, the learning completion of the target learning plan by the student group is obtained based on the learning behavior data. For example, the time between two adjacent learning assessment nodes can be used as the learning time window to obtain the adjacent first learning time window and the second learning time window, and then the first total number of students who choose the target learning plan in the first learning time window and the second total number of students who choose the target learning plan in the second learning time window are counted, and then the learning completion of the target learning plan by the student group is obtained based on the first total number and the second total number.

[0053] In step S202, the selection prominence of the target learning plan by the student group is obtained based on the learning behavior data.

[0054] In this step, the student group's selection prominence for the target learning plan is obtained based on the learning behavior data. Exemplarily, the frequency of the target learning plan appearing in the first learning plan set of the target area can be obtained first, the first learning plan set is the set of all learning plans in the target area, and then the average of the frequencies of the learning plans in the second learning plan set appearing in the first learning plan set is obtained, the second learning plan set is the set of all learning plans in the target area except the target learning plan, and then the student group's selection prominence for the target learning plan is obtained based on the frequency and the average.

[0055] In step S203, the preference index of the student group for the plurality of learning plans is obtained according to the learning completion degree and the selection prominence.

[0056] In this step, the preference index of the student group for the multiple learning plans is obtained according to the learning completion and the selection prominence. For example, the product of the learning completion and the selection prominence can be used as the preference index of the student group for the multiple learning plans.

[0057] Figure 3 FIG. 1 is a flow chart showing a method for obtaining the learning completion degree of a student group for a target learning plan according to an exemplary embodiment. Figure 3 As shown, obtaining the learning completion degree of the student group for the target learning plan may include the following steps: In step S2011, the time between two adjacent learning assessment nodes is taken as the learning time window, and an adjacent first learning time window and a second learning time window are obtained.

[0058] In this step, the time between two adjacent learning assessment nodes is used as the learning time window to obtain the adjacent first learning time window and the second learning time window. Exemplarily, one month can be used as an assessment node time, or one quarter can be used as an assessment node time.

[0059] In step S2012, a first total number of students in the student group who select the target learning plan in the first learning time window and a second total number of students who select the target learning plan in the second learning time window are counted.

[0060] In this step, the total number of students who choose the target learning plan in the first learning time window is counted. , and the second total number of people who select the target learning plan in the second learning time window .in, is the target learning plan, indicating the first learning plan, j is the first learning time window, which means the jth time scale window of the student group in the learning process, j-1 is the second learning time window, which means the j-1th time scale window of the student group in the learning process.

[0061] In step S2013, the learning completion degree of the student group for the target learning plan is obtained based on the first total number of people and the second total number of people.

[0062] In this step, based on the first total number and the second total number , obtain the learning completion degree Wi of the student group for the target learning plan.

[0063] Generally speaking, there are large individual differences among students in terms of learning style, interests, cognitive abilities, etc., so the study plans they choose and the feedback on the study plans will be different. Some students may be more suitable for more time to do exercises every day, while others may be more suitable for consolidating and reviewing classroom knowledge through online classes after class every day. These differences will lead to large fluctuations in the choice and feedback of study plans, which in turn manifests as large differences in the interest index of different student groups for different study plans, resulting in different adaptability of different study plans to individual students. Therefore, the adaptability of specific study plans to student groups can be quantified by analyzing all types of study plans that exist in the student group, the student group's interest in them, and the degree of learning completion.

[0064] Figure 4 FIG. 1 is a flowchart of another method for obtaining the learning completion degree of a student group for a target learning plan according to an exemplary embodiment. Figure 4 As shown, obtaining the learning completion degree of the student group for the target learning plan may include the following steps: In step S20131, the sum of the first total number of people and the second total number of people is obtained.

[0065] In this step, get the first total number of people With the second total number The sum of .

[0066] in, Formula 1 In step S20132, the ratio of the sum to the first total number of people is used as the degree of learning completion of the target learning plan by the student group.

