CN116361454A - Automatic course teaching case assessment method based on Bloom classification method - Google Patents
Automatic course teaching case assessment method based on Bloom classification method Download PDFInfo
- Publication number
- CN116361454A CN116361454A CN202310122823.0A CN202310122823A CN116361454A CN 116361454 A CN116361454 A CN 116361454A CN 202310122823 A CN202310122823 A CN 202310122823A CN 116361454 A CN116361454 A CN 116361454A
- Authority
- CN
- China
- Prior art keywords
- layer
- teaching
- classification
- output end
- input end
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 16
- 238000013210 evaluation model Methods 0.000 claims abstract description 10
- 230000011218 segmentation Effects 0.000 claims abstract description 7
- 238000013145 classification model Methods 0.000 claims abstract description 6
- 238000011156 evaluation Methods 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 19
- 238000011176 pooling Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 13
- 230000004913 activation Effects 0.000 claims description 11
- 230000019771 cognition Effects 0.000 claims description 10
- 239000000463 material Substances 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 5
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000002372 labelling Methods 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- MCNQUWLLXZZZAC-UHFFFAOYSA-N 4-cyano-1-(2,4-dichlorophenyl)-5-(4-methoxyphenyl)-n-piperidin-1-ylpyrazole-3-carboxamide Chemical compound C1=CC(OC)=CC=C1C1=C(C#N)C(C(=O)NN2CCCCC2)=NN1C1=CC=C(Cl)C=C1Cl MCNQUWLLXZZZAC-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- 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
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/374—Thesaurus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a course teaching case automatic assessment method based on a Bloom classification method, which comprises the steps of firstly collecting teaching cases from courses of a computer science to be assessed, and finishing the teaching cases into a document containing a plurality of teaching cases; labeling the well-arranged case data, and standardizing the case data into a standard data set format; building a classification model based on a pre-training language model and a convolutional neural network, and training the model by using the preprocessed case data set; and finally, sending the course teaching case data set to be evaluated into a trained classification model based on a pre-training language model and a convolutional neural network for text classification, and obtaining an accurate classification result of the test case data set to be classified. The method constructs the course teaching case data set of the small sample, the constructed evaluation model enhances the recognition and segmentation capability of Chinese words, has better semantic representation capability and capability of capturing context semantics, and improves the performance of automatically classifying the course teaching cases.
Description
Technical Field
The invention relates to the technical field of Chinese text classification, in particular to a curriculum teaching case automatic evaluation method based on a Bloom classification method.
Background
The blood classification method is applied to the evaluation and classification stage of education achievements in specific fields, and mainly comprises two means of manual evaluation and machine evaluation. Early manual assessment was not only time consuming and laborious, but the assessment results were largely dependent on the subjective tendencies of the educators. The evaluation means based on machine learning standardizes the evaluation standard, so that an evaluator can rely on the evaluation standard, and simultaneously, the evaluation workload is reduced, and the evaluation means mainly comprise a method based on supervised learning and a method based on deep learning.
The supervised learning-based method classifies samples according to learned rules by adjusting parameters of the classifier using samples of known classes. Yusfo et al tried different feature engineering and supervised learning model combinations using Support Vector Machine (SVM) classifiers that were able to determine data based on confidence, but this approach was not good for the high dimensional classification results of cognitive processes. Zhang et al propose classification methods of category frequency-inverse document frequency (CF-IDF), which utilize the frequency of each category label to classify the problem, and which can better determine sample labels with fewer occurrences, but have poor determination effect on labels with larger number of samples. Omar et al apply natural language processing based technical recognition, use important classification keywords in the decision process, use a rule-based method to recognize the desired cognitive process dimension level, the method cannot fully learn rules due to insufficient scale of training sets, and the text sentences used by the method are too simple and direct, so that the evaluation effect is more accurate only in the memory and understanding dimensions. The method based on supervised learning is suitable for data samples with smaller scale and shorter text length, but the supervised learning requires examining the data samples used for training, and requires a lot of calculation time for training to design relevant decision rules.
The method based on deep learning can automatically learn basic features of the text through a model and combine the basic features into advanced features, so that feature extraction of the text is realized, and a proper classifier is selected according to a specific task to realize sample evaluation. With the continuous improvement of computer computing power and the explosive growth of unsupervised text data, deep learning models are widely applied to the field of text classification. Manjuhree et al applied deep learning based model Convolutional Neural Networks (CNNs) and long-term memory networks (LSTMs) to classify evaluation samples into the Bloom taxonomy cognitive process dimension, which collected and manually labeled 844 example samples from a software engineering course. The team follows the data samples as a training set: test set was 7:3, on the test set using the CNN model, the team of authors achieved better results in the low dimension of the cognitive process, but not in the evaluation and above dimensions. In addition, most of the existing data sets are English data, and the data sets in the related Chinese fields are lacking, so that the effect of a deep learning model for automatically classifying the Chinese case data sets is poor, and therefore, development of an automatic evaluation method suitable for the Chinese case data sets for teaching in computer science courses is needed.
