CN117313943A - Test question accuracy prediction method, system, equipment and storage medium - Google Patents
Test question accuracy prediction method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN117313943A CN117313943A CN202311333253.6A CN202311333253A CN117313943A CN 117313943 A CN117313943 A CN 117313943A CN 202311333253 A CN202311333253 A CN 202311333253A CN 117313943 A CN117313943 A CN 117313943A
- Authority
- CN
- China
- Prior art keywords
- test question
- predicted
- test
- accuracy
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 296
- 238000000034 method Methods 0.000 title claims abstract description 53
- 239000013598 vector Substances 0.000 claims abstract description 102
- 238000013507 mapping Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 description 18
- 238000012549 training Methods 0.000 description 18
- 238000004891 communication Methods 0.000 description 7
- 230000011218 segmentation Effects 0.000 description 7
- 238000010801 machine learning Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3347—Query execution using vector based model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Animal Behavior & Ethology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The test question accuracy prediction method, the test question accuracy prediction system, the test question accuracy prediction equipment and the storage medium provided by the invention are used for acquiring identity information of students to be predicted; calling a corresponding initialization vector in an initial vector database according to the identity information; acquiring corresponding historical test question answering data according to the identity information; determining wrong question preference scores of students to be predicted according to the initialization vector and the historical test question answer data; determining target student characteristics according to the wrong preference score; and inputting the target student characteristics into a prediction model of the test question accuracy rate to obtain the accuracy rate of the to-be-predicted test questions completed by the students to be predicted. By the method, student characteristics of the target to be predicted can be enhanced, the knowledge points mastered by the target to be predicted and the weak items can be better known, and therefore accuracy of the prediction result is improved.
Description
Technical Field
The invention relates to the technical field of education, in particular to a test question accuracy prediction method, a test question accuracy prediction system, test question accuracy prediction equipment and a test question accuracy prediction storage medium.
Background
Predicting the accuracy of a student to complete a test question is an important research direction in the education field. Early prediction methods were mainly based on statistical methods such as regression analysis, bayesian networks, etc. In recent years, with the development of machine learning and deep learning techniques, learning models have been increasingly applied to such predictions as Recurrent Neural Networks (RNNs), long and short term memory networks (LSTM), and the like. However, a single model or method may not adequately capture and utilize the underlying information of all student data, such that the accuracy of the predictions is not high.
In view of the foregoing, there is a need to solve the problems of the prior art.
Disclosure of Invention
The invention provides a test question accuracy prediction method, a test question accuracy prediction system, test question accuracy prediction equipment and a test question accuracy prediction storage medium, which are used for solving the defect of low prediction accuracy in the prior art.
The invention provides a test question accuracy prediction method, which comprises the following steps:
acquiring identity information of students to be predicted;
calling a corresponding initialization vector in an initial vector database according to the identity information;
acquiring corresponding historical test question answering data according to the identity information;
determining wrong question preference scores of students to be predicted according to the initialization vector and the historical test question answer data;
determining target student characteristics according to the wrong preference score;
and inputting the target student characteristics into a prediction model of the test question accuracy rate to obtain the accuracy rate of the to-be-predicted test questions completed by the students to be predicted.
According to the test question accuracy prediction method provided by the invention, the wrong question preference score of the student to be predicted is determined according to the initialization vector and the historical test question answer data, and the method is realized by the following steps:
wherein u is the feature vector of the student, v i V in answering data for historical test questions i The test questions of the road are set up,for students u to test questions v i Preference score, W 1 For a first model parameter which can be learned, +.>Preference scores for the questions.
According to the method for predicting the test question accuracy provided by the invention, the target student characteristics are input into a test question accuracy prediction model to obtain the accuracy of the test questions to be predicted, and the method specifically comprises the following steps:
acquiring test question completion condition data, wherein the test question completion condition data comprises the conditions of different students for completing different test questions;
determining examination knowledge points contained in each test question according to the test question knowledge map;
determining the mapping relation between the examination knowledge points and the student characteristics;
acquiring the characteristics of the target students and the test questions to be predicted;
determining target student characteristics of students to be predicted according to the wrong preference scores;
and determining the correct rate of the students to be predicted to finish the test questions to be predicted according to the target student characteristics and the mapping relation.
