Informatization teaching test system adaptive to learning progress

Abstract

The invention relates to the technical field of intelligent education management, in particular to a self-adaptive learning progress informatization teaching test system, which comprises the following contents: a knowledge node construction module, a learning state identification module, a test task generation module, a path scheduling adjustment module and a feedback data backtracking module. According to the method, refined numbering management of knowledge points is realized by constructing a directed edge numbering set, a dependency direction is set in combination with a label propagation algorithm, the semantic expression ability of a node relationship is enhanced, mastering weights and stability coefficients are matched based on answering behaviors, a state weight sequence is formed, and the stability of classification and recognition is improved; cognitive ability coding and time-consuming median value linkage state weight are introduced, questions are screened, a priority queue is constructed, task pushing precision is improved, numbering and sorting weight are fused to construct a path chain, dependency intensity is calculated to expand path branches, and individual suitability and task rhythm coordination ability of path scheduling are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent education management, and in particular to an information-based teaching and testing system with adaptive learning progress. Background Art

[0002] The field of intelligent education management technology encompasses the development of educational information systems, AI-based teaching process optimization, student learning behavior analysis, digital processing of teaching resources, and intelligent assessment mechanisms. The core of this approach lies in the data-driven management of the entire teaching process through computer systems. This includes comprehensive integration of aspects such as the distribution of teaching resources, monitoring of learning progress, collection and processing of student behavior data, and generation of teaching feedback. From a systemic perspective, the development of intelligent education management technology encompasses learning behavior perception, data modeling, learning path planning, and intelligent recommendation mechanisms. Through continuous analysis and dynamic response to individual student learning trajectories, this field builds a learner-centered, information-based teaching environment, thereby supporting multi-dimensional and multi-level educational management and strategic decision-making.

[0003] Among them, the information-based teaching and testing system with adaptive learning progress refers to a management system that adjusts the push rhythm of subsequent learning tasks in real time through factors such as learners' historical learning behavior data, current task completion status, and learning ability evaluation indicators. The technical matters targeted include learning task duration prediction, individual difference identification, learning priority judgment, and rhythm adjustment decision-making. By setting multi-dimensional input variables to construct a feature matrix, calling the trained clustering model to realize the division of learner groups, and matching the corresponding learning resource paths based on the rule engine, combined with the task monitoring mechanism of the segmented time window, the individual's learning advancement rate and the adjustment logic of the test content are determined, so as to dynamically push the most appropriate test nodes and question sequences.

[0004] Existing technologies mostly rely on static course structures and fixed label relationships to generate knowledge point networks, lacking a semantically driven structural inference mechanism, resulting in insufficient expression of hierarchical connections between knowledge points. Answering behavior analysis often focuses on accuracy statistics and coarse-grained behavioral characteristics, neglecting the exploration of deep-level characteristics such as stability and cognitive fluctuations, affecting the comprehensiveness and accuracy of mastery status judgment. Task generation strategies are usually based on rule matching and question bank screening, failing to fully integrate the dynamic characteristics of behavioral data, resulting in a lack of precision control and real-time adaptation capabilities for pushed tasks. The path scheduling process is often based on linear progress, failing to effectively identify the dependency strength between tasks and the impact of individual differences on path construction, easily causing task rhythm imbalance or path arrangement duplication, affecting learning motivation and efficiency. During the teaching and testing process, due to the failure to identify the structural differences in learners' mastery of multiple knowledge points, problems such as repeated test content, excessive jumps, or difficulty imbalance often occur, affecting the evaluation effect and the scientific nature of subsequent learning arrangements. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, the embodiment of the present invention provides an information-based teaching and testing system with adaptive learning progress. The technical solution is as follows:

[0006] On the one hand, an information-based teaching and testing system with adaptive learning progress is provided, which includes:

[0007] The knowledge node construction module extracts the course knowledge structure to obtain knowledge point nodes, constructs directed edges and generates number sets, extracts teaching labels and course outline structure, uses the label propagation algorithm to set the dependency edge direction, constructs a directed graph structure, generates a knowledge point number set and passes it to the learning state recognition module;

[0008] A learning state identification module calls the knowledge point number set, obtains the answering behavior, matches the mastery weight and stability coefficient, records the state weight, uses the support vector machine to classify the sequence, identifies the mastery state, generates a learning state node set and passes it to the test task generation module;

[0009] The test task generation module calls the learning state node set, filters the mastery state nodes, extracts the cognitive ability codes and median time of the test questions, filters the questions based on the state weights and the change in answering time, builds a push task priority queue, and passes it to the path scheduling adjustment module;

[0010] The path scheduling adjustment module calls the push task priority queue, builds a learning path chain according to the knowledge point number, extracts the path number and sorting weight, calculates the node dependency strength score, expands the path chain to form a path branch set, generates a path extension interval and passes it to the feedback data backtracking module.

[0011] As a further solution of the present invention, the knowledge point number set includes knowledge point codes, dependency edge attributes, and node graph sequence identifiers; the learning status node set includes mastery status labels, status confidence scores, and answer performance characteristics; the push task priority queue includes test question numbers, matching score thresholds, and scheduling order indexes; and the path extension interval includes path number sequences, branch node groups, and extended scoring indicators.

[0012] As a further solution of the present invention, the knowledge node construction module includes:

[0013] The structure analysis submodule extracts the course knowledge structure to obtain knowledge point nodes, calls the course teaching tags and course outline structure content, identifies the label field corresponding to each node, classifies and codes the nodes based on the course structure hierarchy, identifies the subject category and index position, and establishes the node distribution hierarchy value;

[0014] The directed edge construction submodule calls the node distribution level value, identifies the direct reference pairs between nodes based on the category and order relationship of the nodes in the structure, establishes a directed connection set based on the reference direction and structural hierarchy, and uses the label propagation algorithm based on the label weight distribution mechanism of the course structure level to calculate the label dependency for each node pair, determine the edge transmission direction, and generate a directed dependency path set;

[0015] The numbering set generation submodule extracts the node numbers and sorting positions in the dependency path based on the directed dependency path set, adjusts the numbering order according to the sequential relationship of the nodes in the path, combines the node position index, connection direction and path sequence to obtain the numbering identifier, and establishes a knowledge point numbering set.

