Data processing method and device, electronic equipment and computer readable storage medium

Abstract

The invention discloses a data processing method, and relates to the technical field of education, and the specific implementation scheme is as follows: collecting learning behavior data of at least one activity subject at different time points in an educational activity; based on the learning behavior data, creating a dynamic network atlas which is used for reflecting key elements of the activity subject and an association relationship of the key elements; on the basis of the dynamic network atlas, determining a cognitive level hierarchy index of each activity subject in the at least one activity subject; and based on the cognitive level hierarchy index and the learning behavior data, generating and sending education recommendation data of each activity subject. Therefore, objectivity and scientificity of the evaluation process are enhanced, managers are helped to understand perceived behavior habits and modes of students more deeply, and educational strategies and management plans are made more effectively.

Description

Technical Field

[0001] The invention belongs to the field of educational technology, and in particular relates to a data processing method and device, an electronic device, and a computer-readable storage medium. Background Art

[0002] As a key component of modern distance education, online education provides people with convenient conditions for continuous learning. With the continuous progress of distance education, the research on the evaluation system and methods of online education effectiveness has received increasing attention.

[0003] At present, the research on the effectiveness of online education mainly focuses on the in-depth longitudinal analysis of cost-effectiveness, and has begun to try to compare the indicators of distance education effectiveness, resource utilization efficiency and graduate quality of different educational institutions (such as online education colleges) across institutions. However, there are relatively few studies on comparative evaluation. Most related studies rely on data and involve the perspective of teachers. However, these studies often focus on the subjective interpretation of teachers and are insufficient in quantitative analysis, which leads to the lack of objectivity in the evaluation of educational effectiveness and cannot fully reflect the actual learning situation and learning effect of students.

[0004] The information disclosed in this background technology section is only intended to increase the understanding of the overall background of the present invention disclosure, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0005] The present invention discloses a method and device for processing data, an electronic device, and a computer-readable storage medium for solving the problem of quantitative analysis effect of existing online education.

[0006] The first aspect of the present invention discloses a data processing method, which includes: collecting learning behavior data of at least one active subject in an educational activity at different time points; creating a dynamic network map based on the learning behavior data, the dynamic network map being used to reflect the key elements of the active subject and the association relationship between the key elements; determining the cognitive level hierarchy index of each active subject in at least one active subject based on the dynamic network map; generating and sending educational recommendation data for each active subject based on the cognitive level hierarchy index and the learning behavior data.

[0007] The second aspect of the present invention discloses a data processing device, which includes: a collection unit, configured to collect learning behavior data of at least one active subject in an educational activity at different time points; a creation unit, configured to create a dynamic network map based on the learning behavior data, and the dynamic network map is used to reflect the key elements of the active subject and the association relationship between the key elements; a determination unit, configured to determine the cognitive level hierarchy index of each active subject in at least one active subject based on the dynamic network map; and a generation unit, configured to generate and send educational recommendation data for each active subject based on the cognitive level hierarchy index and the learning behavior data.

[0008] The third aspect of the present invention discloses an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in any implementation manner of the first aspect.

[0009] A fourth aspect of the present invention provides a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to cause a computer to execute the method described in any implementation of the first aspect.

[0010] The data processing method and device provided by the embodiments disclosed in the present invention first collect the learning behavior data of at least one active subject in an educational activity at different time points; secondly, create a dynamic network map based on the learning behavior data; thirdly, determine the cognitive level hierarchy index of each active subject in the at least one active subject based on the dynamic network map; finally, generate and send the education recommendation data of each active subject based on the cognitive level hierarchy index and the learning behavior data; thereby, quantifying the behavior data of the active subject through the dynamic network map provides a comprehensive perspective for education managers, more accurately reflects the comprehensive quality and teaching effect of the active subject, reduces the subjective evaluation of education results by the education industry, and improves the objectivity and scientificity of education evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a flow chart of an embodiment of a data processing method disclosed in the present invention;

[0012] Figure 2 is a schematic structural diagram of an embodiment of a data processing device disclosed in the present invention;

[0013] Figure 3 It is a block diagram of an electronic device used to implement the data processing method disclosed in the embodiment of the present invention. DETAILED DESCRIPTION

[0014] Unless explicitly stated otherwise, throughout the specification and claims, the term “comprise” or variations such as “include” or “comprising”, etc., will be understood to include the stated elements or components but not to exclude other elements or components.

[0015] The technical solution disclosed in the present invention is described below by means of specific embodiments. It should be understood that one or more steps mentioned in the present invention do not exclude the existence of other methods and steps before and after the combination step, or other methods and steps may be inserted between these explicitly mentioned steps. It should also be understood that these examples are only used to illustrate the present invention and are not used to limit the scope of the present invention. Unless otherwise specified, the numbering of each method step is only for the purpose of identifying each method step, and does not limit the order of arrangement of each method or the scope of implementation of the present invention. Changes or adjustments in their relative relationships can also be regarded as the scope of implementation of the present invention without substantial changes in the technical content.

[0016] The sources of the raw materials and instruments used in the examples are not particularly limited and can be purchased from the market or prepared according to conventional methods known to those skilled in the art.

