Student learning state evaluation method and system based on artificial intelligence

Abstract

The invention discloses a student learning state evaluation method and system based on artificial intelligence, and belongs to the technical field of learning evaluation, and the method comprises the steps: data collection, data preprocessing, clustering model construction, clustering parameter tuning and student learning state evaluation. According to the scheme, on the basis of a reverse neighborhood set, neighborhood density is calculated, center data and edge data are divided, the center data with the maximum concentration degree is selected as a mass center, a cluster is constructed, the cluster is continuously updated by constructing a center neighborhood set, an edge neighborhood set is constructed, and a neighbor screening set is obtained by constructing a weighted undirected graph and calculating cluster density; according to the method, the random offset probability is calculated, the individual position is selected based on the offset threshold value for offset operation, different updating strategies are adopted to update the individual position in different search stages based on the global optimal position and the adjustment factor, learning data of different students are better adapted, and the accuracy and effectiveness of learning state evaluation are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of learning assessment, and specifically refers to a student learning status assessment method and system based on artificial intelligence. Background Art

[0002] The student learning status assessment method uses artificial intelligence technology to automatically assess the student's learning status by analyzing and processing the student's learning data, which can realize intelligent monitoring and management of the entire student learning process, thereby improving the teaching quality and learning efficiency. However, the existing student learning status assessment method has the problem that the student learning data has a complex nonlinear structure, and cannot effectively mine data associations and determine the assessment focus, resulting in inaccurate assessment of the student's learning status; the existing student learning status assessment method has the problem that there are large differences between individual students, and the student learning data presents complex and diverse characteristics. The assessment is difficult to meet the needs of different students, resulting in the inability to accurately assess the student's actual learning status. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a student learning status evaluation method and system based on artificial intelligence. In view of the problem that the student learning data in the existing student learning status evaluation method has a complex nonlinear structure, cannot effectively mine data associations and determine evaluation priorities, and leads to inaccurate student learning status evaluation, this scheme calculates the neighborhood density based on the reverse neighborhood set, and divides the central data and edge data to better capture the complex structure of the student learning data; combines the neighborhood density and the relative distance to obtain the concentration, selects the central data with the largest concentration as the centroid and constructs a cluster, and more accurately determines the focus of the student learning status evaluation; continuously updates the cluster by constructing the central neighborhood set, completes the central data allocation, and ensures the quality of cluster construction; constructs the edge neighborhood set, obtains the neighbor screening set by constructing a weighted undirected graph and calculating the cluster density, completes the edge data allocation, obtains the clustering model, and improves the coverage and efficiency of the evaluation. , and make a more accurate assessment of the students' learning status that is more in line with the actual situation; in view of the fact that there are large differences between individual students in the existing student learning status assessment methods, and the student learning data presents complex and diverse characteristics, the assessment is difficult to meet the needs of different students, resulting in the inability to accurately assess the students' actual learning status. This scheme establishes a parameter search space for clustering parameters, and the initial individual position is used as a representative of the clustering parameters, which provides more possibilities for adapting to the characteristics of different students' learning data; calculates the probability of random offset, and selects individual positions for offset operations based on the offset threshold, which helps to find clustering parameters that are more suitable for the characteristics of different students' learning data; based on the global optimal position and adjustment factor, different update strategies are used to update the individual positions in different search stages to find the optimal clustering parameters, which can better adapt to the learning data of students of different levels and types according to the characteristics of student learning data and the search process, and improve the accuracy and effectiveness of learning status assessment.

[0004] The technical solution adopted by the present invention is as follows: The method for evaluating student learning status based on artificial intelligence provided by the present invention comprises the following steps:

[0005] Step S1: data collection;

[0006] Step S2: data preprocessing;

[0007] Step S3: constructing a clustering model;

[0008] Step S4: clustering parameter tuning;

[0009] Step S5: Assessment of students’ learning status.

[0010] Furthermore, in step S1, the data collection is the collection of historical student learning data and real-time student learning data; the historical student learning data and real-time student learning data both include learning platform data, homework data, test data and classroom interaction data, and the historical student learning data also includes learning status; the learning status is used as a data label, and the data label is not considered during clustering, and is only used when selecting cluster labels.

[0011] Furthermore, in step S2, the data preprocessing is to perform data cleaning, data conversion, data normalization and construction of a learning data set on the collected student learning data; data cleaning includes processing noise, outliers, duplicate values ​​and missing values; data conversion is to convert the data into a vector form; data normalization is to unify the data range based on the maximum and minimum normalization method; and construction of a learning data set is to construct a learning data set based on the student learning data after data cleaning, data conversion and data normalization.