[0016] As a further solution of the present invention, the learning state identification module includes:

[0017] The behavior extraction submodule calls the knowledge point number set to obtain the time, score, and number of revisions in the learner's answer record for each question, performs data item standardization conversion on each type of data, classifies the standardized results based on the knowledge point number, and generates an answer behavior association value;

[0018] The state matching submodule calls the answer behavior association value, compares and analyzes each data item according to the set mastery weight benchmark value and stability coefficient benchmark value, analyzes the mastery matching state of each knowledge point corresponding to the behavior, records the node state offset direction and offset amplitude, and generates a state offset coefficient set;

[0019] The mastery classification submodule extracts the mastery weight value, stability coefficient and offset amplitude value corresponding to each node based on the state offset coefficient set. By extracting the fluctuation rate of answering time, score deviation, accuracy rate and progress rate, the support vector machine is used to identify the learner's mastery status on each knowledge point, including mastery, partial mastery and non-mastery, establish a classification structure table and obtain the learning status node set.

[0020] As a further solution of the present invention, the test task generation module includes:

[0021] A master node screening submodule calls the learning state node set, identifies nodes labeled as master state, extracts corresponding node numbers and state label values, and generates a master node number set;

[0022] The question ability extraction submodule calls the mastery node number set, extracts the test question information corresponding to the node, extracts the cognitive ability code and standard time data of the test question, calculates the median time value of similar questions within the node range, calculates the time fluctuation range and ability code coverage level of the question, and obtains the cognitive feature value of the test question;

[0023] The priority queue construction submodule calculates the median time consumption and state weight difference of each question based on the cognitive feature value of the test question, calculates the task sorting priority based on the state deviation and cognitive coding complexity, screens the test questions, and establishes a push task priority queue.

[0024] As a further solution of the present invention, the specific formula for sorting the computing task priorities is:

[0025] ;

[0026] Calculate task sorting priority;

[0027] in, Representative Priority of test questions, Representative The median time spent on the test questions, Representative The state weight of the test question, Represents the average value of all test question status weights, Representative Test questions and The difference in cognitive ability encoding between knowledge points, represents the average value of cognitive ability coding of all test questions, Represents the total number of knowledge points, Represents the current calculation The identifier of a knowledge point, A number representing each individual test question in the system.

[0028] As a further solution of the present invention, the path scheduling adjustment module includes:

[0029] The path construction submodule calls the push task priority queue, extracts the knowledge point numbers included in the task, arranges the number sets in sequence, establishes path connectivity relationships between the knowledge points, configures path identification numbers for the connectivity relationships, extracts node sorting weight values ​​based on the task sequence, and generates a learning path structure number set;

[0030] The dependency scoring submodule calls the learning path structure number set, identifies the connection edge information of adjacent nodes in the path chain, calculates the dependency weight value between each pair of nodes according to the sorting weight, and obtains the node dependency strength score value;

[0031] The path expansion submodule selects the top two preceding nodes according to the node dependency strength score and uses them as expansion benchmarks, extracts the corresponding path numbers and expands the path chain, establishes the expanded path branch set, and generates the path expansion interval.

[0032] As a further solution of the present invention, the specific formula for identifying the connection edge information of adjacent nodes in the path chain is:

[0033] ;

[0034] Calculate the edge complexity eigenvalue;

[0035] in, Representative Node With node The complexity eigenvalue of the connecting edge between Represents the time slice in the path structure Internal Node With node The information strength value of the connecting edge, is the structural disturbance adjustment factor, Representation node With node In time slice The direction difference of the inner connecting edges, is the direction weight correction factor, is the minimum disturbance offset, Indicates the total number of time slices counted in the path chain. Representation node With node The edge distribution density value between Representation node The mean of the edge distribution density values ​​between all its connected nodes, is the index variable of the time slice sequence number to be summed, is the index number of the starting node in the path chain, The index number of the target node in the path chain.

[0036] As a further embodiment of the present invention, the system further comprises:

[0037] The feedback data backtracking module calls the task's preceding path extension interval, obtains the path node answer sequence and stability parameters, compares the accuracy and time consumption changes, analyzes the learning state change trend, and generates an update path structure task marking instruction;

[0038] The update path structure task marking instruction includes a node update mark, a trend identification type, and a feedback update parameter.

[0039] As a further solution of the present invention, the feedback data backtracking module includes:

[0040] The answer data extraction submodule extracts the path number and node set corresponding to the extended path based on the path extension interval, collects the answer sequence data and stability coefficient corresponding to each node, classifies the answer data by node number, generates node answer accuracy and time consumption records, and establishes node answer change values;

[0041] The state trend calculation submodule calls the node answer change value, performs a horizontal comparison of the node accuracy and time consumption value within the path, determines the state change trend based on the change direction, calculates the trend score value based on the stability parameter, and obtains the learning state change trend value;

[0042] A path label generation submodule extracts the node numbers whose trend score values ​​exceed the state adjustment threshold according to the learning state change trend value, matches the corresponding path number information, integrates the extracted nodes with the path through structural mapping, generates a path update identification structure including the node number, path number and adjustment type, and establishes a path structure update instruction set;

[0043] The state adjustment threshold is calculated by using statistical features in the sliding window to calculate the outlier score, and when the threshold is exceeded, the learning state adjustment of the path structure is triggered.

[0044] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0045] By extracting the knowledge point nodes from the course knowledge structure and introducing them into the teaching labels and course outline semantic structure, directed edges are constructed and uniformly numbered, which effectively realizes the structured expression of knowledge points; the label propagation algorithm is introduced to set the dependency direction, so that the hierarchical logic between knowledge points has the ability of semantic transmission, providing high-quality structural support for subsequent state recognition and path construction; combining the mastery weight and stability coefficient in the process of answering behavior acquisition, a state weight sequence for knowledge points is established, and the support vector machine algorithm is used for classification and identification, which significantly improves the accuracy of mastery state judgment; through the cognitive ability encoding and time-consuming data analysis of learning state nodes, the learner's behavioral characteristics are accurately characterized, and dynamic adaptation in question screening is achieved; in the task push stage, a dual-factor screening mechanism of state weight and answering time change is introduced to build a push priority queue, making the test task more targeted and advanced; based on the number set, a path chain is constructed and a node dependency strength scoring mechanism is introduced to expand the generated path branch set, and personalized process control and task difficulty rhythm adjustment are simultaneously achieved in path scheduling. Multi-link data hierarchical extraction and associative fusion build a complete closed-loop process, solving the problems of structural fragmentation, response delay and low adaptability in traditional learning path planning, and enhancing the system's ability to respond to individual differences among learners and the dynamic adaptability of path recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 is a system flow chart of the present invention;

