A knowledge tracking depth debiasing method, electronic device and storage medium

Abstract

The application discloses a knowledge tracking deep debiasing method, an electronic device and a storage medium, and steps of the method comprise the following steps: 1, data acquisition; 2, building a knowledge tracking network, a counter-embedding generation network and a counter-knowledge tracking network; 3, alternately training the knowledge tracking network, the counter-embedding generation network and the counter-knowledge tracking network to obtain an optimal knowledge tracking model. Through combination of counter-data enhancement and loss reweighting, the application generates counter-deviation data, and reduces a learning rate of a deviation sample in a model training process, effectively avoids that the model uses an association between a deviation attribute and a label as a prediction shortcut, thereby relieving a deviation problem of a deep knowledge tracking model, and more accurate evaluation of a student knowledge state is realized.

Description

Technical Field

[0001] The present invention belongs to the field of data mining and relates to knowledge tracking and model debiasing technology, specifically a knowledge tracking deep debiasing method, electronic equipment and storage medium. Background Art

[0002] Knowledge tracing technology is a fundamental task in intelligent education and personalized learning. Its goal is to predict a student's future performance given their past practice history. Thanks to the rapid development of deep learning technology and the vast amount of data accumulated by online learning platforms, deep knowledge tracing models have achieved tremendous success. However, existing advanced deep knowledge tracing models have neglected the issue of bias. Biased examples in datasets associate biased attributes (the accuracy of students' past answers and target exercises) with labels. Models trained on biased datasets learn and amplify spurious associations between biased attributes and labels, leading to bias in the model. Because the biased attributes of biased examples are highly correlated with labels, the model can exploit this association to make accurate predictions for biased examples. Therefore, evaluating knowledge tracing models using biased datasets does not truly reflect the model's ability to extract student knowledge. Therefore, it is crucial to construct unbiased datasets for unbiased evaluation of existing models and to design a debiasing training method to improve the model's ability to combat bias when trained solely on biased datasets. Summary of the Invention

[0003] In order to address the deficiencies of the above-mentioned prior art, the present invention proposes a knowledge tracking deep debiasing method, electronic device and storage medium, in order to alleviate the bias problem of the deep knowledge tracking model, thereby achieving a more accurate assessment of students' knowledge status.

[0004] In order to achieve the above-mentioned object, the present invention adopts the following technical solutions:

[0005] The invention provides a method for deep debiasing of knowledge tracing, which comprises the following steps:

[0006] Step 1: Data collection;

[0007] Get the student collection , where s n represents the nth student, N is the number of students;

[0008] Get the exercise set , where q i represents the i-th exercise, I is the number of exercises;

[0009] Let the nth student s n For the i-th exercise q i The answer is rn,i , if r n,i =1, indicating the answer is correct, if r n,i =0, indicating an incorrect answer;

[0010] Define the nth student s n The previous T historical answer records are H n , T = [ ( q n , 1 , r n , 1 ) , ( q n , 2 , r n , 2 ) , … , ( q n , t , r n , t ) , … , ( q n , T , r n , T ) ] ,in, represents the nth student s n The tth historical answer record, q n,t represents the nth student s n The tth history exercise, r n,t represents the nth student s n The t-th historical answer result of , T is the n-th student s n Number of historical questions answered;

[0011] Define the nth student s n The tth answer sample is , where H n,t-1 represents the nth student s n The previous t-1 historical answer records, For the nth student s n When answering the history question for the tth time, the correct rate of the most recent w answers is season ; For the nth student s n The tth history exercise q n,t The correct rate of all students in the previous T historical answer records, when q n,t The number of times it appears in the previous T historical answer records of all students is less than L times, so ;

[0012] like Meet the conditions , then Defined as the historical answer performance bias guide sample, denoted as ;

[0013] like Meet the conditions , then Defined as a historical answer performance deviation conflict sample, denoted as ;

[0014] like Meet the conditions , then Defined as the guide sample of exercise answer deviation, denoted as ;

[0015] like Meet the conditions , then It is defined as the conflict sample of the exercise answer deviation, recorded as ; Among them, a th is the threshold for judging sample deviation;

[0016] The unbiased set of historical answer performance is constructed from the conflicting samples of historical answer performance of all students, which is recorded as ;

[0017] The unbiased set of exercise answers is constructed from the conflicting samples of all students’ exercise answers, which is recorded as ;

[0018] Step 2: Build a knowledge tracking network, adversarial embedding generation network, and adversarial knowledge tracking network;