[0017] Educational evaluation is a systematic investigation process in which educators conduct in-depth research on educational activities based on educational goals and relevant standards, aiming to identify their value, strengths and weaknesses, and adjust relevant educational activities accordingly. Through the collected data and information, it is possible to effectively evaluate and quantify the learners' learning process, learning outcomes, and the degree of understanding and mastery of knowledge and skills.

[0018] The evaluation of learners' core literacy has gradually been accepted by educators. A single evaluation tool no longer meets the needs of comprehensive evaluation. It cannot fully evaluate learners' thinking development level and cognitive structure growth. At the same time, it lacks specific tools to effectively utilize the discourse and text data generated in the teaching process.

[0019] In view of the defects in the prior art, the present invention discloses a data processing method. Figure 1 A flow chart 100 of an embodiment of a data processing method is shown. The data processing method comprises the following steps:

[0020] Step 101 : collecting learning behavior data of at least one activity subject in an educational activity at different time points.

[0021] In this embodiment, the educational activity is an activity that provides knowledge learning to the activity subject, and the activity subject is the subject who participates in the educational activity and receives education. For example, the activity includes classroom lectures, and sensors in the classroom can collect information such as speech and behavior learned in the classroom.

[0022] In this embodiment, the educational activity may also be an online educational activity. The learning behavior data of the activity subject may be collected through a learning management system (LMS) related to the online educational activity. LMS is an activity that conducts electronic learning and teaching through digital methods such as computers and networks, and is intended to efficiently manage training and education. It supports multiple functions, including online registration, course management, course allocation, integration of knowledge and information resources in multiple formats, learning assessment, tracking of learning activities and results, and generation of learning reports.

[0023] In this embodiment, the learning behavior data is the behavioral information performed by the activity subject in the educational activity. Specifically, the logging function, online test and homework submission function of the learning management system (LMS) can be used to collect the learning behavior data of the activity subject, such as login frequency, learning time, course participation, learning resource access and other learning behavior data.

[0024] In this embodiment, learning behavior data includes: behavior data, learning effect data, and educational resource data. Among them, behavior data includes: login frequency, learning time, learning progress, learning resource usage, learning interactive behavior and other data; learning effect data includes: test scores, homework scores, project results and other data; educational resource data includes: learning resource type, learning resource content, learning resource usage and other data.

[0025] Step 102: Create a dynamic network map based on the learning behavior data. The dynamic network map is used to reflect the key elements of the activity subject and the relationship between the key elements.

[0026] In this embodiment, the key elements are the most important features in the learning behavior data, and the dynamic network map is a visualization map with the key elements of the activity subject as nodes and the associations between the key elements as edges. The way the nodes in the dynamic network map are connected and the strength of the connection change over time, thus depicting the development and connection process of professional thinking elements in the field of education when solving complex problems.

[0027] In this embodiment, the learning behavior data can be analyzed through network participation analysis to create a dynamic network map. Network participation analysis is an innovative data visualization technology that aims to identify and quantify key elements in learning behavior data and simulate the association structure between these elements to create a dynamic network map. This method cleverly combines quantitative and qualitative analysis and can effectively present the visualization of discourse data and text data.

[0028] In this embodiment, after the characteristics of the learning behavior data are encoded, it is necessary to determine the basic analysis unit and the specific chapters of the analysis. The basic analysis unit refers to the object of analyzing the cognitive network structure m(i, j), which can be an individual, a concept min1-i, 1-j or other objects that need to be analyzed, as shown in formula (1).

[0029] m(i,j)=∏min{(1-i)(1+j)} (1)

[0030] Engagement Network Analysis (ENA) is an innovative data visualization technique that aims to identify and quantify key elements in discourse data and simulate the association structure between these elements to create a dynamic network map. This method cleverly combines quantitative and qualitative analysis and can effectively present the visualization of discourse data w(i)-w(j) and text data.

[0031]

[0032] In formula (2), w(t): represents the weight or importance measure at a certain time point t. w(i)-w(j): represents the importance difference between two different nodes i and j. Formula (2) can be understood as: w(t) is determined by calculating the sum of the importance differences between all pairs of nodes. This sum reflects the distribution of the relative importance of each node in the entire network.

[0033]

[0034] In formula (3), the left side Represents a summation operation, in which all i and j are traversed and calculated. a(i)w(i): is a product relationship, that is, the product of the attribute of node i and its weight. 1-a(i): is related to some characteristics of node i, such as the remaining possibility or other relevant metrics. The symbols in formula (3) represent the mathematical expressions used to quantify key elements and their associated structures in the network participation analysis (ENA) method. Through these expressions, a dynamic network map can be constructed, thereby realizing the visualization of discourse data and text data in learning behavior data.

[0035] Any relatively small complex network a(i)w(i) with fixed elements and dynamic connections can be modeled. The strength and composition of the model cognitive framework 1-a(i) will change over time and activity. Data can be encoded according to certain rules. The connection relationship and strength between data elements are displayed in the dynamic network graph w(t, s), as shown in Equation (4), reflecting the learner's cognitive level and hierarchy.