Disclosure of Invention
The invention aims to solve the problems that the existing small sample case data set is limited in scale number, training samples contain insufficient information and the automatic classification effect on the teaching case data set is poor, and provides a course teaching case automatic assessment method based on a Bloom classification method.
In order to solve the problems, the invention is realized by the following technical scheme:
a course teaching case automatic evaluation method based on a Bloom classification method specifically comprises the following steps:
step 1, collecting teaching cases from courses of a computer science to be evaluated, wherein the teaching cases comprise teaching materials and teaching cases, and the teaching cases are arranged into a document containing a plurality of teaching cases;
the method comprises the steps of extracting the content representing the teaching target of the section in a case into sentences during arrangement, wherein the teaching target contains keywords in the case content, so that the sentences representing the teaching target are used as data texts for automatically classifying the case, screening original teaching materials and teaching plan content, and deleting non-text content in the case and texts containing more formula symbols;
marking the well-arranged teaching cases according to a Bloom classification verb dictionary, wherein the verb dictionary comprises related words in a cognitive process dimension and a knowledge dimension, the related words are verbs, the cases are divided into the cognitive process dimension and the knowledge dimension according to words and contents most relevant to the related words in the teaching cases, the well-marked teaching cases are then arranged into a standard data set format, and the contents comprise Bloom classification labels and teaching targets extracted from the cases;
step 3, constructing a deep learning course case assessment model based on a Bloom classification method;
step 4, training the assessment model built in the step 3 by using the case data set arranged in the step 2, inputting the course case data set, calculating batch data through a loss function to obtain loss, updating by using an Adam gradient descent algorithm, and obtaining a trained assessment model after iterative training for epoch times;
step 5, inputting the course teaching case data set to be evaluated into the evaluation model trained in the step 4 for evaluation;
step 6, outputting an evaluation result to obtain an accurate classification result of the course teaching case data set to be evaluated, wherein the result comprises a macro accuracy rate and a macro F1 value, and a macro accuracy rate calculation formula is as follows:
the macro F1 value calculation formula is:
wherein K is the category number, P i Representing accuracy, P macro Represents macro accuracy value, R macro Representing a macro recall value.
The evaluation model comprises a pre-training language model and a classification model of a convolutional neural network, and consists of a trunk structure, a text convolutional structure and a downsampling structure which are sequentially connected, and particularly consists of an input layer, a pre-training layer, a word embedding layer, a text convolutional layer and an output layer; the output end of the Input layer Input is connected with the Input end of the encoder module, the output end of the encoder module is connected with the Input end of the word embedding layer, the output end of the word embedding layer is connected with the Input end of the text convolution layer, and the output end of the text convolution layer is connected with the Input end of the output layer.
The encoder module consists of a multi-head self-attention module, a first layer residual error module, a second layer residual error module and two feedforward network modules; the input end of the multi-head self-attention module forms the input end of the pre-training layer, the output end of the multi-head self-attention module is connected with the input end of the first layer residual error module, the output end of the first layer residual error module is connected with the input ends of the two feedforward network modules, the output ends of the two feedforward network modules are connected with the input end of the second layer residual error module, and the output end of the second layer residual error module forms the output end of the pre-training layer.
The text convolution layer consists of a convolution kernel, a feature matrix and a full connection layer; the input end of the convolution kernel forms the input end of the text convolution layer, the convolution kernel carries out convolution operation with input data to obtain a feature matrix, the calculated feature matrix is sent to the input end of the full-connection layer, after the full-connection layer carries out pooling operation on the feature matrix, the result is sent to the output end of the full-connection layer, the output end of the full-connection layer carries out calculation by using a softMax activation function, and the output of the softMax activation function forms the output end of the text convolution layer.
The pre-training language model is a pre-training model using Chinese word segmentation, and the pre-word segmentation operation is added into the model to identify Chinese words and segment the Chinese words; the convolutional neural network is a convolutional neural network represented by n-gram features, and the convolutional neural network performs feature extraction and classification by using word vectors containing semantic information.