[0012] Furthermore, in step S3, the construction of the clustering model specifically includes the following steps:

[0013] Step S31: Calculate the neighborhood density, calculate the Euclidean distance between any two student learning data in the learning data set, obtain the K nearest neighbors of each student learning data, and construct a positive neighborhood set , and then construct the reverse neighborhood set , the neighborhood density of each student's learning data is calculated based on the reverse neighborhood set, and the formula used is as follows:

[0014] ;

[0015] In the formula, x i and x j are the i-th and j-th student learning data in the learning dataset, i and j are the student learning data indexes, ρ i is x i The neighborhood density of is x i With x j The Euclidean distance between and They are x i The positive neighbor set and the reverse neighbor set of is x j The positive neighbor set of is x i The Euclidean distance between its Kth nearest neighbor, exp(·) is the exponential function, and α is the neighborhood influence factor;

[0016] Step S32: Data division, if The number of middle school students’ learning data N1i is greater than or equal to βK, then x i Divide into central data; otherwise, x i Divide into edge data; and construct central data sets respectively and edge data collection ; Among them, β is the regulatory factor;

[0017] Step S33: Calculate the concentration, neighborhood density and relative distance of each student's learning data The product of ; Among them, δ i and A i They are x i relative distance and concentration of

[0018] Step S34: central data distribution, including the following steps:

[0019] Step S341: Select the center data with the largest concentration in Q1 as the centroid Z v , based on Z v Construct the corresponding cluster C v , and Z v Remove from Q1; where Z v is the vth centroid;

[0020] Step S342: For C v For each center data in , construct the center neighborhood set respectively, and the formula used is as follows:

[0021] ;

[0022] In the formula, It is C v The w-th center data in yes The central neighborhood set of and They are The positive neighbor set and the reverse neighbor set of is the intersection operator, x g is the g-th central data in Q1, ρ g is x g The neighborhood density, γ is the center control factor, ρ max is the maximum neighborhood density among all students’ learning data;

[0023] Step S343: For Each center data in C is added v and deleted from Q1;

[0024] Step S344: Return to step S342 to iterate until C v The central data in cluster C no longer increases. v After the initial construction is completed, go to step S345;

[0025] Step S345: Return to step S341 to iterate until the number of center data in Q1 is 0, then the center data allocation is completed, and V1 centroids and clusters are obtained, and go to step S35;

[0026] Step S35: Edge data allocation. For each edge data in Q2, the following steps are performed in sequence:

[0027] Step S351: Construct edge data x m The edge neighborhood set of is, the formula used is as follows:

[0028] ;

[0029] In the formula, x m is the mth edge data in Q2, P1 m is x m The edge neighborhood set of and They are x m The positive neighbor set and the reverse neighbor set of is the set of all student learning data except Q2 in the learning dataset, x h yes The h-th central data in h is x h The neighborhood density of is the edge control factor;

[0030] Step S352: For P1 m Each student learning data , respectively calculate The Euclidean distance between the V1 centroids is selected as the cluster constructed by the centroid with the smallest Euclidean distance The corresponding cluster ,Will Each student learning data in is used as a vertex, and the Euclidean distance between two student learning data is used as the weight of the edge between the corresponding two vertices to construct a weighted undirected graph , based on Prim's algorithm The minimum spanning tree of , and then calculate The cluster density ; if x m and The Euclidean distance between , then based on Construct the nearest neighbor screening set P2 m , the formula used is as follows:

[0031] ;

[0032] In the formula, It is P1 m The sth student learning data in yes The corresponding cluster, is based on The weighted undirected graph constructed, yes The minimum spanning tree of yes The cluster density, and They are The total weight and number of edges, P2 m is x m The nearest neighbor screening set of ;

[0033] Step S353: Find P2 m Zhong and x m The student learning data with the smallest Euclidean distance between , respectively calculate The Euclidean distance between the V1 centroids, x m Add to the cluster constructed with the centroid with the smallest Euclidean distance, and add x m Delete from Q2; return to step S351, continue to process the next edge data, until the number of edge data in Q2 is 0, then the edge data allocation is completed; obtain the clustering model, and output the clustering result; wherein, It is P2 m The f-th student learning data in .