[0019] Step 2.1: The knowledge tracking network includes: embedding layer E, knowledge state extraction layer and prediction layer , and used for the nth student s n Exercises for Sequence Data H n,T Process and get the nth student s n The probability of answering the next exercise correctly, thereby constructing the loss of the knowledge tracking network , used to train the embedding layer E and the knowledge state extraction layer and prediction layer , and get the initially trained embedding layer E 1 , the initially trained knowledge state extraction layer and the initially trained prediction layer ;

[0020] Step 2.2, the embedded layer E trained initially 1 , the initially trained knowledge state extraction layer and the initially trained prediction layer Construct an adversarial embedding generation network and use it to train the nth student s n Exercises for Sequence Data H n,T Process and get the nth student s n The probability of correct adversarial generation in the next answer exercise is used to construct the loss of the adversarial embedding generation network , used to train the initially trained embedding layer E 1 , and get the retrained embedding layer E 2 ;

[0021] Step 2.3, the embedded layer E is trained again 2 , the initially trained knowledge state extraction layer and the initially trained prediction layer Construct an adversarial knowledge tracking network and use it to track the nth student s n Exercises for Sequence Data H n,T Process and get the nth student s n The correct adversarial prediction probability of the next answer exercise is constructed to construct the loss of the adversarial knowledge tracking network , used to train the initially trained knowledge state extraction layer and the initially trained prediction layer , and obtain the retrained knowledge state extraction layer and the retrained prediction layer ;

[0022] Step 3: E 1 、 and Assign corresponding values ​​to E, and Finally, the knowledge tracking network, adversarial embedding generation network and adversarial knowledge tracking network are trained alternately according to the process from step 2.1 to step 2.3 to continuously adjust the network parameters until the prediction accuracy of the knowledge tracking network no longer improves, thereby obtaining the optimal knowledge tracking model and using it to process the unbiased set of historical answer performance and the unbiased set of exercise answers to obtain the correct prediction results of students' exercise answers after debiasing.

[0023] The knowledge tracing deep debiasing method of the present invention is also characterized in that step 2.1 includes:

[0024] Step 2.1.1, the embedding layer E is used for the nth student s n Exercises for Sequence Data H n,T Process and output the nth student s n The embedded representation sequence of the second to Tth answer questions E M B n q = [ e m b n , 2 q , e m b n , 3 q , … , e m b n , t q , … , e m b n , T q ] and the nth student s n The embedded representation sequence of the interactive behavior of answering exercises before T-1 times E M B n q r = [ e m b n , 1 q r , e m b n , 2 q r , … , e m b n , t q r , … , e m b n , T − 1 q r ] ;in, represents the nth student s n Answer exercise q for the tth time n,t Embedded representation of represents the nth student s n Answer exercise q for the tth time n,t and its answer results n,t Embedded representation of

[0025] The knowledge state extraction layer right Process and output the nth student s n The knowledge state representation sequence when answering the exercises from the 2nd to the Tth time E M B n h = [ e m b n , 2 h , e m b n , 3 h , … , e m b n , t h , … , e m b n , T h ] ;in, represents the nth student s n The knowledge status representation when answering the exercise for the tth time;

[0026] The prediction layer right and Process and output the nth student s n The probability of answering the next question correctly [ r ^ n , 2 , r ^ n , 3 , … , r ^ n , t , … , r ^ n , T ] ;in, represents the nth student s n The probability of answering the exercise correctly the tth time;

[0027] Step 2.1.2, based on the degree of sample deviation, use formula (1) to calculate the sample The loss weight ;

[0028] (1)

[0029] In formula (1), if To guide the sample for historical performance bias, use formula (2) to calculate Unbiased loss weights based on historical answer performance Otherwise, let ;like To guide the sample for the deviation of the exercise answer, use (3) to calculate Answers to exercises on unbiased loss weights Otherwise, let ;

[0030] (2)

[0031] (3)

[0032] In formula (2) and formula (3), w m It is the maximum reduction in the loss weight of the bias-guided sample;

[0033] Step 2.1.3, use formula (4) to construct the loss function of the knowledge tracking network ;

[0034] (4)

[0035] Step 2.1.4, using the loss function of the knowledge tracking network Training embedding layer E, knowledge state extraction layer and prediction layer , get the initially trained embedding layer E 1 , the initially trained knowledge state extraction layer and the initially trained prediction layer .