[0036]

[0037] In Equation (4), w(t, s): represents a weight or connection strength value in the dynamic network diagram at time point t and activity point s. a(i): represents the attribute or state of a fixed element, which is the characteristic of a certain node or data element. 1 - a(i): represents a measure of a complementary feature or state related to a(i), that is, the part other than a(i). i - a(i): represents a certain difference, variation amount, or other related calculation result, where i is the initial value or total amount, and a(i) is the part subtracted from it. <w(t): represents that the combination of all the above values is less than a time-dependent threshold w(t), which indicates that these values need to meet certain conditions or restrictions. Equation (4) describes the mutual relationship and its constraint conditions among different data and elements under specific time and activity conditions.

[0038] The "stanza" here is similar to the stanza in poetry. Each "stanza" brings together the discourse elements of 1 - a(i). The discourse elements between different "stanzas" are independent of each other, while the discourse elements within the same "stanza" are interrelated.

[0039] In this embodiment, the network participation analysis performs visual processing on the data and displays the projection of the centroid of the encoded element nodes and the positions of each analysis unit in a two-dimensional space perpendicular to the X-axis and Y-axis. At the same time, the weights of the connections are determined, and the matching degree between the formed network and the source data is evaluated through the Pearson correlation coefficient c(n, m) and the Spearman correlation coefficient 1 - n - m, as shown in Equation (5) specifically.

[0040] c(n, m) = lameda(n) - n / 1 - n - m (5)

[0041] Within the same analysis unit, the adjacency matrix r(i) - r(j) is accumulated. The accumulated adjacency matrix is normalized and converted into an adjacency vector x(i - j) in a higher-order space, which records the co-occurrence times of all encoded elements, as shown in Equation (6) specifically.

[0042]

[0043] To interpret and visualize these adjacency vectors, the network participation analysis adopts the Singular Value Decomposition (SVD) algorithm, which aims to reduce the dimension of the high-dimensional space. The SVD algorithm is similar to the principal component analysis, but the key difference is that it does not recalculate the data. In this way, the information in the source data is retained to the greatest extent, thereby minimizing the loss u(i) of data characteristics. This makes the presentation of the data x(i 1) clearer and also facilitates distinguishing the differences between different networks. Specifically, as shown in Equation (7).

[0044] (x - 1) T - 1{x(i),x(i-1),...,x(ij)}<i (7)

[0045] In the network diagram, the connection maxE(i) between nodes reveals the regularity of two nodes appearing at the same time or in the same activity w(i-1). This regularity quantifies the domain knowledge, thinking habits and cognitive elements of an individual (or team) at a specific time point in the discourse data 1-w(i-1), as shown in formula (8).

[0046]

[0047] Step 103, based on the dynamic network graph, determine the cognitive level index of each activity subject in at least one activity subject.

[0048] In this embodiment, the cognitive level index is an index that reflects the cognitive level and level of the activity subject. The cognitive level index includes: learning behavior index, cognitive development index and emotional attitude index. Among them, the learning behavior index is the index of learning time, learning frequency, homework completion, test scores, etc. The cognitive development index is the index of knowledge mastery, thinking ability, problem solving ability, etc. The emotional attitude index is the index of learning interest, learning motivation, learning confidence, etc.

[0049] In this embodiment, by analyzing the characteristics of nodes and connections in the dynamic network map, the cognitive level and hierarchy of the learner can be intuitively displayed. For example, the number and density of nodes in the network map can reflect the breadth and depth of the learner's knowledge, and the strength of the connection can reflect the learner's understanding and mastery of different knowledge points.

[0050] Step 104, based on the cognitive level index and learning behavior data, generate and send educational recommendation data for each activity subject.

[0051] In this embodiment, the educational recommendation data is the recommendation data that can improve the current cognitive level of the activity subject after analyzing the educational level of the activity subject. The cognitive level level index represents that the activity subject is at different cognitive levels. The cognitive level of the activity subject can be divided into three levels: basic level, learners have a low understanding and mastery of knowledge points, their learning behavior is relatively passive, and they lack learning interest and motivation. Intermediate level, learners have a high understanding and mastery of knowledge points, their learning behavior is relatively active, they have a certain learning interest and motivation, but lack in-depth thinking and problem-solving ability. Advanced level, learners have a very high understanding and mastery of knowledge points, their learning behavior is active, they have a strong learning interest and motivation, and they can think deeply and solve problems.

[0052] In this embodiment, the above step 104 includes: determining the cognitive level of the activity subject based on the cognitive level index; generating and sending the educational recommendation data of each activity subject based on the cognitive level and learning behavior data of the activity subject.

[0053] In this embodiment, the educational recommendation data includes: learning resources and learning paths. The above-mentioned educational recommendation data generated and sent for each activity subject based on the cognitive level hierarchy and learning behavior data of the activity subject includes: responding to the cognitive level hierarchy of the activity subject as the basic level, based on the learning behavior data, determining the learning interest of the activity subject, and recommending the learning resources and learning paths corresponding to the learning interest.