[0034] Furthermore, in step S4, the clustering parameter tuning specifically includes the following steps:

[0035] Step S41: Initial individual position, establish a parameter search space for the neighborhood influence factor α, adjustment factor β, center control factor γ and edge control factor ε in the cluster, randomly initialize U individual positions in the parameter search space, use the individual position as the representative of the clustering parameter, and take the average value of the silhouette coefficient of all student learning data in the clustering result obtained based on the individual position as the individual fitness value;

[0036] Step S42: Individual position offset, preset offset threshold B th , calculate the probability of random deviation of each individual position ,like , then the u-th individual position is offset; otherwise, the u-th individual position remains unchanged; the formula used is as follows:

[0037] ;

[0038] ;

[0039] In the formula, is the u-th individual position in the t-th search, yes The probability of random deviation is, u is the individual position index, t is the search number index, T is the maximum search number, and are two individual positions randomly selected during the t-th search, is the offset control factor, min(·) is the minimum value function, yes The individual position after the shift, a max and a min are the maximum and minimum values ​​of the scaling factor, respectively;

[0040] Step S43: Individual position update: different update strategies are used to update individual positions in different search phases; the formula used is as follows:

[0041] ;

[0042] In the formula, is the position of the uth individual in the t+1th search, is the global optimal position at the t-th search, is the average value of all individual positions in the tth search, c1, c2, c3 and c4 are random numbers that do not interfere with each other, UB and LB are the upper and lower limits of the parameter search space, respectively. is the adjustment factor;

[0043] Step S44: The optimal clustering parameters are determined, the fitness threshold is pre-set, and the fitness value of the individual position is updated. When the fitness value of the global optimal position is higher than the fitness threshold, the global optimal position corresponds to the optimal clustering parameter, and the clustering parameter tuning is completed; otherwise, if the maximum number of searches is reached, return to step S41 to re-initialize the individual position; otherwise, the search number is increased by 1 and returns to step S42 to continue searching.

[0044] Furthermore, in step S5, the student learning status evaluation is to input the historical student learning data and the real-time student learning data after data preprocessing into a clustering model constructed based on the optimal clustering parameters for clustering processing, and based on the output clustering result, select the label with the largest number of historical student learning data in the cluster as the cluster label, and use the cluster label to which the real-time student learning data belongs as the evaluation result to obtain the learning status of the real-time student learning data, thereby completing the evaluation of the student learning status.

[0045] The student learning status evaluation system based on artificial intelligence provided by the present invention includes a data acquisition module, a data preprocessing module, a clustering model building module, a clustering parameter tuning module and a student learning status evaluation module;

[0046] The data acquisition module collects historical student learning data and real-time student learning data, and sends the data to the data preprocessing module;

[0047] The data preprocessing module performs data cleaning, data conversion, data normalization and learning data set construction on the collected student learning data, and sends the data to the clustering model construction module;

[0048] The clustering model building module calculates neighborhood density based on the reverse neighborhood set, divides the center data and the edge data, combines the neighborhood density and the relative distance to obtain the concentration, selects the center data with the largest concentration as the centroid and builds the cluster, continuously updates the cluster by building the center neighborhood set, completes the center data allocation, builds the edge neighborhood set, obtains the neighbor screening set by building a weighted undirected graph and calculating the cluster density, completes the edge data allocation, obtains the clustering model, and sends the data to the clustering parameter tuning module;

[0049] The clustering parameter tuning module establishes a parameter search space for clustering parameters, uses the initial individual position as a representative of the clustering parameters, calculates the random offset probability, selects the individual position for offset operation based on the offset threshold, and updates the individual position using different update strategies at different search stages based on the global optimal position and adjustment factor, finds the optimal clustering parameters, and sends the data to the student learning status evaluation module;

[0050] The student learning status evaluation module inputs the student learning data into the clustering model after parameter tuning for processing, obtains the learning status of the real-time student learning data, and completes the evaluation of the student learning status.

[0051] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0052] (1) In view of the problem that the existing methods for evaluating the student learning status have a complex nonlinear structure of student learning data, which cannot effectively mine data associations and determine the evaluation focus, resulting in inaccurate evaluation of the student learning status, this scheme calculates the neighborhood density based on the reverse neighborhood set, and divides the central data and edge data to find the closeness relationship around the data points in the complex data structure, so as to better capture the complex structure of the student learning data; the neighborhood density and relative distance are combined to obtain the concentration, and the central data with the largest concentration is selected as the centroid to construct a cluster, which comprehensively considers the degree of aggregation of the student learning data in the local area and the relative position relationship with other data, so as to more accurately determine the focus of the student learning status evaluation; by constructing the central neighborhood set, the cluster is continuously updated, the central data allocation is completed, and the quality of cluster construction is guaranteed; the edge neighborhood set is constructed, and the neighbor screening set is obtained by constructing a weighted undirected graph and calculating the cluster density, and the edge data allocation is completed to obtain the clustering model, so as to more comprehensively evaluate the student learning status, improve the coverage and efficiency of the evaluation, and make a more accurate evaluation of the student learning status in line with the actual situation.