According to the method for predicting the accuracy of the test questions provided by the invention, the step of determining the examination knowledge points contained in each test question according to the test question knowledge graph specifically comprises the following steps:
acquiring a test question feature vector of each test question according to the test question text information in the test question completion condition data;
and determining examination knowledge points contained in the test questions according to the test question feature vectors and the test question knowledge graph.
According to the method for predicting the accuracy of the test questions, which is provided by the invention, the step of determining the examination knowledge points contained in the test questions according to the characteristic vectors of the test questions and the knowledge graph of the test questions comprises the following steps:
and matching the test question feature vector with the knowledge point feature vector in the test question knowledge graph to determine the examination knowledge point corresponding to the test question feature vector.
According to the method for predicting the accuracy of the test questions provided by the invention, the step of determining the accuracy of the test questions to be predicted for the students to be predicted according to the characteristics of the target students and the mapping relation specifically comprises the following steps:
determining examination knowledge points and knowledge point weights contained in the test questions to be predicted;
determining the accuracy of the examination knowledge points contained in the test questions to be predicted based on the students to be predicted according to the examination knowledge points contained in the test questions to be predicted and the mapping relation;
and determining the accuracy of the test questions to be predicted according to the knowledge point weight and the accuracy of the examined knowledge points.
The method for predicting the test question accuracy provided by the invention further comprises the following steps:
acquiring a test question feature vector of each test question according to the text information of the test question;
determining the test question difficulty of the test questions according to the test question feature vector and the test question knowledge graph;
extracting examination knowledge points of the test questions to be predicted;
determining the grasping degree of the examination knowledge points of the students to be predicted to the predicted test questions according to the historical test question answering data;
and correcting the accuracy of the test questions to be predicted according to the mastering degree and the test question difficulty of the test questions to be predicted.
The invention also provides a test question accuracy prediction system, which comprises:
the information acquisition unit is used for acquiring identity information of the student to be predicted;
the vector calling unit is used for calling a corresponding initialization vector in the initial vector database according to the identity information;
the data acquisition unit is used for acquiring corresponding historical test question answer data according to the identity information;
the coefficient determining unit is used for determining the wrong question preference score of the student to be predicted according to the initialization vector and the historical test question answer data;
the feature determining unit is used for determining the features of the target students according to the wrong preference scores;
and the result prediction unit is used for inputting the characteristics of the target students into a prediction model of the test question accuracy rate to obtain the accuracy rate of the students to be predicted to finish the test questions to be predicted.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the prediction method of the test question accuracy rate according to any one of the above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of predicting test question correctness as described in any of the above.
The invention also provides a computer program product, which comprises a computer program, wherein the computer program realizes the prediction method of the test question accuracy when being executed by a processor.
The test question accuracy prediction method, the test question accuracy prediction system, the test question accuracy prediction equipment and the storage medium provided by the invention are used for acquiring identity information of students to be predicted; calling a corresponding initialization vector in an initial vector database according to the identity information; acquiring corresponding historical test question answering data according to the identity information; determining wrong question preference scores of students to be predicted according to the initialization vector and the historical test question answer data; determining target student characteristics according to the wrong preference score; and inputting the target student characteristics into a prediction model of the test question accuracy rate to obtain the accuracy rate of the to-be-predicted test questions completed by the students to be predicted. By the method, student characteristics of the target to be predicted can be enhanced, the knowledge points mastered by the target to be predicted and the weak items can be better known, and therefore accuracy of the prediction result is improved.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a test question accuracy prediction method provided by the invention;
FIG. 2 is a schematic diagram of a device for predicting the accuracy of a test question according to the present invention;
fig. 3 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to help educators, schools and students to better understand learning conditions, optimize teaching methods, and provide personalized learning advice for students, it is necessary to be able to accurately predict the student's performance in a particular test question or examination. However, a single model or method is generally adopted in the prior art, so that potential information of all student data cannot be fully captured and utilized, and the prediction accuracy is not high.
