Method and apparatus for selecting a recently developed area

Abstract

The embodiment of the application provides a method and device for selecting a recent development zone, comprising: obtaining a first knowledge graph and behavior data of a student; extracting learning features from the behavior data to fill the meta-information corresponding to the knowledge points, and calculating a meta-information ability value of each meta-information and a knowledge point ability value between the knowledge points to obtain a personal ability model of the student; obtaining a group ability model, and calculating a personal mastery level of each knowledge point of the student according to the group ability model and the personal ability model to obtain personal mastery level data of the student; and obtaining a knowledge point with the maximum knowledge point ability value as the recent development zone of the student according to the personal mastery level data, the group mastery level data and the group ability model. The method adaptively recommends the recent development zone according to the gap between the student, the group and the teaching target, so as to stimulate the potential of the student and improve the learning enthusiasm of the student.

Description

Technical Field

[0001] This application relates to the field of online education technology, and more specifically to a method and apparatus for selecting the region of proximal development. Background Technology

[0002] One of the goals of both online and offline education is to enable students to learn more efficiently. Efficiency is reflected in the fact that the knowledge students are currently learning, the questions they are solving, and the thinking they are grasping are all within their capabilities, but require only a little effort to master. The goal is to avoid making the material too easy, which would bore students and waste their time, while also preventing it from being too difficult, which could lead to discouragement or giving up. Providing students with a sense of accomplishment will motivate them, increase their enthusiasm for learning, and unleash their potential.

[0003] However, current online education simply identifies students' weak knowledge based on their accuracy in answering questions, and then uses knowledge graphs to rank students according to their level of weakness and recommend learning paths. It does not find knowledge or questions that are suitable for students' specific abilities, which can easily lead to students losing confidence or developing a fear of difficulty, resisting learning, and resulting in low learning efficiency.

[0004] The expression of students' learning characteristics is often too simplistic; mere accuracy in answering questions is insufficient. A student's learning behaviors throughout the entire online learning process can reflect specific abilities and should therefore be considered as part of their learning characteristics. Furthermore, the range of students' weaknesses is vast, with some weaknesses exceeding their current skill level, which could actually dampen their enthusiasm for learning.

[0005] In response to this phenomenon, educator Vygotsky proposed a theory of child development based on the Zone of Proximal Development (ZPD). He believed that student development has two levels: one is the student's current level, referring to the level of problem-solving achievable independently; the other is the student's potential level, that is, the potential to be acquired through teaching. The difference between the two is the ZPD. Teaching should focus on the student's ZPD, providing challenging content to motivate students, unleash their potential, and help them surpass their ZPD to reach the next developmental stage, thus building upon this foundation for further development in the next ZPD. Summary of the Invention

[0006] Firstly, embodiments of this application provide a method for selecting the zone of proximal development (ZPD). This method first constructs a knowledge graph by extracting knowledge points from teaching materials, richly expressing the relationships and hierarchical structure between knowledge points, expanding the knowledge graph into a multi-layered topological structure from different mastery dimensions of knowledge points. Secondly, it extracts learning features from students' behavioral data to improve the knowledge graph and obtain the student's personal ability model. Then, through a trained group ability model and teaching research experience, it obtains the group mastery level of each knowledge point in the group ability model. Based on the group mastery level of each knowledge point and the student's knowledge point ability value, it obtains the student's personal mastery level data. Finally, by first comparing the distance between the student and each knowledge point in the group, it obtains one or more knowledge points with the smallest distance. Then, based on the group mastery level of the corresponding knowledge point in the group ability model and the corresponding teaching objective level, it further obtains one or more knowledge points that are most likely to achieve the next teaching objective. Finally, it adaptively recommends the ZPD to the student by selecting the knowledge point with the largest ability value.

[0007] The method includes:

[0008] Step S1: Obtain the first knowledge graph and student behavior data, wherein the first knowledge graph consists of at least one knowledge point, each knowledge point corresponds to meta-information of different mastery dimensions, and knowledge point weights are set between knowledge points that are related.

[0009] Step S2: Extract learning features from the behavioral data to fill the meta-information corresponding to the knowledge points, and calculate the meta-information ability value of each meta-information and the knowledge point ability value between the knowledge points to obtain the student's personal ability model;

[0010] Step S3: Obtain the group ability model, calculate the student's individual mastery level for each knowledge point based on the group ability model and the individual ability model, and obtain the student's individual mastery level data. The group ability model includes multiple ability groups, and each knowledge point in each ability group has a group mastery level.

[0011] Step S4: Based on the individual mastery level data, the group mastery level data, and the group ability model, the knowledge point with the highest ability value is obtained as the student's zone of proximal development.

[0012] First, step S1 involves constructing a first knowledge graph for the teaching domain. In some embodiments, this first knowledge graph is obtained by processing and summarizing the knowledge points appearing in various chapters of the teaching materials, and then expanding the knowledge points in the first knowledge graph from different mastery dimensions. Therefore, the method for constructing the first knowledge graph includes: extracting one or more knowledge points from various chapters of the teaching materials; expanding the knowledge points with meta-information from different mastery dimensions; obtaining the meta-information weight and meta-information quantity of the meta-information corresponding to each knowledge point; obtaining the knowledge point quantity of the corresponding knowledge point based on the meta-information weight and the meta-information quantity; and calculating the knowledge point weight based on the relationship between the knowledge points and the knowledge point quantity. Here, the meta-information weight represents the importance of the meta-information in the corresponding knowledge point, and the meta-information quantity is obtained by constructing a meta-information matrix, which represents the number of times the meta-information appears in different chapters of the teaching materials.