Compared with the prior art, the course case data set constructed by the method comprehensively solves the problems that the scale of the traditional Chinese course case data set in the computer science is small, labeling is not standard, evaluation links for two dimensions of a Bloom classification method are lacked, and the traditional machine learning text classification technology is inaccurate for Chinese segmentation in the case data set, word vector semantic learning is insufficient, builds a course teaching case data set with a small sample, standardizes labeling criteria, proposes an automatic evaluation model based on a pre-training language model and a text convolutional neural network, enhances the recognition and segmentation capability of Chinese words, has better semantic representation capability and the capability of capturing context semantics, improves the automatic classification performance of the case data set, and further improves the automatic evaluation performance of applying the Bloom classification method to the Chinese course case data set in the computer science.
Drawings
FIG. 1 is a flow chart of an evaluation method of the present invention;
FIG. 2 is a schematic diagram of an evaluation model structure in the evaluation method of the present invention;
FIG. 3 is a schematic diagram of the encoder module in the evaluation model of the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but is not limited thereto.
Examples
A course teaching case automatic evaluation method based on a Bloom classification method is shown in fig. 1, and specifically comprises the following steps:
step 1: collecting teaching cases from courses of computer science to be evaluated, including teaching materials and teaching plans, and arranging the teaching cases into a document containing a plurality of teaching cases;
the collected case sets are mainly derived from computer science curriculum teaching materials and teaching material related teaching plan, the contents representing the teaching targets of the section in the cases are extracted into sentences during arrangement, and the teaching targets contain keywords in the case contents, so that the sentences representing the teaching targets are used as data texts for automatically classifying the cases, the original teaching material teaching plan contents are screened, and non-text contents in the cases and texts containing more formula symbols are deleted;
marking the well-arranged teaching cases according to a Bloom classification verb dictionary, wherein the verb dictionary comprises related words in a cognitive process dimension and a knowledge dimension, the related words are verbs, the cases are divided into the cognitive process dimension and the knowledge dimension according to words and contents most relevant to the related words in the teaching cases, the well-marked teaching cases are then arranged into a standard data set format, and the contents comprise Bloom classification labels and teaching targets extracted from the cases;
step 3: constructing a classification model based on a pre-training language model and a convolutional neural network, setting network parameters, obtaining loss by calculating a loss function of batch data, updating by using an Adam gradient descent algorithm, and performing iterative training for epoch times;
step 4, training the assessment model built in the step 3 by using the case data set arranged in the step 2, inputting the course case data set, calculating batch data through a loss function to obtain loss, updating by using an Adam gradient descent algorithm, and obtaining a trained assessment model after iterative training for epoch times;
step 5, inputting the course teaching case data set to be evaluated into the evaluation model trained in the step 4 for evaluation;
step 6, outputting an evaluation result to obtain an accurate classification result of the course teaching case data set to be evaluated, wherein the result comprises a macro accuracy rate and a macro F1 value, and a macro accuracy rate calculation formula is as follows:
the macro F1 value calculation formula is:
wherein K is the category number, P i Representing accuracy, P macro Represents macro accuracy value, R macro Representing a macro recall value.
The evaluation model, as shown in fig. 2, comprises a pre-training language model and a classification model of a convolutional neural network, and consists of a main structure, a text convolutional structure and a downsampling structure which are sequentially connected, and particularly comprises an input layer, a pre-training layer, a word embedding layer, a text convolutional layer and an output layer;
1) Backbone structure
In the backbone structure, the output end of the Input layer Input is connected with the Input end of the encoder module, see fig. 3, and the encoder module consists of a multi-head self-attention module, a first layer residual error module, a second layer residual error module and two feedforward network modules; the input end of the multi-head self-attention module forms the input end of the encoder module, the output end of the multi-head self-attention module is connected with the input end of the first layer residual error module, the output end of the first layer residual error module is connected with the input ends of the two feedforward network modules, the output ends of the two feedforward network modules are connected with the input end of the second layer residual error module, the output end of the second layer residual error module forms the output end of the encoder module, and the output end of the encoder module is connected with the input end of the word embedding layer;
the encoder module feeds the input information to a multi-headed self-attention module that, when encoding a particular word, looks at other words in the sentence to determine the weight of the particular word, the multi-headed self-attention mechanism having a computational formula of
The output end of the multi-head self-attention module is connected with a first layer residual error module, the residual error module is used for transmitting output information deeper, the output end of the first layer residual error module is connected with two feedforward neural networks in parallel, the output ends of the two feedforward neural networks are connected with a second layer residual error module, the feedforward neural networks use a ReLU activation function, and a calculation formula is FFN (x) =max (0, xW1+b1) W2+b2;
2) Text convolution structure
In the text convolution structure, a text convolution layer consists of a convolution kernel, a feature matrix and a full connection layer; the input end of the convolution kernel forms the input end of the text convolution layer, the convolution kernel carries out convolution operation with input data to obtain a feature matrix, the calculated feature matrix is sent to the input end of the full-connection layer, after the full-connection layer carries out pooling operation on the feature matrix, the result is sent to the output end of the full-connection layer, the output end of the full-connection layer carries out calculation by using a softMax activation function, the output of the softMax activation function forms the output end of the text convolution layer, and the calculation formula of the softMax activation function is that
Wherein C is the number of output nodes;
3) Downsampling structure
In the downsampling structure, the input end of the pooling layer forms the input end of the downsampling structure, the maximum pooling function in the pooling layer extracts the maximum value in the feature vector to represent the feature, the extracted feature is cascaded and input to the output end of the pooling layer, and the calculation formula of the maximum pooling function is as follows
c is the eigenvector in the current sliding window, < >>
The maximum value in the feature vector is represented, the output end of the pooling layer is connected with the input end of the full-connection layer, the full-connection layer uses a SoftMax activation function to perform normalization processing to obtain probability distribution, the probability distribution is input to the input end of the full-connection layer, and the output end of the full-connection layer forms the output end of the downsampling structure.
