Assessment method for mastering degree of English knowledge points based on correlation analysis

Abstract

The invention relates to the technical field of knowledge point mastering degree evaluation, and discloses an English knowledge point mastering degree evaluation method based on correlation analysis, and the method comprises the steps: constructing English exercise process data into an English knowledge point score matrix, and converting the English knowledge point score matrix into an English knowledge point expression matrix, performing knowledge point association analysis to obtain an association relationship of mastering degrees among the knowledge points, and constructing an English knowledge point association matrix; and the knowledge point mastering degree evaluation model after model parameter optimization is used for evaluation to obtain the mastering degrees of the students on different English knowledge points. According to the method, the score rates of different knowledge points and the co-occurrence times of different knowledge points are calculated by adopting a correlation analysis method to obtain correlation coefficients and correlation relationships among different knowledge points, so that quantitative expression of the correlation relationships among different knowledge points is realized; and mapping the score performance of the knowledge points and the association relationship into the mastering degree of the knowledge points, thereby realizing association evaluation of the mastering degree of the English knowledge points.

Description

Technical Field

[0001] The present invention relates to the technical field of knowledge point mastery evaluation, and in particular to an English knowledge point mastery evaluation method based on association analysis. Background Art

[0002] In the context of globalization, the importance of teaching and learning English as a universal language is self-evident. Especially in other non-English speaking countries, English learning has become a core part of basic education. However, the traditional English teaching method is often based on a unified syllabus and examination content, ignoring the differences in the degree of mastery of individual students' knowledge points. This "standardized" model is difficult to meet the needs of personalized learning. In this context, it is particularly important to accurately evaluate students' mastery of English knowledge points. Traditional English knowledge point evaluation methods mainly rely on teachers' subjective judgment and single test scores, which are difficult to reflect the correlation between students' different knowledge points. For example, students may score high in grammar tests but perform poorly in reading comprehension. This distribution of scores may not only reflect the level of knowledge point mastery, but may also be affected by other factors such as situational comprehension ability or vocabulary. Existing evaluation methods are difficult to deeply explore the potential relationship between students' different knowledge points, such as whether the mastery of a certain grammar knowledge point will affect vocabulary use. Summary of the invention

[0003] In view of this, the present invention proposes an English knowledge point mastery degree assessment method based on association analysis, which mines the learning data of a large number of students through knowledge point association analysis, discovers the intrinsic relationship between different knowledge points, and provides intelligent data-driven English knowledge point mastery degree assessment.

[0004] To achieve the above object, the present invention provides a method for evaluating the mastery of English knowledge points by association analysis, comprising the following steps: S1: Collect students' English exercise process data and mark knowledge points, and construct the English exercise process data after knowledge point marking into an English knowledge point score matrix.

[0005] S2: Convert the English knowledge point score matrix into an English knowledge point performance matrix according to the preset score performance relationship, use the English knowledge point performance matrix to perform knowledge point association analysis to obtain the association relationship between the mastery levels of the knowledge points, and construct an English knowledge point association matrix, wherein the knowledge point association analysis improves the association analysis method.

[0006] S3: construct a knowledge point mastery evaluation model and optimize model parameters, wherein the knowledge point mastery evaluation model takes an English knowledge point performance matrix and an English knowledge point association matrix as inputs and takes mastery evaluation results of different English knowledge points as outputs.

[0007] S4: The knowledge point mastery evaluation model after model parameter optimization is used to receive the students' English knowledge point performance matrix and English knowledge point association matrix, and evaluate the students' mastery of different English knowledge points.

[0008] As a further improvement method of the present invention: Optionally, in step S1, the English exercise process data of the students is collected and the knowledge points are annotated, and the English exercise process data after the knowledge points are annotated is constructed into an English knowledge point score matrix, including: Collect students' English exercise process data, and mark the knowledge points of the English exercises answered by students to obtain the English exercise process data x after knowledge point marking: ; .

[0009] in: represents the N English exercises data after the knowledge points are marked, and N represents the total number of English exercises answered by the students; Represents the nth English exercise data after knowledge point annotation, n ∈[1,N] ; Indicates the knowledge point marking result of the nth English exercise answered by the student; in the embodiment of the present invention, the knowledge point marking result is a set of knowledge points included in the English exercise, wherein the knowledge points include tense, voice, subjunctive mood, preposition, pronoun, etc.; It represents the score of the nth English exercise answered by the student; Indicates the full score for the nth English exercise answered by the student.