[0013] In some application embodiments, the weight of the knowledge point is calculated as follows:

[0014] Where X and Y represent knowledge point X and knowledge point Y respectively, and knowledge point X is a prerequisite knowledge point for knowledge point Y, and x is the same meta-information x contained in knowledge point X and knowledge point Y. It is the probability that x appears in X.

[0015] Secondly, the learning features contained in each knowledge point in the first knowledge graph are elevated to the student's ability dimension to comprehensively evaluate the student's ability and obtain the student's personal ability model. Therefore, in some embodiments, step S2 includes: extracting learning features from the behavioral data; calculating the meta-information ability value of the corresponding knowledge point based on the learning features, wherein the meta-information ability value is the quotient of the sum of the corresponding learning features and the number of learning features; calculating the corresponding knowledge point ability value based on the meta-information ability value, wherein the knowledge point ability value is the quotient of the sum of the meta-information ability values ​​of all meta-information corresponding to the knowledge point and the number of meta-information corresponding to the knowledge point; and filling the knowledge point ability value of each knowledge point in the first knowledge graph to obtain the student's personal ability model.

[0016] Specifically, in some application embodiments, the method for obtaining behavioral data is as follows: obtaining the student's question-answering records, extracting the student's behavioral data based on the question-answering records, wherein each question in the question-answering records corresponds to at least one meta-information of the knowledge point.

[0017] In particular, in some application embodiments, if the student's behavior data is empty, the behavior data of other students with the same student attributes and whose corresponding behavior data is not empty are obtained according to the student's student attributes, and the behavior data of the other students is converted into the student's behavior data.

[0018] Then, through the trained group ability model and teaching and research experience, the group mastery level of each knowledge point in the group ability model is obtained, and the student's individual mastery level data is obtained based on the group mastery level of each knowledge point and the student's knowledge point ability value. In some application embodiments, step S3 includes: obtaining the group ability model; obtaining the matching group for the student based on the group ability model and the individual ability model; mapping the knowledge point ability value corresponding to each knowledge point of the student to the matching group to obtain the student's individual mastery level for each knowledge point, thus forming the student's individual mastery level data.

[0019] Finally, in some application embodiments, a teaching objective level is set for each knowledge point. The teaching objective level is divided into multiple teaching objectives according to different knowledge point ability value ranges. The group mastery level is the average knowledge point ability value of multiple other students corresponding to the knowledge point.

[0020] Therefore, in some corresponding application embodiments, step S4 includes: calculating a first distance for the same knowledge point based on the individual mastery level data and the group mastery level data, and obtaining one or more first knowledge points with the smallest first distance; calculating a second distance between the group mastery level of the first knowledge point in the group mastery level data and the corresponding teaching objective level, and obtaining one or more second knowledge points with the smallest second distance; selecting the second knowledge point with the largest knowledge point ability value as the student's zone of proximal development. In other words, questions corresponding to the second knowledge point are automatically recommended as the student's zone of proximal development.

[0021] Secondly, based on the same concept, embodiments of this application provide a device for selecting the region of proximal development, the device comprising:

[0022] Initialization module: used to acquire the first knowledge graph and student behavior data, wherein the first knowledge graph consists of at least one knowledge point, each knowledge point corresponds to meta-information of different mastery dimensions, and knowledge point weights are set between knowledge points that are related.

[0023] The first expansion module is used to extract learning features from the behavioral data to fill the meta-information corresponding to the knowledge points, and to calculate the meta-information ability value of each meta-information and the knowledge point ability value between the knowledge points to obtain the student's personal ability model.

[0024] The second expansion module is used to obtain the group ability model, calculate the individual mastery level of each knowledge point of the student based on the group ability model and the individual ability model, and obtain the individual mastery level data of the student. The group ability model includes multiple ability groups, and the knowledge points of each ability group have a group mastery level.

[0025] Automatic recommendation module: Based on the individual mastery level data, the group mastery level data, and the group ability model, the knowledge point with the highest ability value is selected as the student's zone of proximal development.

[0026] Thirdly, embodiments of this application provide an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform operations as described in any of the above-mentioned embodiments of the region of proximal development selection method.

[0027] Fourthly, embodiments of this application provide a computer program product, the computer program product comprising: a program or instructions that, when the program or instructions are run on a computer, cause the computer to perform the method for selecting the region of proximal development as described in any of the above embodiments.

[0028] Fifthly, embodiments of this application provide a readable storage medium storing a computer program, the computer program including program code for controlling a process to execute the process, the process including the method for selecting the region of proximal development as described in any of the above-mentioned embodiments.

