CN112102124A - Big data basic algorithm learning automatic evaluation method and system - Google Patents
Big data basic algorithm learning automatic evaluation method and system Download PDFInfo
- Publication number
- CN112102124A CN112102124A CN202010900962.8A CN202010900962A CN112102124A CN 112102124 A CN112102124 A CN 112102124A CN 202010900962 A CN202010900962 A CN 202010900962A CN 112102124 A CN112102124 A CN 112102124A
- Authority
- CN
- China
- Prior art keywords
- basic
- code
- blocks
- feature
- code blocks
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 23
- 239000011159 matrix material Substances 0.000 claims abstract description 70
- 239000013598 vector Substances 0.000 claims abstract description 56
- 238000012360 testing method Methods 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 230000003068 static effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3688—Test management for test execution, e.g. scheduling of test suites
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/40—Transformation of program code
- G06F8/41—Compilation
Abstract
The invention discloses a big data basic algorithm learning automatic evaluation method and a system, wherein the method comprises the following steps: extracting key steps of basic algorithms, and performing feature extraction to form a standard feature matrix of each basic algorithm; for each basic algorithm, acquiring a plurality of source codes of different implementation modes, dividing the source codes according to blocks to obtain basic code blocks, and establishing a corresponding relation between a feature vector in a feature matrix and the basic code blocks of each source code; acquiring basic algorithm operation codes submitted by students, compiling and running, if compiling is successful, testing, outputting a test result, and grading according to the test result; if the compiling fails, dividing the operation code according to blocks to obtain operation code blocks, and calculating an operation characteristic matrix according to the operation code blocks; and calculating the similarity between the operation feature matrix and the standard feature matrix, and grading according to the similarity. The invention can automatically evaluate the basic algorithm compiled by students and automatically locate problem areas.
Description
Technical Field
The invention relates to the technical field of online education, in particular to a big data basic algorithm learning automatic evaluation method and system.
Background
In the big data era, data mining is the most critical job. Mining of large data is the process of finding valuable, potentially useful information and knowledge hidden in it from a massive, incomplete, noisy, fuzzy, random, large database, and is also a decision support process. It is mainly based on artificial intelligence, machine learning, pattern learning, statistics, etc. International authoritative academic organisation ICDM once selected ten classical algorithms in the field of data mining: c4.5, k-Means, SVM, Apriori, EM, PageRank, AdaBoost, kNN, Naive Bayes, and CART. The classical algorithms are basic algorithms of big data, the principles of the algorithms are very clear, and open-source codes well realize programs of the algorithms, but for students, understanding of the principles of the algorithms, writing, running and applying of the basic algorithms are important parts of big data learning of the students. In online education, for a basic algorithm written by students, a conventional evaluation mode is performed by a teacher manual evaluation mode, the most important evaluation basis is the correctness of a program running result, and for a program which fails to be compiled, the evaluation standard is strong in subjectivity, lack of fairness and incapable of effectively positioning a problem code region.
Disclosure of Invention
In view of the above, the invention provides a big data basic algorithm learning automatic evaluation method and system, which are used for solving the problems that the basic algorithm compiled by students cannot be effectively automatically evaluated and the problem area cannot be automatically positioned.
The invention provides a big data basic algorithm learning automatic evaluation method, which comprises the following steps:
extracting key steps of a big data basic algorithm, extracting features of each key step to form a feature vector, and forming a standard feature matrix of each basic algorithm according to the feature vector of each key step;
for each basic algorithm, acquiring a plurality of source codes of different implementation modes, dividing the source codes according to blocks to obtain basic code blocks, and establishing a corresponding relation between a feature vector in a feature matrix and the basic code blocks of each source code;
acquiring basic algorithm operation codes submitted by students, compiling and running, if compiling is successful, testing, outputting a test result, and grading according to the test result;
if the compiling fails, dividing the operation code according to blocks to obtain operation code blocks, and calculating an operation characteristic matrix of the operation code according to the operation code blocks; and calculating the similarity between the operation characteristic matrix and the standard characteristic matrix, and performing basic algorithm learning scoring according to the similarity.
Preferably, the key steps of the basic algorithm are represented by a form of natural language or pseudo code.
Preferably, feature extraction is performed on each key step to form a feature vector, specifically:
and extracting key words and calculating weight by adopting a TF-IDF method, and establishing a vector space model of each key step.