[0010] Optionally, the step of constructing the English exercise process data after knowledge point annotation into an English knowledge point score matrix includes: S11: extract all knowledge point annotation results of N English exercise data, obtain all knowledge points contained in the N English exercise data, and construct all knowledge points contained in the English exercise data into a knowledge point set y: y ={ y m |m ∈ [1, M]} .

[0011] in: represents the mth knowledge point contained in N English exercise data, and M represents the number of types of knowledge points contained in N English exercise data.

[0012] S12: Calculate the score rate of each knowledge point, where the mth knowledge point The score rate is : .

[0013] in: Indicates that it contains knowledge points A collection of English exercises consisting of all English exercises; , c represents a set of English exercises Any English exercises in represents the student's score on English Exercise c, Indicates full marks for English Exercise C.

[0014] S13: Calculate the number of co-occurrences of exercises between any two knowledge points, where knowledge points And knowledge points The number of co-occurrences between exercises is : .

[0015] in: Represents a collection of English exercises The number of English exercises; Represents a collection of English exercises Contains knowledge points The number of English exercises, q ∈[1,M] ; represents the co-occurrence coefficient of the exercises, Set to 10.

[0016] S14: Calculate the knowledge point score association between any two knowledge points, where the knowledge points And knowledge points The knowledge point score correlation between : ; .

[0017] in: Indicates that students include knowledge points at the same time And knowledge points score rate on English exercises; Indicates that it also contains knowledge points And knowledge points A collection of English exercises consisting of all English exercises; , Represents a collection of English exercises Any English exercises in Indicates that students are doing English exercises The exercise score of Expressing English Exercises Full marks for the exercises; Represents the qth knowledge point scoring rate.

[0018] S15: Associate the scores of knowledge points, the number of co-occurrences of exercises between any two knowledge points, and the scores of knowledge points to construct an English knowledge point score matrix: S = [ x , S 1 , S 2 ] ; ; ; S 2 =[ score 1 , score 2 ,..., score m ,..., score M ] .

[0019] in: S represents an English knowledge point score matrix; in the embodiment of the present invention, S is a sawtooth matrix, that is, a matrix in which each row contains a different number of elements; represents the co-occurrence matrix of English knowledge point scores, is a matrix with M rows and M columns. express The matrix element value of the mth row and qth column in , q ∈[1,M] , m ∈[1,M] ; Represents the English knowledge point score rate matrix.

[0020] Optionally, in step S2, converting the English knowledge point score matrix into an English knowledge point performance matrix according to a preset score performance relationship includes: According to the preset score performance relationship, the English knowledge point score matrix Converted into English knowledge point performance matrix: S * = [x, S 1 , S 2 * ] ; S 2 * =[ E 1 , E 2 ,..., E m ,..., E M ] ; .

[0021] in: Represents the English knowledge point performance matrix; Represents the English knowledge point score performance matrix; Indicates the score rate The corresponding score performance, represents the score rate threshold, In the embodiment of the present invention, If it is 3, it means that the student has The score is excellent. If it is 2, it means that the student is in the knowledge point The score is good. If it is 1, it means that the student is in the knowledge point The score represents the passing level.

[0022] Optionally, the method of using the English knowledge point representation matrix to perform knowledge point association analysis to obtain the association relationship between the mastery levels of the knowledge points includes: S21: Based on English knowledge points performance matrix The English exercise process data x after knowledge point annotation is calculated to obtain the co-occurrence support of any two knowledge points. And knowledge points The co-occurrence support between : .

[0023] in: Represents a collection of English exercises The number of English exercises.

[0024] S22: Based on the co-occurrence support between knowledge points and the English exercise process data x, the correlation coefficient between knowledge points is calculated, where knowledge points And knowledge points The correlation coefficient between them is: .

[0025] in: English Exercise Collection The number of English exercises; Indicates that it contains knowledge points A collection of English exercises consisting of all English exercises.

[0026] S23: Based on the correlation coefficient between knowledge points and the correlation of knowledge point scores, the correlation relationship between the mastery degrees of knowledge points is calculated, where knowledge points And knowledge points The correlation between the mastery level is : .

[0027] in: For knowledge points And knowledge points The knowledge point score association between them.

[0028] S24: Construct the correlation relationship between the mastery levels of knowledge points into an English knowledge point correlation matrix h: .

[0029] in: is a matrix with M rows and M columns. express The matrix element value of the mth row and qth column in , q ∈[1,M] , m ∈[1,M] .

