Knowledge tracking method and system based on double-state joint interaction mechanism

Abstract

The invention provides a novel knowledge tracking method and system based on a two-state joint interaction mechanism. The method comprises the following steps: (1) modeling a student knowledge state; (2) modeling a student psychological state to be tested; (3) constructing a static joint interaction mechanism; and (4) constructing a reinforcement learning enhanced dynamic joint interaction mechanism. Technical methods such as a multi-attention mechanism, reinforcement learning and the like are utilized, the psychological state to be tested of a student is integrated into a deep learning-based knowledge tracking model taking a knowledge state as a core, and a complex interaction effect between the knowledge state and the psychological state to be tested is constructed; the objective of the invention is to improve prediction accuracy and interpretability of an existing knowledge tracking model based on deep learning.

Description

Technical Field

[0001] The present invention relates to the technical field of computer data processing, and in particular to a knowledge tracking method and system based on a dual-state joint interaction mechanism. Background Art

[0002] Personalized education in the intelligent era requires providing students with personalized, intelligent and sustainable educational services. As a key technology for achieving personalized education, knowledge tracking aims to evaluate and track students' knowledge status based on their historical learning performance, thereby predicting their performance in future exercises. Knowledge tracking has significant advantages in tracking students' learning progress and optimizing teachers' teaching strategies, making it widely used in learning path planning, learning resource recommendation, and machine teaching.

[0003] The knowledge tracing model based on deep learning has become a research hotspot in the field of knowledge tracing due to its superior prediction performance. According to the neural network structure adopted, it can be roughly divided into the following categories: models based on recurrent neural networks, memory-enhanced networks, and attention networks. Deep Knowledge Tracing (DKT), as a representative model based on recurrent neural networks, is the first model to use deep learning technology in the field of knowledge tracing. It uses recurrent neural networks to model students' knowledge status; Dynamic Key-Value Memory Network (DKVMN) is a classic model based on memory-enhanced networks. It introduces static key matrices and dynamic value matrices to store the representation of knowledge concepts and the degree of students' mastery of knowledge concepts, respectively, and then fine-tunes the students' knowledge status; Self-Attentive Knowledge Tracing (SAKT) is the first model to use an attention network. It learns the correlation between knowledge concepts through the self-attention mechanism, which effectively alleviates the problem of data sparsity. Although most knowledge tracing models based on deep learning have achieved good prediction performance, they still have the following shortcomings: 1. The knowledge tracking model based on deep learning attributes students’ performance only to their knowledge status, while ignoring the psychological factors that affect students’ performance, resulting in the model’s portrayal of knowledge status being inconsistent with students’ actual situation; 2. Due to the complexity and opacity of the internal structure of deep neural networks, knowledge tracking models based on deep learning generally have poor interpretability, making it difficult to conduct attribution analysis and trace the performance of students.

[0004] To solve the above problems, the present invention proposes a knowledge tracking method based on a two-state joint interaction mechanism. Summary of the invention

[0005] The main purpose of the present invention is to provide a knowledge tracking method and system based on a two-state joint interaction mechanism to solve the above technical problems.

[0006] To achieve the above object, the present invention provides a knowledge tracking method based on a two-state joint interaction mechanism, comprising the steps of: S1, knowledge status modeling, includes: extracting the preset elements in the student learning process to form learning features, and using the learning features as input to the existing deep learning-based knowledge tracking model to model the student knowledge status; S2, test-taking psychological state modeling, including: capturing the high-order relationship between practice and answering behavior characteristics through a multi-head attention mechanism to model students' test-taking psychological state; S3, build a static joint interaction mechanism to establish student Correct answer exercise Probability prediction algorithms; S4, build a dynamic joint interaction mechanism enhanced by reinforcement learning, including: through the reinforcement learning Q-learning algorithm, analyze the real-time feedback of students in different exercises to dynamically adjust the prediction weights of knowledge status and test-taking psychological state to find the optimal strategy, so as to obtain the final probability prediction algorithm.

[0007] Furthermore, the step S1 includes: Step S11, construct learning features according to the following formula , , , in, for The enhancement vector, For practice The embedding vector of For the concept of knowledge The embedding vector of is vector concatenation, and is the training parameter, For Students right Response , and for The training parameters are and for The training parameters when Step S12: learning features As the input of the deep learning-based knowledge tracing model, we obtain exist Knowledge level .