In order to solve the problems in the prior art, the invention provides a method for predicting the test question accuracy, so as to improve the accuracy of test question accuracy prediction results. As shown in FIG. 1, a test question accuracy prediction method includes, but is not limited to, steps 110-160:
step 110: acquiring identity information of students to be predicted;
step 120: calling a corresponding initialization vector in an initial vector database according to the identity information;
step 130: acquiring corresponding historical test question answering data according to the identity information;
step 140: determining wrong question preference scores of students to be predicted according to the initialization vector and the historical test question answer data;
step 150: determining target student characteristics according to the wrong preference score;
step 160: and inputting the target student characteristics into a prediction model of the test question accuracy rate to obtain the accuracy rate of the to-be-predicted test questions completed by the students to be predicted.
In this embodiment, in order to conduct targeted test question accuracy prediction on the target to be predicted, the weight coefficient of the target to be predicted needs to be obtained to constructAnd establishing target student characteristics of the target to be predicted. Specifically, the initialization vector u of the student is obtained according to the student id mapping, that is, the student characteristics obtained by analyzing the test question completion condition data. Next, K in the answer data of the historical test questions is calculated 1 The test question entity characteristics related to the target to be predicted randomly adopt K 1 If the test questions wrongly answered by the students are less than K 1 Randomly repeating the steps, and calculating to obtain the student u-to-error problem v by using an attention mechanism i Preference score of (2)
Wherein W is 1 Is a first model parameter that can be learned.
To characterize the topological proximity structure of student u, computing the neighborhood characteristics of u
Wherein the method comprises the steps ofIs normalized to get a preference score:
finally, aggregating the neighborhood features to generate a final target feature vector u':
wherein l is an activation functionNumber W 2 As a second model parameter which can be learned, b 1 Is the first bias term.
The test question accuracy prediction method, the test question accuracy prediction system, the test question accuracy prediction equipment and the storage medium provided by the invention are used for acquiring identity information of students to be predicted; calling a corresponding initialization vector in an initial vector database according to the identity information; acquiring corresponding historical test question answering data according to the identity information; determining wrong question preference scores of students to be predicted according to the initialization vector and the historical test question answer data; determining target student characteristics according to the wrong preference score; and inputting the target student characteristics into a prediction model of the test question accuracy rate to obtain the accuracy rate of the to-be-predicted test questions completed by the students to be predicted. By the method, student characteristics of the target to be predicted can be enhanced, the knowledge points mastered by the target to be predicted and the weak items can be better known, and therefore accuracy of the prediction result is improved.
As a further optional embodiment, the determining the mistopic preference score of the student to be predicted according to the initialization vector and the historical test question answer data is implemented by the following ways:
wherein u is the feature vector of the student, v i V in answering data for historical test questions i The test questions of the road are set up,for students u to test questions v i Preference score, W 1 For a first model parameter which can be learned, +.>Preference scores for the questions.
As a further optional embodiment, inputting the target student characteristic into a prediction model of the test question accuracy rate, and obtaining the accuracy rate of the test question to be predicted for the student to be predicted includes:
and acquiring test question completion condition data, wherein the test question completion condition data comprises the conditions of different students for completing different test questions.
And determining examination knowledge points contained in each test question according to the test question knowledge graph.
And determining the mapping relation between the examination knowledge points and the student characteristics.
And acquiring a weight coefficient of the target to be predicted and the test question to be predicted.
And determining the target student characteristics of the target to be predicted according to the weight coefficient.
And determining the accuracy rate of the target to be predicted to finish the test question to be predicted according to the characteristics of the target students and the mapping relation.