Preferably, the corresponding relation between the feature vector and the basic code block of each source code is one-to-one or one-to-many
Preferably, the calculating the job feature matrix of the job code according to the job code block specifically includes: calculating semantic similarity between each job code block and a basic code block of each source code;
for the operation code blocks and the basic code blocks with the semantic similarity exceeding a set threshold, acquiring the feature vectors corresponding to the basic code blocks from the standard feature matrix, and for the operation code blocks with the semantic similarity smaller than or equal to the set threshold, expressing the operation code blocks by using zero vectors to obtain the feature vectors corresponding to each operation code block; and forming a job feature matrix by using the feature vectors corresponding to each job code block.
In a second aspect of the present invention, an automatic evaluation system for big data base algorithm learning is disclosed, the system comprising:
a standard feature establishing module: the method comprises the steps of selecting a plurality of basic algorithms commonly used in the field of big data, extracting key steps of each basic algorithm, performing feature extraction on each key step to form a feature vector, and forming a standard feature matrix of each basic algorithm according to the feature vector of each key step;
a corresponding relation establishing module: the method comprises the steps of obtaining a plurality of source codes of different implementation modes for each basic algorithm, dividing the source codes according to blocks, extracting semantic features of each block to obtain basic code blocks, forming a block matrix, and establishing a corresponding relation between the basic code blocks of each source code and feature vectors in the feature matrix;
and a dynamic scoring module: acquiring basic algorithm operation codes submitted by students, compiling and running, if compiling is successful, testing, outputting a test result, and grading according to the test result;
a static scoring module: if the compiling fails, dividing the operation code according to blocks to obtain operation code blocks, and calculating an operation characteristic matrix of the operation code according to the operation code blocks; and calculating the similarity between the operation feature matrix and the standard feature matrix, and grading according to the similarity.
Preferably, the static scoring module specifically includes:
dividing the units by blocks: dividing the homework code of the student into blocks to obtain homework code blocks;
a feature calculation unit: calculating semantic similarity between each job code block and a basic code block of each source code; for the operation code blocks and the basic code blocks with the semantic similarity exceeding a set threshold, acquiring the feature vectors corresponding to the basic code blocks from the standard feature matrix, and for the operation code blocks with the semantic similarity smaller than or equal to the set threshold, expressing the operation code blocks by using zero vectors to obtain the feature vectors corresponding to each operation code block; forming a job feature matrix by using the feature vectors corresponding to each job code block;
an automatic scoring unit: and calculating the similarity between the operation characteristic matrix and the standard characteristic matrix, and performing big data basic algorithm learning scoring according to the similarity.
Compared with the prior art, the invention has the following beneficial effects:
1) the method establishes a standard feature matrix for each basic algorithm, establishes a corresponding relation between each feature vector in the standard feature matrix and the basic code blocks of a plurality of source codes, indirectly establishes a corresponding relation between the student's homework codes and the standard feature matrix by calculating the similarity between each student's homework code block and each basic code block of a source code, evaluates the student's homework according to the similarity between the student's homework codes and the standard feature matrix, and improves the accuracy of homework code evaluation;
2) the integral completion degree of the basic algorithm is divided into the completion degree of the basic code blocks in a blocking mode, the basic algorithm of the student is subdivided and evaluated, the problem area of the student homework code can be effectively positioned, a teacher is helped to know the weak point of the student, the pertinence is strong, and meanwhile, the good code habit of the student is favorably cultivated.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of an automatic evaluation method for big data base algorithm learning according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Referring to fig. 1, the present invention provides an automatic evaluation method for big data base algorithm learning, including:
selecting a plurality of basic algorithms commonly used in the field of big data, extracting key steps of each basic algorithm according to the principle of the big data basic algorithm, performing feature extraction on each key step to form feature vectors, and forming a standard feature matrix of each basic algorithm according to the feature vectors of each key step; specifically, the key steps are expressed in a natural language or pseudo code mode, keywords are extracted and weights are calculated by adopting a TF-IDF method, and a vector space model of each key step is established.
For each basic algorithm, acquiring a plurality of source codes of different implementation modes, dividing the source codes according to blocks to obtain basic code blocks, and establishing a corresponding relation between a feature vector in a feature matrix and the basic code blocks of each source code; since most basic algorithms in the field of big data can extract key steps according to the algorithm principle, the implementation modes of each basic algorithm are various, but the key steps cannot be separated, so that each key step of the basic algorithms can have one or more implementation modes, namely one or more code blocks, and the corresponding relation between the feature vector and the basic code block of each source code is one-to-one or one-to-many.