[0008] Furthermore, the step S2 includes: Step S20, the students are practicing The answering behavior feature set on Expressed as a vector, if It is a categorical feature and is represented as a one-hot vector. If it is a numerical feature, it is expressed as a scalar, and the feature is further obtained. Vector representation of ,Will Embedded into a low-dimensional continuous space to obtain a low-dimensional feature vector : ,in, It is a feature The embedding matrix of Step S21, calculate the attention heads according to the following formula The corresponding query vector is , key vector and the value vector : ,in, , , Represents the query vector, key vector, and value vector in the attention head respectively. The projection matrix under Step S22, calculate the attention head Down, Similarity , ,in, Indicates that the inner product is used to calculate the attention head Down similarity; Step S23, by combining all the answering behavior features to represent the attention head The relationship between the following exercises and the characteristics of answering behavior : .

[0009] Furthermore, the step S23 further includes: Collect high-order relationships learned in different subspaces : ; They represent the high-order relationships between the characteristics of practice and answering behaviors in different subspaces; Add in network : ,in, is the activation function, is the projection matrix; The output of the previous layer is used as the input of the next layer to stack multiple multi-head attention layers to capture richer high-order information. Finally, the nonlinear projection model is used to model the student exist Test-taking psychology : ,in, is the logistic sigmoid function, is the projection vector, For deviation.

[0010] Furthermore, in step S3, the step of constructing a static joint interaction mechanism includes: , , , , in, and They represent the static prediction weights of knowledge state and test-taking psychological state in predicting student performance, represents the interaction coefficient of test-taking psychological state on knowledge state, Represents the interaction coefficient between knowledge status and test-taking psychological state.

[0011] Furthermore, in step S4, the step of constructing a dynamic joint interaction mechanism enhanced by reinforcement learning includes: S41, construct the state space S for students The state space of , ,in, for right Response, is the dynamic prediction weight of the knowledge state at the previous moment in the prediction of student performance, then the test-taking psychological state is The prediction weight at time is ; S42, construct the action space A, which is the set of all actions that the agent can take at each moment; action ,action Indicates that at present Status at all times Executed , The value is a number of discrete values ​​ranging from 0 to 1 with an interval of 0.1; S43, construct state transfer function , In Status Take action back, The current state Transfer to , ; S44, construct a reward function R, which is used to define the immediate reward obtained by the agent after taking a certain action in a certain state; the immediate reward , instant rewards For the status Take action Instant rewards received: , .

[0012] Furthermore, in step S4, the Q-learning algorithm is used to learn the real-time feedback of students on different exercises and dynamically adjust the weights of the two states to find the optimal strategy, thereby obtaining the final probability The steps of the prediction algorithm include: S45, using the reinforcement learning Q-learning algorithm to find the optimal strategy , so that the model is in the current state When, according to the strategy Take Action The expected reward accumulated during the whole process Maximize as follows: , , , in, is the discount factor, which determines the impact of future rewards on current The impact weight of the value; Indicates in status The result obtained after taking all possible actions The maximum value among the values; is the learning rate, which is used to control the update ratio of new and old information.

[0013] The present invention also provides a knowledge tracking system based on a two-state joint interaction mechanism, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the system implements the steps of the knowledge tracking method based on a two-state joint interaction mechanism as described in any one of the above items.

[0014] The present invention also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the steps of the knowledge tracking method based on the two-state joint interaction mechanism as described in any one of the above items are implemented: This invention utilizes multi-head attention mechanism, reinforcement learning and other technical methods to integrate students' test-taking psychological state into a knowledge tracking model based on deep learning with knowledge state as the core, and constructs a complex interaction between knowledge state and test-taking psychological state, aiming to improve the prediction accuracy and interpretability of existing knowledge tracking models based on deep learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings are part of the present invention and are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but do not constitute an improper limitation of the present invention. Obviously, the drawings described below are only some embodiments. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the accompanying drawings: Figure 1 Schematic diagram of the flow of a knowledge tracking method based on a two-state joint interaction mechanism in one embodiment of the present invention.

[0016] Figure 2 The figure is a schematic diagram of the hardware structure for running the knowledge tracking method based on the two-state joint interaction mechanism in one embodiment of the present invention.