The test question completion condition data comprise the condition that different students complete different test questions, specifically, the test questions can be existing test questions or test questions for re-proposing, but the range of knowledge points contained in the test questions cannot exceed the range of a test question knowledge graph, and the test question knowledge graph only comprises a knowledge point A, a knowledge point B and a knowledge point C, so that the test questions cannot comprise a knowledge point D. In order to better understand the knowledge points mastered by students, the test questions should cover all knowledge points; meanwhile, students who complete test questions should be as many as possible. In this embodiment, the channel for acquiring the test question completion status data is not limited, and the test question completion status data may be acquired directly from the examination position through the intelligent terminal, or may be acquired from other electronic devices and computer systems through the data transmission interface or remote communication transmission.
In order to analyze the test question completion condition data, a mapping relationship between student features and knowledge points is constructed, and knowledge points contained in each test question need to be extracted. Specifically, in this embodiment, a test question feature vector of a test question may be obtained according to text information of the test question, and further, the test question feature vector includes a knowledge point parameter and a test question difficulty parameter. According to the knowledge point parameters contained in the test question feature vector, the knowledge points contained in the test question can be determined, so that the mapping relation between the examined knowledge points and the student features can be constructed later.
The examination knowledge points related to the test questions need to be associated with the characteristics of the students, and the mapping relation is used for representing the accuracy of a certain examination knowledge point in the students participating in the examination. The application for constructing the mapping relation is not limited, and a person skilled in the art can select a hash algorithm, a neural network model and the like according to actual situations to implement.
The weight coefficient of the target to be predicted and the test question to be predicted need to be obtained so as to conduct targeted test question accuracy prediction on the target to be predicted. Therefore, the weight coefficient of the target to be predicted needs to be obtained to correct the mapping relation between the examination knowledge points and the student characteristics, so as to obtain the mapping relation between the examination knowledge points and the target characteristics to be predicted. It can be understood that the knowledge points contained in the test questions to be predicted cannot exceed the range of the test question knowledge graph.
According to the foregoing, an initial vector of the student, that is, a student characteristic, can be obtained, but the student characteristic does not reflect the actual situation of the target to be predicted well. Therefore, the student characteristics need to be readjusted according to the weight coefficient of the target to be predicted, so as to obtain the required target student characteristics. Illustratively, the mastering condition of each knowledge point of the student can be determined according to the historical problem making condition of the student, so that the characteristics of the student can be further adjusted to obtain the required characteristics of the target student.
And after the target student characteristics of the target to be predicted are obtained, determining the accuracy of the target to be predicted to finish the test question to be predicted according to the mapping relation. Specifically, the feature vector of the target student and the feature vector of the test question to be predicted are input into a scoring function, and the output result of the scoring function is the accuracy rate of the completion of the test question to be predicted by the target to be predicted.
As a further optional embodiment, the step of determining the examination knowledge points included in each test question according to the test question knowledge map specifically includes:
acquiring a test question feature vector of each test question according to the test question text information in the test question completion condition data;
and determining examination knowledge points contained in the test questions according to the test question feature vectors and the test question knowledge graph.