[0036] Furthermore, the step 2.2 includes:

[0037] Step 2.2.1, the initially trained embedding layer E 1 For the nth student s n Exercises for Sequence Data H n,T Process and output the nth student s n The adversarial generation embedding representation sequence of the 2nd to Tth answer questions E M B n q , a d v = [ e m b n , 2 q , a d v , e m b n , 3 q , a d v , … , e m b n , t q , a d v , … , e m b n , T q , a d v ] and the nth student s n The adversarial output embedding representation sequence of the interactive behavior of the first T-1 times of answering exercises E M B n q r , a d v = [ e m b n , 1 q r , a d v , e m b n , 2 q r , a d v , … , e m b n , t q r , a d v , … , e m b n , T − 1 q r , a d v ] ;in, represents the nth student s n Answer exercise q for the tth time n,t adversarial generation of embedding representations, represents the nth student s n Answer exercise q for the tth time n,t and its answer results n,t adversarial generation of embedding representations;

[0038] The initially trained knowledge state extraction layer right Process and output the nth student s n The adversarial generation of knowledge state representation sequence when answering exercises from the 2nd to the Tth time E M B n h , a d v = [ e m b n , 2 h , a d v , e m b n , 3 h , a d v , … , e m b n , t h , a d v , … , e m b n , T h , a d v ] ;in, represents the nth student s n The adversarial generation of knowledge state representation when answering the exercise for the tth time;

[0039] The initially trained prediction layer right and Process and output the nth student s n The correct adversarial generation probability for the next answer exercise [ r ^ a d v n , 2 , r ^ a d v n , 3 , … , r ^ a d v n , t , … , r ^ a d v n , T ] ;in, represents the nth student s n The probability of correct adversarial generation for answering the exercise for the tth time;

[0040] Step 2.2.2, use formula (5) to construct the loss function of the adversarial embedding generation network :

[0041] (5)

[0042] In formula (5), is the mean square error loss The weight of is the prediction loss of the adversarial embedding generation network and is obtained by formula (6); is the mean square error loss between the student's knowledge state representation and the adversarial knowledge state representation, and is obtained by formula (7);

[0043] (6)

[0044] (7)

[0045] In formula (7), represents the L2 norm; Indicates the first training, the knowledge state extraction layer trained initially Output the nth student s n The adversarial generation of knowledge state representation sequence when answering the exercise for the tth time; Indicates that except for the first training, the knowledge state extraction layer of the initial training is Output the nth student s n The adversarial generation of knowledge state representation sequence when answering the exercise for the tth time;

[0046] Step 2.2.3, Fixation and , and use the loss function of the adversarial embedding generation network To E 1 Train and get the retrained embedding layer E 2 .

[0047] Furthermore, the step 2.3 includes:

[0048] Step 2.3.1, the retrained embedding layer E 2 For the nth student s n Exercises for Sequence Data H n,T Process and output the nth student s n The adversarial prediction embedding representation sequence of the 2nd to Tth answer questions E M B n q , ∗ = [ e m b n , 2 q , ∗ , e m b n , 3 q , ∗ , … , e m b n , t q , ∗ , … , e m b n , T q , ∗ ] and the nth student s n The adversarial prediction embedding representation sequence of the interactive behavior of the first T-1 answering exercises E M B n q r , ∗ = [ e m b n , 1 q r , ∗ , e m b n , 2 q r , ∗ , … , e m b n , t q r , ∗ , … , e m b n , T − 1 q r , ∗ ] ;in, represents the nth student s n Answer exercise q for the tth time n,t The adversarial prediction embedding representation, represents the nth student s n Answer exercise q for the tth time n,t and its answer results n,t adversarial prediction embedding representation;

[0049] The initially trained knowledge state extraction layer right Process and output the nth student s n The adversarial prediction knowledge state representation sequence when answering the exercises from the 2nd to the Tth time E M B n h , * = [ e m b n , 2 h , * , e m b n , 3 h , * , … , e m b n , t h , * , … , e m b n , T h , * ] ;in, represents the nth student s n The adversarial prediction knowledge state representation when answering the exercise for the tth time;

[0050] The initially trained prediction layer right and Process and output the nth student s n The correct adversarial prediction probability of the next answer exercise [ r ^ * n , 2 , r ^ * n , 3 , … , r ^ * n , t , … , r ^ * n , T ] ;in, represents the nth student s n The adversarial prediction probability of answering the exercise correctly the tth time;

[0051] Step 2.3.2, use formula (8) to construct the loss function of the adversarial knowledge tracking network ;

[0052] (8)

[0053] Step 2.3.3, fix E 2 Parameters, using adversarial knowledge to track the loss function of the network The knowledge state extraction layer trained initially and the initially trained prediction layer Train and obtain the retrained knowledge state extraction layer and the retrained prediction layer .

[0054] The electronic device of the present invention includes a memory and a processor, and is characterized in that the memory is used to store a program that supports the processor to execute the knowledge tracking deep debiasing method, and the processor is configured to execute the program stored in the memory.