The code block is formed by packaging a plurality of lines of codes together to form an independent data body for realizing a specific algorithm, and in basic algorithm programming, the coding and writing blocks of various basic code blocks have important significance for code multiplexing and code structure optimization. The partitioning by blocks may be basic block partitioning according to a code structure, or may be ampere block partitioning according to a function module.
Acquiring basic algorithm operation codes submitted by students, compiling and running, if compiling is successful, testing, outputting a test result, and grading according to the test result;
if the compiling fails, dividing the operation code according to blocks to obtain operation code blocks, and calculating an operation characteristic matrix of the operation code according to the operation code blocks; and calculating the similarity between the operation feature matrix and the standard feature matrix, and grading according to the similarity.
The calculating the job feature matrix of the job code according to the job code block specifically includes: vector space models of the job code blocks and the basic code blocks can be respectively constructed, and semantic similarity between each job code block and the basic code block of each source code is calculated in a mode of calculating cosine similarity of the vector space models; for the operation code blocks and the basic code blocks with the semantic similarity exceeding a set threshold, acquiring the feature vectors corresponding to the basic code blocks from the standard feature matrix, and for the operation code blocks with the semantic similarity smaller than or equal to the set threshold, expressing the operation code blocks by using zero vectors to obtain the feature vectors corresponding to each operation code block; and forming a job feature matrix by using the feature vectors corresponding to each job code block.
The method comprises the steps of screening out basic code blocks matched with the operation code blocks by calculating semantic similarity between each operation code block and the basic code block of each source code, if the similarity is higher than a set threshold value, successfully matching, taking the eigenvector corresponding to the basic code block as the eigenvector of the operation code block, if the similarity is smaller than or equal to the set threshold value, taking a zero vector as the eigenvector to obtain the eigenvector corresponding to each operation code block, constructing an operation characteristic matrix, and finally grading according to the similarity between the operation characteristic matrix and the standard characteristic matrix. The integral completion degree of the basic algorithm is divided into the completion degree of the basic code blocks in a blocking mode, the basic algorithm of the student is subdivided and evaluated, the problem code blocks are positioned, meanwhile, the student can be helped to develop good code habits, and a code style meeting code specifications is formed.
Corresponding to the embodiment of the method, the invention provides a big data basic algorithm learning automatic evaluation system, which comprises:
a standard feature establishing module: the method comprises the steps of selecting a plurality of basic algorithms commonly used in the field of big data, extracting key steps of each basic algorithm, performing feature extraction on each key step to form a feature vector, and forming a standard feature matrix of each basic algorithm according to the feature vector of each key step;
a corresponding relation establishing module: the method comprises the steps of obtaining a plurality of source codes of different implementation modes for each basic algorithm, dividing the source codes according to blocks, extracting semantic features of each block to obtain basic code blocks, forming a block matrix, and establishing a corresponding relation between the basic code blocks of each source code and feature vectors in the feature matrix;
and a dynamic scoring module: acquiring basic algorithm operation codes submitted by students, compiling and running, if compiling is successful, testing, outputting a test result, and grading according to the test result;
a static scoring module: if the compiling fails, dividing the operation code according to blocks to obtain operation code blocks, and calculating an operation characteristic matrix of the operation code according to the operation code blocks; and calculating the similarity between the operation feature matrix and the standard feature matrix, and grading according to the similarity. The static scoring module specifically comprises:
dividing the units by blocks: dividing the homework code of the student into blocks to obtain homework code blocks;
a feature calculation unit: calculating semantic similarity between each job code block and a basic code block of each source code; for the operation code blocks and the basic code blocks with the semantic similarity exceeding a set threshold, acquiring the feature vectors corresponding to the basic code blocks from the standard feature matrix, and for the operation code blocks with the semantic similarity smaller than or equal to the set threshold, expressing the operation code blocks by using zero vectors to obtain the feature vectors corresponding to each operation code block; forming a job feature matrix by using the feature vectors corresponding to each job code block;
an automatic scoring unit: and calculating the similarity between the operation characteristic matrix and the standard characteristic matrix, and performing big data basic algorithm learning scoring according to the similarity.