[0054] The data processing method disclosed in the present invention first collects the learning behavior data of at least one active subject in an educational activity at different time points; secondly, based on the learning behavior data, a dynamic network map is created, and the dynamic network map is used to reflect the key elements of the active subject and the correlation relationship of the key elements; then, based on the dynamic network map, the cognitive level level index of each active subject in at least one active subject is determined; finally, based on the cognitive level level index and the learning behavior data, the educational recommendation data of each active subject is generated and sent. Thus, advanced data mining technologies such as cluster analysis and classification prediction are used to achieve the segmentation and feature identification of learner behavior. This in-depth analysis enables educational managers to understand the habits, needs and potential problems of different learners, so that more personalized and effective education strategies can be formulated for different groups.

[0055] In a specific implementation, the data processing method disclosed in the present invention includes: when at least one activity subject has currently or historically participated in an educational activity, the learning behavior data of at least one activity subject is collected through a learning management system, and the performance, achievements, and use of educational resources of the activity subject in the educational activity can be identified through the learning behavior data. The most important feature in the learning behavior data is extracted and used as a key element; the attributes of the key elements are identified, and the association relationship of the key elements is determined based on the attributes, and a dynamic network map is created based on the key elements and the association relationship; the cognitive level and hierarchical indicators of each activity subject are determined through the characteristics of the nodes and connections in the dynamic network map, wherein the cognitive level and hierarchical indicators include: the knowledge breadth and depth indicators of the activity subject, and the understanding and mastery of different knowledge points by the activity subject; the cognitive level level of each activity subject is determined through the cognitive level and hierarchical indicators of each activity subject; based on the cognitive level level and learning behavior data, the educational recommendation data of each activity subject is generated and sent. , wherein the current learning level of the activity subject can be determined based on the cognitive level of the activity subject, and whether the learning resources in the learning behavior data meet the current learning level can be detected. If not, new recommended learning resources and learning paths are generated, and the new recommended learning resources and learning paths are sent to the corresponding activity subject as educational recommendation data; or based on the cognitive level of the activity subject, the level stage is determined, such as any one of the basic level stage, the intermediate level stage, and the advanced level stage, and the educational recommendation data corresponding to the determined level stage is generated, wherein the educational recommendation data can be data for different subjects, and the different subjects can be one of the activity subject, the educational subject, and the management subject.

[0056] In some optional implementations disclosed in the present invention, the above-mentioned generation and sending of educational recommendation data for each activity subject based on cognitive level level indicators and learning behavior data includes at least one of the following: based on cognitive level level indicators and learning behavior data, obtaining push data of each activity subject, and sending corresponding push data to each activity subject; based on cognitive level level indicators and the learning behavior data, obtaining educational strategies for each activity subject, and sending educational strategies to educational subjects; based on cognitive level level indicators, obtaining management strategies to be sent to management subjects.

[0057] In an optional implementation of the present invention, the push data includes: learning paths and resources. The above-mentioned push data of each activity subject is obtained based on the cognitive level hierarchy indicators and learning behavior data, and the corresponding push data is sent to each activity subject, including: by clustering the learning behavior data, identifying the learning behavior patterns that match the cognitive level hierarchy indicators of the activity subject, and recommending learning content that is consistent with their learning style and learning goals based on these patterns; combining the historical learning data and learning progress of the activity subject in the learning behavior data to recommend personalized learning paths and resources.

[0058] Optionally, the push data may also include: exercises, learning materials and Q&A services. The above-mentioned push data of each activity subject is obtained based on the cognitive level index and learning behavior data, and the corresponding push data is sent to each activity subject. It also includes: using the classification prediction model to identify the key factors that affect the performance of the activity subject in the learning behavior data, and predict the learning effect of the activity subject on specific knowledge points. According to the prediction results, a personalized tutoring plan is provided for the activity subject, including targeted exercises, learning materials and Q&A services.

[0059] In an optional implementation of the present invention, the above-mentioned educational strategies for each activity subject are obtained based on the cognitive level hierarchy indicators and the learning behavior data, and the educational strategies are sent to the educational subjects, including: analyzing the interactive behaviors and learning status of the activity subjects in the classroom under various cognitive level hierarchy indicators in the learning behavior data, identifying activity subjects with learning difficulties and classroom management problems; providing targeted classroom management strategy suggestions for the educational subjects, such as adjusting the teaching content, teaching methods and classroom interaction methods.

[0060] In an optional implementation of the present invention, the above-mentioned educational strategy for each activity subject also includes: analyzing the learning effect and weak links of the activity subject, and providing personalized teaching strategy suggestions for the education subject, such as adjusting the teaching progress, teaching focus and teaching methods.

[0061] In an optional implementation of the present invention, the management strategy sent to the management subject based on the cognitive level index includes: analyzing the use of educational resources by the activity subject based on the cognitive level index, identifying educational resources with high frequency of use and good effects, and educational resources with low frequency of use and poor effects, and providing educational resource optimization strategy suggestions to the management subject, such as increasing high-quality educational resources and eliminating inefficient educational resources. The management strategy sent to the management subject based on the cognitive level index also includes: analyzing the learning effects and influencing factors of the activity subject, and providing educational policy formulation strategy suggestions to the management subject, such as adjusting enrollment policies, teaching plans and curriculum settings.