[0055] The present invention provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and the computer program executes the steps of the knowledge tracking deep debiasing method when the computer program is executed by a processor.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] 1. The present invention proposes a method for dividing unbiased samples in a knowledge tracking dataset, namely, judging whether a sample is unbiased by the association between its bias attributes and labels, thereby realizing the construction of an unbiased set for more accurately measuring the ability of the knowledge tracking model to evaluate students' knowledge status.

[0058] 2. The present invention proposes an adversarial data enhancement method and loss reweighting method suitable for knowledge tracking. First, the adversarial prediction loss is used to generate enhanced data that is adversarial to the bias. Then, the loss weight is calculated based on the degree of bias of the sample. The weighted prediction loss is used on the original data and the enhanced data to train the knowledge tracking model to reduce the model's learning rate for biased samples, thereby achieving deep debiasing of the model and more accurately evaluating the student's knowledge status. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a block diagram of the knowledge tracking deep debiasing method of the present invention. DETAILED DESCRIPTION

[0060] In this embodiment, Figure 1 As shown in the figure, a deep debiasing method for knowledge tracing generates data that is resistant to bias by combining adversarial data augmentation and loss reweighting. It also reduces the learning rate of biased samples during model training, effectively preventing the model from using the association between biased attributes and labels as a prediction shortcut, thereby alleviating the bias problem of the deep knowledge tracing model. Specifically, the method includes the following steps:

[0061] Step 1: Data collection;

[0062] Get the student collection , where s n represents the nth student, N is the number of students;

[0063] Get the exercise set , where q i represents the i-th exercise, I is the number of exercises;

[0064] Let the nth student s n For the i-th exercise q i The answer is r n,i , if r n,i =1, indicating the answer is correct, if rn,i =0, indicating an incorrect answer;

[0065] Define the nth student s n The previous T historical answer records are H n , T = [ ( q n , 1 , r n , 1 ) , ( q n , 2 , r n , 2 ) , … , ( q n , t , r n , t ) , … , ( q n , T , r n , T ) ] ,in, represents the nth student s n The tth historical answer record, q n,t represents the nth student s n The tth history exercise, r n,t represents the nth student s n The t-th historical answer result of , T is the n-th student s n The number of historical answers.

[0066] Define the nth student s n The tth answer sample is , where H n,t-1 represents the nth student s n The previous t-1 historical answer records, For the nth student s n The correct rate of the most recent w answers in the tth historical answering time, in this embodiment, w=10, when season ; For the nth student s n The tth history exercise q n,t The correct rate of all students in the previous T historical answer records, when q n,t The number of times it appears in the previous T historical answer records of all students is less than L times, so ; In this embodiment, L=3.

[0067] like Meet the conditions , then Defined as the historical answer performance bias guide sample, denoted as ;

[0068] like Meet the conditions , then Defined as a historical answer performance deviation conflict sample, denoted as ;

[0069] like Meet the conditions , then Defined as the guide sample of exercise answer deviation, denoted as ;

[0070] like Meet the conditions , then It is defined as the conflict sample of the exercise answer deviation, recorded as ; Among them, a th is the threshold for judging sample deviation. In this embodiment, a th =0.4.

[0071] The unbiased set of historical answer performance is constructed from the conflicting samples of historical answer performance of all students, which is recorded as ;

[0072] The unbiased set of exercise answers is constructed from the conflicting samples of all students’ exercise answers, which is recorded as .

[0073] Step 2: Build a knowledge tracking network, adversarial embedding generation network, and adversarial knowledge tracking network;

[0074] Step 2.1, the knowledge tracking network includes: embedding layer E, knowledge state extraction layer and prediction layer , and used for the nth student s n Exercises for Sequence Data H n,T Process and get the nth student s n The probability of answering the next exercise correctly, thereby constructing the loss of the knowledge tracking network , used to train the embedding layer E and the knowledge state extraction layer and prediction layer , and get the initially trained embedding layer E 1 , the initially trained knowledge state extraction layer and the initially trained prediction layer .

[0075] Step 2.1.1, embedding layer E for nth student s n Exercises for Sequence Data H n,T Process and output the nth student s n The embedded representation sequence of the second to Tth answer questions E M B n q = [ e m b n , 2 q , e m b n , 3 q , … , e m b n , t q , … , e m b n , T q ] and the nth student s n The embedded representation sequence of the interactive behavior of answering exercises before T-1 times E M B n q r = [ e m b n , 1 q r , e m b n , 2 q r , … , e m b n , t q r , … , e m b n , T − 1 q r ] ;in, represents the nth student s n Answer exercise q for the tth time n,t Embedded representation of represents the nth student s n Answer exercise q for the tth time n,t and its answer results n,t Embedded representation of

[0076] Knowledge State Extraction Layer right Process and output the nth student s n The knowledge state representation sequence when answering the exercises from the 2nd to the Tth time E M B n h = [ e m b n , 2 h , e m b n , 3 h , … , e m b n , t h , … , e m b n , T h ] ;in, represents the nth student s n The knowledge status representation when answering the exercise for the tth time;

[0077] Prediction layer right and Process and output the nth student s n The probability of answering the next question correctly [ r ^ n , 2 , r ^ n , 3 , … , r ^ n , t , … , r ^ n , T ] ;in, represents the nth student s n The probability of answering the exercise correctly the tth time.