[0029] This application proposes a method and apparatus for selecting the zone of proximal development (ZPD). First, a knowledge graph is constructed with knowledge points as nodes to richly express the relationships and hierarchical structure between knowledge points, expanding the knowledge graph into a multi-layered topological structure based on different mastery dimensions of the knowledge points. Second, learning features are extracted from student behavioral data to refine the knowledge graph and obtain the student's individual ability model. Then, combining the group's level and teaching experience, the student's individual mastery level data is obtained based on their knowledge point ability values. Finally, by comparing the student's level with the group's level, and the group's level with the teaching objectives, one or more knowledge points are identified as most likely to achieve the next teaching objective. The knowledge point with the highest ability value is then adaptively recommended as the ZPD for the student.

[0030] It is worth mentioning that, more importantly, this application embodiment adaptively recommends the zone of proximal development based on the gap between students and groups and teaching objectives, in order to stimulate students' potential and improve their learning motivation.

[0031] For students without behavioral data, the first knowledge graph can be initialized by referring to the learning characteristics of students in the same group. Furthermore, based on the relationships between knowledge points, the ability of knowledge points for which learning characteristics cannot be obtained can be predicted. In addition, by establishing the relationship between questions and meta-information in the question bank, questions that meet the criteria of the zone of proximal development can be selected for training and improvement based on the student's ability value. Attached Figure Description

[0032] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0033] Figure 1 This is a flowchart of a method for selecting the region of proximal development according to an embodiment of this application;

[0034] Figure 2 This is a partial schematic diagram of the first knowledge graph according to an embodiment of this application;

[0035] Figure 3 This is a schematic diagram illustrating the relationship between knowledge points according to embodiments of this application;

[0036] Figure 4 This is a title information diagram according to an embodiment of this application;

[0037] Figure 5 This is an example diagram illustrating the relationship between the title and metadata according to embodiments of this application;

[0038] Figure 6 This is a schematic diagram illustrating knowledge points according to an embodiment of this application;

[0039] Figure 7 This is a schematic diagram illustrating the relationship between the title and metadata according to an embodiment of this application;

[0040] Figure 8 This is a structural block diagram of a device for selecting the region of proximal development according to an embodiment of this application;

[0041] Figure 9 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0042] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0043] It should be noted that the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification in other embodiments. In some other embodiments, the methods may include more or fewer steps than described in this specification. Furthermore, a single step described in this specification may be broken down into multiple steps in other embodiments; and multiple steps described in this specification may be combined into a single step in other embodiments.

[0044] This embodiment provides a method for selecting the region of proximal development, for details please refer to... Figure 1 , Figure 1 This is a flowchart of a method for selecting the region of proximal development according to an embodiment of this application.

[0045] like Figure 1 As shown, the method includes steps S1-S4:

[0046] Step S1: Obtain the first knowledge graph and student behavior data, wherein the first knowledge graph consists of at least one knowledge point, each knowledge point corresponds to meta-information of different mastery dimensions, and knowledge point weights are set between knowledge points that are related.

[0047] Step S2: Extract learning features from the behavioral data to fill the meta-information corresponding to the knowledge points, and calculate the meta-information ability value of each meta-information and the knowledge point ability value between the knowledge points to obtain the student's personal ability model;

[0048] Step S3: Obtain the group ability model, calculate the student's individual mastery level for each knowledge point based on the group ability model and the individual ability model, and obtain the student's individual mastery level data. The group ability model includes multiple ability groups, and each knowledge point in each ability group has a group mastery level.

[0049] Step S4: Based on the individual mastery level data, the group mastery level data, and the group ability model, the knowledge point with the highest ability value is obtained as the student's zone of proximal development.

[0050] In step S1, a knowledge graph for the teaching domain is constructed to more richly express the relationships and hierarchical structure between knowledge points, expanding the knowledge graph into a multi-layered topological structure from different dimensions of knowledge point mastery. In some embodiments, the first knowledge graph is obtained by processing and summarizing the knowledge appearing in various chapters of the teaching materials, with knowledge points as the basis, and the knowledge points in the knowledge graph are expanded in multiple dimensions, such as NLP related methods: TF-IDF, bag-of-words model, etc., extracting multi-dimensional meta-information such as knowledge, methods, and ideas of the corresponding knowledge points to expand the knowledge points in the knowledge graph.

[0051] In other words, the method for constructing the first knowledge graph includes: extracting one or more knowledge points from each chapter of the textbook; expanding the knowledge points with meta-information of different mastery dimensions; obtaining the meta-information weight and meta-information amount of the meta-information corresponding to each knowledge point; obtaining the knowledge point information amount corresponding to the knowledge point based on the meta-information weight and the meta-information amount; and calculating the knowledge point weight based on the association between the knowledge points and the knowledge point information amount.

[0052] For details, please refer to the following: Figure 2 , Figure 2 This is a partial schematic diagram of the first knowledge graph according to an embodiment of this application.

[0053] like Figure 2 As shown, the knowledge points include: "absolute value calculation," "number line," "three elements of the number line," "definition of absolute value," etc. The mastery of the "meaning of absolute value" dimension is categorized into three types of meta-information: "knowledge," "method," and "idea." Each knowledge point can have multiple meta-information components. For example, the knowledge related to the "meaning of absolute value" includes concepts of algebraic expressions, rational expressions, simplification, equal division, and the basic properties of inequalities, etc.; the ideas include holistic thinking, equation thinking, function thinking, transformation thinking, analogy thinking, and the combination of number and shape thinking, etc.; and the methods include classification and discussion, completing the square, factorization, substitution, discriminant method, method of undetermined coefficients, construction method, proof by contradiction, area method, geometric transformation method, verification method, elimination method, and graphical method. Each piece of knowledge, each idea, and each method constitutes a meta-information component.