[0053] (2) In view of the fact that there are large differences between individual students in the existing student learning status assessment methods, and the student learning data presents complex and diverse characteristics, the assessment is difficult to meet the needs of different students, resulting in the inability to accurately assess the students' actual learning status. This scheme establishes a parameter search space for clustering parameters. The initial individual position is used as a representative of the clustering parameters, which can explore a variety of possible clustering parameter combinations and provide more possibilities for adapting to the characteristics of different student learning data. The random offset probability is calculated, and the individual position is selected for offset operation based on the offset threshold to avoid the clustering parameters from falling into the local optimum, which helps to find clustering parameters that are more suitable for the characteristics of different student learning data. Based on the global optimal position and adjustment factor, different update strategies are used to update the individual position at different search stages to find the optimal clustering parameters. According to the characteristics of the student learning data and the search process, the clustering parameters are adjusted more reasonably, which can better adapt to the learning data of students of different levels and types, and improve the accuracy and effectiveness of learning status assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram of the process of the student learning status assessment method based on artificial intelligence provided by the present invention;

[0055] Figure 2 A schematic diagram of a student learning status assessment system based on artificial intelligence provided by the present invention;

[0056] Figure 3 is a schematic diagram of the process of step S3;

[0057] Figure 4 It is a schematic diagram of the process of step S4.

[0058] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0060] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0061] Example 1, see Figure 1 The present invention provides an artificial intelligence-based student learning status assessment method, which comprises the following steps:

[0062] Step S1: Data collection, collecting historical student learning data and real-time student learning data;

[0063] Step S2: Data preprocessing, data cleaning, data conversion, data normalization and construction of learning data set processing for the collected student learning data;

[0064] Step S3: construct a clustering model, calculate the neighborhood density based on the reverse neighborhood set, and divide the central data and the edge data, combine the neighborhood density and the relative distance to obtain the concentration, select the central data with the largest concentration as the centroid and construct a cluster, continuously update the cluster by constructing the central neighborhood set, complete the central data allocation, construct the edge neighborhood set, obtain the neighbor screening set by constructing a weighted undirected graph and calculating the cluster density, complete the edge data allocation, and obtain the clustering model;

[0065] Step S4: Clustering parameter tuning, establish a parameter search space for clustering parameters, use the initial individual position as the representative of the clustering parameters, calculate the random offset probability, select the individual position for offset operation based on the offset threshold, and use different update strategies to update the individual position in different search stages based on the global optimal position and adjustment factor to find the optimal clustering parameters;

[0066] Step S5: Student learning status evaluation: input student learning data into the clustering model after parameter tuning for processing, obtain the learning status of real-time student learning data, and complete the evaluation of student learning status.

[0067] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, both historical student learning data and real-time student learning data include learning platform data, homework data, test data and classroom interaction data. The historical student learning data also includes learning status; the learning platform data includes the time and frequency of students logging into the learning platform, the length of time they stay on each course page and the progress of watching teaching videos; the homework data includes the grades of students' submitted homework, the time it takes to complete the homework and the number of times the homework is submitted; the test data includes the test scores and the test time; the classroom interaction data includes the number of questions students ask in class, the accuracy of their answers to questions and the activeness of their participation in group discussions; the learning status includes excellent, good, average and poor. The learning status is used as a data label. The data label is not considered during clustering and is only used when selecting cluster labels.

[0068] Example 3, see Figure 1 This embodiment is based on the above embodiment. In step S2, data cleaning includes processing noise, outliers, duplicate values ​​and missing values; data conversion is to convert data into vector form; data normalization is to unify the data range based on the maximum and minimum normalization method; and constructing a learning data set is to construct a learning data set based on the student learning data after data cleaning, data conversion and data normalization.

[0069] Example 4, see Figure 1 and Figure 3 Based on the above embodiment, in step S3, building a clustering model specifically includes the following steps:

[0070] Step S31: Calculate the neighborhood density, calculate the Euclidean distance between any two student learning data in the learning data set, obtain the K nearest neighbors of each student learning data, and construct a positive neighborhood set , and then construct the reverse neighborhood set , the neighborhood density of each student's learning data is calculated based on the reverse neighborhood set, and the formula used is as follows:

[0071] ;

[0072] In the formula, x i and x j are the i-th and j-th student learning data in the learning dataset, i and j are the student learning data indexes, ρ i is x i The neighborhood density of is xi With x j The Euclidean distance between and They are x i The positive neighbor set and the reverse neighbor set of is x j The positive neighbor set of is x i is the Euclidean distance to its K-th nearest neighbor, exp(·) is an exponential function, and α is a neighborhood influence factor in the range (0, 1);

[0073] Step S32: Data division, if The number of middle school students’ learning data N1 i is greater than or equal to βK, then x i Divide into central data; otherwise, x i Divide into edge data; and construct central data sets respectively and edge data collection ; Where β is a regulation factor in the range of (0, 1);