It should be noted that, although the examples described above are illustrative, this is not a limitation of the present invention, and thus the present invention is not limited to the above-described specific embodiments. Other embodiments, which are apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein, are considered to be within the scope of the invention as claimed.
Claims (6)
1. A course teaching case automatic evaluation method based on a Bloom classification method is characterized by comprising the following steps:
step 1, collecting teaching cases from courses of a computer science to be evaluated, wherein the teaching cases comprise teaching materials and teaching cases, and the teaching cases are arranged into a document containing a plurality of teaching cases;
extracting the content representing the teaching target of the section into sentences in the case during arrangement, taking the sentences representing the teaching target as data texts for automatic case classification, screening the original teaching materials and teaching plan content, and deleting non-text content and texts containing more formula symbols in the case;
marking the well-arranged teaching cases according to a Bloom classification verb dictionary, wherein the verb dictionary comprises related words in a cognitive process dimension and a knowledge dimension, the related words are verbs, the cases are divided into the cognitive process dimension and the knowledge dimension according to words and contents most relevant to the related words in the teaching cases, the well-marked teaching cases are then arranged into a standard data set format, and the contents comprise Bloom classification labels and teaching targets extracted from the cases;
step 3, constructing a deep learning course case assessment model based on a Bloom classification method;
step 4, training the assessment model built in the step 3 by using the case data set arranged in the step 2, inputting the course case data set, calculating batch data through a loss function to obtain loss, updating by using an Adam gradient descent algorithm, and obtaining a trained assessment model after iterative training for epoch times;
step 5, inputting the course teaching case data set to be evaluated into the evaluation model trained in the step 4 for evaluation;
step 6, outputting an evaluation result to obtain an accurate classification result of the course teaching case data set to be evaluated, wherein the result comprises a macro accuracy rate and a macro F1 value, and a macro accuracy rate calculation formula is as follows:
the macro F1 value calculation formula is:
wherein K is the category number, P i Representing accuracy, P macro Represents macro accuracy value, R macro Representing a macro recall value.
2. The method for automatic assessment of course teaching cases according to claim 1, wherein: the evaluation model comprises a pre-training language model and a classification model of a convolutional neural network, and consists of a trunk structure, a text convolutional structure and a downsampling structure which are sequentially connected, and particularly consists of an input layer, a pre-training layer, a word embedding layer, a text convolutional layer and an output layer; the output end of the Input layer Input is connected with the Input end of the encoder module, the output end of the encoder module is connected with the Input end of the word embedding layer, the output end of the word embedding layer is connected with the Input end of the text convolution layer, and the output end of the text convolution layer is connected with the Input end of the output layer.
3. The automatic course teaching case assessment method according to claim 2, wherein: the pre-training language model is a pre-training model using Chinese word segmentation, and the pre-word segmentation operation is added into the model to identify Chinese words and segment the Chinese words; the convolutional neural network is a convolutional neural network represented by n-gram features, and the convolutional neural network performs feature extraction and classification by using word vectors containing semantic information.
4. The automatic course teaching case assessment method according to claim 2, wherein: the encoder module consists of a multi-head self-attention module, a first layer residual error module, a second layer residual error module and two feedforward network modules; the input end of the multi-head self-attention module forms the input end of the pre-training layer, the output end of the multi-head self-attention module is connected with the input end of the first layer residual error module, the output end of the first layer residual error module is connected with the input ends of the two feedforward network modules, the output ends of the two feedforward network modules are connected with the input end of the second layer residual error module, and the output end of the second layer residual error module forms the output end of the pre-training layer.
