Knowledge tracking method and knowledge tracking model based on forgetting attention mechanism, computer system and storage medium

Abstract

The invention relates to the technical field of knowledge tracking, in particular to a knowledge tracking method based on a forgetting attention mechanism, a knowledge tracking model, a computer system and a storage medium. A rule that student knowledge declines along with time is simulated by introducing a forgetting factor based on relative position coding, an answer sequence embedded representation more conforming to a real learning scene is constructed, and feature fusion is performed on the answer sequence embedded representation and a question sequence embedded representation, so that prediction is more targeted and accurate. The method aims at solving the problem of knowledge tracking prediction deviation caused by the forgetting effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of knowledge tracing, and particularly relates to a knowledge tracing method based on a forgetting attention mechanism, a knowledge tracing model, a computer system and a storage medium. BACKGROUND

[0002] Knowledge tracing (KT) is one of the core tasks in intelligent education systems, and its goal is to predict the answering performance of a student on future exercises based on the student's historical answering records.

[0003] Traditional knowledge tracing methods mainly include two categories: one is a traditional method based on a probabilistic graphical model, and the other is a model method based on deep learning. However, both have their own limitations: the traditional probabilistic graphical model has a certain interpretability, for example, the Rasch model can describe the answering accuracy through the difference between the student ability parameter and the question difficulty parameter, but its prediction performance is limited and it is difficult to capture complex learning processes; while the deep learning model can automatically learn the dynamic changes of the student's knowledge state through the neural network, and the prediction accuracy is significantly improved, but it often has the problem of insufficient interpretability.

[0004] On the other hand, the inventors found in the process of conceiving and implementing the present application that in real learning scenarios, the knowledge memory of a student will gradually decline over time, which is called the “forgetting effect”, but the current mainstream knowledge tracing methods using attention mechanisms generally ignore this effect: on the one hand, traditional knowledge tracing models only rely on historical sequence similarity for prediction when modeling, and fail to effectively model the forgetting process, thereby causing prediction bias; on the other hand, existing models usually only rely on historical learning states when predicting the next question answering performance of a student, and lack explicit introduction of “target exercise” information, thereby causing the model to be difficult to distinguish between different questions, reducing the prediction specificity and accuracy.

[0005] Therefore, the present application proposes a new knowledge tracing method to overcome the prediction bias caused by the “forgetting effect”. SUMMARY

[0006] The main purpose of the present application is to provide a knowledge tracing method based on a forgetting attention mechanism, which aims to solve the problem of how to overcome the knowledge tracing prediction bias caused by the “forgetting effect”.

[0007] To achieve the above purpose, the present application provides a knowledge tracing method based on a forgetting attention mechanism, which comprises: obtaining a question sequence embedding representation and an answering sequence embedding representation obtained by embedding and representing student learning record data; The question sequence embedding representation is represented as a corresponding similarity weight matrix, and a forgetting factor generated based on relative position coding is introduced to correct the similarity weight; The answer sequence embedding representation is weighted and summed based on the corrected similarity weight to obtain a fusion embedding representation; According to the fusion embedding representation and the question sequence embedding representation, an optimization representation is determined to predict the correctness of the student in the next answering based on the optimization representation.

[0008] Optionally, the forgetting factor generated based on relative position coding is introduced to correct the similarity weight, specifically including: The sequence length of the question sequence embedding representation is obtained, and a relative position embedding matrix is constructed according to the sequence length ; The relative position embedding matrix is subjected to learnable embedding and linear transformation to obtain a forgetting rate : In the formula, is a learnable parameter, is a Sigmoid function, is a relative position index, is the position index of the current question in the sequence, is the position index of the historical question in the sequence; The similarity weight is corrected according to the forgetting rate to obtain the corrected similarity weight : In the formula, is a normalized exponential function.

[0009] Optionally, the question sequence embedding representation includes a knowledge point embedding representation and a question difficulty embedding representation, and the answer sequence embedding representation includes a knowledge point embedding representation and an answer correctness embedding representation.