[0074] Step S33: Calculate the concentration, neighborhood density and relative distance of each student's learning data The product of ; Among them, δ i and A i They are x i The relative distance and concentration of j is x j Neighborhood density, ρ max is the maximum neighborhood density among all students’ learning data;

[0075] Step S34: central data distribution, including the following steps:

[0076] Step S341: Select the center data with the largest concentration in Q1 as the centroid Z v , based on Z v Construct the corresponding cluster C v , and Z v Remove from Q1; where Z v is the vth centroid;

[0077] Step S342: For C v For each center data in , construct the center neighborhood set respectively, and the formula used is as follows:

[0078] ;

[0079] In the formula, It is C vThe w-th center data in yes The central neighborhood set of and They are The positive neighbor set and the reverse neighbor set of is the intersection operator, x g is the g-th central data in Q1, ρ g is x g The neighborhood density of , γ is the center control factor in the range of (0, 1);

[0080] Step S343: For Each center data in C is added v and deleted from Q1;

[0081] Step S344: Return to step S342 to iterate until C v The central data in cluster C no longer increases. v After the initial construction is completed, go to step S345;

[0082] Step S345: Return to step S341 to iterate until the number of center data in Q1 is 0, then the center data allocation is completed, and V1 centroids and clusters are obtained, and go to step S35;

[0083] Step S35: Edge data allocation. For each edge data in Q2, the following steps are performed in sequence:

[0084] Step S351: Construct edge data x m The edge neighborhood set of is, the formula used is as follows:

[0085] ;

[0086] In the formula, x m is the mth edge data in Q2, P1 m is x m The edge neighborhood set of and They are x m The positive neighbor set and the reverse neighbor set of is the set of all student learning data except Q2 in the learning dataset, x h yes The h-th central data in h is x h The neighborhood density of is the edge control factor in the range of (0, 1);

[0087] Step S352: For P1 mEach student learning data , respectively calculate The Euclidean distance between the V1 centroids is selected as the cluster constructed by the centroid with the smallest Euclidean distance The corresponding cluster ,Will Each student learning data in is used as a vertex, and the Euclidean distance between two student learning data is used as the weight of the edge between the corresponding two vertices to construct a weighted undirected graph , based on Prim's algorithm The minimum spanning tree of , and then calculate The cluster density ; if x m and The Euclidean distance between , then based on Construct the nearest neighbor screening set P2 m , the formula used is as follows:

[0088] ;

[0089] In the formula, It is P1 m The sth student learning data in yes The corresponding cluster, is based on The weighted undirected graph constructed, yes The minimum spanning tree of yes The cluster density, and They are The total weight and number of edges, P2 m is x m The nearest neighbor screening set of ;

[0090] Step S353: Find P2 m Zhong and x m The student learning data with the smallest Euclidean distance between , respectively calculate The Euclidean distance between the V1 centroids, x m Add to the cluster constructed with the centroid with the smallest Euclidean distance, and add x m Delete from Q2; return to step S351, continue to process the next edge data, until the number of edge data in Q2 is 0, then the edge data allocation is completed; obtain the clustering model, and output the clustering result; wherein, It is P2 m The f-th student learning data in .

[0091] By performing the above operations, the existing student learning status evaluation methods have the problem that student learning data has a complex nonlinear structure, cannot effectively mine data associations and determine evaluation priorities, and lead to inaccurate student learning status evaluation. This solution calculates neighborhood density based on the reverse neighborhood set, divides the central data and edge data, finds the closeness relationship around the data points in the complex data structure, and better captures the complex structure of student learning data; combines neighborhood density and relative distance to obtain concentration, selects the central data with the largest concentration as the centroid and constructs clusters, comprehensively considers the degree of aggregation of student learning data in the local area and the relative position relationship with other data, and more accurately determines the focus of student learning status evaluation; continuously updates clusters by constructing a central neighborhood set, completes central data allocation, and ensures the quality of cluster construction; constructs an edge neighborhood set, obtains a neighbor screening set by constructing a weighted undirected graph and calculating cluster density, completes edge data allocation, and obtains a clustering model, which more comprehensively evaluates students' learning status, improves the coverage and efficiency of evaluation, and makes a more accurate evaluation of students' learning status that conforms to the actual situation.