[0067] In this step, the sum With the first total number The ratio of is taken as the learning completion degree Wi of the student group for the target learning plan.

[0068] Where Wi = Formula 2 Indicates The first The first The total number of students in each study program is Select the first The ratio of the number of students who choose a study plan to the total number of students who choose the plan is the student completion rate Wi. This ratio indicates whether students are willing to continue studying along the same plan after their initial selection. A high ratio means that students have a high degree of recognition and loyalty to the plan and believe that the plan can continue to meet their learning needs.

[0069] Figure 5 FIG. 1 is a flow chart showing a method for obtaining the selection prominence of a target learning plan by a student group according to an exemplary embodiment. Figure 5 As shown, obtaining the selection prominence of the target learning plan by the student group may include the following steps: In step S2021, the frequency of occurrence of the target learning plan in a first learning plan set in a target region is obtained, where the first learning plan set is a set of all learning plans in the target region.

[0070] In this step, the frequency of the target learning plan appearing in the first learning plan set A in the target region is obtained. , the first learning plan set is the set of all learning plans in the target area.

[0071] In step S2022, the average frequency of occurrence of learning plans in a second learning plan set in the first learning plan set is obtained, and the second learning plan set is a set of all learning plans in the target area except the target learning plan.

[0072] In this step, obtain the second learning plan set The mean frequency of the learning plans in the first learning plan set , the second learning plan set It is the collection of all learning programs in the target region except the target learning program.

[0073] In step S2023, the selection prominence of the target learning plan by the student group is obtained based on the frequency and the mean.

[0074] In this step, based on the frequency and mean , obtain the selection prominence Ti of the student group for the target learning plan. Exemplarily, the selection prominence Ti of the student group for the target learning plan can be obtained by the following formula: Formula 3 in, Represents the The frequency with which a learning plan appears in the target area learning plan set A, Represents The average frequency of the learning plans in the set appearing in the target area learning plan set A. The exponential function with the natural constant e as the base represents the expansion of the formula value to prevent the value from being too small to be conducive to subsequent analysis.

[0075] It indicates the The frequency of occurrence of a learning plan in the target area learning plan set A is The ratio of the product of the mean frequency of the learning plan in the target area learning plan set A to 10 is the selection prominence Ti. The larger the value, the more prominent the learning plan is. The frequency of a learning plan in the target area learning plan set A is greater than the frequency of other learning plans in the set, then The more popular a study plan is among the student population, the greater the students' preference index for it.

[0076] Figure 6 FIG. 1 is a flowchart of another method for obtaining a preference index of a student group for multiple learning plans according to an exemplary embodiment. Figure 6 As shown, obtaining the preference index of the student group for the plurality of learning plans according to the learning completion degree and the selection prominence may include the following steps: In step S2031, the product of the learning completion degree and the selection prominence degree is used as the preference index of the student group for the multiple learning plans.

[0077] In this step, the product of learning completion Wi and selection prominence Ti is used as the preference index of the student group for multiple learning plans. . Exemplary, preference index of student groups for multiple study programs It can be obtained by the following formula: Formula 4 The student group's learning completion degree Wi for the target learning plan is used to modify the student's choice prominence Ti of the learning plan, and the student group's preference index for multiple learning plans is obtained. The larger the value, the more likely the student group is to choose If the student group is willing to continue to study along the same plan, the student group has a higher degree of sustained interest and recognition in the study plan, and the greater the preference for it, the higher the preference index. The larger the value of .

[0078] Figure 7 FIG. 1 is a flow chart showing a method for obtaining a learning interest factor of a target student according to an exemplary embodiment. Figure 7 As shown, obtaining the learning interest factor of the target student individual according to the preference index of the student group for the learning plan may include the following steps: In step S301, the information entropy of the selected learning plan of the target student individual is obtained.

[0079] In this step, the information entropy of the probability of the target student individual choosing a learning plan is obtained .