[0017] 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

[0018] The following is a clear and complete description of the technical problems solved by the embodiments of the present invention, the technical solutions adopted, and the technical effects achieved in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other equivalent or obviously modified embodiments obtained by ordinary technicians in this field without creative work fall within the scope of protection of the present invention. The embodiments of the present invention can be concretized in a variety of different ways as defined and covered in the claims.

[0019] It should be noted that in the following description, many specific details are given for ease of understanding, but it is obvious that the present invention can be implemented without these specific details.

[0020] It should be noted that, in the absence of clear limitation or conflict, the various embodiments of the present invention and the technical features therein can be combined with each other to form a technical solution.

[0021] Please refer to Figure 1 ,The present invention proposes a knowledge tracking method based on a two-state joint interaction mechanism, including steps S1-S4.

[0022] S1, knowledge status modeling, includes: extracting preset elements in the student learning process to form learning features, and using the learning features as input to the existing deep learning-based knowledge tracking model to model the student knowledge status.

[0023] Student learning interaction includes the following elements: (1) Student ; (2) Exercises done ; (3) Knowledge concepts examined ; (4) right Response , combining the above elements to comprehensively construct student learning characteristics .

[0024] For features , according to the binary variable The values ​​of are respectively designed to design the learning features corresponding to the correct response and the wrong response .

[0025] Furthermore, the step S1 includes: Step S11, construct learning features according to the following formula , , , in, for The enhancement vector, For practice The embedding vector of For the concept of knowledge The embedding vector of is vector concatenation, and is the training parameter, For Students right Response , and for The training parameters are and for The training parameters when Step S12: learning features As the input of the deep learning-based knowledge tracing model, we obtain exist Knowledge level .

[0026] S2, test-taking psychological state modeling, includes: capturing the high-order relationship between practice and answering behavior characteristics through a multi-head attention mechanism to model students' test-taking psychological state.

[0027] Furthermore, the step S2 includes: Step S20, the students are practicing The answering behavior feature set on Expressed as a vector, if It is a categorical feature and is represented as a one-hot vector. If it is a numerical feature, it is expressed as a scalar, and the feature is further obtained. Vector representation of ,Will Embedded into a low-dimensional continuous space to obtain a low-dimensional feature vector : ,in, It is a feature The embedding matrix of Step S21, calculate the attention heads according to the following formula The corresponding query vector is , key vector and the value vector : in, , , Represents the query vector, key vector, and value vector in the attention head respectively. The projection matrix under Step S22, calculate the attention head Down, Similarity , ,in, Indicates that the inner product is used to calculate the attention head Down similarity; Step S23, by combining all the answering behavior features to represent the attention head The relationship between the following exercises and the characteristics of answering behavior : .

[0028] because yes With all the answering behavior features (in the attention head Therefore, it represents the high-order relationship between the practice and answering behavior characteristics learned by the model. Further collect the high-order relationships learned in different subspaces .

[0029] Furthermore, the step S23 further includes: Collect high-order relationships learned in different subspaces : , They represent the high-order relationships between the characteristics of practice and answering behaviors in different subspaces; Add in network : ,in, is the activation function, is the projection matrix; The output of the previous layer is used as the input of the next layer to stack multiple multi-head attention layers to capture richer high-order information. Finally, the nonlinear projection model is used to model the student exist Test-taking psychology : ,in, is the logistic sigmoid function, is the projection vector, For deviation.

[0030] S3, build a static joint interaction mechanism to establish student Correct answer exercise Probability prediction algorithm.

[0031] In the static joint interaction mechanism, students’ performance is determined by both their knowledge state and their test-taking psychological state. Correct answer exercise Probability Depend on exist Knowledge level and test-taking psychology Joint decision.

[0032] The construction of the static joint interaction mechanism in step S3 is to accurately quantify the complex interactive relationship between the knowledge state and the test-taking psychological state, thereby introducing the interaction coefficient and . represents the interaction coefficient of test-taking psychological state on knowledge state, Represents the interaction coefficient between knowledge status and test-taking psychological state.

[0033] Furthermore, in step S3, the step of constructing a static joint interaction mechanism includes: , , , , in, and They represent the static prediction weights of knowledge state and test-taking psychological state in predicting student performance, represents the interaction coefficient of test-taking psychological state on knowledge state, Represents the interaction coefficient between knowledge status and test-taking psychological state.