In this embodiment, the text information of the test questions needs to be converted into test question feature vectors, each of the test questions corresponds to a test question feature vector set, and the test question feature vector set includes a plurality of knowledge point feature vectors. For example, first, the obtained test question text information may be subjected to sentence-level segmentation processing to obtain a plurality of sentences. Then, word segmentation processing is carried out on each sentence respectively, so that the phrase forming the sentence is obtained. Illustratively, the text content includes the sentence "the price of a shirt is two hundred", and the phrase "the price of a shirt is two hundred" can be obtained after word segmentation. Here, there are various word segmentation algorithms that can be used, for example, in some embodiments, a dictionary-based word segmentation algorithm may be used, where a sentence is segmented into words according to a dictionary, and then an optimal combination mode of the words is searched; in some embodiments, word segmentation algorithm based on words may be used, where the sentence is divided into individual words, and then the words are combined into words, so as to find an optimal combination mode. After the sentence is subjected to word segmentation, a word embedding vector corresponding to each word in the phrase can be determined through a pre-established dictionary, and of course, in some embodiments, the word embedding vector can be obtained by mapping the word into a vector space with uniform lower dimensionality, and strategies for generating the mapping include a neural network, dimension reduction of a word co-occurrence matrix, a probability model, an interpretable knowledge base method and the like. For example, for a sentence with a price of "shirt" of two hundred ", word embedding vectors corresponding to words in the sentence are first determined one by one, wherein the word vector corresponding to the word" shirt "is (0,5,1,1), the word vector corresponding to the word" is (0, 1), the word vector corresponding to the word "price" is (4,2,3,1), the word vector corresponding to the word "yes" is (0, 1,0, 1), and the word vector corresponding to the word "two hundred" is (1,0,0,4). After determining word embedding vectors corresponding to each word in two hundred, the word embedding vectors can be accumulated, the accumulated vectors can be recorded as phrase vectors, such as phrase "shirt, price, namely, phrase vector 420 corresponding to two hundred" is (5,8,4,8), normalization processing is carried out on the phrase vectors, namely, the vectors corresponding to the obtained sentences can be set, for example, when normalization processing is carried out, element sums in the vectors corresponding to the sentences are 1, and the price of the sentence "shirt is two hundred" can be represented by the vector (0.2,0.32,0.16,0.32). It can be understood that, referring to the above manner, vectors corresponding to all sentences in the text content of the test question text information can be determined, and these vectors are spliced or constructed into a matrix, so that structured data containing all feature information of the text content 320 can be obtained. Of course, similarly, the above manner of extracting text feature information based on the semantics of the text content is only used for illustration, and is not meant to limit the practical implementation of the application, but text feature information may be extracted based on dimensions such as grammar features, language features, keyword hit features, and the like, and text feature information extracted from multiple dimensions may be integrated to obtain new text feature information, which is not described herein again.
And then, matching the obtained vector with the test question knowledge graph to obtain the examination knowledge points contained in the test questions.
As a further optional embodiment, the step of determining the examination knowledge points included in the test question according to the test question feature vector and the test question knowledge map specifically includes:
and matching the test question feature vector with the knowledge point feature vector in the test question knowledge graph to determine the examination knowledge point corresponding to the test question feature vector.
As a further optional embodiment, the step of determining, according to the characteristics of the target student and the mapping relationship, the accuracy rate of the target to be predicted to complete the test question to be predicted specifically includes:
determining examination knowledge points and knowledge point weights contained in the test questions to be predicted;
determining the accuracy of the examination knowledge points contained in the test questions to be predicted based on the target to be predicted according to the examination knowledge points contained in the test questions to be predicted and the mapping relation;
and determining the accuracy of the test questions to be predicted according to the knowledge point weight and the accuracy of the examined knowledge points.
In this embodiment, because there may be more than one examination knowledge point included in the test question to be predicted, it is necessary to obtain the examination knowledge points included in the test question to be predicted and the weights of the corresponding knowledge points, and after determining the examination knowledge points included in the test question to be predicted, it may determine the accuracy of completing the corresponding examination knowledge points by the target to be predicted according to the mapping relationship between the examination knowledge points and the target student characteristics. And determining the accuracy of the test questions to be predicted according to the accuracy of each examination knowledge point and the corresponding knowledge point weight. For example, the questions to be pre-tested include a knowledge point a, a knowledge point B and a knowledge point C, and then, according to the mapping relation between the examined knowledge point and the target student feature, the correct rates corresponding to the knowledge point a, the knowledge point B and the knowledge point C are obtained to be 70%, 80% and 60%, and when the weights of the knowledge point a, the knowledge point B and the knowledge point C are equal, the correct rate of the target to be predicted to complete the questions to be predicted is 70%. 1/3+80%. 1/3+60%. 1/3=70%.
As a further optional embodiment, a method for predicting the test question accuracy further includes:
acquiring a test question feature vector of each test question according to the text information of the test question;
and determining the test question difficulty of the test questions according to the test question feature vector and the test question knowledge graph.
Extracting examination knowledge points of the test questions to be predicted;
determining the grasping degree of the examination knowledge points of the target to be predicted according to the historical examination question answering data;
and correcting the accuracy of the test questions to be predicted according to the mastering degree and the test question difficulty of the test questions to be predicted.