[0062] In an optional implementation of the present invention, the educational subject is a subject that provides educational resources to the activity subject, such as a teacher; the management subject is a subject that manages the activity subject and the educational subject, such as a management staff.

[0063] The method for generating educational recommendation data provided by an optional implementation of the present invention obtains push data of each activity subject based on cognitive level hierarchy indicators and learning behavior data, and sends corresponding push data to each activity subject; obtains educational strategies of each activity subject based on cognitive level hierarchy indicators and the learning behavior data, and sends educational strategies to the educational subjects; obtains management strategies sent to management subjects based on cognitive level hierarchy indicators; and can recommend educational recommendation data of different contents based on different objects, thereby achieving diversity in the educational recommendation data obtained.

[0064] In some optional implementations disclosed in the present invention, the above method also includes: obtaining evaluation results of each activity subject based on the educational goal information and learning behavior data of the educational activity; the above education recommendation data is also obtained based on the evaluation result education recommendation data.

[0065] In an optional implementation of the present invention, the evaluation result is the result of evaluating whether the learning behavior data meets the educational objectives. The evaluation result may include multiple aspects, including: one or more of learning progress and understanding, knowledge mastery, and personalized learning level.

[0066] In an optional implementation of the present invention, the above-mentioned evaluation results of each activity subject obtained based on the educational goal information and learning behavior data of the educational activity include: based on the educational goal of the educational activity, the learning behavior data of the activity subject is evaluated to obtain the evaluation results of each activity subject.

[0067] In an optional implementation of the present invention, evaluating the learning behavior data of the activity subject may also include: analyzing the learning behavior data through multiple models to obtain various evaluation results, wherein the multiple models may include: a learning analysis model, a knowledge graph model, and a learning style model. The learning analysis model is a model based on educational goals. The learning analysis model compares the learning behavior data with the course objectives and teaching syllabus to evaluate the students' learning progress and understanding. The knowledge graph model converts the learning content into a knowledge graph, and evaluates the students' mastery of knowledge by analyzing the interaction between learning and knowledge nodes in the learning behavior data. The learning style model analyzes the students' learning styles, such as visual, auditory, kinesthetic, etc., based on the students' learning behavior data, to obtain the personalized learning degree and provide a reference for personalized learning.

[0068] In this embodiment, after obtaining the evaluation results, the education recommendation data can be obtained directly based on the evaluation results, the learning behavior data and the cognitive level index. Among them, the evaluation results can help the education system identify the learning levels and needs of different activity subjects, so as to provide more accurate personalized learning resources and learning path recommendations. For example, for activity subjects whose evaluation results show that they have learning difficulties, more targeted tutoring materials and exercises can be recommended to help them overcome learning obstacles; and for activity subjects with excellent learning, the system can recommend more challenging learning content to stimulate their learning interest and potential. The evaluation results can help teachers understand the learning situation of the activity subjects, find the weak links in teaching, and thus adjust the teaching strategies and methods to improve the teaching effect. For example, teachers can find that the activity subjects generally have difficulty understanding a certain knowledge point based on the evaluation results, and can strengthen the explanation and practice of the knowledge point in a targeted manner to help the activity subjects better master the knowledge point. The evaluation results can provide decision-making support for education managers and help them formulate more scientific and reasonable education policies and plans. For example, education managers can analyze the learning behaviors and learning effects of different activity subjects based on the evaluation results, understand the weak links in education, and thus formulate targeted improvement measures to improve the overall education quality.

[0069] The data processing method provided by the optional implementation of the present invention obtains the evaluation results of each activity subject based on the educational goal information and learning behavior data of the educational activities; the above-mentioned education recommendation data is also obtained based on the evaluation results, thereby improving the reliability and accuracy of the education recommendation data.

[0070] In some optional implementations disclosed in the present invention, the above-mentioned creation of a dynamic network map based on learning behavior data includes: determining key elements based on the learning behavior data, and using the key elements as network nodes; determining the attributes of the key elements based on the learning behavior data; and connecting each network node based on the attributes to create a dynamic network map.

[0071] In an optional implementation of the present invention, the key element is a factor in the learning behavior data that affects the learning effect of the interactive subject, and the factor is obtained by extracting the features of the learning behavior data, such as learning motivation, learning strategy, learning environment, etc. Features can also be variables extracted from the learning behavior data, such as students' learning time, learning frequency, learning progress, etc.

[0072] In the optional implementation of the present invention, the attribute is the specific value of the feature, for example, the learning time can be expressed as "long" or "short", and the learning frequency can be expressed as "high" or "low". The attribute of the key element is the specific manifestation of the key element. For example, if the key element is learning motivation, the attribute of learning motivation, that is, learning motivation, is specifically manifested as "learning interest", "learning goal", etc.; for another example, if the key element is learning strategy, the attribute of learning strategy, that is, learning strategy, is specifically manifested as "active learning", "cooperative learning", etc.