[0078] Step 2.1.2, based on the degree of sample deviation, use formula (1) to calculate the sample The loss weight ;

[0079] (1)

[0080] In formula (1), if To guide the sample for historical performance bias, use formula (2) to calculate Unbiased loss weights based on historical answer performance Otherwise, let ;like To guide the sample for the deviation of the exercise answer, use (3) to calculate Answers to exercises on unbiased loss weights Otherwise, let ;

[0081] (2)

[0082] (3)

[0083] In formula (2) and formula (3), w m is the maximum reduction in the loss weight of the sample guided by the deviation. In this embodiment, w m =0.7.

[0084] Step 2.1.3, use formula (4) to construct the loss function of the knowledge tracking network ;

[0085] (4)

[0086] Step 2.1.4, using the loss function of the knowledge tracking network Training embedding layer E, knowledge state extraction layer and prediction layer , get the initially trained embedding layer E 1 , the initially trained knowledge state extraction layer and the initially trained prediction layer .

[0087] Step 2.2, the embedded layer E trained initially 1 , the initially trained knowledge state extraction layer and the initially trained prediction layer Construct an adversarial embedding generation network and use it to train the nth student s n Exercises for Sequence Data H n,T Process and get the nth student s n The probability of correct adversarial generation in the next answer exercise is used to construct the loss of the adversarial embedding generation network , used to train the initially trained embedding layer E 1 , and get the retrained embedding layer E 2 ;

[0088] Step 2.2.1, the first trained embedding layer E 1 For the nth student s n Exercises for Sequence Data H n,T Process and output the nth student s n The adversarial generation embedding representation sequence of the 2nd to Tth answer questions E M B n q , a d v = [ e m b n , 2 q , a d v , e m b n , 3 q , a d v , … , e m b n , t q , a d v , … , e m b n , T q , a d v ] and the nth student s n The adversarial output embedding representation sequence of the interactive behavior of the first T-1 times of answering exercises E M B n q r , a d v = [ e m b n , 1 q r , a d v , e m b n , 2 q r , a d v , … , e m b n , t q r , a d v , … , e m b n , T − 1 q r , a d v ] ;in, represents the nth student s n Answer exercise q for the tth time n,t adversarial generation of embedding representations, represents the nth student s n Answer exercise q for the tth time n,t and its answer results n,t adversarial generation of embedding representations;

[0089] Initially trained knowledge state extraction layer right Process and output the nth student s nThe adversarial generation of knowledge state representation sequence when answering exercises from the 2nd to the Tth time E M B n h , a d v = [ e m b n , 2 h , a d v , e m b n , 3 h , a d v , … , e m b n , t h , a d v , … , e m b n , T h , a d v ] ;in, represents the nth student s n The adversarial generation of knowledge state representation when answering the exercise for the tth time;

[0090] Initially trained prediction layer right and Process and output the nth student s n The correct adversarial generation probability for the next answer exercise [ r ^ a d v n , 2 , r ^ a d v n , 3 , … , r ^ a d v n , t , … , r ^ a d v n , T ] ;in, represents the nth student s n The probability of correct adversarial generation for answering the exercise for the tth time.

[0091] Step 2.2.2, use formula (5) to construct the loss function of the adversarial embedding generation network :

[0092] (5)

[0093] In formula (5), is the mean square error loss The weight of =1, is the prediction loss of the adversarial embedding generation network and is obtained by formula (6); is the mean square error loss between the student's knowledge state representation and the adversarial knowledge state representation, and is obtained by formula (7);

[0094] (6)

[0095] (7)

[0096] In formula (7), represents the L2 norm; Indicates the first training, the knowledge state extraction layer trained initially Output the nth student s n The adversarial generation of knowledge state representation sequence when answering the exercise for the tth time; Indicates that except for the first training, the knowledge state extraction layer of the initial training is Output the nth student s n The adversarial generation of knowledge state representation sequence when answering the exercise for the tth time;

[0097] Step 2.2.3, Fixation and , and use the loss function of the adversarial embedding generation network To E 1 Train and get the retrained embedding layer E 2 .