[0092] Example 5, see Figure 1 and Figure 4 This embodiment is based on the above embodiment. In step S4, clustering parameter tuning specifically includes the following steps:

[0093] Step S41: Initial individual position, establish a parameter search space for the neighborhood influence factor α, adjustment factor β, center control factor γ and edge control factor ε in the cluster, randomly initialize U individual positions in the parameter search space, use the individual position as the representative of the clustering parameter, and take the average value of the silhouette coefficient of all student learning data in the clustering result obtained based on the individual position as the individual fitness value;

[0094] Step S42: Individual position offset, preset offset threshold B th , calculate the probability of random deviation of each individual position ,like , then the u-th individual position is offset; otherwise, the u-th individual position remains unchanged; the formula used is as follows:

[0095] ;

[0096] ;

[0097] In the formula, is the u-th individual position in the t-th search, yes The probability of random deviation is, u is the individual position index, t is the search number index, T is the maximum search number, and are two individual positions randomly selected during the t-th search, , is the offset control factor in the range of (0, 0.1], min(·) is the minimum value function, yes The individual position after the shift, a max and a min are the maximum and minimum values ​​of the scaling factor, respectively;

[0098] Step S43: Individual position update: different update strategies are used to update individual positions in different search phases; the formula used is as follows:

[0099] ;

[0100] In the formula, is the position of the uth individual in the t+1th search, is the global optimal position at the tth search. The global optimal position is the individual position with the largest fitness value. is the average value of all individual positions in the tth search, c1, c2, c3 and c4 are random numbers in the range of (0, 1) that do not interfere with each other, UB and LB are the upper and lower limits of the parameter search space, respectively. is an adjustment factor in the range of (0.1, 0.5);

[0101] Step S44: The optimal clustering parameters are determined, the fitness threshold is pre-set, and the fitness value of the individual position is updated. When the fitness value of the global optimal position is higher than the fitness threshold, the global optimal position corresponds to the optimal clustering parameter, and the clustering parameter tuning is completed; otherwise, if the maximum number of searches is reached, return to step S41 to re-initialize the individual position; otherwise, the search number is increased by 1 and returns to step S42 to continue searching.

[0102] By performing the above operations, in view of the fact that there are large differences between individual students in the existing student learning status assessment methods, the student learning data presents complex and diverse characteristics, and the assessment is difficult to meet the needs of different students, resulting in the inability to accurately assess the students' actual learning status, this scheme establishes a parameter search space for clustering parameters. The initial individual position is used as a representative of the clustering parameters, and a variety of possible clustering parameter combinations can be explored, providing more possibilities for adapting to the characteristics of different student learning data; the random offset probability is calculated, and the individual position is selected for offset operation based on the offset threshold to avoid the clustering parameters from falling into the local optimum, which is helpful to find clustering parameters that are more suitable for the characteristics of different student learning data; based on the global optimal position and adjustment factor, different update strategies are used to update the individual position in different search stages to find the optimal clustering parameters. According to the characteristics of the student learning data and the search process, the clustering parameters are adjusted more reasonably, which can better adapt to the learning data of students of different levels and types, and improve the accuracy and effectiveness of learning status assessment.

[0103] Example 6, see Figure 1 This embodiment is based on the above embodiment. In step S5, the student learning status evaluation is to input the historical student learning data and the real-time student learning data after data preprocessing into the clustering model constructed based on the optimal clustering parameters for clustering processing. Based on the output clustering result, the label with the largest number of historical student learning data in the cluster is selected as the cluster label, and the cluster label to which the real-time student learning data belongs is used as the evaluation result to obtain the learning status of the real-time student learning data, thereby completing the evaluation of the student learning status.

[0104] Embodiment 7, see Figure 2 , this embodiment is based on the above embodiment, and the student learning status evaluation system based on artificial intelligence provided by the present invention includes a data acquisition module, a data preprocessing module, a clustering model building module, a clustering parameter tuning module and a student learning status evaluation module;

[0105] The data acquisition module collects historical student learning data and real-time student learning data, and sends the data to the data preprocessing module;

[0106] The data preprocessing module performs data cleaning, data conversion, data normalization and learning data set construction on the collected student learning data, and sends the data to the clustering model construction module;

[0107] The clustering model building module calculates neighborhood density based on the reverse neighborhood set, divides the center data and the edge data, combines the neighborhood density and the relative distance to obtain the concentration, selects the center data with the largest concentration as the centroid and builds the cluster, continuously updates the cluster by building the center neighborhood set, completes the center data allocation, builds the edge neighborhood set, obtains the neighbor screening set by building a weighted undirected graph and calculating the cluster density, completes the edge data allocation, obtains the clustering model, and sends the data to the clustering parameter tuning module;

[0108] The clustering parameter tuning module establishes a parameter search space for clustering parameters, uses the initial individual position as a representative of the clustering parameters, calculates the random offset probability, selects the individual position for offset operation based on the offset threshold, and updates the individual position using different update strategies at different search stages based on the global optimal position and adjustment factor, finds the optimal clustering parameters, and sends the data to the student learning status evaluation module;

[0109] The student learning status evaluation module inputs the student learning data into the clustering model after parameter tuning for processing, obtains the learning status of the real-time student learning data, and completes the evaluation of the student learning status.