[0030] Optionally, constructing a knowledge point mastery degree assessment model in step S3 includes: A knowledge point mastery degree assessment model is constructed, which takes an English knowledge point performance matrix and an English knowledge point association matrix as input, and takes the mastery degree assessment results of different English knowledge points as output, wherein the knowledge point mastery degree assessment model includes an input layer, an association fusion layer, a knowledge point mastery degree mapping layer and an output layer, the input layer is used to receive the English knowledge point performance matrix and the English knowledge point association matrix, the association fusion layer is used to associate and fuse the knowledge point performance matrix and the English knowledge point association matrix to obtain English knowledge point association fusion features, and the knowledge point mastery degree mapping layer is used to map the English knowledge point association fusion features to obtain the students' mastery degree of different knowledge points and output them.

[0031] The English exercise process data and the real English knowledge point mastering sequence of the students in group D after knowledge point annotation are obtained, and the matrix construction from step S1 to step S2 is performed to obtain the English knowledge point performance matrix and the English knowledge point association matrix of the students in group D. The English knowledge point performance matrix, the English knowledge point association matrix and the real English knowledge point mastering sequence of the students in group D are constructed as the training data set data of the knowledge point mastering degree evaluation model: data ={(S(d), h(d), F d )|d ∈ [1, D]} ; .

[0032] in: Represents the English knowledge point performance matrix of group d students , English knowledge point association matrix And the sequence of mastering real English knowledge points , d ∈ [1, D] ; Indicates the knowledge points of group d students The true mastery level of , T represents transposition, m ∈ [1,M] .

[0033] Optionally, the model parameters in the knowledge point mastery evaluation model are optimized based on the training data set data, including: S31: Initialize and generate model parameters in the U group of knowledge point mastery evaluation models, where the u-th group of model parameters generated by initialization are , set the current iteration number of the model parameters to t, the maximum iteration number to Max, then the model parameters The result of the tth iteration is , u ∈ [1,U] ; They represent the mapping matrix and bias in the knowledge point mastery level mapping layer respectively.

[0034] S32: Construct a fitness function of the model parameters based on the training data set data, substitute the model parameters into the fitness function, and obtain the fitness value of the model parameters, where the model parameters The fitness value is : ; .

[0035] in: English knowledge point representation matrix Correlation matrix with English knowledge points The associated fusion features of English knowledge points obtained by associated fusion; for The mth row in ; Represents the fitness function.

[0036] S33: According to the fitness value of the U group of model parameters after the tth iteration, the iteration step length of the model parameters is calculated, where the model parameters The iteration step length is : ; ; .

[0037] in: represents the gamma function; Represents the model parameter with the minimum fitness value after the tth iteration; represents the iteration coefficient; represents the beta function.

[0038] S34: Iterate the model parameters using the iteration step, where the model parameters The iteration formula is: .

[0039] in: z represents the spiral control parameter, and z is set to 0.2; Represents a random number between 0 and 1.

[0040] S35: Let t = t + 1, return to step S34, until the maximum number of iterations is reached, and calculate the fitness value of the U group model parameters at this time, and select the model parameter with the smallest fitness value as the model parameter optimization result .

[0041] Optimizing results using model parameters Construct a model to evaluate the degree of mastery of knowledge points.

[0042] Optionally, in step S4, the knowledge point mastery degree evaluation model is used to receive the student's English knowledge point performance matrix and English knowledge point association matrix, and the student's mastery degree on different English knowledge points is evaluated, including: The knowledge point mastery evaluation model is used to receive the students' English knowledge point performance matrix and English knowledge point association matrix, and evaluate the students' mastery of different English knowledge points. The evaluation process is as follows: S41: Input layer receives English knowledge point representation matrix And the English knowledge point association matrix h.

[0043] S42: Association fusion layer for knowledge point representation matrix And the English knowledge point association matrix h is associated and fused to obtain the English knowledge point association fusion feature : .

[0044] in: T stands for transpose; It is in the form of a matrix with M rows and 1 column.

[0045] S43: Knowledge point mastery level mapping layer to English knowledge point related fusion features Mapping is performed to obtain the students' mastery of different knowledge points, where the mapping formula is: ; .

[0046] in: Represents the associated fusion features of English knowledge points The mapping result is It is a matrix with M rows and 1 column. The mth row in That is, the student's mth knowledge point The degree of mastery, m ∈ [1,M] ; is the mapping matrix The mth row in the mapping matrix It is a matrix with M rows and M columns; Indicates the offset.

[0047] The knowledge points whose mastery level is below the preset threshold are marked as students' weak English knowledge points.