In this embodiment, in order to further ensure accuracy of accuracy prediction, the grasping degree of the examination knowledge point of the test question to be predicted of the target to be predicted is further determined, and then the accuracy of the test question to be predicted is corrected according to the grasping degree and the test question difficulty of the test question to be predicted. For example, when the mastering degree is greater than the test question difficulty of the test questions to be predicted, a preset value is added on the basis of the original prediction accuracy; and when the mastering degree is smaller than the test question difficulty of the test questions to be predicted, the preset value is reduced on the basis of the original prediction accuracy. The grasping degree of the examination knowledge points of the target to be predicted can be calculated through a machine learning model.
Here, the training data set with the label can be used for training, and the history test question answering data can be input into the initialized mastery degree test model for training. Specifically, after the data in the historical test question answer data is input into the initialized mastery degree test model, the recognition result output by the model, namely the mastery degree result, can be obtained, and the accuracy of prediction of the recognition model can be evaluated according to the mastery degree result and the label, so that parameters of the model are updated. For a mastery test model, the accuracy of the model prediction result can be measured by a Loss Function (Loss Function), which is defined on a single training data and is used for measuring the prediction error of one training data, specifically determining the Loss value of the training data through the label of the single training data and the prediction result of the model on the training data. In actual training, one training data set has a lot of training data, so that a Cost Function (Cost Function) is generally adopted to measure the overall error of the training data set, and the Cost Function is defined on the whole training data set and is used for calculating the average value of the prediction errors of all the training data, so that the prediction effect of the model can be better measured. For a general machine learning model, based on the cost function, a regular term for measuring the complexity of the model can be used as a training objective function, and based on the objective function, the loss value of the whole training data set can be obtained. There are many kinds of common loss functions, such as 0-1 loss function, square loss function, absolute loss function, logarithmic loss function, cross entropy loss function, etc., which can be used as the loss function of the machine learning model, and will not be described in detail herein. In the embodiment of the application, one loss function can be selected to determine the loss value of training. Based on the trained loss value, updating the parameters of the model by adopting a back propagation algorithm, and iterating for several rounds to obtain the trained mastery degree test model. Specifically, the number of iteration rounds may be preset, or training may be considered complete when the test set meets the accuracy requirements.
Referring to fig. 2, the test question accuracy prediction system provided by the present invention is described below, and the test question accuracy prediction system described below and the test question accuracy prediction method described above may be referred to correspondingly.
An information acquisition unit 210 for acquiring identity information of a student to be predicted;
a vector calling unit 220, configured to call a corresponding initialization vector in an initial vector database according to the identity information;
a data obtaining unit 230, configured to obtain corresponding historical test question answer data according to the identity information;
a coefficient determining unit 240, configured to determine a wrong question preference score of the student to be predicted according to the initialization vector and the historical test question answer data;
a feature determining unit 250 for determining a target student feature according to the wrong preference score;
the result prediction unit 260 is configured to input the target student characteristic into a prediction model of the test question accuracy rate, so as to obtain the accuracy rate of the test question to be predicted for the student to complete.
Fig. 3 illustrates a physical schematic diagram of an electronic device, as shown in fig. 3, where the electronic device may include: processor 310, communication interface (Communications Interface) 320, memory 330 and communication bus 340, wherein processor 310, communication interface 320, memory 330 accomplish communication with each other through communication bus 340. The processor 310 may call logic instructions in the memory 330 to perform a method of predicting test question correctness, the method comprising:
acquiring identity information of students to be predicted;
calling a corresponding initialization vector in an initial vector database according to the identity information;
acquiring corresponding historical test question answering data according to the identity information;
determining wrong question preference scores of students to be predicted according to the initialization vector and the historical test question answer data;
determining target student characteristics according to the wrong preference score;
and inputting the target student characteristics into a prediction model of the test question accuracy rate to obtain the accuracy rate of the to-be-predicted test questions completed by the students to be predicted.