[0010] Optionally, the expression of the question sequence embedding representation is: In the formula, represents the latent representation of a knowledge point , wherein, is the one-hot encoding of the knowledge point , and is a learnable mapping matrix; represents the difficulty vector of a question ; Indicates the question and knowledge point The interactive variation vector is used to characterize the differences between different questions on the same knowledge point. Represents feature combinations, This indicates element-wise multiplication.

[0011] Optionally, the response sequence embedding representation expression is: In the formula, Representing knowledge points The potential representation, in which, For knowledge points One-hot encoding, It is a learnable mapping matrix; Let represent the response vector, where One-hot encoding for correct or incorrect answers. It is a learnable mapping matrix; Represents feature combinations, This indicates element-wise multiplication.

[0012] Optionally, determining the optimized representation based on the fused embedding representation and the question sequence embedding representation specifically includes: The fusion embedding representation and the embedded representation of the question sequence The optimized representation is obtained by sequentially passing through a fully connected layer, residual connections, and normalization. : In the formula, Represents the normalization function. This represents the residual connection function.

[0013] Optionally, predicting the student's answer result in the next question based on the optimized representation specifically includes: When responding to a prediction instruction, the current input sequence of questions is embedded in the representation. The optimized representation generated at historical moments By concatenating the vectors, the prediction vector is obtained. : Predicting students' accuracy in the next test using a fully connected layer and a Sigmoid activation function. : In the formula, For learnable parameters, This is the Sigmoid function.

[0014] Furthermore, to achieve the above objectives, this application also provides a knowledge tracing model, which includes: The input and embedding representation module is used to obtain the question sequence embedding representation and the answer sequence embedding representation after embedding the student learning record data; The forgetting attention modeling and feature optimization module is used to calculate the similarity weight matrix corresponding to the question sequence embedding representation, and to introduce a forgetting factor generated based on relative position encoding to correct the similarity weight; the answer sequence embedding representation is weighted and summed based on the corrected similarity weight to obtain the fused embedding representation; and the optimized representation is determined based on the fused embedding representation and the question sequence embedding representation. The prediction and output module is used to predict the student's accuracy rate in the next round of questions based on the optimized representation.

[0015] In addition, to achieve the above objectives, this application also provides a computer system comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the knowledge tracking method based on the forgetting attention mechanism as described in any of the preceding claims.

[0016] In addition, to achieve the above objectives, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the knowledge tracking method based on the forgetting attention mechanism as described in any of the preceding claims.

[0017] This application has at least the following beneficial effects: By introducing a forgetting factor based on relative position encoding to simulate the decay of students' knowledge over time, a more realistic answer sequence embedding representation is constructed. The answer sequence embedding representation is then fused with the question sequence embedding representation to make the prediction more targeted and accurate. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating the knowledge tracking method based on the forgetting attention mechanism involved in the embodiments of this application; Figure 2 This is a schematic diagram of the architecture of the knowledge tracking model involved in the embodiments of this application; Figure 3 This is a schematic diagram of the hardware operating environment of the computer system involved in the embodiments of this application.

[0019] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] To better understand the above technical solutions, exemplary embodiments of this disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of this disclosure to those skilled in the art.

[0021] First Embodiment Reference Figure 1 This embodiment provides a knowledge tracking method based on the forgetting attention mechanism, the method including the following steps: Step S10: Obtain the question sequence embedding representation and the answer sequence embedding representation obtained after embedding the student learning record data; In this embodiment, the student learning record data is pre-embedded to obtain question sequence embedding and answer sequence embedding. When the execution subject performs knowledge tracking, it performs an acquisition action to obtain the aforementioned two embedding representations.

[0022] In some alternative implementations, student learning record data is embedded based on the Rasch model.

[0023] Further, and optionally, the student learning record data includes three types of data: knowledge points, exercise difficulty, and correct / incorrect answers. Exercise embedding representation is obtained from knowledge point embedding representation and exercise difficulty embedding representation, and answer sequence embedding representation is obtained from knowledge point embedding representation and correct / incorrect answer embedding representation.