[0080] In step S302, the learning interest factor of the target student individual is obtained according to the information entropy of the target student individual's selected learning plan and the preference indexes of the plurality of learning plans.

[0081] In this step, the information entropy of the target student's individual choice of learning plan is and preference index for multiple study plans , obtain the learning interest factor of the target student . Exemplary, the learning interest factor of the target student It can be obtained by the following formula: Formula 5 in, is the information entropy, which represents the information entropy of the probability of the target student selecting the target learning plan in the historical learning plan selection data, M represents the total number of learning plans of the target student in the historical learning plan selection data, and m represents the mth learning plan among the M learning plans. represents the student preference index for the mth learning plan, KPI represents the learning interest factor of the target student, and norm is the normalization processing.

[0082] It represents 1 minus the mean of the preference index of all learning plans in the historical learning plan selection data of the target students, that is, it represents the difference between the learning plan selected by the target students and the group preference. The larger the value is, the more unique the learning plan selected by the target students is, that is, the more inconsistent it is with the group preference.

[0083] The learning interest factor of the target student is obtained by multiplying the information entropy of the probability of the target student selecting the target learning plan in the historical learning plan selection data and the difference between the learning plan selected by the target student and the group preference. , the larger the value, the more diverse and unique the target student's choices in the historical learning plan data are. In this case, it can be considered that the student has a strong autonomous learning ability and exploratory spirit, and can choose a suitable learning plan according to his or her own needs and interests, rather than blindly following the group's preferences. The larger the value of , the greater the individual's learning interest factor.

[0084] Figure 8 FIG. 1 is a flow chart showing a method for obtaining learning behavior characteristic factors of a target student individual according to an exemplary embodiment. Figure 8 As shown, the step of obtaining the learning behavior characteristic factor of the target student individual according to the learning interest factor of the target student individual may include the following steps: In step S401, the correlation degree between the learning plans of the target individual students is obtained.

[0085] In this step, the degree of correlation L between the learning plans of the target individual students is obtained. Exemplarily, the probability that any one of all the learning plans of the target individual student is selected by the student group can be obtained first, and then based on the probability, the joint probability that any two learning plans of all the learning plans of the target individual student are selected in the student group is obtained, and then the distribution of the joint probability is used as the joint entropy of the learning plan combination, and finally the degree of correlation L between the learning plans of the target individual student is obtained based on the joint entropy of the learning plan combination.

[0086] In step S402, the learning behavior characteristic factor of the target student individual is obtained according to the product of the association degree and the learning interest factor.

[0087] In this step, according to the association degree L and the learning interest factor The product of , to obtain the learning behavior characteristic factor of the target student individual .in, . Formula 6 Fig. 9 FIG. 1 is a flowchart showing a method for obtaining the degree of association between individual learning plans of target students according to an exemplary embodiment. Fig. 9 As shown, obtaining the degree of association between the target student individual learning plans may include the following steps: In step S4011, the probability of any one of all the learning plans of the target individual student being selected by the student group is obtained.

[0088] In this step, the probability Px of any one of all the learning plans of the target individual student being selected by the student group is obtained. Exemplarily, the probability Px can be obtained from the historical selection data of the learning plan.

[0089] In step S4012, based on the probability, the joint probability of any two combinations of all the learning plans of the target individual student being selected in the student group is obtained.

[0090] In this step, according to the probability Px, the joint probability Pxy of any two learning plan combinations among all learning plans of the target student individual being selected in the student group is obtained. The joint probability Pxy can be obtained by the existing joint probability calculation method.

[0091] In step S4013, the distribution of the joint probability is used as the joint entropy of the learning plan combination.

[0092] In this step, the probability distribution of the joint probability Pxy is used as the joint entropy of the learning plan combination .

[0093] In step S4014, the correlation degree between the learning plans of the target individual students is obtained according to the joint entropy of the learning plan combination.