[0073] The method for constructing a dynamic network map provided by an optional implementation of the present invention determines key elements based on learning behavior data and uses the key elements as network nodes; determines the attributes of the key elements based on the learning behavior data; and connects each network node based on the attributes to create a dynamic network map. Thus, with key elements as nodes and the attributes of the key elements as connection relationships, the learning behavior data of the active subject can be effectively quantified, thereby improving the reliability of the dynamic network map.

[0074] In some optional implementations disclosed in the present invention, the above-mentioned determination of key elements based on learning behavior data includes: preprocessing the learning behavior data to obtain preprocessed data; extracting educational behavior data from the preprocessed data; extracting relevant features from the educational behavior data; clustering the relevant features to determine group characteristics of different learner groups; and determining key elements based on the group characteristics.

[0075] In an optional implementation of the present invention, preprocessing the learning behavior data to obtain the preprocessed data includes: cleaning, arranging and standardizing the learning behavior data to obtain the preprocessed data, which can effectively ensure the accuracy and consistency of the data.

[0076] In an optional implementation of the present invention, the preprocessed data includes: login frequency, learning time, course participation, and interactive information, etc. The above-mentioned extracting educational behavior data from the preprocessed data; extracting relevant features from the educational behavior data includes: extracting features related to learning behavior from the preprocessed data, such as learning time distribution, learning path, learning resource usage, and other related features, which can reflect the learning behavior pattern of the activity subject.

[0077] In an optional implementation of the present invention, clustering the relevant features to determine the group characteristics of different learner groups; based on the group characteristics, determining the key factors includes: using a clustering algorithm to group learners according to their learning behavior characteristics, and identifying learner groups with similar behavior patterns. By analyzing the characteristics of different groups, the key factors that affect the learning effect can be determined.

[0078] The method for determining key factors provided in an optional implementation of the present invention preprocesses learning behavior data to obtain preprocessed data; extracts educational behavior data from the preprocessed data; extracts relevant features from the educational behavior data; clusters the relevant features to determine group characteristics of different learner groups; and determines key factors based on the group characteristics, thereby improving the reliability and accuracy of obtaining the key factors.

[0079] Optionally, the above-mentioned determination of key factors based on learning behavior data includes: preprocessing the learning behavior data to obtain preprocessed data; extracting factors affecting learning effects from the preprocessed data, such as learners' learning behaviors, learning habits, learning attitudes, etc., to obtain key factors.

[0080] In some optional implementations disclosed in the present invention, the above-mentioned determination of the attributes of key factors based on learning behavior data includes: preprocessing the learning behavior data to obtain preprocessed data; extracting educational behavior data in the preprocessed data; extracting relevant features in the educational behavior data; clustering the relevant features to determine group characteristics of different learner groups; performing importance analysis on the group characteristics to obtain at least one important feature; detecting whether at least one important feature obeys a normal distribution; and in response to detecting that an important feature obeys a normal distribution, determining that the important feature is an attribute of a key factor.

[0081] In an optional implementation of the present invention, importance analysis is performed on group features to obtain at least one important feature, including: using information gain, chi-square test and other methods to evaluate the influence of each feature on the learning effect, so as to achieve the purpose of importance analysis of the extracted features.

[0082] In an optional implementation of the present invention, the attributes of each key element are tested for normality, such as using methods such as the KS test or the Shapiro-Wilk test, to determine whether they obey the normal distribution. If the attribute obeys the normal distribution, the statistical analysis method can be more effectively applied for subsequent analysis. When detecting whether at least one important feature obeys the normal distribution, it is first assumed that the entire population obeys the normal distribution, and then the hypothesis is verified by sorting samples and calculating the test statistic. If the verification result shows that the important feature obeys the normal distribution, the hypothesis is accepted; otherwise, the hypothesis is rejected to ensure the reliability of the course statistics at different significance levels. The purpose of the normal distribution test is to identify the attributes that have an important influence on the decision attribute by selecting the most important attributes and adding them to the attribute set, and then gradually removing the attributes. This ensures that the attribute set contains important attributes and does not change the degree of dependence between the original attribute set and the decision attribute. Finally, the remaining attribute set is reduced or is a minimum attribute set defined by the user.

[0083] The method for determining the attributes of key elements provided in an optional implementation of the present invention comprises the following steps: preprocessing learning behavior data to obtain preprocessed data; extracting educational behavior data from the preprocessed data; extracting relevant features from the educational behavior data; clustering the relevant features to determine group characteristics of different learner groups; performing importance analysis on the group characteristics to obtain at least one important feature; detecting whether at least one important feature obeys a normal distribution; and in response to detecting that an important feature obeys a normal distribution, determining that the important feature is an attribute of the key element, thereby improving the accuracy of obtaining the attributes of the key elements through the verification method of the normal distribution.

[0084] In some optional implementations disclosed in the present invention, the above method, wherein, based on the dynamic network graph, determining the cognitive level hierarchy index of each active subject in at least one active subject includes: clustering the nodes in the dynamic network graph to obtain different types of learning groups; based on the learning behavior data, obtaining the learning characteristics and quantitative indicators of the active subjects in each learning group; based on the learning characteristics and quantitative indicators of each node, determining the cognitive level hierarchy index of each active subject in at least one active subject.