[0024] Further and optionally, the expression representing the question sequence embedding is: In the formula, Representing knowledge points The potential representation, in which, For knowledge points One-hot encoding, It is a learnable mapping matrix; Indicates the topic The difficulty vector; Indicates the question and knowledge point The interactive variation vector is used to characterize the differences between different questions on the same knowledge point. Represents feature combinations, This indicates element-wise multiplication.

[0025] Further and optionally, the response sequence embedding representation expression is: In the formula, Representing knowledge points The potential representation, in which, For knowledge points One-hot encoding, It is a learnable mapping matrix; Let represent the response vector, where One-hot encoding for correct or incorrect answers. It is a learnable mapping matrix; Represents feature combinations, This indicates element-wise multiplication.

[0026] It should be noted that the sequence embedding representation structure obtained through the above method retains the idea in the Rasch model that "question difficulty affects answer performance," while enhancing scalability through vectorization.

[0027] Step S20: Calculate the similarity weight matrix corresponding to the question sequence embedding representation, and introduce a forgetting factor generated based on relative position encoding to correct the similarity weight; After obtaining the two embedding representations, the question sequence embedding representation is selected, and the similarity weight corresponding to each question embedding representation in the question sequence embedding representation is calculated. According to the corresponding order of the question embedding representations in the sequence, the similarity weights are constructed into a similarity weight matrix.

[0028] For example, let the similarity weight be... Then its calculation expression is: in, Representation of the embedding of the question sequence at time With another topic sequence embedding representation Similarity between them This is the scaling factor.

[0029] In this embodiment, considering that students' knowledge retention gradually declines over time in real learning scenarios, and that the models in this system typically rely solely on historical sequence similarity for prediction, failing to effectively model the forgetting process and leading to prediction bias, a forgetting factor based on relative position encoding is introduced in this step to simulate the decay of students' knowledge over time. The aim is to improve the prediction accuracy and interpretability of the knowledge tracing model.

[0030] Further and optionally, the introduction of a forgetting factor generated based on relative position encoding to correct the similarity weights specifically includes: Step S21: Obtain the sequence length of the question sequence embedding representation, and construct a relative position embedding matrix based on the sequence length. ; Step S22, embedding the relative position matrix By performing learnable embeddings and linear transformations, the forgetting rate can be obtained. : In the formula, For learnable parameters, For the Sigmoid function, Relative position index, This represents the index of the question's position in the sequence at the current moment. This represents the position index of the question at a historical moment within the sequence. Step S23, based on the forgetting ratio Similarity weights The similarity weights are then adjusted to obtain the corrected weights. : In the formula, It is a normalized exponential function.

[0031] Step S30: The answer sequence embedding representation is weighted and summed based on the corrected similarity weights to obtain the fused embedding representation; After obtaining the corrected similarity weights, the answer sequence embedding representation is weighted and summed based on the corrected similarity weights to obtain the fused embedding representation.

[0032] For example, the mathematical expression for the fused embedding representation is: Its sequence form is T represents the number of fused embedding representations.

[0033] Step S40: Determine an optimized representation based on the fused embedding representation and the question sequence embedding representation, so as to predict the student's accuracy in the next question based on the optimized representation.

[0034] After obtaining the fused embedding representation, it is combined with the previously obtained question sequence embedding representation for feature integration and optimization.

[0035] Further and optionally, the fusion embedding representation And question sequence embedding representation The optimized representation is obtained by sequentially passing through a fully connected layer, residual connections, and normalization. : In the formula, Represents the normalization function. This represents the residual connection function.

[0036] After obtaining the optimized representation, the optimized representation is used to predict the student's accuracy rate in the next test.

[0037] Furthermore, and optionally, the optimized representation is used for prediction not instantaneously, but rather invoked when a prediction is needed: Upon receiving a prediction instruction from the user, respond to the instruction by explicitly inputting the embedding of the target exercise. and the optimized representation generated at historical moments. By concatenating the vectors, the prediction vector is obtained. : Predicting students' accuracy in the next test using a fully connected layer and a Sigmoid activation function. : In the formula, For learnable parameters, This is the Sigmoid function.

[0038] In the technical solution provided in this embodiment, a forgetting factor based on relative position encoding is introduced to simulate the decay of students' knowledge over time, and a response sequence embedding representation that is more in line with the real learning scenario is constructed. The response sequence embedding representation and the question sequence embedding representation are feature fused to make the prediction more targeted and accurate.

[0039] Verification Implementation Examples To verify the effectiveness of the knowledge tracking method based on the forgetting attention mechanism proposed in this application, the knowledge tracking model (hereinafter referred to as Ours) built based on the forgetting attention mechanism was tested on multiple public datasets in this verification embodiment. Hyperparameter search was used to find the optimal hyperparameter configuration to improve model performance and generalization ability.

[0040] To ensure the fairness of the comparison, all models compared in this verification embodiment (including DKT, DKT+, SAKT, and SimpleKT) underwent hyperparameter search and were tested under their respective optimal configurations, thereby ensuring that the comparison results are of reference value.

[0041] The experimental results are shown in Tables 1 and 2 below: Table 1. AUC Comparison Results

[0042] Table 2. Comparison Results of ACC

[0043] In Tables 1 and 2, Question Level represents the evaluation method that uses the question as the basic prediction object; KC Level represents the evaluation method that uses the knowledge point as the basic prediction object. All-in-One means that when a question is associated with multiple knowledge points, all related knowledge points are predicted simultaneously to avoid the label leakage problem introduced by predicting them one by one.

[0044] AS2009, AL2005, BD2006, NIPS34, Statics2011, and AS2015 represent commonly used public datasets for knowledge tracing. AS2009 is the ASSISTments2009 dataset, AL2005 is the Algebra2005 dataset, BD2006 is the Bridge2006 dataset, and NIPS34 is the Task 3 & 4 dataset from the NeurIPS 2020 Education Challenge. All are widely used for comparing and evaluating knowledge tracing models. POJ is a public dataset for code clone detection tasks, used to evaluate the performance of models in retrieving semantically similar code.

[0045] The results show that the proposed method outperforms existing comparative models in terms of AUC (Area Under Curve) and ACC (Accuracy) on most datasets, indicating that its predictive performance and generalization ability have been further improved. Compared with traditional knowledge tracking models based on attention mechanisms, this application has achieved stable improvements on datasets of different sizes and types, demonstrating that the proposed mechanism can effectively enhance the expressive power of the model.

[0046] The forgetting attention mechanism introduced in this application improves the model's utilization of historical information to some extent, making the prediction results more consistent with students' actual learning process. Experimental results demonstrate good performance, validating its effectiveness and applicability.

[0047] As one implementation scheme, Figure 2 This is a schematic diagram of the hardware operating environment of the computer system involved in the embodiments of this application.

[0048] like Figure 2As shown, the computer system may include: a processor 1001, such as a CPU; a memory 1005; a user interface 1003; a network interface 1004; and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0049] Those skilled in the art will understand that Figure 2 The computer system architecture shown does not constitute a limitation on the computer system and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0050] like Figure 2 As shown, the memory 1005, as a storage medium, may include an operating system, a network communication module, a user interface module, and computer programs. The operating system is a program that manages and controls the hardware and software resources of the computer system, as well as the operation of the computer programs and other software or programs.

[0051] exist Figure 2 In the computer system shown, the user interface 1003 is mainly used to connect to the terminal and communicate with the terminal; the network interface 1004 is mainly used to communicate with the backend server; and the processor 1001 can be used to call the computer program stored in the memory 1005.

[0052] In this embodiment, the computer system includes: a memory 1005, a processor 1001, and a computer program stored in the memory and executable on the processor, wherein: When processor 1001 calls a computer program stored in memory 1005, it performs the following operations: Obtain the question sequence embedding representation and the answer sequence embedding representation after embedding the student learning record data; Calculate the similarity weight matrix corresponding to the embedding representation of the question sequence, and introduce a forgetting factor generated based on relative position encoding to correct the similarity weight; The answer sequence embedding representation is weighted and summed based on the corrected similarity weights to obtain the fused embedding representation; Based on the fusion embedding representation and the question sequence embedding representation, an optimized representation is determined to predict the student's accuracy rate in the next question based on the optimized representation.