The invention establishes a standard feature matrix for each basic algorithm, establishes the corresponding relation between each feature vector in the standard feature matrix and the basic code blocks of a plurality of source codes, indirectly establishes the corresponding relation between the student's homework codes and the standard feature matrix by calculating the similarity between each student's homework code block and each basic code block of the source codes, evaluates the student's homework according to the similarity between the student's homework codes and the standard feature matrix, and improves the accuracy of homework code evaluation.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. A big data base algorithm learning automatic evaluation method is characterized by comprising the following steps:
extracting key steps of a big data basic algorithm, extracting features of each key step to form a feature vector, and forming a standard feature matrix of each basic algorithm according to the feature vector of each key step;
for each basic algorithm, acquiring a plurality of source codes of different implementation modes, dividing the source codes according to blocks to obtain basic code blocks, and establishing a corresponding relation between a feature vector in a feature matrix and the basic code blocks of each source code;
acquiring basic algorithm operation codes submitted by students, compiling and running, if compiling is successful, testing, outputting a test result, and grading according to the test result;
if the compiling fails, dividing the operation code according to blocks to obtain operation code blocks, and calculating an operation characteristic matrix of the operation code according to the operation code blocks; and calculating the similarity between the operation characteristic matrix and the standard characteristic matrix, and performing basic algorithm learning scoring according to the similarity.
2. The big data base algorithm learning automatic evaluation method according to claim 1, wherein the key steps of the base algorithm are represented by a form of natural language or pseudo code.
3. The big data base algorithm learning automatic evaluation method according to claim 1, wherein feature extraction is performed on each key step to form a feature vector, specifically:
and extracting key words and calculating weight by adopting a TF-IDF method, and establishing a vector space model of each key step.
4. The big data base algorithm learning automatic evaluation method according to claim 1, wherein the correspondence between the feature vector and the basic code block of each source code is one-to-one or one-to-many.
5. The big data base algorithm learning automatic evaluation method according to claim 1, wherein the calculating of the job feature matrix of the job code according to the job code block is specifically: calculating semantic similarity between each job code block and a basic code block of each source code;
for the operation code blocks and the basic code blocks with the semantic similarity exceeding a set threshold, acquiring the feature vectors corresponding to the basic code blocks from the standard feature matrix, and for the operation code blocks with the semantic similarity smaller than or equal to the set threshold, expressing the operation code blocks by using zero vectors to obtain the feature vectors corresponding to each operation code block; and forming a job feature matrix by using the feature vectors corresponding to each job code block.
6. A big data base algorithm learning automatic evaluation system, the system comprising:
a standard feature establishing module: the method comprises the steps of selecting a plurality of basic algorithms commonly used in the field of big data, extracting key steps of each basic algorithm, performing feature extraction on each key step to form a feature vector, and forming a standard feature matrix of each basic algorithm according to the feature vector of each key step;
a corresponding relation establishing module: the method comprises the steps of obtaining a plurality of source codes of different implementation modes for each basic algorithm, dividing the source codes according to blocks, extracting semantic features of each block to obtain basic code blocks, forming a block matrix, and establishing a corresponding relation between the basic code blocks of each source code and feature vectors in the feature matrix;
and a dynamic scoring module: acquiring basic algorithm operation codes submitted by students, compiling and running, if compiling is successful, testing, outputting a test result, and grading according to the test result;
a static scoring module: if the compiling fails, dividing the operation code according to blocks to obtain operation code blocks, and calculating an operation characteristic matrix of the operation code according to the operation code blocks; and calculating the similarity between the operation feature matrix and the standard feature matrix, and grading according to the similarity.