[0048] Figure 2 Schematic diagram of the system framework of the present invention; DETAILED DESCRIPTION

[0049] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0050] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0051] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0052] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0053] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0054] The present invention provides an information-based teaching and testing system with adaptive learning progress. Figures 1 to 2 The present invention provides a technical solution, an information-based teaching and testing system with adaptive learning progress, comprising:

[0055] The knowledge node construction module extracts the course knowledge structure to obtain knowledge point nodes, constructs directed edges and generates number sets, extracts teaching labels and course outline structure, uses the label propagation algorithm to set the dependency edge direction, constructs a directed graph structure, generates a knowledge point number set and passes it to the learning state recognition module;

[0056] The learning state identification module calls the knowledge point number set, obtains the answering behavior, matches the mastery weight and stability coefficient, records the state weight, uses the support vector machine to classify the sequence, identifies the mastery state, generates the learning state node set and passes it to the test task generation module;

[0057] The test task generation module calls the learning state node set, filters the mastery state nodes, extracts the cognitive ability code and median time of the test questions, filters the questions based on the state weight and the change in answering time, builds a push task priority queue, and passes it to the path scheduling adjustment module;

[0058] The path scheduling and adjustment module calls the push task priority queue, builds a learning path chain based on the knowledge point number, extracts the path number and sorting weight, calculates the node dependency strength score, expands the path chain to form a path branch set, generates the path extension interval, and passes it to the feedback data backtracking module;

[0059] The feedback data backtracking module calls the task's preceding path extension interval, obtains the path node answer sequence and stability parameters, compares the accuracy and time changes, analyzes the learning state change trend, and generates task marking instructions for updating the path structure.

[0060] The knowledge point number set includes knowledge point encoding, dependency edge attributes, and node graph sequence identifiers; the learning status node set includes mastery status labels, status confidence scores, and answer performance characteristics; the push task priority queue includes test question numbers, matching score thresholds, and scheduling order indexes; the path extension interval includes path number sequences, branch node groups, and extended scoring indicators; the update path structure task marking instructions include node update marks, trend identification types, and feedback update parameters.

[0061] See also Figure 2 , the knowledge node construction modules include:

[0062] The structure analysis submodule extracts the course knowledge structure to obtain knowledge point nodes, calls the course teaching tags and course outline structure content, identifies the label field corresponding to each node, classifies and codes the nodes based on the course structure hierarchy, identifies the subject category and index position, and establishes the node distribution hierarchy value;

[0063] The structure analysis sub-module starts from the extraction of the curriculum knowledge structure, calls the teaching tags and the content of the curriculum syllabus structure. In the specific implementation process, first, it is necessary to extract the title information, sub-titles and key terms of each chapter in the curriculum content, and compare and match them with the module structure listed in the teaching syllabus. For example, in a "Higher Mathematics" course, "Derivatives and Differentials", "Definite Integrals", and "Function Limits" are used as the first-level structure nodes respectively. At the same time, secondary tags such as "Definition", "Geometric Meaning", and "Calculation Rules" are extracted from the syllabus for corresponding mapping. Then, these nodes are classified and coded according to the structural hierarchy. The classification coding is numbered based on the chapter level of the node in the curriculum. For example, the first-level node coding is set as A, the second-level node is A1, A2, and the third-level node is A1.1, A1.2. During the classification process, teaching tags such as "Basic Concepts", "Example Analysis", and "Knowledge Expansion" are called, and their structural hierarchy positions are judged according to the order in which they appear in the syllabus. For example, if "Basic Concepts" is at the beginning of the chapter, its classification level is 1. Further, by analyzing the relationship between different tags and the themes to which the nodes belong in the curriculum, the method of attributing theme keywords is used to identify that the nodes belong to different theme categories such as "Calculus" and "Linear Algebra", and index positions are assigned according to their order in the curriculum system. Suppose the "Derivatives" chapter is taught in the 3rd week, and its index position is 3. Combining the above classification coding and position index, the distribution level value of each node is finally constructed. For example, the A1.2 node represents the second sub-point of the first section of Chapter A, and its level value is (1, 2). During this process, the recognition of the tag field adopts the method of pure text retrieval and comparison. Suppose the tag set is , for each course node , match the corresponding fields in it to generate a tag set , and then use the matching position and the order relationship of the tag in the syllabus to determine its classification number. When performing the "judgment" action, the level number i of the node where it is located is compared with the tag index j to which it belongs. When i < j, it is marked as a superior node, and vice versa as an inferior node. Suppose the reference level is 2. If the node "Mean Value Theorem for Differentials" has a number of 3.1.2 and its tag position is at the second level, then it is judged as an inferior node. Here, the reference level 2 is obtained through curriculum structure statistics. Suppose the curriculum has a total of 5 levels of structure, then the middle value 3 is selected as the reference level, and the following interval division is set: level values 1-2 are upper-level nodes, 3 is the middle-level node, and 4-5 are lower-level nodes. Finally, a distribution level table of the nodes is established, as shown in Table 1;

[0064] Table 1 Distribution Level Table of Course Nodes

[0065]

[0066] As shown in Table 1, the nodes are systematically distributed according to the course structure level. Based on the label type and the course outline position, the level value and index position corresponding to each node are obtained to ensure that the node classification code has a logical order of superiors and subordinates.

[0067] The directed edge construction submodule calls the node distribution level value, identifies the direct reference pairs between nodes based on the category and order relationship of the nodes in the structure, and establishes a directed connection set based on the reference direction and structural hierarchy. Based on the label weight distribution mechanism of the course structure level, the label propagation algorithm is used to calculate the label dependency for each node pair, determine the edge transmission direction, and generate a directed dependency path set.