[0053] In addition, refer to Figure 3 This embodiment also proposes a knowledge tracing model, which includes: The input and embedding representation module 100 is used to obtain the question sequence embedding representation and the answer sequence embedding representation after embedding the student learning record data; The forgetting attention modeling and feature optimization module 200 is used to calculate the similarity weight matrix corresponding to the question sequence embedding representation, and introduce a forgetting factor generated based on relative position encoding to correct the similarity weight; the answer sequence embedding representation is weighted and summed based on the corrected similarity weight to obtain the fused embedding representation; and the optimized representation is determined based on the fused embedding representation and the question sequence embedding representation. The prediction and output module 300 is used to predict the student's accuracy rate in the next round of answering questions based on the optimized representation.

[0054] Furthermore, and optionally, the knowledge tracing model may also perform the following operations: Obtain the sequence length of the question sequence embedding representation, and construct a relative position embedding matrix based on the sequence length. ; Embedding matrix of relative positions By performing learnable embeddings and linear transformations, the forgetting rate can be obtained. : In the formula, For learnable parameters, For the Sigmoid function, Relative position index, This represents the index of the question's position in the sequence at the current moment. This represents the position index of the question at a historical moment within the sequence. According to the forgetting rate Similarity weights The similarity weights are then adjusted to obtain the corrected weights. : In the formula, It is a normalized exponential function.

[0055] Furthermore, and optionally, the knowledge tracing model may also perform the following operations: The question sequence embedding representation includes knowledge point embedding representation and question difficulty embedding representation, and the answer sequence embedding representation includes knowledge point embedding representation and correct / incorrect answer embedding representation.

[0056] Furthermore, and optionally, the knowledge tracing model may also perform the following operations: The expression representing the embedding of the question sequence is: In the formula, Representing knowledge points The potential representation, in which, For knowledge points One-hot encoding, It is a learnable mapping matrix; Indicates the topic The difficulty vector; Indicates the question and knowledge point The interactive variation vector is used to characterize the differences between different questions on the same knowledge point. Represents feature combinations, This indicates element-wise multiplication.

[0057] Furthermore, and optionally, the knowledge tracing model may also perform the following operations: The embedded representation of the response sequence is: In the formula, Representing knowledge points The potential representation, in which, For knowledge points One-hot encoding, It is a learnable mapping matrix; Let represent the response vector, where One-hot encoding for correct or incorrect answers. It is a learnable mapping matrix; Represents feature combinations, This indicates element-wise multiplication.

[0058] Furthermore, and optionally, the knowledge tracing model may also perform the following operations: The fusion embedding representation and the embedded representation of the question sequence The optimized representation is obtained by sequentially passing through a fully connected layer, residual connections, and normalization. : In the formula, Represents the normalization function. This represents the residual connection function.

[0059] Furthermore, and optionally, the knowledge tracing model may also perform the following operations: When responding to a prediction instruction, the current input sequence of questions is embedded in the representation. The optimized representation generated at historical moments By concatenating the vectors, the prediction vector is obtained. : Predicting students' accuracy in the next test using a fully connected layer and a Sigmoid activation function. : In the formula, For learnable parameters, This is the Sigmoid function.

[0060] Furthermore, those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in a computer system to implement the process steps of the embodiments of the above methods.

[0061] Therefore, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the various steps of the knowledge tracking method based on the forgetting attention mechanism as described in the above embodiments.

[0062] The computer-readable storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0063] It should be noted that, since the storage medium provided in the embodiments of this application is the storage medium used to implement the methods of the embodiments of this application, those skilled in the art can understand the specific structure and variations of the storage medium based on the methods described in the embodiments of this application, and therefore will not be repeated here. All storage media used in the methods of the embodiments of this application fall within the scope of protection of this application.