[0085] In the optional implementation of the present invention, clustering is one of the key steps in determining the cognitive level index. It divides the nodes in the network graph into different learning groups, so that the learning characteristics and quantitative indicators of each group can be analyzed more effectively, and finally the cognitive level index can be determined.

[0086] In an optional implementation of the present invention, the nodes in the dynamic network graph are the key elements of each activity subject, that is, the most important features in the learning behavior data; based on the similarity of the nodes in the dynamic network graph, a clustering algorithm is used to group learners according to their learning behavior characteristics, and identify groups of learners with similar behavior patterns.

[0087] In an optional implementation of the present invention, after dividing the groups in the dynamic network graph, the characteristics of each group are extracted to obtain learning characteristics, the indicators that affect the learning characteristics are detected, and the quantitative indicators of the groups are obtained. The quantitative indicators within the same threshold range are used as cognitive level indicators of the activity subjects.

[0088] The method for determining cognitive level hierarchical indicators provided by the optional implementation of the present invention first clusters the nodes of the dynamic network map to obtain different types of learning groups; secondly, based on the learning behavior data, obtains the learning characteristics and quantitative indicators of the active subjects in each learning group; finally, based on the learning characteristics and quantitative indicators of each node, determines the cognitive level hierarchical indicators of each active subject in at least one active subject. Determining the cognitive level hierarchical indicators of each active subject by using the quantitative indicators of the learning group can effectively ensure the reliability and accuracy of the cognitive level hierarchical indicators.

[0089] Further references Figure 2 As an implementation of the methods shown in the above figures, the present invention discloses an embodiment of a data processing device, which is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0090] like Figure 2 As shown, the data processing device 200 provided in this embodiment includes: a collection unit 201, a creation unit 202, a determination unit 203, and a generation unit 204. Among them, the above-mentioned collection unit 201 can be configured to collect learning behavior data of at least one active subject in an educational activity at different time points. The above-mentioned creation unit 202 can be configured to create a dynamic network map based on the learning behavior data, and the dynamic network map is used to reflect the key elements of the active subject and the association relationship between the key elements. The above-mentioned determination unit 203 can be configured to determine the cognitive level level index of each active subject in at least one active subject based on the dynamic network map. The above-mentioned generation unit 204 can be configured to generate and send educational recommendation data for each active subject based on the cognitive level level index and the learning behavior data.

[0091] In this embodiment, in the data processing device 200, the specific processing of the collection unit 201, the creation unit 202, the determination unit 203, and the generation unit 204 and the technical effects thereof can be referred to respectively. Figure 1 The relevant descriptions of step 101, step 102, step 103, and step 104 in the corresponding embodiment are not repeated here.

[0092] In one embodiment disclosed in the present invention, the above-mentioned generation unit 204 is configured to: obtain push data of each activity subject based on cognitive level level indicators and learning behavior data, and send corresponding push data to each activity subject; obtain education strategies of each activity subject based on cognitive level level indicators and the learning behavior data, and send education strategies to education subjects; obtain management strategies sent to management subjects based on cognitive level level indicators.

[0093] In some embodiments disclosed in the present invention, the above-mentioned device also includes: an evaluation unit (not shown in the figure), and the above-mentioned evaluation unit is configured to: obtain evaluation results of each activity subject based on the educational goal information of the educational activity and the learning behavior data; the educational recommendation data is also obtained based on the evaluation results.

[0094] In some optional implementations disclosed in the present invention, the above-mentioned educational goal information includes: multiple educational evaluation dimensions, and the evaluation unit is further configured to: extract feedback vocabulary of the activity subject in the learning behavior data; use multiple educational evaluation dimensions to evaluate the feedback vocabulary to obtain evaluation results of each activity subject.

[0095] The educational recommendation data cognitive level hierarchy indicators and the learning behavior data are used to obtain the educational strategy educational recommendation data of each activity subject. In some optional implementation methods disclosed in the present invention, the above-mentioned creation unit 202 is further configured to: determine the key elements based on the learning behavior data, and use the key elements as network nodes; determine the attributes of the key elements based on the learning behavior data; based on the attributes, connect each network node to create a dynamic network map.

[0096] In some optional implementations disclosed in the present invention, the creation unit 202 is further configured to: pre-process the learning behavior data to obtain pre-processed data; extract the educational behavior data in the pre-processed data; extract relevant features in the educational behavior data; cluster the relevant features to determine the group characteristics of different learner groups; and determine the key elements based on the group characteristics.

[0097] In some optional implementations disclosed in the present invention, the creation unit 202 is further configured to: pre-process the learning behavior data to obtain pre-processed data; extract the educational behavior data in the pre-processed data; extract relevant features in the educational behavior data; cluster the relevant features to determine the group characteristics of different learner groups; and determine key elements based on the group characteristics.

[0098] In some optional implementations disclosed in the present invention, the above-mentioned determination unit 203 is further configured to: cluster the nodes in the dynamic network graph to obtain different types of learning groups; based on the learning behavior data, obtain the learning characteristics and quantitative indicators of the active subjects in each learning group; based on the learning characteristics and quantitative indicators of each node, determine the cognitive level hierarchy indicators of each active subject in at least one active subject.