[0068] The directed edge construction submodule is based on the reference relationship between nodes and calls the node distribution level value. During the execution process, the level value combination of each pair of adjacent nodes is first extracted. For example, for nodes A1.1 and A1.2, the level values ​​are 1 and 2 respectively. A directed connection edge is established according to their order in the course structure.<A1.1→A1.2> , then identify all node pairs with continuous hierarchical values ​​but different label attributes as direct reference pairs. For example, the node labeled "Basic Concepts" followed by the node "Example Analysis" can be judged as a reference explanation instance of the knowledge point. When constructing edge pairs, a directional relationship is used to form a unidirectional link from the low level to the high level. When executing the "judgment" operation, the label dependency of the formed edge is calculated according to the label type. Assume that the weight of the label "Basic Concepts" is 0.7 and the weight of the "Example Analysis" is 0.3, then the edge<A1.1→A1.2> Dependence = 0.7× 0.3 = 0.21. When executing the "calculate" action, the product of the weights between labels is used as the dependency value. The dependency threshold is set to 0.15 (obtained from the statistical approximate average value. The average dependency of all label combinations in the course is set to 0.15, which is taken as the screening benchmark). If the edge dependency is lower than the threshold, the edge is removed. For example, = 0.12, then discard<A1.1→A1.3> Edges, if they are higher than the threshold, are retained, and finally a directed dependency path set is formed. In this process, through the "screening" action, all node-edge combinations with a level difference greater than 2 in the path are removed. For example, the level difference between A1.1 and A1.4 is 3, so delete<A1.1→A1.4> , only the path edges with level difference ≤ 2 are retained to form the path set.

[0069] The number set generation submodule extracts the node numbers and sorting positions in the dependency path based on the directed dependency path set, adjusts the numbering order according to the order of the nodes in the path, combines the node position index, connection direction and path sequence to obtain the number identifier, and establishes the knowledge point number set;

[0070] The number set generation submodule is based on the aforementioned path set expansion, extracts the node numbers in the path and their sequential positions in the path, and in the specific implementation, reads the dependent paths in sequence.<A1.1→A1.2→A2.1> , extract the node number sequence {A1.1, A1.2, A2.1}, corresponding to the sequential position {1,2,3}, and then perform an "adjustment" operation on the path node position. If a node appears in multiple paths, its position in the shortest path is used as the basis for unified number adjustment. For example, A2.1 in path It is ranked 3rd in the path If it is in the second position, then its number is uniformly adjusted to the second position. When executing the "judgment" action, all paths containing this node are compared, and the path with the shortest length is selected to determine the number position. Then, according to the path direction, the starting node is assigned the number K001, and the subsequent nodes are numbered K002, K003, etc. Finally, the node position index, connection direction and path sequence are combined to generate a number identifier, for example, the path<A1.1→A1.2→A2.1> Generate the number set as K001, K002, K003, path<A2.1→A2.3> Generate K003 and K004. During the "calculation" process, the frequency of each node in all paths needs to be counted. If the frequency of a node is greater than the average number of path nodes (assuming the average path length is 3), it is marked as a core node. For example, A2.1 appears 5 times and the number of paths is 4, then the frequency is 1.25 > 3 / 4 = 0.75, and it is marked as a core node. The number is preferably prefixed with "C", that is, C003, to provide a basis for subsequent knowledge graph association.

[0071] See also Figure 2 , the learning state recognition module includes:

[0072] The behavior extraction submodule calls the knowledge point number set to obtain the time, score, and number of revisions from the learner's answer record for each question. It then performs data item standardization on each type of data, classifies the standardized results based on the knowledge point number, and generates an answer behavior association value.

[0073] Based on the knowledge point number set as the index, the learner's answer record data for each question is called. In actual operation, the corresponding knowledge point number, answer time, score value and modification times of each answer record are first read. Then the above three behavioral data are standardized item by item. The standardization adopts the Z-score method. For each data, its full sample mean and standard deviation are calculated first. For example, taking the answer time as an example, the original data is , the sample mean is calculated as:

[0074] , the standard deviation is: , and calculate the normalized value: , for the score value set and modification times Perform the same calculation to get the mean 、 , standard deviation 、 , and then calculate the standardized values, combined with the knowledge point number , forming a behavior triple , each knowledge point is classified and merged to form the final answer behavior association value. If a knowledge point corresponds to multiple records, the average of each indicator is calculated according to the following formula: ,in , and finally generate standardized answer behavior values ​​classified by number;

[0075] Table 2 Original and standardized data of answering behavior

[0076]

[0077] As shown in Table 2, each data item in the answer record has completed the standardization conversion and is organized into a set of standardized behavior vectors according to the knowledge point number, forming the basic data for subsequent status analysis.

[0078] The state matching submodule calls the answer behavior association value and compares and analyzes each data item according to the set mastery weight benchmark value and stability coefficient benchmark value. It analyzes the mastery matching status of each knowledge point corresponding to the behavior, records the node state offset direction and offset amplitude, and generates a state offset coefficient set.

[0079] Based on the input of the answer behavior association value, during the processing, it is necessary to first read the three standardized behavior values ​​corresponding to each knowledge point number: answering time, score value, and number of revisions, and call the preset mastering weight benchmark value and stability coefficient benchmark value, and calculate the numerical difference of each data item by item. The mastering weight benchmark value is set to score standardization ≥ 0.5, and the stability coefficient benchmark value is set to number of revisions standardization ≤ 0.3. Combined with the K001 behavior vector of [-0.63, 0.63, -0.39], its score is standardized at 0.63>0.5, which is judged as mastered, the number of revisions is standardized at -0.39<0.3, which is judged as stable, and the time consumption is standardized at -0.63, which is judged as high answering efficiency. For this type of matching state, the "judgment" action is performed, and the rule is: if the score is standardized ≥0.5 and the number of revisions is standardized ≤0.3, the state match is positive mastery, if the score is standardized <0.5 and the number of revisions is >0.3, it is not mastered, and if only one of the two is met, it is partially mastered. The record of the state deviation direction is marked according to the direction of the current behavior value relative to the benchmark value, for example The direction of the score deviation from the baseline value is positive, with an amplitude of 0.63-0.5=0.13, which is recorded as a positive offset. The "calculation" operation is (behavior value-baseline value), and the absolute value of the offset amplitude is taken, and the result is 0.13. Finally, the offset direction and offset amplitude under each knowledge point number are recorded and output as a state offset coefficient set. The state of each node is composed of three indicators, which represent the mastery degree offset (score), stability offset (number of modifications) and efficiency offset (time consumption). The values ​​are obtained through difference calculation, without involving model calls, to ensure that the processing action is a repeatable and verifiable numerical derivation process.

[0080] The mastery classification submodule extracts the mastery weight value, stability coefficient, and offset amplitude value corresponding to each node based on the state offset coefficient set. By extracting the fluctuation rate of answering time, score deviation, accuracy rate, and progress rate, it uses a support vector machine to identify the learner's mastery status at each knowledge point, including mastery, partial mastery, and non-mastery. It then establishes a classification structure table and obtains the learning state node set.