[0098] Step 2.3, the embedded layer E is trained again 2 , the initially trained knowledge state extraction layer and the initially trained prediction layer Construct an adversarial knowledge tracking network and use it to track the nth student s n Exercises for Sequence Data H n,T Process and get the nth student s n The correct adversarial prediction probability of the next answer exercise is constructed to construct the loss of the adversarial knowledge tracking network , used to train the initially trained knowledge state extraction layer and the initially trained prediction layer , and obtain the retrained knowledge state extraction layer and the retrained prediction layer ;

[0099] Step 2.3.1, retrain the embedding layer E 2 For the nth student s n Exercises for Sequence Data H n,T Process and output the nth student s n The adversarial prediction embedding representation sequence of the 2nd to Tth answer questions E M B n q , ∗ = [ e m b n , 2 q , ∗ , e m b n , 3 q , ∗ , … , e m b n , t q , ∗ , … , e m b n , T q , ∗ ] and the nth student s n The adversarial prediction embedding representation sequence of the interactive behavior of the first T-1 answering exercises E M B n q r , ∗ = [ e m b n , 1 q r , ∗ , e m b n , 2 q r , ∗ , … , e m b n , t q r , ∗ , … , e m b n , T − 1 q r , ∗ ] ;in, represents the nth student s n Answer exercise q for the tth time n,t The adversarial prediction embedding representation, represents the nth student s n Answer exercise q for the tth time n,t and its answer results n,t Adversarial prediction embedding representation.

[0100] Initially trained knowledge state extraction layer right Process and output the nth student s n The adversarial prediction knowledge state representation sequence when answering the exercises from the 2nd to the Tth time E M B n h , * = [ e m b n , 2 h , * , e m b n , 3 h , * , … , e m b n , t h , * , … , e m b n , T h , * ] ;in, represents the nth student sn The adversarial prediction knowledge state representation when answering the exercise for the tth time;

[0101] Initially trained prediction layer right and Process and output the nth student s n The correct adversarial prediction probability of the next answer exercise [ r ^ * n , 2 , r ^ * n , 3 , … , r ^ * n , t , … , r ^ * n , T ] ;in, represents the nth student s n The adversarial prediction probability of answering the exercise correctly the tth time.

[0102] Step 2.3.2, use formula (8) to construct the loss function of the adversarial knowledge tracking network ;

[0103] (8)

[0104] Step 2.3.3, fix E 2 Parameters, using adversarial knowledge to track the loss function of the network The knowledge state extraction layer trained initially and the initially trained prediction layer Train and obtain the retrained knowledge state extraction layer and the retrained prediction layer .

[0105] Step 3: E 1 、 and Assign corresponding values ​​to E, and Finally, the knowledge tracking network, adversarial embedding generation network and adversarial knowledge tracking network are trained alternately according to the process from step 2.1 to step 2.3 to continuously adjust the network parameters until the prediction accuracy of the knowledge tracking network no longer improves, thereby obtaining the optimal knowledge tracking model and using it to process the unbiased set of historical answer performance and the unbiased set of exercise answers to obtain the biased prediction results of the students' exercise answer accuracy.

[0106] In this embodiment, an electronic device includes a memory and a processor, wherein the memory is used to store a program that supports the processor to execute the above method, and the processor is configured to execute the program stored in the memory.

[0107] In this embodiment, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are executed.

[0108] The test results of the present invention are further described in conjunction with the following charts:

[0109] In order to verify the debiasing effect of the present invention on the existing knowledge tracing model, two commonly used benchmark models, qDKT (deep knowledge tracing using exercise information) and AKT (context-aware knowledge tracing), were selected to conduct experiments on three commonly used knowledge tracing datasets, Assist2009, Ednet-kt1, and Statics2011. Ours represents the application of the method proposed in this invention on the corresponding benchmark deep knowledge tracing model, and for fair comparison, the settings of the hyperparameters of Ours and the benchmark model, including model hyperparameters and training hyperparameters such as learning rate, L2 regularization coefficient, mini-batch size, etc., are consistent. The unbiased set D of historical answer performance and the unbiased set D of exercise answer were used respectively. q An unbiased evaluation was performed on the optimal knowledge tracking model obtained after training, using AUC (Area Under the Curve) and ACC (Accuracy) as evaluation indicators. The experimental results are shown in Tables 1 and 2.

[0110] Table 1 Performance comparison between the baseline model and the proposed method on an unbiased set of historical answer performance

[0111]

[0112] Table 2 Performance comparison between the baseline model and the proposed method on an unbiased set of exercise answers

[0113]

[0114] As can be seen from Tables 1 and 2, the method proposed in the present invention significantly improves the AUC and ACC indicators of the baseline model on both the unbiased set of historical answer performance and the unbiased set of exercise answers, verifying the effectiveness of the present invention in debiasing the knowledge tracking model.