[0099] In the data processing device provided by the embodiment disclosed in the present invention, first, the collection unit 201 collects the learning behavior data of at least one active subject in the educational activity at different time points; secondly, the creation unit 202 creates a dynamic network map based on the learning behavior data, and the dynamic network map is used to reflect the key elements of the active subject and the association relationship of the key elements; then, the determination unit 203 determines the cognitive level level index of each active subject in at least one active subject based on the dynamic network map; finally, the generation unit 204 generates and sends the educational recommendation data of each active subject based on the cognitive level level index and the learning behavior data. Therefore, the behavioral data of the active subject is quantified through the dynamic network map, which provides a comprehensive perspective for educational managers, more accurately reflects the comprehensive quality and teaching effect of the active subject, reduces the subjective evaluation of the education results by the education industry, and improves the objectivity and scientificity of the education evaluation.

[0100] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0101] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their modes are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0102] like Figure 3 As shown, the device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0103] A number of components in the device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0104] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as data processing methods. For example, in some embodiments, the data processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the data processing method in any other appropriate manner (e.g., by means of firmware).

[0105] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0106] The program code for implementing the method disclosed in the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the mode / operation specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0107] In the context disclosed by the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0108] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0109] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0110] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in the disclosure of the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in the disclosure of the present invention can be achieved, and this document does not limit this.

[0111] The foregoing description of specific exemplary embodiments disclosed in the present invention is for the purpose of illustration and demonstration. These descriptions are not intended to limit the present invention to the precise form disclosed, and it is clear that many changes and variations can be made based on the above teachings. The purpose of selecting and describing the exemplary embodiments is to explain the specific principles disclosed in the present invention and their practical applications, so that those skilled in the art can realize and utilize the various exemplary embodiments disclosed in the present invention and various selections and changes. The scope of the present invention is intended to be limited by the claims and their equivalents.

Claims

1. A data processing method, the method comprising: Collect learning behavior data of at least one subject in an educational activity at different time points; Based on the learning behavior data, a dynamic network map is created, wherein the dynamic network map is used to reflect the key elements of the activity subject and the association relationship between the key elements; Based on the dynamic network graph, determining the cognitive level index of each activity subject in the at least one activity subject; Based on the cognitive level index and the learning behavior data, educational recommendation data for each activity subject is generated and sent.

2. According to the method of claim 1, the generating and sending of educational recommendation data for each activity subject based on the cognitive level index and the learning behavior data comprises at least one of the following: Based on the cognitive level index and the learning behavior data, push data of each activity subject is obtained, and corresponding push data is sent to each activity subject; Based on the cognitive level index and the learning behavior data, obtain the educational strategy of each activity subject, and send the educational strategy to the education subject; Based on the cognitive level index, a management strategy is obtained and sent to the management subject.

3. The method according to claim 1, further comprising: Based on the educational goal information of the educational activity and the learning behavior data, obtaining evaluation results of each activity subject; The educational recommendation data is also obtained based on the evaluation results.

4. The method according to any one of claims 1 to 3, wherein: The creating a dynamic network graph based on the learning behavior data includes: Based on the learning behavior data, determining key elements, and using the key elements as network nodes; Determining attributes of key elements based on the learning behavior data; Based on the attributes, various network nodes are connected to create a dynamic network graph.

5. The method according to claim 4, wherein: Determining the key elements based on the learning behavior data includes: Preprocessing the learning behavior data to obtain preprocessed data; extracting educational behavior data from the preprocessed data; Extracting relevant features from the educational behavior data; Clustering the relevant features to determine group characteristics of different learner groups; Based on the population characteristics, key elements are identified.

6. The method according to claim 4, wherein: Determining the attributes of key elements based on the learning behavior data includes: Preprocessing the learning behavior data to obtain preprocessed data; extracting educational behavior data from the preprocessed data; Extracting relevant features from the educational behavior data; Clustering the relevant features to determine group characteristics of different learner groups; Performing importance analysis on the group characteristics to obtain at least one important characteristic; detecting whether the at least one important feature obeys a normal distribution; In response to detecting that an important feature follows a normal distribution, the important feature is determined to be an attribute of a key element.

7. The method according to any one of claims 1 to 3, wherein: Based on the dynamic network graph, determining the cognitive level index of each activity subject in the at least one activity subject includes: Clustering the nodes in the dynamic network graph to obtain different types of learning groups; Based on the learning behavior data, the learning characteristics and quantitative indicators of the active subjects in each learning group are obtained; Based on the learning characteristics and quantitative indicators of each node, the cognitive level level indicator of each activity subject in the at least one activity subject is determined.

8. A data processing device, characterized in that: The device comprises: A collection unit is configured to collect learning behavior data of at least one activity subject in an educational activity at different time points; A creating unit, configured to create a dynamic network map based on the learning behavior data, wherein the dynamic network map is used to reflect the key elements of the activity subject and the association relationship between the key elements; A determination unit configured to determine a cognitive level index of each activity subject in the at least one activity subject based on the dynamic network graph; The generating unit is configured to generate and send the educational recommendation data of each activity subject based on the cognitive level index and the learning behavior data.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 7.

Images