[0048] In order to solve the above problem, the present invention provides an electronic device, the electronic device comprising: A memory storing at least one instruction; Communication interface, enabling electronic equipment to communicate; and The processor executes the instructions stored in the memory to implement the above-mentioned method for assessing the mastery of English knowledge points through association analysis.

[0049] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned method for assessing the mastery of English knowledge points based on association analysis.

[0050] Compared with the prior art, the present invention proposes a method for evaluating the mastery of English knowledge points based on association analysis, which has the following advantages: First, this scheme proposes a quantitative method for the correlation between knowledge points. It collects students' English exercise process data, and extracts students' score rates in different knowledge points, the number of co-occurrences of different knowledge points in the same English exercise, and the co-occurrence score rates to form an English knowledge point score matrix. The score rates of students in different English knowledge points and the correlation information of any two English knowledge points in the answered exercises are represented in a matrix to achieve the mapping between the English knowledge point score relationship and the English exercise process data, and the score expression relationship is used to reduce the dimension of the score rate data. The correlation coefficient and correlation relationship between different knowledge points are calculated using the correlation analysis method. The higher the frequency of two knowledge points appearing in the same English exercise and the higher the mutual information, the higher the correlation coefficient between the two knowledge points, the higher the similarity of the scores of the two knowledge points, the higher the knowledge point score correlation, and the higher the correlation relationship between the corresponding knowledge points, so as to achieve the quantitative representation of the correlation relationship between different knowledge points.

[0051] At the same time, this scheme constructs a knowledge point mastery evaluation model, adopts multiple groups of student data to optimize the model parameters, and adopts the Beta flight strategy and spiral iteration method to iteratively process the model parameters in the solution process, so as to improve the solution range of the model parameters and avoid falling into the local optimal solution. The knowledge point mastery evaluation model after the model parameters are optimized is used to receive the students' English knowledge point performance matrix and English knowledge point association matrix, and evaluate the students' mastery of different English knowledge points, so as to realize the association evaluation of the mastery of English knowledge points. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A schematic diagram of a flow chart of a method for evaluating the mastery of English knowledge points based on association analysis provided by one embodiment of the present invention.

[0053] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0055] The embodiment of the present application provides a method for assessing the mastery of English knowledge points by association analysis. The execution subject of the method for assessing the mastery of English knowledge points by association analysis includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for assessing the mastery of English knowledge points by association analysis can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0056] Embodiment 1: A method for evaluating the mastery of English knowledge points based on association analysis comprises the following steps: S1: Collect students' English exercise process data and mark knowledge points, and construct the English exercise process data after knowledge point marking into an English knowledge point score matrix.

[0057] In the step S1, the students' English exercise process data is collected and knowledge points are marked, and the English exercise process data after knowledge point marking is constructed into an English knowledge point score matrix, including: Collect students' English exercise process data, and mark the knowledge points of the English exercises answered by students to obtain the English exercise process data x after knowledge point marking: ; .

[0058] in: represents the N English exercises data after the knowledge points are marked, and N represents the total number of English exercises answered by the students; Represents the nth English exercise data after knowledge point annotation, n ∈[1,N] ; Indicates the knowledge point marking result of the nth English exercise answered by the student; in the embodiment of the present invention, the knowledge point marking result is a set of knowledge points included in the English exercise, wherein the knowledge points include tense, voice, subjunctive mood, preposition, pronoun, etc.; It represents the score of the nth English exercise answered by the student; Indicates the full score for the nth English exercise answered by the student.

[0059] The English exercise process data after knowledge point annotation is constructed into an English knowledge point score matrix, including: S11: extract all knowledge point annotation results of N English exercise data, obtain all knowledge points contained in the N English exercise data, and construct all knowledge points contained in the English exercise data into a knowledge point set y: y ={ y m |m ∈ [1, M]} .

[0060] in: represents the mth knowledge point contained in N English exercise data, and M represents the number of types of knowledge points contained in N English exercise data.

[0061] S12: Calculate the score rate of each knowledge point, where the mth knowledge point The score rate is : .

[0062] in: Indicates that it contains knowledge points A collection of English exercises consisting of all English exercises; , c represents a set of English exercises Any English exercises in represents the student's score on English Exercise c, Indicates full marks for English Exercise C.

[0063] S13: Calculate the number of co-occurrences of exercises between any two knowledge points, where knowledge points And knowledge points The number of co-occurrences between exercises is : .

[0064] in: Represents a collection of English exercises The number of English exercises; Represents a collection of English exercises Contains knowledge points The number of English exercises, q ∈[1,M] ; represents the co-occurrence coefficient of the exercises, Set to 10.