[0054] Furthermore, this method employs the concepts of information content and conditional entropy from information theory to calculate the information content of each knowledge point and the knowledge point weights among knowledge points in the first knowledge graph. The meta-information weight represents the importance of the meta-information within the corresponding knowledge point, and the information content of the meta-information is obtained by constructing a meta-information matrix, where the meta-information matrix represents the frequency of the meta-information appearing in different textbook chapters.

[0055] Therefore, the formula for obtaining the weight of the knowledge point is as follows:

[0056] Where X and Y represent knowledge point X and knowledge point Y respectively, and knowledge point X is a prerequisite knowledge point for knowledge point Y, and x is the same meta-information x contained in knowledge point X and knowledge point Y. It is the probability that x appears in X.

[0057] Then, based on the amount of meta-information corresponding to each knowledge point in the first knowledge graph, the information content of the knowledge point is calculated. The calculation method is as follows:

[0058]

[0059] in, Indicates the amount of information in a knowledge point. This indicates the weight of the metadata corresponding to that knowledge point. This indicates the amount of metadata corresponding to this knowledge point.

[0060] In light of the meaning of the teaching scenario and the knowledge points that students need to master, such as "absolute value calculation," they must first master its prerequisite knowledge points, for example... Figure 2 The prerequisite knowledge points for "absolute value calculation" include "number line," "three elements of a number line," and "definition of absolute value," while conditional entropy refers to the degree of reduction of uncertainty based on known partial information. If we know that a student has mastered the "definition of absolute value," we cannot accurately judge whether they have mastered "absolute value calculation." However, if we know that a student has mastered the definition of absolute value, the number line, and calculation, we can more likely determine their level of mastery. This method is used to calculate the knowledge point weights in the first knowledge graph. Therefore, the specific method for calculating the knowledge point weights between knowledge points is as follows: .

[0061] refer to Figure 3 , Figure 3 This is a schematic diagram illustrating the relationship between knowledge points according to embodiments of this application. For example... Figure 3 As shown, X and Y represent knowledge point X and knowledge point Y, respectively, and knowledge point X is a prerequisite knowledge point for knowledge point Y. x is the same metadata contained in knowledge point X and knowledge point Y. It is the probability that x appears in X.

[0062] Specifically, after constructing the first knowledge graph, the association between the questions in the question bank and the metadata is established. The questions in the question bank are matched with our teaching materials to recommend the most suitable questions to students based on their zone of proximal development. Each question corresponds to at least one metadata item related to the aforementioned knowledge point. Furthermore, by obtaining the student's question-answering records, the student's behavioral data is extracted from these records. See details for further information. Figure 4 , Figure 4 This is a title information diagram based on an embodiment of this application. For example... Figure 4 As shown, based on the infographic of this question, the following metadata can be extracted: the geometric meaning of absolute value, absolute value itself, number line, and classification discussion. Therefore, this question is treated as Q1, and the relationship between Q1 and the metadata is established as follows: Figure 5 , Figure 5 This is an example diagram illustrating the relationship between the title and metadata according to an embodiment of this application.

[0063] In step S2, learning features are extracted from students' behavioral data to improve the knowledge graph and obtain the student's personal ability model. Then, through the trained group ability model and teaching and research experience, the group mastery level of each knowledge point in the group ability model is obtained. Based on the group mastery level of each knowledge point and the student's knowledge point ability value, the student's personal mastery level data is obtained.

[0064] Specifically, in some embodiments, the method for obtaining behavioral data is as follows: obtaining the student's problem-solving records, extracting the student's behavioral data based on the problem-solving records, wherein each question in the problem-solving records corresponds to at least one meta-information of the knowledge point.

[0065] In addition, in some embodiments, if the student's behavior data is empty, the behavior data of other students with the same student attributes and whose corresponding behavior data is not empty are obtained according to the student's student attributes, and the behavior data of the other students is converted into the student's behavior data.

[0066] Specifically, if the target student has not yet generated behavioral data, a weighted average can be calculated based on the student's self-evaluation, teacher evaluation, grade level, and other student attributes, along with the learning characteristics of other students with behavioral data who share the same attributes. The dimensions of student self-evaluation include learning ability and attentiveness, while teacher evaluation also includes these dimensions, using a 10-point scoring system. Based on the target student's attributes, the top 20 students with behavioral data exhibiting the highest similarity in student attributes are identified, and the similarity between the target student and these other students is calculated using cosine similarity.

[0067] ,

[0068] The student's individual ability model is obtained by weighting and averaging the learning characteristics of the student and filling the first knowledge graph. The specific calculation method is as follows:

[0069] ,

[0070] in, Indicates the target students. This refers to the other students mentioned above. Let represent the cosine similarity between the target student and the k-th student.