[0034] S4, build a dynamic joint interaction mechanism enhanced by reinforcement learning, including: through the reinforcement learning Q-learning algorithm, analyze the real-time feedback of students in different exercises to dynamically adjust the prediction weights of knowledge status and test-taking psychological state to find the optimal strategy, so as to obtain the final probability prediction algorithm.

[0035] Furthermore, in step S4, the step of constructing a dynamic joint interaction mechanism enhanced by reinforcement learning includes: S41, construct the state space S for students The state space of , ,in, for right Response, is the dynamic prediction weight of the knowledge state at the previous moment in the prediction of student performance, then the test-taking psychological state is The prediction weight at time is ; In reinforcement learning, the state space S describes the information the agent receives in the environment; S42, construct the action space A, which is the set of all actions that the agent can take at each moment; action ,action Indicates that at present Status at all times Executed , The value is a number of discrete values ​​ranging from 0 to 1 with an interval of 0.1; S43, construct state transfer function , In Status Take action back, The current state Transfer to , ; S44, construct a reward function R, which is used to define the immediate reward obtained by the agent after taking a certain action in a certain state; the immediate reward , instant rewards For the status Take action Instant rewards received: , .

[0036] Furthermore, in step S4, the weights of the two states are dynamically adjusted by learning the real-time feedback of students on different exercises through reinforcement learning Q-learning algorithm to find the optimal strategy, thereby obtaining the final probability The steps of the prediction algorithm include: S45, using the reinforcement learning Q-learning algorithm to find the optimal strategy , so that the model is in the current state When the strategy Take Action The expected reward accumulated during the whole process Maximize as follows: , , , in, is the discount factor, which determines the impact of future rewards on current The impact weight of the value; Indicates in status The result obtained after taking all possible actions The maximum value among the values; is the learning rate, which is used to control the update ratio of new and old information.

[0037] This invention utilizes multi-head attention mechanism, reinforcement learning and other technical methods to integrate students' test-taking psychological state into a knowledge tracking model based on deep learning with knowledge state as the core, and constructs a complex interaction between knowledge state and test-taking psychological state, aiming to improve the prediction accuracy and interpretability of existing knowledge tracking models based on deep learning.

[0038] The present invention also provides a knowledge tracking system based on a two-state joint interaction mechanism, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the knowledge tracking method based on a two-state joint interaction mechanism as described in any one of the above items when executing the computer program.

[0039] The present invention also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the steps of the knowledge tracking method based on the two-state joint interaction mechanism as described in any one of the above items are implemented.

[0040] Figure 2 FIG. 1 is a schematic diagram of the hardware structure for running a knowledge tracking method based on a two-state joint interaction mechanism provided by an embodiment of the present invention. Figure 2 As shown, the embodiment / computer 6 includes: a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and executable on the processor 60, such as a program for executing a knowledge tracking method based on a two-state joint interaction mechanism. When the processor 60 executes the computer program 62, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 60 executes the computer program 62, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0041] Exemplarily, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 62 in the computer 6.

[0042] The computer 6 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will appreciate that Figure 2 It is only an example of computer 6 and does not constitute a limitation of computer 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer 6 may also include input and output devices, network access devices, buses, etc.

[0043] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0044] The memory 61 may be an internal storage unit of the computer 6, such as a hard disk or memory of the computer 6. The memory 61 may also be an external storage device of the terminal device / computer 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device. Further, the memory 61 may also include both an internal storage unit of the computer 6 and an external storage device. The memory 61 is used to store the computer program and other programs and data required by the terminal device. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0045] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0046] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0047] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0048] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0049] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0050] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0051] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0052] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A knowledge tracking method based on a two-state joint interaction mechanism, characterized in that: Includes steps: S1, knowledge status modeling, includes: extracting the preset elements in the student learning process to form learning features, and using the learning features as input to the existing deep learning-based knowledge tracking model to model the student knowledge status; S2, test-taking psychological state modeling, including: capturing the high-order relationship between practice and answering behavior characteristics through a multi-head attention mechanism to model students' test-taking psychological state; S3, build a static joint interaction mechanism to establish student Correct answer exercise Probability prediction algorithms; S4, build a dynamic joint interaction mechanism enhanced by reinforcement learning, including: through the reinforcement learning Q-learning algorithm, analyze the real-time feedback of students in different exercises to dynamically adjust the prediction weights of knowledge status and test-taking psychological state to find the optimal strategy, so as to obtain the final probability prediction algorithm.