[0065] S14: Calculate the knowledge point score association between any two knowledge points, where the knowledge points And knowledge points The knowledge point score correlation between : ; .

[0066] in: Indicates that students include knowledge points at the same time And knowledge points score rate on English exercises; Indicates that it also contains knowledge points And knowledge points A collection of English exercises consisting of all English exercises; , Represents a collection of English exercises Any English exercises in Indicates that students are doing English exercises The exercise score of Expressing English Exercises Full marks for the exercises; Represents the qth knowledge point scoring rate.

[0067] S15: Associate the scores of knowledge points, the number of co-occurrences of exercises between any two knowledge points, and the scores of knowledge points to construct an English knowledge point score matrix: S = [ x , S 1 , S 2 ] ; ; ; S 2 =[ score 1 , score 2 ,..., score m ,..., score M ] .

[0068] in: S represents an English knowledge point score matrix; in the embodiment of the present invention, S is a sawtooth matrix, that is, a matrix in which each row contains a different number of elements; represents the co-occurrence matrix of English knowledge point scores, is a matrix with M rows and M columns. express The matrix element value of the mth row and qth column in , q ∈[1,M] , m ∈[1,M] ; Represents the English knowledge point score rate matrix.

[0069] S2: Convert the English knowledge point score matrix into an English knowledge point performance matrix according to the preset score performance relationship, use the English knowledge point performance matrix to perform knowledge point association analysis to obtain the association relationship between the mastery levels of the knowledge points, and construct an English knowledge point association matrix.

[0070] In step S2, the English knowledge point score matrix is ​​converted into an English knowledge point performance matrix according to a preset score performance relationship, including: According to the preset score performance relationship, the English knowledge point score matrix Converted into English knowledge point performance matrix: S * = [x, S 1 , S 2 * ] ; S 2 * =[ E 1 , E 2 ,..., E m ,..., E M ] ; .

[0071] in: Represents the English knowledge point performance matrix; Represents the English knowledge point score performance matrix; Indicates the score rate The corresponding score performance, represents the score rate threshold, In the embodiment of the present invention, If it is 3, it means that the student has The score is excellent. If it is 2, it means that the student is in the knowledge point The score is good. If it is 1, it means that the student is in the knowledge point The score represents the passing level.

[0072] The method of using the English knowledge point representation matrix to perform knowledge point association analysis to obtain the association relationship between the mastery levels of the knowledge points includes: S21: Based on English knowledge points performance matrix The English exercise process data x after knowledge point annotation is calculated to obtain the co-occurrence support of any two knowledge points. And knowledge points The co-occurrence support between : .

[0073] in: Represents a collection of English exercises The number of English exercises.

[0074] S22: Based on the co-occurrence support between knowledge points and the English exercise process data x, the correlation coefficient between knowledge points is calculated, where knowledge points And knowledge points The correlation coefficient between them is: .

[0075] in: English Exercise Collection The number of English exercises; Indicates that it contains knowledge points A collection of English exercises consisting of all English exercises.

[0076] S23: Based on the correlation coefficient between knowledge points and the correlation of knowledge point scores, the correlation relationship between the mastery degrees of knowledge points is calculated, where knowledge points And knowledge points The correlation between the mastery level is : .

[0077] in: For knowledge points And knowledge points The knowledge point score association between them.

[0078] S24: Construct the correlation relationship between the mastery levels of knowledge points into an English knowledge point correlation matrix h: .

[0079] in: is a matrix with M rows and M columns. express The matrix element value of the mth row and qth column in , q ∈[1,M] , m ∈[1,M] .

[0080] S3: construct a knowledge point mastery evaluation model and optimize model parameters, wherein the knowledge point mastery evaluation model takes an English knowledge point performance matrix and an English knowledge point association matrix as inputs and takes mastery evaluation results of different English knowledge points as outputs.

[0081] The step S3 constructs a knowledge point mastery evaluation model, including: A knowledge point mastery degree assessment model is constructed, which takes an English knowledge point performance matrix and an English knowledge point association matrix as input, and takes the mastery degree assessment results of different English knowledge points as output, wherein the knowledge point mastery degree assessment model includes an input layer, an association fusion layer, a knowledge point mastery degree mapping layer and an output layer, the input layer is used to receive the English knowledge point performance matrix and the English knowledge point association matrix, the association fusion layer is used to associate and fuse the knowledge point performance matrix and the English knowledge point association matrix to obtain English knowledge point association fusion features, and the knowledge point mastery degree mapping layer is used to map the English knowledge point association fusion features to obtain the students' mastery degree of different knowledge points and output them.