[0064] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0065] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0066] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0067] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0068] It should be noted that any reference signs placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. This application can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0069] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0070] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A knowledge tracing method based on a forgetting attention mechanism, characterized in that, The method comprises the following steps: obtaining a question sequence embedding representation and an answer sequence embedding representation obtained after embedding representation of student learning record data is performed; calculating a similarity weight matrix corresponding to the question sequence embedding representation, and introducing a forgetting factor generated based on relative position coding to correct the similarity weight; performing weighted summation on the answer sequence embedding representation based on the corrected similarity weight to obtain a fusion embedding representation; determining an optimization representation based on the fusion embedding representation and the question sequence embedding representation, so as to predict the correctness rate of the student in the next answering based on the optimization representation. 2.The knowledge tracing method based on the forgetting attention mechanism of claim 1, wherein, The introduction of the forgetting factor generated based on the relative position coding to correct the similarity weight specifically comprises: obtaining a sequence length of the question sequence embedding representation, constructing a relative position embedding matrix according to the sequence length ; to the relative position embedding matrix performing a learnable embedding and a linear transformation, resulting in a forgetting ratio : ； In the formula, is a learnable parameter, is a Sigmoid function, is a relative position index, is a position index of the current moment question in the sequence, is a position index of the historical moment question in the sequence; According to the forgetting ratio The similarity weight The similarity weight is modified to obtain a modified similarity weight : ； In the formula, is a normalized exponential function. 3.The knowledge tracing method based on the forgetting attention mechanism of claim 1, wherein, The question sequence embedding representation comprises a knowledge point embedding representation and a question difficulty embedding representation, and the answer sequence embedding representation comprises a knowledge point embedding representation and an answer correctness embedding representation. 4.The knowledge tracing method based on the forgetting attention mechanism of claim 3, wherein, The expression of the question sequence embedding representation is: ； wherein, represents a potential representation of a knowledge point , wherein, is a one-hot encoding of a knowledge point , is a learnable mapping matrix; represents a difficulty vector of a question ; represents an interaction vector of a question and a knowledge point , used to depict the difference of different questions under the same knowledge point, represents a feature combination, represents an element-wise multiplication. 5.The knowledge tracing method based on the forgetting attention mechanism according to claim 3 or 4, wherein, The expression of the answer sequence embedding representation is: ； wherein, represents a potential representation of a knowledge point , wherein, is a one-hot encoding of the knowledge point , and is a learnable mapping matrix; represents an answer vector, wherein is a one-hot encoding of the correctness of the answer, is a learnable mapping matrix; represents a feature combination, represents an element-wise multiplication. 6.The knowledge tracing method based on the forgetting attention mechanism of claim 1, wherein, The determination of the optimization representation based on the fusion embedding representation and the question sequence embedding representation specifically comprises: said fusion embedding representation and said title sequence embedding representation , sequentially through a fully connected layer, a residual connection, and a normalization process, to obtain the optimized representation : ； wherein denotes a normalization function, denotes a residual connection function. 7.The knowledge tracing method based on the forgetting attention mechanism according to claim 1 or 6, wherein, The prediction of the answering result of the student in the next answering based on the optimization representation specifically comprises: In response to the prediction instruction, embedding the current input question sequence representation with the optimization representation generated at the historical time concatenating to obtain a prediction vector : ； Predicting the accuracy of the student in the next question by a fully connected layer with a sigmoid activation function : ； In the formula, is a learnable parameter, is a sigmoid function.

8. A knowledge tracking model, characterized by, The knowledge tracking model comprises: an input and embedding representation module, configured to obtain a question sequence embedding representation and an answer sequence embedding representation obtained after embedding representation of student learning record data is performed; a forgetting attention modeling and feature optimization module, configured to calculate a similarity weight matrix corresponding to the question sequence embedding representation, and introduce a forgetting factor generated based on relative position coding to correct the similarity weight; perform weighted summation on the answer sequence embedding representation based on the corrected similarity weight to obtain a fusion embedding representation; and determine an optimization representation based on the fusion embedding representation and the question sequence embedding representation; a prediction and output module, configured to predict the correctness rate of the student in the next answering based on the optimization representation.

9. A computer system, characterized by The computer system comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program, when executed by the processor, implements the steps of the knowledge tracking method based on the forgetting attention mechanism according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program, when executed by the processor, implements the steps of the knowledge tracking method based on the forgetting attention mechanism according to any one of claims 1 to 7.

Images