[0071] Then, the learning features contained in each meta-information in the first knowledge graph are elevated to the student's ability dimension to comprehensively evaluate the student's ability. Therefore, in some embodiments, step S2 includes: extracting learning features from the behavioral data; calculating the meta-information ability value of the corresponding knowledge point based on the learning features, wherein the meta-information ability value is the quotient of the sum of the corresponding learning features and the number of the learning features; calculating the corresponding knowledge point ability value based on the meta-information ability value, wherein the knowledge point ability value is the quotient of the sum of the meta-information ability values ​​of all meta-information corresponding to the knowledge point and the number of meta-information corresponding to the knowledge point; and filling the knowledge point ability value of each knowledge point in the first knowledge graph to obtain the student's personal ability model.

[0072] The corresponding meta-information capability value is calculated based on the learned features, where each meta-information includes one or more learned features. The method for calculating the meta-information capability value is as follows: .in The capability value representing the i-th meta-information. Let N represent the j-th learned feature of the i-th metadata, and N represent the total number of N learned features of the i-th metadata.

[0073] The corresponding knowledge point ability value is calculated based on the meta-information ability value, where each knowledge point includes one or more meta-information items. The method for calculating the knowledge point ability value is as follows: .in, The value represents the ability value of the k-th knowledge point, and M represents the M metadata contained in knowledge point k.

[0074] Additionally, if the learning feature corresponding to the metadata is empty, then the knowledge point ability value of the knowledge point is calculated based on the ability values ​​of the adjacent knowledge points and the adjacent knowledge points. The specific calculation method is as follows:

[0075] ,

[0076] in, Representative knowledge points The knowledge points related to k'. See details in the reference section. Figure 6 , Figure 6 This is a schematic diagram of knowledge points according to an embodiment of this application.

[0077] like Figure 6 As shown, the student has no learning characteristics for knowledge point 4, but has learning characteristics for related knowledge points 1, 2, and 6. Therefore, the knowledge point ability value for knowledge point 4 is:

[0078] ,

[0079] in, , and etc. all represent the knowledge points between two knowledge points.

[0080] In step S3, combining the level of the group and teaching and research experience, the personal mastery level data of the student is obtained according to the knowledge point ability value of the student. That is to say, through the trained group ability model and teaching and research experience, the group mastery level of each knowledge point in the group ability model is obtained, and the personal mastery level data of the student is obtained according to the group mastery level of each knowledge point and the knowledge point ability value of the student.

[0081] In some embodiments, there is a teaching objective level corresponding to each of the knowledge points. The teaching objective level is divided into multiple teaching objectives according to different knowledge point ability value intervals. The group mastery level is the average value of the knowledge point ability values of multiple other students corresponding to the knowledge point.

[0082] Among them, the group ability model extracts the behavior data of a large number of other students, calculates the personal ability model of each student, and uses the k-means method to cluster these students to obtain four groups of excellent, good, medium, and poor.

[0083] For each knowledge point of each student in the above group ability model, mark the mastery level with teaching and research experience to obtain the knowledge point mastery level of each student for each knowledge point.

[0084] ,

[0085] where i represents the i-th student, Knowledge represents the set of knowledge points, and Level represents the knowledge point mastery level of each knowledge point.

[0086] According to the obtained student mastery level data, count the proportion of the number of people in each level. The statistical method is:

[0087] ,

[0088] where represents the group mastery level data of the i-th group for the k-th knowledge point, i belongs to {excellent, good, medium, poor}, j belongs to {know, understand, apply, analyze, synthesize, evaluate}, represents the average value of the knowledge point ability values of all students in the j-th level of the k-th knowledge point of the i-th group for the knowledge point.

[0089] That is to say, in some embodiments, the group ability model includes 4 ability groups, namely: excellent, good, medium, and poor. The teaching objective level includes 6 levels, namely: know, understand, apply, analyze, synthesize, evaluate.

[0090] Then, based on the student's personal ability model, the corresponding ability group is determined. By comparing the student's knowledge point ability value with the group mastery level of the corresponding matching ability group, the student's personal mastery level for each knowledge point is obtained.

[0091] In other words, in some embodiments, step S3 specifically includes: obtaining the group capability model; obtaining the matching group for the student based on the group capability model and the individual capability model; mapping the knowledge point capability value corresponding to each knowledge point of the student to the matching group to obtain the individual mastery level of each knowledge point of the student, and forming the student's individual mastery level data.

[0092] In some embodiments, the method for determining a specific ability group in the student matching ability group model is as follows: calculate the distance between the student and each of the four ability groups (Excellent, Good, Average, and Poor), and select the ability group with the smallest distance as the matching group. The calculation method is as follows:

[0093] ,

[0094] Where i represents the student, j represents the group, and j belongs to {Excellent, Good, Average, Poor}. This represents the student's ability value for the m-th knowledge point. This represents the evaluation ability value of the m-th knowledge in the j-th group.

[0095] To determine the distribution position of each knowledge point of the student in the group ability model, the knowledge points in the group ability model are first divided into six equal parts according to the teaching objective level. That is, each teaching objective level corresponds to a knowledge point ability value range. Then, based on the correspondence between the student's ability value of each knowledge point and the group mastery level in the group ability model, the student's individual mastery level of each knowledge point is obtained, thus forming the student's individual mastery level data.