[0082] The English exercise process data and the real English knowledge point mastering sequence of the students in group D after knowledge point annotation are obtained, and the matrix construction from step S1 to step S2 is performed to obtain the English knowledge point performance matrix and the English knowledge point association matrix of the students in group D. The English knowledge point performance matrix, the English knowledge point association matrix and the real English knowledge point mastering sequence of the students in group D are constructed as the training data set data of the knowledge point mastering degree evaluation model: data ={(S(d), h(d), F d )|d ∈ [1, D]} ; .

[0083] in: Represents the English knowledge point performance matrix of group d students , English knowledge point association matrix And the sequence of mastering real English knowledge points , d ∈ [1, D] ; Indicates the knowledge points of group d students The true mastery level of , T represents transposition, m ∈ [1,M] .

[0084] Based on the training data set data, the model parameters in the knowledge point mastery evaluation model are optimized, including: S31: Initialize and generate model parameters in the U group of knowledge point mastery evaluation models, where the u-th group of model parameters generated by initialization are , set the current iteration number of the model parameters to t, the maximum iteration number to Max, then the model parameters The result of the tth iteration is , u ∈ [1,U] ; They represent the mapping matrix and bias in the knowledge point mastery level mapping layer respectively.

[0085] S32: Construct a fitness function of the model parameters based on the training data set data, substitute the model parameters into the fitness function, and obtain the fitness value of the model parameters, where the model parameters The fitness value is : ; .

[0086] in: English knowledge point representation matrix Correlation matrix with English knowledge points The associated fusion features of English knowledge points obtained by associated fusion; for The mth row in ; Represents the fitness function.

[0087] S33: According to the fitness value of the U group of model parameters after the tth iteration, the iteration step length of the model parameters is calculated, where the model parameters The iteration step length is : ; ; .

[0088] in: represents the gamma function; Represents the model parameter with the minimum fitness value after the tth iteration; represents the iteration coefficient; represents the beta function.

[0089] S34: Iterate the model parameters using the iteration step, where the model parameters The iteration formula is: .

[0090] in: z represents the spiral control parameter, and z is set to 0.2; Represents a random number between 0 and 1.

[0091] S35: Let t = t + 1, return to step S34, until the maximum number of iterations is reached, and calculate the fitness value of the U group model parameters at this time, and select the model parameter with the smallest fitness value as the model parameter optimization result .

[0092] Optimizing results using model parameters Construct a model to evaluate the degree of mastery of knowledge points.

[0093] S4: The knowledge point mastery evaluation model after model parameter optimization is used to receive the students' English knowledge point performance matrix and English knowledge point association matrix, and evaluate the students' mastery of different English knowledge points.

[0094] In step S4, the knowledge point mastery degree evaluation model is used to receive the student's English knowledge point performance matrix and English knowledge point association matrix, and the student's mastery degree on different English knowledge points is evaluated, including: The knowledge point mastery evaluation model is used to receive the students' English knowledge point performance matrix and English knowledge point association matrix, and evaluate the students' mastery of different English knowledge points. The evaluation process is as follows: S41: Input layer receives English knowledge point representation matrix And the English knowledge point association matrix h.

[0095] S42: Association fusion layer for knowledge point representation matrix And the English knowledge point association matrix h is associated and fused to obtain the English knowledge point association fusion feature : .

[0096] in: T stands for transpose; It is in the form of a matrix with M rows and 1 column.

[0097] S43: Knowledge point mastery level mapping layer to English knowledge point related fusion features Mapping is performed to obtain the students' mastery of different knowledge points, where the mapping formula is: ; .

[0098] in: Represents the associated fusion features of English knowledge points The mapping result is It is a matrix with M rows and 1 column. The mth row in That is, the student's mth knowledge point The degree of mastery, m ∈ [1,M] ; is the mapping matrix The mth row in the mapping matrix It is a matrix with M rows and M columns; Indicates the offset.

[0099] The knowledge points whose mastery level is below the preset threshold are marked as students' weak English knowledge points.