5. The automatic course teaching case assessment method according to claim 2, wherein: the text convolution layer consists of a convolution kernel, a feature matrix and a full connection layer; the input end of the convolution kernel forms the input end of the text convolution layer, the convolution kernel carries out convolution operation with input data to obtain a feature matrix, the calculated feature matrix is sent to the input end of the full-connection layer, and after the full-connection layer carries out pooling operation on the feature matrix, the feature matrix is pooledThe output end of the full connection layer is calculated by using a SoftMax activation function, the output of the SoftMax activation function forms the output end of the text convolution layer, and the calculation formula of the SoftMax activation function is as follows
Wherein C is the number of output nodes.
6. The automated course teaching case assessment method of claim 5, wherein: the input end of the pooling layer forms an input end of a downsampling structure, the maximum pooling function in the pooling layer extracts the maximum value in the feature vector to represent the feature, the extracted feature is cascaded and input to the output end of the pooling layer, and the calculation formula of the maximum pooling function is as follows
c is the eigenvector in the current sliding window, < >>
The maximum value in the feature vector is represented, the output end of the pooling layer is connected with the input end of the full-connection layer, the full-connection layer uses a SoftMax activation function to perform normalization processing to obtain probability distribution, the probability distribution is input to the input end of the full-connection layer, and the output end of the full-connection layer forms the output end of the downsampling structure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310122823.0A CN116361454A (en) | 2023-02-16 | 2023-02-16 | Automatic course teaching case assessment method based on Bloom classification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310122823.0A CN116361454A (en) | 2023-02-16 | 2023-02-16 | Automatic course teaching case assessment method based on Bloom classification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116361454A true CN116361454A (en) | 2023-06-30 |
Family
ID=86912416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310122823.0A Pending CN116361454A (en) | 2023-02-16 | 2023-02-16 | Automatic course teaching case assessment method based on Bloom classification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116361454A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116611349A (en) * | 2023-07-18 | 2023-08-18 | 华东交通大学 | Neural network-based roller wire drying process parameter optimization method and system |
-
2023
- 2023-02-16 CN CN202310122823.0A patent/CN116361454A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116611349A (en) * | 2023-07-18 | 2023-08-18 | 华东交通大学 | Neural network-based roller wire drying process parameter optimization method and system |
| CN116611349B (en) * | 2023-07-18 | 2023-10-10 | 华东交通大学 | Neural network-based roller wire drying process parameter optimization method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108984526B (en) | Document theme vector extraction method based on deep learning | |
| CN107133220B (en) | Geographic science field named entity identification method | |
| CN108460089B (en) | Multi-feature fusion Chinese text classification method based on Attention neural network | |
| CN111309912B (en) | Text classification method, apparatus, computer device and storage medium | |
| CN107590177B (en) | Chinese text classification method combined with supervised learning | |
| CN111985247B (en) | Microblog user interest identification method and system based on multi-granularity text feature representation | |
| CN110188195B (en) | Text intention recognition method, device and equipment based on deep learning | |
| CN110427458B (en) | Social network bilingual five-classification emotion analysis method based on double-gate LSTM | |
| CN109492105B (en) | Text emotion classification method based on multi-feature ensemble learning | |
| CN104966105A (en) | Robust machine error retrieving method and system | |
| CN111966825A (en) | Power grid equipment defect text classification method based on machine learning | |
| CN112966068A (en) | Resume identification method and device based on webpage information | |
| CN110232128A (en) | Topic file classification method and device | |
| CN114416979A (en) | Text query method, text query equipment and storage medium | |
| CN114722835A (en) | Text emotion recognition method based on LDA and BERT fusion improved model | |
| CN111191033B (en) | Open set classification method based on classification utility | |
| CN116361454A (en) | Automatic course teaching case assessment method based on Bloom classification method | |
| CN113312907B (en) | Remote supervision relation extraction method and device based on hybrid neural network | |
| CN113160917B (en) | Electronic medical record entity relation extraction method | |
| CN114691525A (en) | Test case selection method and device | |
| CN112347247B (en) | Specific category text title classification method based on LDA and Bert | |
| CN112784601A (en) | Key information extraction method and device, electronic equipment and storage medium | |
| CN116050419B (en) | Unsupervised identification method and system oriented to scientific literature knowledge entity | |
| CN116595170A (en) | Medical text classification method based on soft prompt | |
| CN115879463A (en) | Course element recognition model training and recognition method based on text mining |
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 |