[0096] In step S4, by comparing the student's level with the group's level, and the group's level with the learning objectives, one or more knowledge points are identified as the easiest to achieve the next learning objective. The knowledge point with the highest ability value is then adaptively recommended as the student's zone of proximal development. In other words, by first comparing the distance between the student and each knowledge point in the group, one or more knowledge points with the smallest distance are identified. Then, based on the group's mastery level of the corresponding knowledge point in the group's ability model and the corresponding learning objective level, one or more knowledge points as the easiest to achieve the next learning objective are further identified. The knowledge point with the highest ability value is then adaptively recommended as the student's zone of proximal development.

[0097] Specifically, in some embodiments, step S4 includes: calculating a first distance for the same knowledge point based on the individual mastery level data and the group mastery level data, and obtaining one or more first knowledge points with the smallest first distance; calculating a second distance between the group mastery level of the first knowledge point in the group mastery level data and the corresponding teaching objective level, and obtaining one or more second knowledge points with the smallest second distance; and selecting the second knowledge point with the largest knowledge point ability value as the student's zone of proximal development.

[0098] The formula for calculating the first distance between a student's individual mastery level data and the group mastery level data for the same knowledge point is as follows: ,in This indicates the student's mastery level i of knowledge point k. Let j represent the mastery level of knowledge point k in the group mastery hierarchy model. The hierarchy distance between knowledge points in the student's individual mastery hierarchy data and group mastery hierarchy data is used as the first distance. Preliminary knowledge point selection is performed based on this first distance, selecting one or more knowledge points with the smallest distance as the first knowledge point. The specific selection formula is as follows: .

[0099] Given the set of first knowledge points selected above, calculate the second distance between the group mastery level of the first knowledge point and the corresponding teaching objective level in the group mastery level data, and obtain one or more second knowledge points with the smallest second distance. The calculation method is as follows:

[0100] ,

[0101] in This indicates that the group has mastered knowledge point k at level i within the hierarchical data. Let j represent the teaching objective mastery level of knowledge point k in the group mastery hierarchy model. The distance between the group mastery level data and the teaching objective level is used as the second distance. This second distance is then used to select one or more second knowledge points with the smallest second distance. The specific selection formula is as follows: .

[0102] Finally, the second knowledge point with the highest ability score is selected as the student's zone of proximal development (ZPD). Based on the ZPD, questions corresponding to the selected knowledge point and with the highest ability score are recommended to the student. The method for calculating the question ability score is as follows:

[0103] ,

[0104] in, Indicates the question number. This represents the metadata capability value of the k-th metadata item, where n represents the number of metadata items related to the i-th question. (Reference) Figure 7 , Figure 7 This is a schematic diagram illustrating the relationship between the title and metadata according to an embodiment of this application, such as... Figure 7 As shown, question Q1 includes meta-information 1, meta-information 2, and meta-information 3, so the ability value of question Q1 is:

[0105] .

[0106] Example 2

[0107] Based on the same concept, this application provides a device for selecting the region of proximal development, used to implement the method for selecting the region of proximal development described in Embodiment 1, with reference to... Figure 8 , Figure 8 This is a structural block diagram of a device for selecting the region of proximal development according to an embodiment of this application.

[0108] like Figure 8 As shown, the device includes the following modules:

[0109] Initialization module: used to acquire the first knowledge graph and student behavior data, wherein the first knowledge graph consists of at least one knowledge point, each knowledge point corresponds to meta-information of different mastery dimensions, and knowledge point weights are set between knowledge points that are related.

[0110] The first expansion module is used to extract learning features from the behavioral data to fill the meta-information corresponding to the knowledge points, and to calculate the meta-information ability value of each meta-information and the knowledge point ability value between the knowledge points to obtain the student's personal ability model.

[0111] The second expansion module is used to obtain the group ability model, calculate the individual mastery level of each knowledge point of the student based on the group ability model and the individual ability model, and obtain the individual mastery level data of the student. The group ability model includes multiple ability groups, and the knowledge points of each ability group have a group mastery level.

[0112] Automatic recommendation module: Based on the individual mastery level data, the group mastery level data, and the group ability model, the knowledge point with the highest ability value is selected as the student's zone of proximal development.

[0113] Example 3

[0114] This embodiment also provides an electronic device, see reference. Figure 9It includes a memory 404 and a processor 402, the memory 404 storing a computer program and the processor 402 being configured to run the computer program to perform the steps of any of the network request merging methods in Embodiment 1 above.

[0115] Specifically, the processor 402 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0116] Memory 404 may include a mass storage device for data or instructions. For example, and not limitingly, memory 404 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 404 may include removable or non-removable (or fixed) media. Where appropriate, memory 404 may include removable or non-removable (or fixed) media. Where appropriate, memory 404 may be internal or external to a data processing device. In a particular embodiment, memory 404 is non-volatile memory. In a particular embodiment, memory 404 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these.Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), Extended Data Out Dynamic Random-Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0117] The memory 404 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 402.

[0118] The processor 402 reads and executes computer program instructions stored in the memory 404 to implement any of the data entry methods in the above embodiments.

[0119] Optionally, the electronic device may further include a transmission device 406 and an input / output device 408, wherein the transmission device 406 is connected to the processor 402, and the input / output device 408 is connected to the processor 402.