[0100] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0101] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method 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, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0102] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0103] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for evaluating the mastery of English knowledge points based on association analysis, characterized in that: The method comprises: S1: Collect students' English practice process data and mark knowledge points, and construct the English practice process data after knowledge point marking into an English knowledge point score matrix; S2: converting the English knowledge point score matrix into an English knowledge point performance matrix according to the preset score performance relationship, performing knowledge point association analysis using the English knowledge point performance matrix to obtain the association relationship between the mastery degrees of the knowledge points, and constructing an English knowledge point association matrix; S3: constructing a knowledge point mastery evaluation model and optimizing model parameters, wherein the knowledge point mastery evaluation model takes an English knowledge point performance matrix and an English knowledge point association matrix as inputs and takes mastery evaluation results of different English knowledge points as outputs; S4: The knowledge point mastery evaluation model after model parameter optimization is used to receive the students' English knowledge point performance matrix and English knowledge point association matrix, and evaluate the students' mastery of different English knowledge points.

2. The method for evaluating the mastery of English knowledge points by association analysis according to claim 1, characterized in that: The S1 step includes: Collect students' English exercise process data, and mark the knowledge points of the English exercises answered by students to obtain the English exercise process data x after knowledge point marking: ； ； in: represents the N English exercises data after the knowledge points are marked, and N represents the total number of English exercises answered by the students; Represents the nth English exercise data after knowledge point annotation, ; Indicates the knowledge point marking result of the nth English exercise answered by the student; It represents the score of the nth English exercise answered by the student; Indicates the full score for the nth English exercise answered by the student.

3. The method for evaluating the mastery of English knowledge points by association analysis according to claim 2, characterized in that: The English exercise process data after knowledge point annotation is constructed into an English knowledge point score matrix, including: S11: extract all knowledge point annotation results of N English exercise data, obtain all knowledge points contained in the N English exercise data, and construct all knowledge points contained in the English exercise data into a knowledge point set y: ； in: represents the mth knowledge point contained in the N English exercise data, and M represents the number of types of knowledge points contained in the N English exercise data; S12: Calculate the score rate of each knowledge point, where the mth knowledge point The score rate is : ； in: Indicates that it contains knowledge points A collection of English exercises consisting of all English exercises; , c represents a set of English exercises Any English exercises in represents the student's score on English Exercise c, It means full marks for English Exercise C; S13: Calculate the number of co-occurrences of exercises between any two knowledge points, where knowledge points And knowledge points The number of co-occurrences between exercises is : ； in: Represents a collection of English exercises The number of English exercises; Represents a collection of English exercises Contains knowledge points The number of English exercises, ; represents the co-occurrence coefficient of the exercises, Set to 10; S14: Calculate the knowledge point score association between any two knowledge points, where the knowledge points And knowledge points The knowledge point score correlation between : ； ； in: Indicates that students include knowledge points at the same time And knowledge points score rate on English exercises; Indicates that it also contains knowledge points And knowledge points A collection of English exercises consisting of all English exercises; , Represents a collection of English exercises Any English exercises in Indicates that students are doing English exercises The exercise score of Expressing English Exercises Full marks for the exercises; Represents the qth knowledge point Scoring rate; S15: Associate the scores of knowledge points, the number of co-occurrences of exercises between any two knowledge points, and the scores of knowledge points to construct an English knowledge point score matrix: ； ； ； ； in: S represents the English knowledge point score matrix; represents the English knowledge point score co-occurrence matrix, is a matrix with M rows and M columns. express The matrix element value of the mth row and qth column in , , ; Represents the English knowledge point score rate matrix.

4. The method for evaluating the mastery of English knowledge points by association analysis according to claim 3, characterized in that: The S2 step includes: According to the preset score performance relationship, the English knowledge point score matrix Converted into English knowledge point performance matrix: ； ； ； in: Represents the English knowledge point performance matrix; Represents the English knowledge point score performance matrix; Indicates the score rate The corresponding score performance, represents the score rate threshold, .

5. The method for evaluating the mastery of English knowledge points by association analysis according to claim 4, characterized in that: The method of using the English knowledge point representation matrix to perform knowledge point association analysis to obtain the association relationship between the mastery levels of the knowledge points includes: S21: Based on English knowledge points performance matrix The English exercise process data x after knowledge point annotation is calculated to obtain the co-occurrence support of any two knowledge points. And knowledge points The co-occurrence support between : ； in: Represents a collection of English exercises The number of English exercises; S22: Based on the co-occurrence support between knowledge points and the English exercise process data x, the correlation coefficient between knowledge points is calculated, where knowledge points And knowledge points The correlation coefficient between them is: ； in: English Exercise Collection The number of English exercises; Indicates that it contains knowledge points A collection of English exercises consisting of all English exercises; S23: Based on the correlation coefficient between knowledge points and the correlation of knowledge point scores, the correlation relationship between the mastery degrees of knowledge points is calculated, where knowledge points And knowledge points The correlation between the mastery level is : ； in: For knowledge points And knowledge points The knowledge point score association between them; S24: Construct the correlation relationship between the mastery levels of knowledge points into an English knowledge point correlation matrix h: ； in: is a matrix with M rows and M columns. express The matrix element value of the mth row and qth column in , , .