Claims

1. A knowledge tracking deep debiasing method, characterized in that: The following steps are involved: Step 1: Data collection; Get the student collection , where s n represents the nth student, N is the number of students; Get the exercise set , where q i represents the i-th exercise, I is the number of exercises; Let the nth student s n For the i-th exercise q i The answer is r n,i , if r n,i =1, indicating the answer is correct, if r n,i =0, indicating an incorrect answer; Define the nth student s n The previous T historical answer records are ,in, represents the nth student s n The tth historical answer record, q n,t represents the nth student s n The tth history exercise, r n,t represents the nth student s n The t-th historical answer result of , T is the n-th student s n Number of historical questions answered; Define the nth student s n The tth answer sample is , where H n,t-1 represents the nth student s n The previous t-1 historical answer records, For the nth student s n When answering the history question for the tth time, the correct rate of the most recent w answers is season ; For the nth student s n The tth history exercise q n,t The correct rate of all students in the previous T historical answer records, when q n,t The number of times it appears in the previous T historical answer records of all students is less than L times, so ; like Meet the conditions , then Defined as the historical answer performance bias guide sample, denoted as ; like Meet the conditions , then Defined as a historical answer performance deviation conflict sample, denoted as ; like Meet the conditions , then Defined as the guide sample of exercise answer deviation, denoted as ; like Meet the conditions , then It is defined as the conflict sample of the exercise answer deviation, recorded as ; Among them, a th is the threshold for judging sample deviation; The unbiased set of historical answer performance is constructed from the conflicting samples of historical answer performance of all students, which is recorded as ; The unbiased set of exercise answers is constructed from the conflicting samples of all students’ exercise answers, which is recorded as ; Step 2: Build a knowledge tracking network, adversarial embedding generation network, and adversarial knowledge tracking network; Step 2.1: The knowledge tracking network includes: embedding layer E, knowledge state extraction layer and prediction layer , and used for the nth student s n Exercises for Sequence Data H n,T Process and get the nth student s n The probability of answering the next exercise correctly, thereby constructing the loss of the knowledge tracking network , used to train the embedding layer E and the knowledge state extraction layer and prediction layer , and get the initially trained embedding layer E 1 , the initially trained knowledge state extraction layer and the initially trained prediction layer ; Step 2.2, the embedded layer E trained initially 1 , the initially trained knowledge state extraction layer and the initially trained prediction layer Construct an adversarial embedding generation network and use it to train the nth student s n Exercises for Sequence Data H n,T Process and get the nth student s n The probability of correct adversarial generation in the next answer exercise is used to construct the loss of the adversarial embedding generation network , used to train the initially trained embedding layer E 1 , and get the retrained embedding layer E 2 ; Step 2.3, the embedded layer E is trained again 2 , the initially trained knowledge state extraction layer and the initially trained prediction layer Construct an adversarial knowledge tracking network and use it to track the nth student s n Exercises for Sequence Data H n,T Process and get the nth student s n The correct adversarial prediction probability of the next answer exercise is constructed to construct the loss of the adversarial knowledge tracking network , used to train the initially trained knowledge state extraction layer and the initially trained prediction layer , and obtain the retrained knowledge state extraction layer and the retrained prediction layer ; Step 3: E 1 、 and Assign corresponding values ​​to E, and Finally, the knowledge tracking network, adversarial embedding generation network and adversarial knowledge tracking network are trained alternately according to the process from step 2.1 to step 2.3 to continuously adjust the network parameters until the prediction accuracy of the knowledge tracking network no longer improves, thereby obtaining the optimal knowledge tracking model and using it to process the unbiased set of historical answer performance and the unbiased set of exercise answers to obtain the correct prediction results of students' exercise answers after debiasing.