[0120] The transmission device 406 can be used to receive or send data via a network. Specific examples of the network described above may include wired or wireless networks provided by the communication provider of the electronic device. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 406 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0121] Input / output device 408 is used to input or output information. In this embodiment, the input information may be a current data table, such as an epidemic investigation document, feature data, template table, etc., and the output information may be feature fingerprints, fingerprint templates, text classification recommendation information, file template configuration mapping table, file template configuration information table, etc.

[0122] Optionally, in this embodiment, the processor 402 can be configured to perform the following steps via a computer program:

[0123] Step S1: Obtain the first knowledge graph and student behavior data, wherein the first knowledge graph consists of at least one knowledge point, each knowledge point corresponds to meta-information of different mastery dimensions, and knowledge point weights are set between knowledge points that are related.

[0124] Step S2: Extract learning features from the behavioral data to fill the meta-information corresponding to the knowledge points, and calculate the meta-information ability value of each meta-information and the knowledge point ability value between the knowledge points to obtain the student's personal ability model;

[0125] Step S3: Obtain the group ability model, calculate the student's individual mastery level for each knowledge point based on the group ability model and the individual ability model, and obtain the student's individual mastery level data. The group ability model includes multiple ability groups, and each knowledge point in each ability group has a group mastery level.

[0126] Step S4: Based on the individual mastery level data, the group mastery level data, and the group ability model, the knowledge point with the highest ability value is obtained as the student's zone of proximal development.

[0127] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0128] Furthermore, in conjunction with any of the region of proximal development selection methods in Embodiment 1 above, this application embodiment can be implemented using a computer program product. This computer program product includes: a program or instructions that, when executed on a computer, cause the computer to execute any of the region of proximal development selection methods in Embodiment 1 above.

[0129] Furthermore, in conjunction with any of the methods for selecting the region of proximal development in Embodiment 1 above, this application embodiment can provide a readable storage medium for implementation. This readable storage medium stores a computer program; when executed by a processor, the computer program implements any of the methods for selecting the region of proximal development in Embodiment 1 above.

[0130] Generally, various embodiments can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects of the invention can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device, but the invention is not limited thereto. Although various aspects of the invention may be shown and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that, by way of non-limiting example, these blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0131] Embodiments of the present invention can be implemented by computer software, which may be executable by a data processor of a mobile device, such as a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products), including software routines, applets, and / or macros, can be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. A computer program product may include one or more computer-executable components configured to perform embodiments when the program is run. One or more computer-executable components may be at least one piece of software code or a portion thereof. Additionally, it should be noted that any block in the logical flow of the figures may represent a program step, or interconnected logical circuitry, blocks and functions, or a combination of program steps and logical circuitry, blocks and functions. The software may be stored on physical media such as memory chips or blocks of storage implemented within a processor, magnetic media such as hard disks or floppy disks, and optical media such as, for example, DVDs and their data variants, CDs, etc. The physical medium is a non-transient medium.

[0132] Those skilled in the art should understand that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0133] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for selecting the zone of proximal development, characterized in that, Includes the following steps: Step S1: Obtain the first knowledge graph and student behavior data, wherein the first knowledge graph consists of at least one knowledge point, each knowledge point corresponds to meta-information of different mastery dimensions, and knowledge points with correlation are assigned knowledge point weights, the calculation method of the knowledge point weights is as follows: Where X and Y represent knowledge point X and knowledge point Y respectively, and knowledge point X is a prerequisite knowledge point for knowledge point Y, and x is the same meta-information x contained in knowledge point X and knowledge point Y. It is the probability that x appears in X; Step S2: Extract learning features from the behavioral data to fill the meta-information corresponding to the knowledge points, and calculate the meta-information ability value of each meta-information and the knowledge point ability value between the knowledge points. Fill the knowledge point ability value of each knowledge point in the first knowledge graph to obtain the student's personal ability model; wherein, the method for calculating the meta-information ability value is as follows: , The capability value representing the i-th meta-information. Let j represent the j-th learning feature of the i-th metadata, and N represent the total number of learning features for the i-th metadata. The method for calculating the knowledge point ability value is as follows: , The value represents the ability of the kth knowledge point, and M represents that knowledge point k contains M meta-information. Step S3: Obtain the group ability model. Based on the group ability model and the individual ability model, obtain the matching group for the student. The group ability model includes four ability groups: excellent, good, average, and poor. The method for determining a certain ability group in the student's matching ability group model is as follows: calculate the distance between the student and each of the four ability groups (excellent, good, average, and poor) respectively, and take the ability group with the smallest distance as the matching group; map the ability value of each knowledge point of the student to the matching group to obtain the individual mastery level of each knowledge point of the student. The group ability model includes multiple ability groups, and each knowledge point of the ability group has a group mastery level. The group mastery level is the average of the ability values ​​of multiple other students corresponding to the knowledge point. Step S4: Obtain the student's zone of proximal development (ZPD) based on the individual mastery level data, the group mastery level data, and the group ability model. A teaching objective level is set for each knowledge point, and this level is divided into multiple teaching objectives based on different knowledge point ability value ranges. The group mastery level is the average knowledge point ability value of multiple other students for the corresponding knowledge point. Specifically, a first distance is calculated for the same knowledge point based on the individual mastery level data and the group mastery level data, and one or more first knowledge points with the smallest first distance are obtained. A second distance is calculated between the group mastery level of the first knowledge point in the group mastery level data and the corresponding teaching objective level, and one or more second knowledge points with the smallest second distance are obtained. The second knowledge point with the largest ability value is selected as the student's ZPD.