[0110] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0111] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0112] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A student learning status assessment method based on artificial intelligence, characterized by: The method comprises the following steps: Step S1: Data collection, collecting historical student learning data and real-time student learning data; Step S2: data preprocessing; Step S3: constructing a clustering model; Step S4: clustering parameter tuning; Step S5: student learning status evaluation, inputting student learning data into the clustering model after parameter tuning for processing, obtaining the learning status of real-time student learning data, and completing the evaluation of student learning status; Step S4 includes step S42: individual position offset, presetting offset threshold B th , calculate the probability of random deviation of each individual position ,like , then the u-th individual position is offset; otherwise, the u-th individual position remains unchanged; the formula used is as follows: ； ； In the formula, is the u-th individual position in the t-th search, yes The probability of random deviation is, u is the individual position index, t is the search number index, T is the maximum search number, and are two individual positions randomly selected during the t-th search, is the offset control factor, min(·) is the minimum value function, yes The individual position after the shift, a max and a min are the maximum and minimum values ​​of the scaling factor, respectively.

2. The method for evaluating student learning status based on artificial intelligence according to claim 1, characterized in that: In step S3, the construction of the clustering model specifically includes the following steps: Step S31: Calculate the neighborhood density, calculate the Euclidean distance between any two student learning data in the learning data set, obtain the K nearest neighbors of each student learning data, and construct a positive neighborhood set , and then construct the reverse neighborhood set , the neighborhood density of each student's learning data is calculated based on the reverse neighborhood set, and the formula used is as follows: ； In the formula, x i and x j are the i-th and j-th student learning data in the learning dataset, i and j are the student learning data indexes, ρ i is x i The neighborhood density of is x i With x j The Euclidean distance between and They are x i The positive neighbor set and the reverse neighbor set of is x j The positive neighbor set of is x i The Euclidean distance between its Kth nearest neighbor, exp(·) is the exponential function, and α is the neighborhood influence factor; Step S32: Data division, if The number of middle school students’ learning data N1 i is greater than or equal to βK, then x i Divide into central data; otherwise, x i Divide into edge data; and construct central data sets respectively and edge data collection ; Among them, β is the regulatory factor; Step S33: Calculate the concentration, neighborhood density and relative distance of each student's learning data The product of ; Among them, δ i and A i They are x i relative distance and concentration of Step S34: central data distribution; Step S35: Edge data allocation.

3. The method for evaluating student learning status based on artificial intelligence according to claim 2 is characterized in that: In step S34, the central data distribution specifically includes the following steps: Step S341: Select the center data with the largest concentration in Q1 as the centroid Z v , based on Z v Construct the corresponding cluster C v , and Z v Delete from Q1; where Z v is the vth centroid; Step S342: For C v For each center data in , construct the center neighborhood set respectively, and the formula used is as follows: ； In the formula, It is C v The w-th center data in yes The central neighborhood set of and They are The positive neighbor set and the reverse neighbor set of is the intersection operator, x g is the g-th central data in Q1, ρ g is x g The neighborhood density, γ is the center control factor, ρ max is the maximum neighborhood density among all students’ learning data; Step S343: For Each center data in C is added v and deleted from Q1; Step S344: Return to step S342 to iterate until C v The central data in cluster C no longer increases. v After the initial construction is completed, go to step S345; Step S345: Return to step S341 to iterate until the number of center data in Q1 is 0, then the center data allocation is completed, and V1 centroids and clusters are obtained, and go to step S35.

4. The method for evaluating student learning status based on artificial intelligence according to claim 2, characterized in that: In step S35, the edge data allocation is to perform the following steps in sequence for each edge data in Q2: Step S351: Construct edge data x m The edge neighborhood set of is, the formula used is as follows: ； In the formula, x m is the mth edge data in Q2, P1 m is x m The edge neighborhood set of and They are x m The positive neighbor set and the reverse neighbor set of is the set of all student learning data except Q2 in the learning dataset, x h yes The h-th central data in h is x h The neighborhood density of is the edge control factor; Step S352: For P1 m Each student learning data , respectively calculated The Euclidean distance between the V1 centroids is selected as the cluster constructed by the centroid with the smallest Euclidean distance The corresponding cluster ,Will Each student learning data in is used as a vertex, and the Euclidean distance between two student learning data is used as the weight of the edge between the corresponding two vertices to construct a weighted undirected graph , based on Prim's algorithm The minimum spanning tree of , and then calculate The cluster density ; if x m and The Euclidean distance between , then based on Construct the nearest neighbor screening set P2 m , the formula used is as follows: ； In the formula, It is P1 m The sth student learning data in yes The corresponding cluster, is based on The weighted undirected graph constructed, yes The minimum spanning tree of yes The cluster density, and They are The total weight and number of edges, P2 m is x m The nearest neighbor screening set of ; Step S353: Find P2 m Zhong and x m The student learning data with the smallest Euclidean distance between , respectively calculated The Euclidean distance between the V1 centroids, x m Add to the cluster constructed by the centroid with the smallest Euclidean distance, and add x m Delete from Q2; return to step S351, continue to process the next edge data, until the number of edge data in Q2 is 0, then the edge data allocation is completed; Get the clustering model and output the clustering results; among them, It is P2 m The f-th student learning data in .