[0094] In this step, the joint entropy of the combined learning plan , obtain the correlation degree L between the target student individual learning plans. Exemplarily, the correlation degree L between the target student individual learning plans can be obtained by the following formula: L= Formula 7 Combining formula 6-7, we can get the following formula: Formula 8 in, is the learning behavior characteristic factor of the target student, represents the total number of combinations of all the learning plans selected by the target student in history. Represents For the total number of learning plan combinations For study plan combinations, Represents the The joint entropy of the learning plan combination, e is a natural constant, Represents the learning interest factor of the target student.

[0095] It represents the mean of the joint entropy of any two learning plans in the set of all learning plans historically selected by the target student, that is, the degree of correlation L between any two learning plans. The smaller the value, the greater the joint entropy between the learning plans selected by the student, which means that the uncertainty or confusion of the joint probability distribution between the learning plans is higher, that is, the smaller the correlation, which further indicates that the student has a higher diversity in choosing learning plans, that is, he is more inclined to try different learning plans; on the contrary, if the value is larger, it means that the student is more inclined to choose certain specific learning plans when choosing learning plans.

[0096] It represents the correlation degree L between any two learning plans in the set of all learning plans selected by the target student and their learning interest factor The product of the learning interest factor is calculated through the association degree L. Modify and obtain the learning behavior characteristic factors of the target students The larger the value is, the more diverse all the learning plans selected by the target student in the individual history are, and the correlation between the selected learning plans is small, which means that the student shows a wider range of interests and exploration behaviors in the learning process and is not limited to certain specific learning plans. Therefore, it is necessary to provide diversified educational resources and means when formulating educational strategies in the future.

[0097] In summary, the embodiment of the present application provides an applied education learning behavior data mining method based on action logic, the method comprising: for a target course, obtaining the learning behavior data of a student group for the target course, the learning behavior data comprising a plurality of learning plans; based on the learning behavior data, obtaining the preference index of the student group for the plurality of learning plans; based on the preference index of the student group for the learning plan, obtaining the learning interest factor of the target individual student; based on the learning interest factor of the target individual student, obtaining the learning behavior characteristic factor of the target individual student; based on the learning behavior characteristic factor of the target individual student, tailoring a learning plan for the target individual student. The embodiment of the present application obtains the learning behavior characteristic factor of the target individual student by mining the learning behavior data of the student group and the learning behavior data of the individual student, and tailors a learning plan for the target individual student based on the learning behavior characteristic factor, thereby realizing personalized teaching and tutoring for the target individual student and improving the teaching quality and teaching effect of the teaching system.

[0098] The present application also provides a computer-readable storage medium on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the applied educational learning behavior data mining method based on action logic provided by the present application are implemented.

[0099] Fig.10 FIG. 1 is a block diagram of an applied education learning behavior data mining system based on action logic according to an exemplary embodiment. Fig.10 As shown, an embodiment of the present application provides an applied education learning behavior data mining system 1000 based on action logic, including a server 1100.

[0100] Fig.11 is a block diagram of a server according to an exemplary embodiment. Fig.11 The server 1100 includes one or more processors 1122 and a memory resource represented by a memory 1132 for storing instructions executable by the processor 1122, such as an application. The application stored in the memory 1132 may include one or more modules each corresponding to a set of instructions. In addition, the processor 1122 is configured to execute instructions to perform the above-mentioned action logic-based applied education learning behavior data mining method.

[0101] The server 1100 may also include a power component 1126 configured to perform power management of the server 1100, a communication component 1150 configured to connect the server 1100 to a network, and an input / output interface 1158. The server 1100 may operate based on an operating system stored in the memory 1132.

[0102] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable electronic device, and the computer program has a code portion for executing the above-mentioned action logic-based applied educational learning behavior data mining method when executed by the programmable electronic device.

[0103] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application.