Further, the logic instructions in the memory 330 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, where the computer program product includes a computer program, where the computer program can be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer can execute a method for predicting accuracy of a test question provided by the above methods, where the method includes:
acquiring identity information of students to be predicted;
calling a corresponding initialization vector in an initial vector database according to the identity information;
acquiring corresponding historical test question answering data according to the identity information;
determining wrong question preference scores of students to be predicted according to the initialization vector and the historical test question answer data;
determining target student characteristics according to the wrong preference score;
and inputting the target student characteristics into a prediction model of the test question accuracy rate to obtain the accuracy rate of the to-be-predicted test questions completed by the students to be predicted.
In still another aspect, the present invention provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform a method of predicting a test question accuracy provided by the above methods, the method comprising:
acquiring identity information of students to be predicted;
calling a corresponding initialization vector in an initial vector database according to the identity information;
acquiring corresponding historical test question answering data according to the identity information;
determining wrong question preference scores of students to be predicted according to the initialization vector and the historical test question answer data;
determining target student characteristics according to the wrong preference score;
and inputting the target student characteristics into a prediction model of the test question accuracy rate to obtain the accuracy rate of the to-be-predicted test questions completed by the students to be predicted.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The test question accuracy prediction method is characterized by comprising the following steps of:
acquiring identity information of students to be predicted;
calling a corresponding initialization vector in an initial vector database according to the identity information;
acquiring corresponding historical test question answering data according to the identity information;
determining wrong question preference scores of students to be predicted according to the initialization vector and the historical test question answer data;
determining target student characteristics according to the wrong preference score;
and inputting the target student characteristics into a prediction model of the test question accuracy rate to obtain the accuracy rate of the to-be-predicted test questions completed by the students to be predicted.
2. The method for predicting test question accuracy according to claim 1, wherein the determining of the wrong question preference score of the student to be predicted according to the initialization vector and the historical test question answer data is achieved by:
wherein u is the feature vector of the student, v i V in answering data for historical test questions i The test questions of the road are set up,for students u to test questions v i Preference score, W 1 For a first model parameter which can be learned, +.>Preference scores for the questions.
3. The method for predicting the accuracy of a test question according to claim 1, wherein the step of inputting the target student characteristics into a prediction model of the accuracy of the test question to obtain the accuracy of the test question to be predicted by the student to be predicted, specifically comprises the steps of:
acquiring test question completion condition data, wherein the test question completion condition data comprises the conditions of different students for completing different test questions;
determining examination knowledge points contained in each test question according to the test question knowledge map;
determining the mapping relation between the examination knowledge points and the student characteristics;
acquiring the characteristics of the target students and the test questions to be predicted;
determining target student characteristics of students to be predicted according to the wrong preference scores;
and determining the correct rate of the students to be predicted to finish the test questions to be predicted according to the target student characteristics and the mapping relation.
4. The method for predicting test question accuracy according to claim 3, wherein the step of determining the examination knowledge points included in each test question according to the test question knowledge graph specifically comprises:
acquiring a test question feature vector of each test question according to the test question text information in the test question completion condition data;
and determining examination knowledge points contained in the test questions according to the test question feature vectors and the test question knowledge graph.
5. The method for predicting the accuracy of a test question according to claim 4, wherein the step of determining the examination knowledge points included in the test question according to the feature vector of the test question and the knowledge graph of the test question specifically comprises:
and matching the test question feature vector with the knowledge point feature vector in the test question knowledge graph to determine the examination knowledge point corresponding to the test question feature vector.
6. The method for predicting the accuracy of questions according to claim 3, wherein the step of determining the accuracy of the questions to be predicted by the students to be predicted according to the target student characteristics and the mapping relation comprises the following steps:
determining examination knowledge points and knowledge point weights contained in the test questions to be predicted;
determining the accuracy of the examination knowledge points contained in the test questions to be predicted based on the students to be predicted according to the examination knowledge points contained in the test questions to be predicted and the mapping relation;
and determining the accuracy of the test questions to be predicted according to the knowledge point weight and the accuracy of the examined knowledge points.