[0081] The received state offset coefficient set is used as the basic data. During the processing, the mastery weight value, stability coefficient and offset amplitude value corresponding to each node are extracted. When performing the "judgment" operation on these values, a standard threshold must be set. The mastery weight ≥ 0.5 is judged as mastered, ∈ [0.2, 0.5) is partially mastered, < 0.2 is not mastered, the stability coefficient ≤ 0.3 is judged as stable, otherwise it is unstable, and the offset amplitude ≥ 0.5 is recorded as high volatility. Combined with the K003 node score offset of -1.05-0.5=-1.55, the mastery weight is far lower than the benchmark and is judged as not mastered. The modification number offset is 0.39> 0.3, which is judged as unstable. The node state is marked as not mastered-unstable type, and then the fluctuation rate of the answering time corresponding to each node is extracted. Assume the same knowledge The maximum and minimum time spent on multiple point recognition questions are 350s and 250s respectively, so the fluctuation rate is (350-250) / 250=0.4. The score deviation is calculated as (actual score-full score) / full score. Taking a score of 6.5 as an example, the deviation is (10-6.5) / 10=0.35. The accuracy rate is calculated as the number of correct answers / total number of answers, and the improvement rate is calculated as the last score-first score / first score. If the first score is 6 and the last score is 8, the improvement rate is (8-6) / 6=0.33. These values ​​are used as auxiliary references for judgment. When constructing the classification structure table, the above parameters are combined and each node is classified and labeled. The result is output as a set of learning status nodes, marking each node as mastered, partially mastered, or not mastered.

[0082] See also Figure 2 , the test task generation module includes:

[0083] The master node screening submodule calls the learning state node set, identifies the nodes labeled as master state, extracts the corresponding node number and state label value, and generates the master node number set;

[0084] The learning status node set is called as the data source. During the execution process, all node records marked as mastered are first read. A "judgment" operation is performed on each record to extract whether the status field value is "mastered". If it is "mastered", its node number information is read. For example, if the status field in the node number set is [mastered, not mastered, partially mastered, mastered], the screening results are items 1 and 4, corresponding to node numbers K001 and K003 respectively. Then, a new number set is constructed, which only contains node numbers with the status field of "mastered". In this process, it is necessary to ensure that the same node number is recorded only once. The "filter" operation is performed on duplicate items, and redundant numbers are removed through the set deduplication logic. The remaining node numbers are assigned a sequence label index value as the sorting reference field. When performing the "extract" action, the status field and node field are read through the field index. At the same time, double-field verification is performed on the read fields to ensure that the number field is not empty and the status field accurately matches the value "mastered". Finally, the filtered node number list is organized into a number set and output as the mastered node number set.

[0085] The question ability extraction submodule calls the master node number set, extracts the test question information corresponding to the node, extracts the cognitive ability code and standard time data of the test question, calculates the median time value of similar questions within the node range, calculates the time fluctuation range and ability code coverage level of the question, and obtains the cognitive feature value of the test question;

[0086] During the execution process, the node number set is used as the input basis. First, the test question records associated with each node number are read. For example, number K001 corresponds to questions Q101 and Q102, and number K003 corresponds to questions Q104 and Q105. The question numbers, cognitive ability coding fields, and standard time fields of these questions are read in turn to construct the original question feature data set. When performing the "calculation" operation, the median time data of the questions under the same node number must be extracted. For example, the time data of node K001 is [120, 150] seconds, and the median time is (120+150) / 2 = 135 seconds. The time data of node K003 is [200,160] seconds, and the median time is (200+160) / 2 = 180 seconds, and at the same time, statistics are performed on the number of covered questions for each type of cognitive ability coding. When performing the "statistics" action, cognitive coding is used as the grouping basis, and the number of questions appearing under each coding is counted. For example, code A1 appears in Q101 and Q103 with a frequency of 2, and code B2 only appears in Q105 with a frequency of 1. After the statistics are completed, each code is sorted by frequency as a reference for coverage level, and a "comparison" operation is performed to identify high-coverage and low-coverage codes. When dividing the interval, codes with a frequency ≥ 2 are defined as high-coverage codes, and codes with a frequency = 1 are defined as low-coverage codes. Correspondingly, A1 is a high-coverage code and B2 is a low-coverage code. Finally, the question number, corresponding node number, cognitive code, median time consumption and coverage level are sorted into a set of question cognitive feature values. The results are shown in the following table;

[0087] Table 3 Test question information and cognitive ability coverage

[0088]

[0089] As shown in Table 3, the test questions under the mastery node have been classified according to the node number and their cognitive ability coding and standard time-consuming data have been extracted, providing a direct reference for the subsequent cognitive feature collection and processing.

[0090] The priority queue construction submodule calculates the median time consumption and state weight difference of each question based on the cognitive feature value of the test question, calculates the task sorting priority based on the state deviation and cognitive coding complexity, screens the test questions, and establishes a priority queue for pushing tasks;

[0091] The specific formula for calculating task sorting priority is:

[0092] ;

[0093] Calculate task sorting priority;

[0094] in, Representative Priority of test questions, Representative The median time spent on the test questions, Representative The state weight of the test question, Represents the average value of all test question status weights, Representative Test questions and The difference in cognitive ability encoding between knowledge points, represents the average value of cognitive ability coding of all test questions, Represents the total number of knowledge points, Represents the current calculation The identifier of a knowledge point, A number representing each independent test question in the system;

[0095] formula:

[0096] ;

[0097] Detailed explanation of the formula and the process of formula calculation and derivation:

[0098] This formula is used to calculate the priority of each test question , the test questions with higher priority values ​​will be prioritized in the push task. The formula gives a numerical value to measure the priority of the test questions by comprehensively considering the status weight of each test question, the time required for the test question, and the cognitive ability matching degree of each knowledge point;

[0099] Parameter meaning and setting value:

[0100] For the The state weight of the test question is set to 0.6;

[0101] is the average value of the state weights of all test questions, set to 0.5;

[0102] For the The median time taken for the test questions is set to 300 seconds;

[0103] For the Test questions and The difference in cognitive ability encoding between knowledge points, the difference in cognitive ability The calculation method is: , the dimension of the difference in cognitive ability coding is dimensionless, because cognitive ability coding It is a standardized value, usually in the range [0,1], without unit, and does not involve physical quantities, so its difference is also unitless. The absolute value and square root operation will not change its dimensionless characteristics. The cognitive ability difference between the test question and the second knowledge point is 0.3;

[0104] : The average value of cognitive ability coding of all test items, set to 0.4;

[0105] : Total number of knowledge points. Set to 10;

[0106] Substitute the parameters into the formula for calculation:

[0107] ;

[0108] ;

[0109] ;

[0110] ;

[0111] , ;

[0112] ;

[0113] ;

[0114] Result interpretation:

[0115] Calculated priority Indicates the priority of this test question. A smaller priority value indicates that the test question is relatively easy, the learner has a good grasp of it, it takes relatively little time to complete, and it has a high degree of alignment with the cognitive ability encoding. Therefore, this question has a lower priority, and the system may prioritize other test questions that are more suitable for the current learning state.