2. The knowledge tracking method based on the dual-state joint interaction mechanism according to claim 1 is characterized in that: The step S1 comprises: Step S11, construct learning features according to the following formula , ， ， in, for The enhancement vector, For practice The embedding vector of For the concept of knowledge The embedding vector of is vector concatenation, and is the training parameter, For Students right Response , and for The training parameters are and for The training parameters when Step S12: learning features As the input of the deep learning-based knowledge tracing model, we obtain exist Knowledge level .

3. The knowledge tracking method based on the dual-state joint interaction mechanism according to claim 2 is characterized in that: The step S2 comprises: Step S20, the students are practicing The answering behavior feature set on Expressed as a vector, if Belonging to the classification feature is represented as a one-hot vector. If it is a numerical feature, it is expressed as a scalar, and the feature is further obtained. Vector representation of ,Will Embedded into a low-dimensional continuous space to obtain a low-dimensional feature vector : ,in, It is a feature The embedding matrix of Step S21, calculate the attention heads according to the following formula The corresponding query vector is , key vector and the value vector : in, , , Represents the query vector, key vector, and value vector in the attention head respectively. The projection matrix under Step S22, calculate the attention head Down, Similarity , ,in, Indicates that the inner product is used to calculate the attention head Down similarity; Step S23, by combining all the answering behavior features to represent the attention head The relationship between the following exercises and the characteristics of answering behavior : .

4. The knowledge tracking method based on the dual-state joint interaction mechanism according to claim 3 is characterized in that: The step S23 further comprises: Collect high-order relationships learned in different subspaces : , They represent the high-order relationships between the characteristics of practice and answering behaviors in different subspaces; Add in network : ,in, is the activation function, is the projection matrix; The output of the previous layer is used as the input of the next layer to stack multiple multi-head attention layers to capture richer high-order information. Finally, the nonlinear projection model is used to model the student exist Test-taking psychology : ,in, is the logistic sigmoid function, is the projection vector, For deviation.

5. The knowledge tracking method based on the dual-state joint interaction mechanism according to claim 4 is characterized in that: In step S3, the step of constructing a static joint interaction mechanism includes: ， ， ， ， in, and They represent the static prediction weights of knowledge state and test-taking psychological state in predicting student performance, represents the interaction coefficient of test-taking psychological state on knowledge state, Represents the interaction coefficient between knowledge status and test-taking psychological state.

6. The knowledge tracking method based on the dual-state joint interaction mechanism according to claim 5 is characterized in that: In step S4, the step of constructing a dynamic joint interaction mechanism enhanced by reinforcement learning includes: S41, construct the state space S for students The state space of , ,in, for right Response, is the dynamic prediction weight of the knowledge state at the previous moment in the prediction of student performance, then the test-taking psychological state is The prediction weight at time is ; S42, construct the action space A, which is the set of all actions that the agent can take at each moment; action ,action Indicates that at present Status at all times Executed , The value is a number of discrete values ​​ranging from 0 to 1 with an interval of 0.1; S43, construct state transfer function , In Status Take action back, The current state Transfer to , ; S44, construct a reward function R, which is used to define the immediate reward obtained by the agent after taking a certain action in a certain state; the immediate reward , instant rewards For the status Take action Instant rewards received: , .

7. The knowledge tracking method based on the dual-state joint interaction mechanism according to claim 6 is characterized in that: In step S4, the Q-learning algorithm is used to learn the real-time feedback of students on different exercises and dynamically adjust the weights of the two states to find the optimal strategy, thereby obtaining the final probability The steps of the prediction algorithm include: S45, using the reinforcement learning Q-learning algorithm to find the optimal strategy , so that the model is in the current state When, according to the strategy Take Action The expected reward accumulated during the whole process Maximize as follows: ， ， ， in, is the discount factor, which determines the impact of future rewards on current The impact weight of the value; Indicates in status The result obtained after taking all possible actions The maximum value among the values; is the learning rate, which is used to control the update ratio of new and old information.

8. A knowledge tracking system based on a two-state joint interaction mechanism, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the knowledge tracking method based on the two-state joint interaction mechanism are implemented as described in any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the knowledge tracking method based on a two-state joint interaction mechanism as described in any one of claims 1 to 7 are implemented.

Images