5. The method for evaluating student learning status based on artificial intelligence according to claim 1, characterized in that: In step S4, the clustering parameter tuning specifically includes the following steps: Step S41: Initial individual position, establish a parameter search space for the neighborhood influence factor α, adjustment factor β, center control factor γ and edge control factor ε in the cluster, randomly initialize U individual positions in the parameter search space, use the individual position as the representative of the clustering parameter, and take the average value of the silhouette coefficient of all student learning data in the clustering result obtained based on the individual position as the individual fitness value; Step S42: individual position offset; Step S43: Individual position update: different update strategies are used to update individual positions in different search phases; the formula used is as follows: ； In the formula, is the position of the uth individual at the t+1th search, is the global optimal position at the t-th search, is the average value of all individual positions in the tth search, c1, c2, c3 and c4 are random numbers that do not interfere with each other, UB and LB are the upper and lower limits of the parameter search space, respectively. is the adjustment factor; Step S44: The optimal clustering parameters are determined, the fitness threshold is pre-set, and the fitness value of the individual position is updated. When the fitness value of the global optimal position is higher than the fitness threshold, the global optimal position corresponds to the optimal clustering parameter, and the clustering parameter tuning is completed; otherwise, if the maximum number of searches is reached, return to step S41 to re-initialize the individual position; otherwise, the search number is increased by 1 and returns to step S42 to continue searching.

6. The method for evaluating student learning status based on artificial intelligence according to claim 1, characterized in that: In step S1, the data collection is to collect historical student learning data and real-time student learning data; the historical student learning data and real-time student learning data both include learning platform data, homework data, test data and classroom interaction data, and the historical student learning data also includes learning status; the learning status is used as a data label, and the data label is not considered during clustering, and is only used when selecting cluster labels.

7. The method for evaluating student learning status based on artificial intelligence according to claim 1, characterized in that: In step S5, the student learning status evaluation is to input the historical student learning data and real-time student learning data after data preprocessing into the clustering model constructed based on the optimal clustering parameters for clustering processing. Based on the output clustering result, the label with the largest number of historical student learning data in the cluster is selected as the cluster label, and the cluster label to which the real-time student learning data belongs is used as the evaluation result to obtain the learning status of the real-time student learning data, thereby completing the student learning status evaluation.

8. The method for evaluating student learning status based on artificial intelligence according to claim 1, characterized in that: In step S2, the data preprocessing is to clean, convert, normalize and construct a learning data set for the collected student learning data; data cleaning includes processing noise, outliers, duplicate values ​​and missing values; Data conversion is to convert data into vector form; data normalization is to unify the data range based on the maximum and minimum normalization method; Constructing a learning data set is to construct a learning data set based on the student learning data after data cleaning, data conversion and data normalization.

9. An artificial intelligence-based student learning status assessment system, used to implement an artificial intelligence-based student learning status assessment method as claimed in any one of claims 1 to 8, characterized in that: It includes data collection module, data preprocessing module, clustering model building module, clustering parameter tuning module and student learning status evaluation module; The data acquisition module collects historical student learning data and real-time student learning data, and sends the data to the data preprocessing module; The data preprocessing module performs data cleaning, data conversion, data normalization and learning data set construction on the collected student learning data, and sends the data to the clustering model construction module; The clustering model building module calculates neighborhood density based on the reverse neighborhood set, divides the center data and the edge data, combines the neighborhood density and the relative distance to obtain the concentration, selects the center data with the largest concentration as the centroid and builds the cluster, continuously updates the cluster by building the center neighborhood set, completes the center data allocation, builds the edge neighborhood set, obtains the neighbor screening set by building a weighted undirected graph and calculating the cluster density, completes the edge data allocation, obtains the clustering model, and sends the data to the clustering parameter tuning module; The clustering parameter tuning module establishes a parameter search space for clustering parameters, uses the initial individual position as a representative of the clustering parameters, calculates the random offset probability, selects the individual position for offset operation based on the offset threshold, and updates the individual position using different update strategies at different search stages based on the global optimal position and adjustment factor, finds the optimal clustering parameters, and sends the data to the student learning status evaluation module; The student learning status evaluation module inputs the student learning data into the clustering model after parameter tuning for processing, obtains the learning status of the real-time student learning data, and completes the evaluation of the student learning status.

Images