[0116] See also Figure 2 ,The path scheduling adjustment module includes:

[0117] The path construction submodule calls the push task priority queue, extracts the knowledge point numbers included in the task, arranges the number sets in sequence, establishes path connectivity relationships between knowledge points, configures path identification numbers for the connectivity relationships, extracts node sorting weight values ​​based on the task sequence, and generates a learning path structure number set;

[0118] Call the push task priority queue as the input source. During the execution process, first extract the knowledge point number set corresponding to each task. Task T01 contains ["K001", "K002", "K004"], task T02 contains ["K003", "K005"], and task T03 contains ["K002", "K006"]. Perform a sequential sorting operation on each number set and sort the set according to the task set sequence weight value. The sorting is based on the value from large to small. For example, the sorting weight in task T01 is [0.9, 0.7,0.5], the corresponding knowledge point numbers are arranged in sequence as K001→K002→K004, and then the "establishment" action is executed to establish directed connection pairs between adjacent knowledge point numbers to generate a path connectivity relationship set. For example, the path constructed by T01 is K001→K002→K004, T02 is K003→K005, and T03 is K002→K006. After the connectivity relationship is established, the "configuration" action is executed to assign a path identification number to each path, for example, numbered P001, P002, and P003 in task sequence, and the sequence position and weight of the nodes in each path are recorded. The node sorting weight is the set value in the task, recorded as K001-0.9, K002-0.7, K004-0.5, etc. The final structure is a path structure set consisting of path number, node number, node sorting position and its sorting weight, and the output is a learning path structure number set.

[0119] The dependency scoring submodule calls the learning path structure number set, identifies the connection edge information of adjacent nodes in the path chain, calculates the dependency weight value between each pair of nodes based on the sorting weight, and obtains the node dependency strength score value;

[0120] The specific formula for identifying the connection edge information of adjacent nodes in the path chain is:

[0121] ;

[0122] Calculate the edge complexity eigenvalue;

[0123] in, Representative Node With node The complexity eigenvalue of the connecting edge between Represents the time slice in the path structure Internal Node With node The information strength value of the connecting edge, is the structural disturbance adjustment factor, Representation node With node In time slice The direction difference of the inner connecting edges, is the direction weight correction factor, is the minimum disturbance offset, Indicates the total number of time slices counted in the path chain. Representation node With node The edge distribution density value between Representation node The mean of the edge distribution density values ​​between all its connected nodes, is the index variable of the time slice sequence number to be summed, is the index number of the starting node in the path chain, is the index number of the target node in the path chain;

[0124] formula:

[0125] ;

[0126] Detailed explanation of the formula and the process of formula calculation and derivation:

[0127] Formula used to calculate the node With node The complexity eigenvalue of the connection edge between the nodes is used to evaluate the information complexity of the connection edge between adjacent nodes in the path chain;

[0128] Parameter meaning and setting value:

[0129] For the Nodes in a time slice With node The information strength value of the connecting edge is set to 3.5;

[0130] is the structural disturbance adjustment factor, and its set value is 0.8;

[0131] For the Nodes in a time slice With node The direction difference between the connecting edges is set to 2;

[0132] is the direction weight correction factor, and the set value is 1.2;

[0133] is the minimum disturbance offset, and the setting value is 0.5;

[0134] The total number of time slices counted in the path chain is set to 3;

[0135] For nodes With node The edge density between them is obtained by measuring the distribution of edges in the network and is set to 0.6;

[0136] For nodes The mean of the edge distribution density values ​​between all connected nodes is set to 0.5;

[0137] Substitute the parameters into the formula for calculation:

[0138] First time slice: , , the calculation items are: Second time slice: Same as above, the calculation item is 5.5;

[0139] The third time slice: Same as above, the calculation item is 5.5;

[0140] Numerator sum: ;

[0141] ;

[0142] Final calculation:

[0143] ;

[0144] The result 5.32 shows that the node With node The complexity eigenvalue of the connecting edges between nodes is 5.32, which is used to evaluate the information complexity of the connecting edges between adjacent nodes in the path chain.

[0145] The path expansion submodule selects the top two nodes according to the node dependency strength score and uses them as expansion benchmarks. It then extracts the corresponding path number and expands the path chain, establishes the expanded path branch set, and generates the path expansion interval.

[0146] The path extension operation is performed according to the node dependency strength score value. First, the score records of the predecessor nodes corresponding to all nodes are read. For example, the predecessor nodes corresponding to node K004 are K001 and K002, with scores of 0.91 and 0.88 respectively. When performing the "select" action, the score fields are compared, and the first two values ​​are taken as the extension reference nodes. The judgment standard is the score value sorting. The dependency value greater than 0.85 is strong dependency, between 0.75 and 0.85 is medium dependency, and below 0.75 is weak dependency. According to the above rules, the predecessor nodes K001 and K002 of node K004 are both strong dependency nodes. Then, the selected predecessor nodes are respectively selected. Take the path number where it is located. For example, K001 is in path P001, and K002 appears in both P001 and P003. When executing the "Extract" action, copy the path segment where it is located and splice the current node K004 at the end to form an extended path chain K001→K002→K004, K002→K004, etc. Then execute the "Create" action to generate an extended path branch set and number the new path branch. For example, expand from P001 to form P001a, and expand from P003 to form P003a. The final output path extension interval set is the extended path set plus its path source identifier and path sequence;

[0147] Table 4 Node dependency strength score table

[0148]

[0149] As shown in Table 4, each node completes the path expansion basic construction based on the top two predecessor nodes in terms of scores during path expansion. The scores are used to judge the dependency strength and screen the expansion node chain.