2. The knowledge tracking depth debiasing method according to claim 1, characterized in that: The step 2.1 includes: Step 2.1.1, the embedding layer E is used for the nth student s n Exercises for Sequence Data H n,T Process and output the nth student s n The embedded representation sequence of the second to Tth answer questions and the nth student s n The embedded representation sequence of the interactive behavior of answering exercises before T-1 times ;in, represents the nth student s n Answer exercise q for the tth time n,t Embedded representation of represents the nth student s n Answer exercise q for the tth time n,t and its answer results n,t Embedded representation of The knowledge state extraction layer right Process and output the nth student s n The knowledge state representation sequence when answering the exercises from the 2nd to the Tth time ;in, represents the nth student s n The knowledge status representation when answering the exercise for the tth time; The prediction layer right and Process and output the nth student s n The probability of answering the next question correctly ;in, represents the nth student s n The probability of answering the exercise correctly the tth time; Step 2.1.2, based on the degree of sample deviation, use formula (1) to calculate the sample The loss weight ; (1) In formula (1), if To guide the sample for historical performance bias, use formula (2) to calculate Unbiased loss weights based on historical answer performance Otherwise, let ;like To guide the sample for the deviation of the exercise answer, use (3) to calculate Answers to exercises on unbiased loss weights Otherwise, let ; (2) (3) In formula (2) and formula (3), w m It is the maximum reduction in the loss weight of the bias-guided sample; Step 2.1.3, use formula (4) to construct the loss function of the knowledge tracking network ; (4) Step 2.1.4, using the loss function of the knowledge tracking network Training embedding layer E, knowledge state extraction layer and prediction layer , get the initially trained embedding layer E 1 , the initially trained knowledge state extraction layer and the initially trained prediction layer .

3. The knowledge tracking depth debiasing method according to claim 2, characterized in that: The step 2.2 includes: Step 2.2.1, the initially trained embedding layer E 1 For the nth student s n Exercises for Sequence Data H n,T Process and output the nth student s n The adversarial generation embedding representation sequence of the 2nd to Tth answer questions and the nth student s n The adversarial output embedding representation sequence of the interactive behavior of the first T-1 times of answering exercises ;in, represents the nth student s n Answer exercise q for the tth time n,t adversarial generation of embedding representations, represents the nth student s n Answer exercise q for the tth time n,t and its answer results n,t adversarial generation of embedding representations; The initially trained knowledge state extraction layer right Process and output the nth student s n The adversarial generation of knowledge state representation sequence when answering exercises from the 2nd to the Tth time ;in, represents the nth student s n The adversarial generation of knowledge state representation when answering the exercise for the tth time; The initially trained prediction layer right and Process and output the nth student s n The correct adversarial generation probability for the next answer exercise ;in, represents the nth student s n The probability of correct adversarial generation for answering the exercise for the tth time; Step 2.2.2, use formula (5) to construct the loss function of the adversarial embedding generation network : (5) In formula (5), is the mean square error loss The weight of is the prediction loss of the adversarial embedding generation network and is obtained by formula (6); is the mean square error loss between the student's knowledge state representation and the adversarial knowledge state representation, and is obtained by formula (7); (6) (7) In formula (7), represents the L2 norm; Indicates the first training, the knowledge state extraction layer trained initially Output the nth student s n The adversarial generation of knowledge state representation sequence when answering the exercise for the tth time; Indicates that except for the first training, the knowledge state extraction layer of the initial training is Output the nth student s n The adversarial generation of knowledge state representation sequence when answering the exercise for the tth time; Step 2.2.3, Fixation and , and use the loss function of the adversarial embedding generation network To E 1 Train and get the retrained embedding layer E 2 .

4. The knowledge tracking depth debiasing method according to claim 3, characterized in that: The step 2.3 includes: Step 2.3.1, the retrained embedding layer E 2 For the nth student s n Exercises for Sequence Data H n,T Process and output the nth student s n The adversarial prediction embedding representation sequence of the 2nd to Tth answer questions and the nth student s n The adversarial prediction embedding representation sequence of the interactive behavior of the first T-1 answering exercises ;in, represents the nth student s n Answer exercise q for the tth time n,t The adversarial prediction embedding representation, represents the nth student s n Answer exercise q for the tth time n,t and its answer results n,t adversarial prediction embedding representation; The initially trained knowledge state extraction layer right Process and output the nth student s n The adversarial prediction knowledge state representation sequence when answering the exercises from the 2nd to the Tth time ;in, represents the nth student s n The adversarial prediction knowledge state representation when answering the exercise for the tth time; The initially trained prediction layer right and Process and output the nth student s n The correct adversarial prediction probability of the next answer exercise ;in, represents the nth student s n The adversarial prediction probability of answering the exercise correctly the tth time; Step 2.3.2, use formula (8) to construct the loss function of the adversarial knowledge tracking network ; (8) Step 2.3.3, fix E 2 Parameters, using adversarial knowledge to track the loss function of the network The knowledge state extraction layer trained initially and the initially trained prediction layer Train and obtain the retrained knowledge state extraction layer and the retrained prediction layer .

5. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store a program that supports the processor to execute the knowledge tracing deep debiasing method according to any one of claims 1 to 4, and the processor is configured to execute the program stored in the memory.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the knowledge tracing deep debiasing method according to any one of claims 1 to 4 are executed.

Images