Claims

1. Data mining method of applied education learning behavior based on action logic, It is characterized in that The method comprises: For a target course, obtaining learning behavior data of a student group for the target course, wherein the learning behavior data includes a plurality of learning plans; According to the learning behavior data, obtaining the preference index of the student group for the plurality of learning plans; Obtaining a learning interest factor of a target student individual according to the preference index of the student group for the learning plan; According to the learning interest factor of the target student individual, obtaining the learning behavior characteristic factor of the target student individual; A learning plan is tailored for the target student individual based on the learning behavior characteristic factors of the target student individual.

2. According to the action logic-based applied education learning behavior data mining method of claim 1, It is characterized in that The obtaining of the preference index of the student group for the plurality of learning plans comprises: According to the learning behavior data, obtaining the learning completion degree of the student group for the target learning plan; According to the learning behavior data, obtaining the selection prominence of the target learning plan by the student group; According to the learning completion degree and the selection prominence, the preference index of the student group for the plurality of learning plans is obtained.

3. The method for mining applied educational learning behavior data based on action logic according to claim 2, It is characterized in that The obtaining of the learning completion degree of the student group for the target learning plan includes: Taking the time between two adjacent learning assessment nodes as the learning time window, obtaining the adjacent first learning time window and the second learning time window; Counting a first total number of students in the student group who select the target learning plan in the first learning time window, and a second total number of students who select the target learning plan in the second learning time window; The degree of learning completion of the target learning plan by the student group is obtained based on the first total number of people and the second total number of people.

4. The method for mining applied educational learning behavior data based on action logic according to claim 3, It is characterized in that The obtaining of the learning completion degree of the student group for the target learning plan includes: Obtaining the sum of the first total number of people and the second total number of people; The ratio of the sum to the first total number of people is used as the learning completion degree of the student group for the target learning plan.

5. The method for mining applied educational learning behavior data based on action logic according to claim 2, It is characterized in that The obtaining the selection prominence of the target learning plan by the student group includes: Obtaining a frequency of occurrence of the target learning plan in a first learning plan set in a target region, where the first learning plan set is a set of all learning plans in the target region; Obtaining an average of the frequencies of occurrence of learning plans in a second learning plan set in the first learning plan set, wherein the second learning plan set is a set of all learning plans in the target region except the target learning plan; According to the frequency and the mean, the selection prominence of the target learning plan by the student group is obtained.

6. The method for mining applied educational learning behavior data based on action logic according to claim 2, It is characterized in that The step of obtaining the preference index of the student group for the plurality of learning plans according to the learning completion degree and the selection prominence degree includes: The product of the learning completion degree and the selection prominence is used as the preference index of the student group for the multiple learning plans.

7. The method for mining applied educational learning behavior data based on action logic according to claim 1, It is characterized in that The step of obtaining the learning interest factor of the target student individual according to the preference index of the student group for the learning plan includes: Obtain the information entropy of the target student's individual choice of study plan; The learning interest factor of the target student individual is obtained according to the information entropy of the selected learning plan of the target student individual and the preference indexes of the plurality of learning plans.

8. The method for mining applied educational learning behavior data based on action logic according to claim 1, It is characterized in that The step of obtaining the learning behavior characteristic factor of the target student individual according to the learning interest factor of the target student individual includes: Obtaining the degree of correlation between the learning plans of the target students; The learning behavior characteristic factor of the target student individual is obtained according to the product of the association degree and the learning interest factor.

9. The method for mining applied educational learning behavior data based on action logic according to claim 8, It is characterized in that The obtaining of the correlation between the target student individual learning plans includes: Obtaining the probability of any one of all the learning plans of the target individual student being selected by the student group; According to the probability, obtaining the joint probability of any two study plan combinations among all study plans of the target individual student being selected in the student group; Using the distribution of the joint probability as the joint entropy of the learning plan combination; According to the joint entropy of the combination of learning plans, the degree of association between the learning plans of the target individual students is obtained.

10. An applied education learning behavior data mining system based on action logic, It is characterized in that The system comprises a server, wherein the server comprises: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 9.

Images