[0150] See also Figure 2 , the feedback data backtracking module includes:

[0151] The answer data extraction submodule extracts the path number and node set corresponding to the extended path based on the path extension interval, collects the answer sequence data and stability coefficient corresponding to each node, classifies the answer data by node number, generates node answer accuracy and time consumption records, and establishes node answer change values;

[0152] Taking the path extension interval as the input starting point, during the execution process, the path number and node number pairing relationship in the extended path set is first read. For example, path P001 contains nodes K001, K002, and K003, path P001a contains K004, and path P003a also contains K004. Then, the answer sequence data of each node is read, including the answer accuracy, average time and stability coefficient. When executing the "collection" action, the answer record table corresponding to the node number is checked one by one to extract the accuracy value. For example, K001 is 0.85 and the time consumption is 130 seconds. , the stability coefficient is 0.25, and then the above three data are classified and merged according to the node number. That is, if K004 appears in multiple paths, its answer records in each path need to be recorded and saved separately, and the path number field is marked. When performing the "classification" operation, the node number is used as the primary key and the path number is used as the subkey to establish a multi-value structure. After the classification is completed, the accuracy and time consumption of each node constitute the basic data of the node answer change. Subsequently, a comprehensive form containing the node number, path number, accuracy, time consumption, and stability coefficient fields is established to provide a data source for subsequent trend analysis;

[0153] Table 5 Node answer data record table

[0154]

[0155] As shown in Table 5, node K004 is recorded multiple times because it appears in two expansion paths at the same time. Its accuracy and time consumption values ​​in different paths are different, which are used to calculate the change in answering trend.

[0156] The state trend calculation submodule calls the node answer change value, performs a horizontal comparison of the node accuracy and time consumption value within the path, determines the state change trend based on the change direction, calculates the trend score value based on the stability parameter, and obtains the learning state change trend value;

[0157] The answer change value of the calling node is based on the path number as the grouping basis during the processing. The accuracy and average time consumption data of each node in the same path are extracted, and the data between nodes are "compared" to identify the change direction of their values ​​with the path sequence. For example, the accuracy of K001 in path P001 is 0.85, K002 is 0.70, and K003 is 0.55, which decreases successively. The trend direction is a negative downward trend. The time consumption is 130, 160, and 210 seconds, which is an upward trend. When executing the "judgment" action, if the accuracy rate decreases and the time consumption increases, it is marked as mastering the weakening trend. If the accuracy rate increases and the time consumption decreases, it is mastering the strengthening trend. Others are regarded as stable trends. Then read the stability coefficient of the node. For example, K003 is 0.45, and the stability benchmark threshold is set to 0.30. If the stability coefficient is higher than 0.30, it is marked as an unstable node. The "Calculate" operation converts the trend direction into a trend score. The trend score is set as follows: accuracy change rate × weight a - time change rate × weight b - instability penalty c. Assume a = 1.0, b = 0.5, and c = 0.2 × (stability coefficient - 0.3). Taking K001 to K003 as an example, the accuracy decreases by 0.85-0.55 = 0.30, and the time increase is 210-130 = 80 seconds. The normalized time change rate is 80 / 130≈0.615, and the stability penalty is 0.2 × (0.45-0.3) = 0.03. The trend score is -0.30 × 1-0.615 × 0.5-0.03 = -0.6375, indicating a negative shift in the learning trend. A trend score value less than 0 indicates a decline in mastery, and a value greater than 0 indicates an enhancement. Finally, the trend score and trend direction identifier of each node are output.

[0158] The path label generation submodule extracts the node numbers whose trend scores exceed the state adjustment threshold based on the learning state change trend value, matches them with the corresponding path number information, integrates the extracted nodes with the path structure mapping, generates a path update identification structure including the node number, path number and adjustment type, and establishes a path structure update instruction set;

[0159] Taking the learning status change trend value as the input, during the execution process, perform an "extraction" action on the trend score values of all nodes. Set the state adjustment threshold to ±0.5. If the trend score is greater than 0.5 or less than -0.5, trigger the path update mechanism, record the node number information of the nodes whose score values exceed the interval. For example, the score of K003 is -0.6375 < -0.5, so it is included in the scope of change. Then perform a "matching" operation on the node numbers to find their path number information in the original path structure. For example, K003 is located in path P001. Finally, structurally integrate the node number, path number, and adjustment type. The adjustment type is "downward adjustment" or "enhanced adjustment" to generate a path update identification record item, such as <K003, P001, downward adjustment>. Finally, the update records of all nodes that meet the conditions form a path structure update instruction set for the system to call when updating the path;

[0160] The state adjustment threshold calculates the outlier score through the statistical features within the sliding window, and setting it to exceed the set threshold triggers the learning state adjustment of the path structure.

[0161] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0162] It should be understood that the term "and / or" as used herein simply describes the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0163] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0164] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0165] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0166] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0167] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0168] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0169] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0170] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical disks.

[0171] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. The information-based teaching and testing system with adaptive learning progress is characterized by: The system comprises: The knowledge node construction module extracts the course knowledge structure to obtain knowledge point nodes, constructs directed edges and generates number sets, extracts teaching labels and course outline structure, uses the label propagation algorithm to set the dependency edge direction, constructs a directed graph structure, generates a knowledge point number set and passes it to the learning state recognition module; A learning state identification module calls the knowledge point number set, obtains the answering behavior, matches the mastery weight and stability coefficient, records the state weight, uses the support vector machine to classify the sequence, identifies the mastery state, generates a learning state node set and passes it to the test task generation module; The test task generation module calls the learning state node set, filters the mastery state nodes, extracts the cognitive ability codes and median time of the test questions, filters the questions based on the state weights and the change in answering time, builds a push task priority queue, and passes it to the path scheduling adjustment module; The path scheduling adjustment module calls the push task priority queue, builds a learning path chain according to the knowledge point number, extracts the path number and sorting weight, calculates the node dependency strength score, expands the path chain to form a path branch set, generates a path extension interval and passes it to the feedback data backtracking module.

2. The information-based teaching and testing system with adaptive learning progress according to claim 1 is characterized in that: The knowledge point number set includes knowledge point codes, dependency edge attributes, and node graph sequence identifiers; the learning status node set includes mastery status labels, status confidence scores, and answer performance characteristics; the push task priority queue includes test question numbers, matching score thresholds, and scheduling order indexes; and the path extension interval includes path number sequences, branch node groups, and extended scoring indicators.