6. The method for evaluating the mastery of English knowledge points by association analysis according to claim 1, characterized in that: The S3 step includes: Construct a knowledge point mastery degree assessment model, the knowledge point mastery degree assessment model takes an English knowledge point performance matrix and an English knowledge point association matrix as input, and takes the mastery degree assessment results of different English knowledge points as output, wherein the knowledge point mastery degree assessment model includes an input layer, an association fusion layer, a knowledge point mastery degree mapping layer and an output layer, the input layer is used to receive the English knowledge point performance matrix and the English knowledge point association matrix, the association fusion layer is used to associate and fuse the knowledge point performance matrix and the English knowledge point association matrix to obtain English knowledge point association fusion features, and the knowledge point mastery degree mapping layer is used to map the English knowledge point association fusion features to obtain the students' mastery degree of different knowledge points and output them; The English exercise process data and the real English knowledge point mastering sequence of the students in group D after knowledge point annotation are obtained, and the matrix construction from step S1 to step S2 is performed to obtain the English knowledge point performance matrix and the English knowledge point association matrix of the students in group D. The English knowledge point performance matrix, the English knowledge point association matrix and the real English knowledge point mastering sequence of the students in group D are constructed as the training data set data of the knowledge point mastering degree evaluation model: ； ； in: Represents the English knowledge point performance matrix of group d students , English knowledge point association matrix And the sequence of mastering real English knowledge points , ; Indicates the knowledge points of group d students The true mastery level of , T represents transposition, .

7. The method for evaluating the mastery of English knowledge points by association analysis according to claim 6, characterized in that: Based on the training data set data, the model parameters in the knowledge point mastery evaluation model are optimized, including: S31: Initialize and generate model parameters in the U group of knowledge point mastery evaluation models, where the u-th group of model parameters generated by initialization are , set the current iteration number of the model parameters to t, the maximum iteration number to Max, then the model parameters The result of the tth iteration is , ; The mapping matrix and the bias in the knowledge point mastery level mapping layer are represented in turn; S32: Construct a fitness function of the model parameters based on the training data set data, substitute the model parameters into the fitness function, and obtain the fitness value of the model parameters, where the model parameters The fitness value is : ； ； in: English knowledge point representation matrix Correlation matrix with English knowledge points The associated fusion features of English knowledge points obtained by associated fusion; for The mth row in ; represents the fitness function; S33: According to the fitness value of the U group of model parameters after the tth iteration, the iteration step length of the model parameters is calculated, where the model parameters The iteration step length is : ； ； ； in: represents the gamma function; Represents the model parameter with the minimum fitness value after the tth iteration; represents the iteration coefficient; represents the beta function; S34: Iterate the model parameters using the iteration step, where the model parameters The iteration formula is: ； in: z represents the spiral control parameter, and z is set to 0.2; Represents a random number between 0 and 1; S35: Let t = t + 1, return to step S34, until the maximum number of iterations is reached, and calculate the fitness value of the U group model parameters at this time, and select the model parameter with the smallest fitness value as the model parameter optimization result ; Optimizing results using model parameters Construct a model to evaluate the degree of mastery of knowledge points.

8. The method for evaluating the mastery of English knowledge points by association analysis according to claim 7, characterized in that: The S4 step includes: The knowledge point mastery evaluation model is used to receive the students' English knowledge point performance matrix and English knowledge point association matrix, and evaluate the students' mastery of different English knowledge points. The evaluation process is as follows: S41: Input layer receives English knowledge point representation matrix And the English knowledge point association matrix h; S42: Association fusion layer for knowledge point representation matrix And the English knowledge point association matrix h is associated and fused to obtain the English knowledge point association fusion feature : ； in: T stands for transpose; It is a matrix with M rows and 1 column; S43: Knowledge point mastery level mapping layer to English knowledge point related fusion features Mapping is performed to obtain the students' mastery of different knowledge points, where the mapping formula is: ； ； in: Represents the associated fusion features of English knowledge points The mapping result is It is a matrix with M rows and 1 column. The mth row in That is, the student's mth knowledge point The degree of mastery, ; is the mapping matrix The mth row in the mapping matrix It is a matrix with M rows and M columns; Indicates the offset; The knowledge points whose mastery level is below the preset threshold are marked as students' weak English knowledge points.

Images