7. The big data base algorithm learning automatic evaluation system according to claim 6, wherein the static scoring module specifically comprises:
dividing the units by blocks: dividing the homework code of the student into blocks to obtain homework code blocks;
a feature calculation unit: calculating semantic similarity between each job code block and a basic code block of each source code; for the operation code blocks and the basic code blocks with the semantic similarity exceeding a set threshold, acquiring the feature vectors corresponding to the basic code blocks from the standard feature matrix, and for the operation code blocks with the semantic similarity smaller than or equal to the set threshold, expressing the operation code blocks by using zero vectors to obtain the feature vectors corresponding to each operation code block; forming a job feature matrix by using the feature vectors corresponding to each job code block;
an automatic scoring unit: and calculating the similarity between the operation characteristic matrix and the standard characteristic matrix, and performing big data basic algorithm learning scoring according to the similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010900962.8A CN112102124A (en) | 2020-08-31 | 2020-08-31 | Big data basic algorithm learning automatic evaluation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010900962.8A CN112102124A (en) | 2020-08-31 | 2020-08-31 | Big data basic algorithm learning automatic evaluation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112102124A true CN112102124A (en) | 2020-12-18 |
Family
ID=73756954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010900962.8A Pending CN112102124A (en) | 2020-08-31 | 2020-08-31 | Big data basic algorithm learning automatic evaluation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112102124A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809139A (en) * | 2014-01-29 | 2015-07-29 | 日本电气株式会社 | Code file query method and device |
| CN106326112A (en) * | 2016-08-15 | 2017-01-11 | 江苏海事职业技术学院 | Method and device for automatically correcting program homework |
| CN110309503A (en) * | 2019-05-21 | 2019-10-08 | 昆明理工大学 | A kind of subjective item Rating Model and methods of marking based on deep learning BERT--CNN |
| CN110502361A (en) * | 2019-08-29 | 2019-11-26 | 扬州大学 | Fine granularity defect positioning method towards bug report |
| CN110852653A (en) * | 2019-11-22 | 2020-02-28 | 成都国腾实业集团有限公司 | Automatic scoring system applied to computer programming questions |
-
2020
- 2020-08-31 CN CN202010900962.8A patent/CN112102124A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809139A (en) * | 2014-01-29 | 2015-07-29 | 日本电气株式会社 | Code file query method and device |
| CN106326112A (en) * | 2016-08-15 | 2017-01-11 | 江苏海事职业技术学院 | Method and device for automatically correcting program homework |
| CN110309503A (en) * | 2019-05-21 | 2019-10-08 | 昆明理工大学 | A kind of subjective item Rating Model and methods of marking based on deep learning BERT--CNN |
| CN110502361A (en) * | 2019-08-29 | 2019-11-26 | 扬州大学 | Fine granularity defect positioning method towards bug report |
| CN110852653A (en) * | 2019-11-22 | 2020-02-28 | 成都国腾实业集团有限公司 | Automatic scoring system applied to computer programming questions |
Non-Patent Citations (3)
| Title |
|---|
| 张丽萍等: "基于AST的多语言代码抄袭检测方法研究", 《内蒙古师范大学学报(自然科学汉文版)》 * |
| 李郴等: "编程题综合评分方法的研究", 《计算机与网络》 * |
| 王浩宇等: "《移动应用安全分析》", 31 August 2019, 北京邮电大 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Luna et al. | An evolutionary algorithm for the discovery of rare class association rules in learning management systems | |
| Minaei-Bidgoli et al. | Using genetic algorithms for data mining optimization in an educational web-based system | |
| CN111708873A (en) | Intelligent question answering method and device, computer equipment and storage medium | |
| Zhang et al. | Deep Learning+ Student Modeling+ Clustering: A Recipe for Effective Automatic Short Answer Grading. | |
| Amershi et al. | Unsupervised and supervised machine learning in user modeling for intelligent learning environments | |
| CN113254678B (en) | Training method of cross-media retrieval model, cross-media retrieval method and equipment thereof | |
| Cavalcanti et al. | Detection and evaluation of cheating on college exams using supervised classification | |
| Parikh et al. | Validating causal inference methods | |
| Garczarek | Classification rules in standardized partition spaces | |
| Geetha et al. | Prediction of the academic performance of slow learners using efficient machine learning algorithm | |
| Drăgulescu et al. | Predicting assignment submissions in a multi-class classification problem | |
| CN110991172B (en) | Domain name recommendation method, domain name recommendation model training method and electronic equipment | |
| CN112102124A (en) | Big data basic algorithm learning automatic evaluation method and system | |
| CN116861358A (en) | BP neural network and multi-source data fusion-based computing thinking evaluation method | |
| Akram et al. | Automated assessment of computer science competencies from student programs with gaussian process regression | |
| Galhardi et al. | Automatic grading of portuguese short answers using a machine learning approach | |
| US20210398025A1 (en) | Content Classification Method | |
| Xiaohui | An adaptive genetic algorithm-based background elimination model for English text | |
| Aldabbas | An iot based framework for students’ interaction and plagiarism detection in programming assignments | |
| Pelánek et al. | Towards design-loop adaptivity: identifying items for revision | |
| Chaturvedi et al. | Clustering Examples in Web-based Tutoring Systems based on Relevance of Concepts | |
| Menaka et al. | Performance of Data Mining Classifiers on Kolb’s Learning Style Inventory (KLSI)’ | |
| Hemantkumar et al. | A Survey on Educational Data Mining using Association Rule Mining | |
| Wang et al. | Textbook Enhanced Student Learning Outcome Prediction | |
| CN110019772A (en) | A kind of text mood classification method and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201218 |