3. The information-based teaching and testing system with adaptive learning progress according to claim 1 is characterized in that: The knowledge node construction module includes: The structure analysis submodule extracts the course knowledge structure to obtain knowledge point nodes, calls the course teaching tags and course outline structure content, identifies the label field corresponding to each node, classifies and codes the nodes based on the course structure hierarchy, identifies the subject category and index position, and establishes the node distribution hierarchy value; The directed edge construction submodule calls the node distribution level value, identifies the direct reference pairs between nodes based on the category and order relationship of the nodes in the structure, establishes a directed connection set based on the reference direction and structural hierarchy, and uses the label propagation algorithm based on the label weight distribution mechanism of the course structure level to calculate the label dependency for each node pair, determine the edge transmission direction, and generate a directed dependency path set; The numbering set generation submodule extracts the node numbers and sorting positions in the dependency path based on the directed dependency path set, adjusts the numbering order according to the sequential relationship of the nodes in the path, combines the node position index, connection direction and path sequence to obtain the numbering identifier, and establishes a knowledge point numbering set.

4. The information-based teaching and testing system with adaptive learning progress according to claim 3 is characterized in that: The learning state recognition module includes: The behavior extraction submodule calls the knowledge point number set to obtain the time, score, and number of revisions in the learner's answer record for each question, performs data item standardization conversion on each type of data, classifies the standardized results based on the knowledge point number, and generates an answer behavior association value; The state matching submodule calls the answer behavior association value, compares and analyzes each data item according to the set mastery weight benchmark value and stability coefficient benchmark value, analyzes the mastery matching state of each knowledge point corresponding to the behavior, records the node state offset direction and offset amplitude, and generates a state offset coefficient set; The mastery classification submodule extracts the mastery weight value, stability coefficient and offset amplitude value corresponding to each node based on the state offset coefficient set. By extracting the fluctuation rate of answering time, score deviation, accuracy rate and progress rate, the support vector machine is used to identify the learner's mastery status on each knowledge point, including mastery, partial mastery and non-mastery, establish a classification structure table and obtain the learning status node set.

5. The information-based teaching and testing system with adaptive learning progress according to claim 4 is characterized in that: The test task generation module includes: A master node screening submodule calls the learning state node set, identifies nodes labeled as master state, extracts corresponding node numbers and state label values, and generates a master node number set; The question ability extraction submodule calls the mastery node number set, extracts the test question information corresponding to the node, extracts the cognitive ability code and standard time data of the test question, calculates the median time value of similar questions within the node range, calculates the time fluctuation range and ability code coverage level of the question, and obtains the cognitive feature value of the test question; The priority queue construction submodule calculates the median time consumption and state weight difference of each question based on the cognitive feature value of the test question, calculates the task sorting priority based on the state deviation and cognitive coding complexity, screens the test questions, and establishes a push task priority queue.

6. The information-based teaching and testing system with adaptive learning progress according to claim 5 is characterized in that: The specific formula for sorting the computing task priority is: ； Calculate task sorting priority; in, Representative Priority of test questions, Representative The median time spent on the test questions, Representative The state weight of the test question, Represents the average value of all test question status weights, Representative Test questions and The difference in cognitive ability encoding between knowledge points, represents the average value of cognitive ability coding of all test questions, Represents the total number of knowledge points, Represents the current calculation The identifier of a knowledge point, A number representing each individual test question in the system.

7. The information-based teaching and testing system with adaptive learning progress according to claim 5 is characterized in that: The path scheduling adjustment module includes: The path construction submodule calls the push task priority queue, extracts the knowledge point numbers included in the task, arranges the number sets in sequence, establishes path connectivity relationships between the knowledge points, configures path identification numbers for the connectivity relationships, extracts node sorting weight values ​​based on the task sequence, and generates a learning path structure number set; The dependency scoring submodule calls the learning path structure number set, identifies the connection edge information of adjacent nodes in the path chain, calculates the dependency weight value between each pair of nodes according to the sorting weight, and obtains the node dependency strength score value; The path expansion submodule selects the top two preceding nodes according to the node dependency strength score and uses them as expansion benchmarks, extracts the corresponding path numbers and expands the path chain, establishes the expanded path branch set, and generates the path expansion interval.

8. The information-based teaching and testing system with adaptive learning progress according to claim 7 is characterized in that: The specific formula for identifying the connection edge information of adjacent nodes in the path chain is: ； Calculate the edge complexity eigenvalue; in, Representative Node With node The complexity eigenvalue of the connecting edge between Represents the time slice in the path structure Internal Node With node The information strength value of the connecting edge, is the structural disturbance adjustment factor, Representation node With node In time slice The direction difference of the inner connecting edges, is the direction weight correction factor, is the minimum disturbance offset, Indicates the total number of time slices counted in the path chain. Representation node With node The edge distribution density value between Representation node The mean of the edge distribution density values ​​between all its connected nodes, is the index variable of the time slice sequence number to be summed, is the index number of the starting node in the path chain, The index number of the target node in the path chain.

9. The information-based teaching and testing system with adaptive learning progress according to claim 1 is characterized in that: The system further comprises: The feedback data backtracking module calls the task's preceding path extension interval, obtains the path node answer sequence and stability parameters, compares the accuracy and time consumption changes, analyzes the learning state change trend, and generates an update path structure task marking instruction; The update path structure task marking instruction includes a node update mark, a trend identification type, and a feedback update parameter.

10. The information-based teaching and testing system with adaptive learning progress according to claim 9 is characterized in that: The feedback data backtracking module includes: The answer data extraction submodule extracts the path number and node set corresponding to the extended path based on the path extension interval, collects the answer sequence data and stability coefficient corresponding to each node, classifies the answer data by node number, generates node answer accuracy and time consumption records, and establishes node answer change values; The state trend calculation submodule calls the node answer change value, performs a horizontal comparison of the node accuracy and time consumption value within the path, determines the state change trend based on the change direction, calculates the trend score value based on the stability parameter, and obtains the learning state change trend value; A path label generation submodule extracts the node numbers whose trend score values ​​exceed the state adjustment threshold according to the learning state change trend value, matches the corresponding path number information, integrates the extracted nodes with the path through structural mapping, generates a path update identification structure including the node number, path number and adjustment type, and establishes a path structure update instruction set; The state adjustment threshold is calculated by using statistical features in the sliding window to calculate the outlier score, and when the threshold is exceeded, the learning state adjustment of the path structure is triggered.

Images