2. The method for selecting the zone of proximal development according to claim 1, characterized in that, The method for constructing the first knowledge graph includes: Extract one or more knowledge points from various chapters of the textbook; The knowledge points are expanded with meta-information of different mastery dimensions, wherein the weight of the meta-information is the importance of the meta-information in the corresponding knowledge point; Obtain the meta-information weight and meta-information quantity of each knowledge point, wherein the meta-information quantity is obtained by constructing a meta-information matrix, and the meta-information matrix represents the number of times the meta-information appears in different textbook chapters; The knowledge point information quantity corresponding to the knowledge point is obtained based on the meta-information weight and the meta-information information quantity; The weight of each knowledge point is calculated based on the relationships between them and the amount of information contained in each knowledge point.

3. The method for selecting the zone of proximal development according to claim 1, characterized in that, Step S2 includes: Extract learning features from the behavioral data; The meta-information capability value of the corresponding knowledge point is calculated based on the learning features, wherein the meta-information capability value is the quotient of the sum of the corresponding learning features and the number of the learning features; The corresponding knowledge point capability value is calculated based on the meta-information capability value, wherein the knowledge point capability value is the quotient of the sum of the meta-information capability values ​​of all meta-information corresponding to the knowledge point and the number of meta-information corresponding to the knowledge point. The student's personal ability model is obtained by filling in the knowledge point ability value of each knowledge point in the first knowledge graph.

4. The method for selecting the zone of proximal development according to claim 1, characterized in that, The acquisition of student behavioral data includes: acquiring the student's problem-solving records, extracting the student's behavioral data based on the problem-solving records, wherein each problem in the problem-solving records corresponds to at least one unit of information for at least one knowledge point; extracting learning features from the behavioral data includes: if the student's behavioral data is empty, acquiring the behavioral data of other students with the same student attributes and whose corresponding behavioral data is not empty, and converting the behavioral data of the other students into the student's behavioral data; if the learning feature corresponding to the knowledge point is empty, acquiring the knowledge point ability value and corresponding knowledge point weight of at least one adjacent knowledge point that is related to the knowledge point, and calculating the knowledge point ability value of the knowledge point based on the knowledge point ability value and the knowledge point weight.

5. A device for selecting the region of proximal development, characterized in that, Includes the following modules: Initialization module: Used to acquire a first knowledge graph and student behavior data, wherein the first knowledge graph consists of at least one knowledge point, each knowledge point corresponds to meta-information of different mastery dimensions, and knowledge points with correlations are assigned knowledge point weights, the calculation method of the knowledge point weights is as follows: Where X and Y represent knowledge point X and knowledge point Y respectively, and knowledge point X is a prerequisite knowledge point for knowledge point Y, and x is the same meta-information x contained in knowledge point X and knowledge point Y. It is the probability that x appears in X; The first expansion module is used to extract learning features from the behavioral data to fill the meta-information corresponding to the knowledge points, and to calculate the meta-information ability value of each meta-information and the knowledge point ability value between the knowledge points, thereby filling the knowledge point ability value of each knowledge point in the first knowledge graph to obtain the student's personal ability model. The method for calculating the meta-information ability value is as follows: , The capability value representing the i-th meta-information. Let j represent the j-th learning feature of the i-th metadata, and N represent the total number of learning features for the i-th metadata. The method for calculating the knowledge point ability value is as follows: , The value represents the ability of the kth knowledge point, and M represents that knowledge point k contains M meta-information. The second expansion module is used to obtain a group ability model. Based on the group ability model and the individual ability model, the module obtains the matching group for the student. The group ability model includes four ability groups: excellent, good, average, and poor. The method for determining a certain ability group in the student's matching ability group model is as follows: calculate the distance between the student and each of the four ability groups (excellent, good, average, and poor) respectively, and take the ability group with the smallest distance as the matching group; map the ability value of each knowledge point of the student to the matching group to obtain the individual mastery level of each knowledge point of the student. The group ability model includes multiple ability groups, and each knowledge point of the ability group has a group mastery level. The group mastery level is the average of the ability values ​​of multiple other students corresponding to the knowledge point. Automatic Recommendation Module: Based on the individual mastery level data, the group mastery level data, and the group ability model, the student's zone of proximal development (ZPD) is obtained. For each knowledge point, a teaching objective level is set, which is divided into multiple teaching objectives based on different knowledge point ability value ranges. The group mastery level is the average knowledge point ability value of multiple other students for the corresponding knowledge point. Specifically, a first distance is calculated based on the individual mastery level data and the group mastery level data for the same knowledge point, and one or more first knowledge points with the smallest first distance are obtained. A second distance is calculated between the group mastery level of the first knowledge point in the group mastery level data and the corresponding teaching objective level, and one or more second knowledge points with the smallest second distance are obtained. The second knowledge point with the largest knowledge point ability value is selected as the student's ZPD.

6. A computer program product, characterized in that, Includes a software code portion, which, when the computer program product is run on a computer, is used to execute the method for selecting the region of proximal development according to any one of claims 1 to 4.

Images