7. The method for predicting question correctness of claim 6, further comprising:
acquiring a test question feature vector of each test question according to the text information of the test question;
determining the test question difficulty of the test questions according to the test question feature vector and the test question knowledge graph;
extracting examination knowledge points of the test questions to be predicted;
determining the grasping degree of the examination knowledge points of the students to be predicted to the predicted test questions according to the historical test question answering data;
and correcting the accuracy of the test questions to be predicted according to the mastering degree and the test question difficulty of the test questions to be predicted.
8. The prediction system of the test question accuracy is characterized by comprising:
the information acquisition unit is used for acquiring identity information of the student to be predicted;
the vector calling unit is used for calling a corresponding initialization vector in the initial vector database according to the identity information;
the data acquisition unit is used for acquiring corresponding historical test question answer data according to the identity information;
the coefficient determining unit is used for determining the wrong question preference score of the student to be predicted according to the initialization vector and the historical test question answer data;
the feature determining unit is used for determining the features of the target students according to the wrong preference scores;
and the result prediction unit is used for inputting the characteristics of the target students into a prediction model of the test question accuracy rate to obtain the accuracy rate of the students to be predicted to finish the test questions to be predicted.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method for predicting the accuracy of questions as claimed in any one of claims 1 to 7 when executing the program.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the method of predicting question correctness according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311333253.6A CN117313943A (en) | 2023-10-13 | 2023-10-13 | Test question accuracy prediction method, system, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311333253.6A CN117313943A (en) | 2023-10-13 | 2023-10-13 | Test question accuracy prediction method, system, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117313943A true CN117313943A (en) | 2023-12-29 |
Family
ID=89255079
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311333253.6A Pending CN117313943A (en) | 2023-10-13 | 2023-10-13 | Test question accuracy prediction method, system, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117313943A (en) |
-
2023
- 2023-10-13 CN CN202311333253.6A patent/CN117313943A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110188331B (en) | Model training method, dialogue system evaluation method, device, equipment and storage medium | |
CN109635274B (en) | Text input prediction method, device, computer equipment and storage medium | |
CN109376222B (en) | Question-answer matching degree calculation method, question-answer automatic matching method and device | |
US11409964B2 (en) | Method, apparatus, device and storage medium for evaluating quality of answer | |
US11610064B2 (en) | Clarification of natural language requests using neural networks | |
CN109977199B (en) | Reading understanding method based on attention pooling mechanism | |
US11461613B2 (en) | Method and apparatus for multi-document question answering | |
CN113705092B (en) | Disease prediction method and device based on machine learning | |
CN111368096A (en) | Knowledge graph-based information analysis method, device, equipment and storage medium | |
CN114254208A (en) | Identification method of weak knowledge points and planning method and device of learning path | |
CN111460101A (en) | Knowledge point type identification method and device and processor | |
CN117076688A (en) | Knowledge question-answering method and device based on domain knowledge graph and electronic equipment | |
CN110929532B (en) | Data processing method, device, equipment and storage medium | |
CN114742319A (en) | Method, system and storage medium for predicting scores of law examination objective questions | |
CN117573985B (en) | Information pushing method and system applied to intelligent online education system | |
CN110852071A (en) | Knowledge point detection method, device, equipment and readable storage medium | |
WO2021147405A1 (en) | Customer-service statement quality detection method and related device | |
CN113705207A (en) | Grammar error recognition method and device | |
CN110334204B (en) | Exercise similarity calculation recommendation method based on user records | |
CN116861358A (en) | BP neural network and multi-source data fusion-based computing thinking evaluation method | |
CN112698977B (en) | Method, device, equipment and medium for positioning server fault | |
CN111666770B (en) | Semantic matching method and device | |
CN117313943A (en) | Test question accuracy prediction method, system, equipment and storage medium | |
CN113539520A (en) | Method, device, computer equipment and storage medium for implementing inquiry session | |
CN112131889A (en) | Intelligent Chinese subjective question scoring method and system based on big data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |