CN118051442B - Test case multiplexing method and system based on spectral clustering - Google Patents
Test case multiplexing method and system based on spectral clustering Download PDFInfo
- Publication number
- CN118051442B CN118051442B CN202410444426.XA CN202410444426A CN118051442B CN 118051442 B CN118051442 B CN 118051442B CN 202410444426 A CN202410444426 A CN 202410444426A CN 118051442 B CN118051442 B CN 118051442B
- Authority
- CN
- China
- Prior art keywords
- test case
- test
- similarity
- attribute
- spectral clustering
- 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.)
- Active
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 251
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000003595 spectral effect Effects 0.000 title claims abstract description 38
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 26
- 241000544061 Cuculus canorus Species 0.000 claims abstract description 12
- 238000010845 search algorithm Methods 0.000 claims abstract description 12
- 238000013461 design Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims description 26
- 239000011159 matrix material Substances 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000003064 k means clustering Methods 0.000 claims description 9
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 5
- 238000013522 software testing Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a test case multiplexing method and a system based on spectral clustering, wherein the method comprises the following steps: step 1, selecting the attribute of a test case; step 2, extracting attributes of the historical test cases, and storing the extraction results in a test case multiplexing library in a collection mode; step 3, performing spectral clustering operation on the specific attribute information by using a spectral clustering algorithm; step 4, the user inputs each attribute information and key words of the tested item, searches and matches from the generated test case cluster by using a cuckoo search algorithm, and judges whether the test case is matched; the matched test cases are combined with the input data information, and the test cases applicable to the tested items are output; and if not, the tester designs a new test case, inputs the new test case into a test case multiplexing library, and generates a new reusable test case by using a spectral clustering algorithm.
Description
Technical Field
The invention relates to the field of software testing, in particular to a test case multiplexing method and system based on spectral clustering.
Background
In modern software development, test cases are a critical tool for verifying that the functionality of the software is in line with expectations and for checking that the program structure inside the software is correct. However, designing and writing test cases is often very time consuming because of the significant human and time investment required. To improve test efficiency, current solutions use historical test data and accumulated knowledge to guide the design and writing of new test cases. The core of the method is to reuse the existing test cases, thereby avoiding repeated work and shortening the test period. By analyzing past test results and experience, a tester can more quickly determine new test needs and design more comprehensive and efficient test cases. The method not only can improve the testing efficiency, but also can improve the skill level of the testers, help the testers to better cope with various testing scenes, and improve the quality of software testing.
Patent CN 112527650A discloses a test case multiplexing method and multiplexing device. According to the invention, firstly, source analysis and data analysis are carried out on historical test cases, then, case information analysis is carried out on data obtained through analysis, and the matched test cases and input test data are combined to carry out new test case output through a directional script data module, so that test case multiplexing is completed. The method can well realize test case multiplexing of similar items, but the method still has a plurality of problems:
1. The classification method of the history test cases is too simple: the method only carries out basic source analysis and data decomposition on the historical test cases, and classifies the test cases according to the basic source analysis and the data decomposition, and the method can cause the condition that the recommended test cases are inconsistent with the test cases intended by the user in the process of recommending the test cases.
2. The limitation of selecting target design specification information is large: limitations that users may face include, but are not limited to, limited input options, constraints on input parameters, and the like. This may limit the user to flexibly input according to the requirements of a specific project, resulting in a situation that the recommended test case does not conform to the actual test scenario.
3. The processing method is ambiguous when the system cannot find the proper test case: when the system cannot find a matching test case, no explicit processing method is provided.
Disclosure of Invention
The invention aims to: a test case multiplexing method and system based on spectral clustering are provided to solve the above problems existing in the prior art.
The technical scheme is as follows: a test case multiplexing method based on a spectral clustering algorithm comprises the following steps:
step 1, selecting the attribute of a test case;
step 2, extracting attributes of the historical test cases, and storing the extraction results in a test case multiplexing library in a collection mode;
step 3, performing spectral clustering operation on the specific attribute information by using a spectral clustering algorithm;
Step 4, the user inputs each attribute information and key words of the tested item, searches and matches from the generated test case cluster by using a cuckoo search algorithm, and judges whether the test case is matched;
the matched test cases are combined with the input data information, and the test cases applicable to the tested items are output;
And if not, the tester designs a new test case, inputs the new test case into a test case multiplexing library, and generates a new reusable test case by using a spectral clustering algorithm.
According to the invention, the spectral clustering algorithm is designed to add attribute labels to test cases, extract corresponding attribute information, calculate the distance of each attribute information, cluster similar attributes, and search the most conforming test cases through the input keywords, so that the success rate of multiplexing the test cases and the conformity with the actual scenes are greatly improved, the most similar test cases with the input keywords can be efficiently selected, the selection efficiency of the test cases is improved, the redundancy and repetition of the test cases are reduced, the software test flow is accelerated, the test period is shortened, and the release speed and quality of software are improved.
In a further embodiment, the attribute of the test case includes a test type, a case name, a test description, a precondition, a test input, a test step, and a test result.
In a further embodiment, in the test case multiplex library, the attribute of the test case is used as a primary key, and specific information of each attribute is stored as a value corresponding to the primary key.
In a further embodiment, the step of the spectral clustering algorithm is:
And step 01, extracting specific information of each attribute from the test case multiplexing library, and constructing an attribute matrix. Wherein each row represents a test case and each column represents an attribute.
And 02, converting the attribute information of each test case into a feature vector, wherein the method is realized through a Bag of Words model (Bag of Words). For each attribute, representing it as a vector, each dimension of the feature vector corresponding to a vocabulary, each element of the feature vector representing the frequency or weight of occurrence of the vocabulary in the attribute information, cosine similarity is used to calculate the similarity distance of the respective attribute, comprising:
Wherein, And/>Representing two vectors respectively,/>Representing the dot product of two vectors,/>And/>Respectively representing the modes of the two vectors, and obtaining the range in/>, through cosine similarity calculation,/>A similarity value between the two attributes, the closer the value is to 1, the higher the similarity between the two attributes is;
Step 03, each test case is represented as a node in the graph, and each node has a unique identifier, which may be an ID or other identifier of the test case.
According to cosine similarity, calculating similarity between each pair of test cases to obtain a similarity matrix, wherein each elementThe similarity between the test case i and the test case j is represented; for each element in the similarity matrix/>When the test case is larger than the set threshold value, adding an edge in the graph, and connecting the test case/>And test case j, the weight of the edge is the similarity/>;
Step 04, calculating a Laplacian matrix according to the similarity graph, wherein the calculation formula is as followsWherein/>For degree matrix,/>Is an adjacency matrix;
Step 05, carrying out eigenvector decomposition on the Laplace matrix to obtain an eigenvector matrix;
step 06, constructing a new feature space according to feature vectors corresponding to the first few minimum feature values;
And 07, clustering the test cases in the feature space through a K-Means clustering algorithm to determine the clustering number K, in the K-Means clustering process, firstly randomly selecting K initial centroids, then distributing each data point into the cluster where the centroid closest to the initial centroid is located, updating the centroid of each cluster, and repeating the K-Means clustering process until the centroid is not changed or the maximum iteration number is reached.
In a further embodiment, the process of using a cuckoo search algorithm to retrieve matches from the generated test case clusters is:
Step 001: randomly selecting a plurality of clusters from the generated test case clusters as part of an initial population; it is necessary to ensure that the population size covers the various situations that need to be tested.
Step 002: according to the input keywords, calculating the similarity between the keywords and each cluster, wherein the calculation formula of the similarity is expressed as follows:
Wherein testcase represents a test case set in the initialized population, inputKeywords represents an input keyword set, J () represents calculation using Jaccard similarity, and the calculation formula is:
wherein A and B are respectively two input vectors, Representing the intersection size of the two,/>Representing the union size of the two;
and step 003, traversing the test case multiplexing library, and selecting the test case with higher fitness as an optimal solution for output.
And in the combining step 003, the test cases are output through a cuckoo search algorithm, and the output module combines the test cases with the test data of the tested items to output the test cases.
A test case multiplexing system based on spectral clustering, comprising:
The input module is used for inputting the attribute and data information of the visual test cases of the items to be tested;
the retrieval module is used for carrying out retrieval matching on the attribute information of the tested item and the test case cluster;
the output module is used for combining the searched optimal test cases with the input test data and outputting test cases applicable to the items to be tested;
The creation module is used for creating a new test case by a tester when the test case which is the same or similar to the tested item is not matched, inputting the new test case into the test case database and generating a test case cluster.
The beneficial effects are that: the invention discloses a test case multiplexing method and a test case multiplexing system based on spectral clustering.
Drawings
FIG. 1 is a flow chart of the steps of the method of the present invention;
fig. 2 is a diagram of a system architecture of the present invention.
Detailed Description
The application relates to a test case multiplexing method and a test case multiplexing system based on spectral clustering, which select the attribute of an embedded software test case: test type, use case name, test description, preconditions, test inputs, test steps, test results. Then extracting attributes of the historical test cases, and storing the extraction results in a test case multiplexing library in a collection mode; selecting an attribute in the embedded software test case as a label, and carrying out spectrum classification on specific attribute information; the user inputs each attribute information and key words of the tested item, and the cuckoo search algorithm is used for searching and matching from the generated test case cluster; combining the matched test cases with the data information of the tested item to generate test cases applicable to the tested item; if the test cases which are the same or similar to the tested items are not searched, the testers design new test cases, input the new test cases into a test case multiplexing library, and generate new reusable test cases by using a spectral clustering algorithm. The extraction method of the reusable test cases effectively improves the efficiency of software testing and reduces the related cost.
The following is a detailed explanation of the embodiments.
A test case multiplexing method based on a spectral clustering algorithm comprises the following steps:
step 1, selecting the attribute of a test case;
step 2, extracting attributes of the historical test cases, and storing the extraction results in a test case multiplexing library in a collection mode;
step 3, performing spectral clustering operation on the specific attribute information by using a spectral clustering algorithm;
Step 4, the user inputs each attribute information and key words of the tested item, searches and matches from the generated test case cluster by using a cuckoo search algorithm, and judges whether the test case is matched;
the matched test cases are combined with the input data information, and the test cases applicable to the tested items are output;
And if not, the tester designs a new test case, inputs the new test case into a test case multiplexing library, and generates a new reusable test case by using a spectral clustering algorithm.
According to the invention, the spectral clustering algorithm is designed to add attribute labels to test cases, extract corresponding attribute information, calculate the distance of each attribute information, cluster similar attributes, and search the most conforming test cases through the input keywords, so that the success rate of multiplexing the test cases and the conformity with the actual scenes are greatly improved, the most similar test cases with the input keywords can be efficiently selected, the selection efficiency of the test cases is improved, the redundancy and repetition of the test cases are reduced, the software test flow is accelerated, the test period is shortened, and the release speed and quality of software are improved.
The attributes of the test case comprise a test type, a case name, a test description, preconditions, test inputs, test steps and test results.
In the test case multiplexing library, the attribute of the test case is used as a primary key, and specific information of each attribute is stored as a value corresponding to the primary key.
The spectral clustering algorithm comprises the following steps:
And step 01, extracting specific information of each attribute from the test case multiplexing library, and constructing an attribute matrix. Wherein each row represents a test case and each column represents an attribute.
And 02, converting the attribute information of each test case into a feature vector, wherein the method is realized through a Bag of Words model (Bag of Words). For each attribute, representing it as a vector, each dimension of the feature vector corresponding to a vocabulary, each element of the feature vector representing the frequency or weight of occurrence of the vocabulary in the attribute information, cosine similarity is used to calculate the similarity distance of the respective attribute, comprising:
Wherein, And/>Representing two vectors respectively,/>Representing the dot product of two vectors,/>And/>Respectively representing the modes of the two vectors, and obtaining the range in/>, through cosine similarity calculation,/>A similarity value between the two attributes, the closer the value is to 1, the higher the similarity between the two attributes is;
step 03, each test case is represented as a node in the graph, and each node has a unique identifier, which may be an ID or other identifier of the test case. According to cosine similarity, calculating similarity between each pair of test cases to obtain a similarity matrix, wherein each element The similarity between the test case i and the test case j is represented; for each element in the similarity matrix/>When the test case is larger than the set threshold value, adding an edge in the graph, and connecting the test case/>And test case j, the weight of the edge is the similarity/>;
Step 04, calculating a Laplacian matrix according to the similarity graph, wherein the calculation formula is as followsWherein/>For degree matrix,/>Is an adjacency matrix;
Step 05, carrying out eigenvector decomposition on the Laplace matrix to obtain an eigenvector matrix;
step 06, constructing a new feature space according to feature vectors corresponding to the first few minimum feature values;
And 07, clustering the test cases in the feature space through a K-Means clustering algorithm to determine the clustering number K, in the K-Means clustering process, firstly randomly selecting K initial centroids, then distributing each data point into the cluster where the centroid closest to the initial centroid is located, updating the centroid of each cluster, and repeating the K-Means clustering process until the centroid is not changed or the maximum iteration number is reached.
The process of searching and matching from the cluster of the generated test cases by using the cuckoo search algorithm comprises the following steps:
Step 001: randomly selecting a plurality of clusters from the generated test case clusters as part of an initial population; it is necessary to ensure that the population size covers the various situations that need to be tested.
Step 002: according to the input keywords, calculating the similarity between the keywords and each cluster, wherein the calculation formula of the similarity is expressed as follows:
Wherein testcase represents a test case set in the initialized population, inputKeywords represents an input keyword set, J () represents calculation using Jaccard similarity, and the calculation formula is:
wherein A and B are respectively two input vectors, Representing the intersection size of the two,/>Representing the union size of the two;
and step 003, traversing the test case multiplexing library, and selecting the test case with higher fitness as an optimal solution for output.
And in the combining step 003, the test cases are output through a cuckoo search algorithm, and the output module combines the test cases with the test data of the tested items to output the test cases.
A test case multiplexing system based on spectral clustering, comprising:
The input module is used for inputting the attribute and data information of the visual test cases of the items to be tested so as to better match and detect the test cases;
The search module is used for carrying out search matching on the attribute information of the tested item and the cluster of the test case, and matching and searching are carried out in the test case library by using a cuckoo search algorithm according to the attribute information and the keyword information of the current embedded software item; the module can quickly find out a subset of test cases similar or close to the current project, thereby providing multiplexing of the test cases;
The output module is used for combining the searched optimal test cases with the input test data, outputting test cases applicable to the items to be tested, and facilitating the development and the test of testers;
the creation module is used for creating a new test case when the test case which is the same as or similar to the tested item is not matched, inputting the new test case into the test case database, and generating a test case cluster, so that the newly generated test case can form a new cluster, and the content of the test case library is enriched;
description of working principle:
step 1, selecting the attribute of a test case;
step 2, extracting attributes of the historical test cases, and storing the extraction results in a test case multiplexing library in a collection mode;
step 3, performing spectral clustering operation on the specific attribute information by using a spectral clustering algorithm;
Step 4, the user inputs each attribute information and key words of the tested item, searches and matches from the generated test case cluster by using a cuckoo search algorithm, and judges whether the test case is matched;
the matched test cases are combined with the input data information, and the test cases applicable to the tested items are output;
And if not, the tester designs a new test case, inputs the new test case into a test case multiplexing library, and generates a new reusable test case by using a spectral clustering algorithm.
Finally, it should be emphasized that the above-described embodiments are merely illustrative of 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, those skilled in the art will appreciate that they may make modifications to the above-described aspects or equivalents to some or all of the features thereof. Such modifications and substitutions do not bring the essence of the corresponding technical solutions beyond the scope of the technical solutions of the embodiments of the present invention, and they should be included in the scope of the claims and the specification of the present invention.
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to the specific details of the embodiments, and various equivalent changes can be made to the technical solutions of the present invention within the scope of the technical concept of the present invention, and all such equivalent changes belong to the protection scope of the present invention.
Claims (5)
1. A test case multiplexing method based on a spectral clustering algorithm is characterized by comprising the following steps:
step 1, selecting the attribute of a test case;
step 2, extracting attributes of the historical test cases, and storing the extraction results in a test case multiplexing library in a collection mode;
step 3, performing spectral clustering operation on the specific attribute information by using a spectral clustering algorithm;
Step 4, the user inputs each attribute information and key words of the tested item, searches and matches from the generated test case cluster by using a cuckoo search algorithm, and judges whether the test case is matched;
the matched test cases are combined with the input data information, and the test cases applicable to the tested items are output;
If not, the tester designs a new test case, inputs the new test case into a test case multiplexing library, and generates a new reusable test case by using a spectral clustering algorithm;
The spectral clustering algorithm comprises the following steps:
step 01, extracting specific information of each attribute from a test case multiplexing library, and constructing an attribute matrix;
Step 02, converting attribute information of each test case into a feature vector, wherein each dimension of the feature vector corresponds to a vocabulary, each element of the feature vector represents frequency or weight of occurrence of the vocabulary in the attribute information, and cosine similarity is used for calculating similarity distance of each attribute, and the method comprises the following steps:
Wherein, And/>Representing two vectors respectively,/>Representing the dot product of two vectors,/>And/>Respectively representing the modes of the two vectors, and obtaining the range in/>, through cosine similarity calculation,/>A similarity value between the two attributes, the closer the value is to 1, the higher the similarity between the two attributes is;
step 03, representing each test case as a node in the graph, wherein each node has a unique identifier, and calculating the similarity between each pair of test cases according to cosine similarity to obtain a similarity matrix, and each element is represented by a unique identifier The similarity between the test case i and the test case j is represented; for each element in the similarity matrix/>When the test case is larger than the set threshold value, adding an edge in the graph, and connecting the test case/>And test case j, the weight of the edge is the similarity/>;
Step 04, calculating a Laplacian matrix according to the similarity graph, wherein the calculation formula is as followsWherein/>For degree matrix,/>Is an adjacency matrix;
Step 05, carrying out eigenvector decomposition on the Laplace matrix to obtain an eigenvector matrix;
Step 06, constructing a new feature space according to the feature vector corresponding to the minimum feature value;
and 07, clustering the test cases in the feature space through a K-Means clustering algorithm, determining the clustering number K, randomly selecting K initial centroids in the K-Means clustering process, distributing each data point to the cluster where the centroid closest to the initial centroid is located, updating the centroid of each cluster, and repeating the K-Means clustering process until the centroid is not changed or the maximum iteration number is reached.
2. The test case multiplexing method based on the spectral clustering algorithm as claimed in claim 1, wherein the method is characterized in that: the attributes of the test case comprise a test type, a case name, a test description, preconditions, test inputs, test steps and test results.
3. The test case multiplexing method based on the spectral clustering algorithm as claimed in claim 1, wherein the method is characterized in that: in the test case multiplexing library, the attribute of the test case is used as a primary key, and specific information of each attribute is stored as a value corresponding to the primary key.
4. The test case multiplexing method based on the spectral clustering algorithm as claimed in claim 1, wherein the method is characterized in that: the process of searching and matching from the cluster of the generated test cases by using the cuckoo search algorithm comprises the following steps:
step 001: randomly selecting a plurality of clusters from the generated test case clusters as part of an initial population;
step 002: according to the input keywords, calculating the similarity between the keywords and each cluster, wherein the calculation formula of the similarity is expressed as follows:
Wherein testcase represents a test case set in the initialized population, inputKeywords represents an input keyword set, J () represents calculation using Jaccard similarity, and the calculation formula is:
wherein A and B are respectively two input vectors,/> Representing the size of the intersection of the two,Representing the union size of the two;
and step 003, traversing the test case multiplexing library, and selecting the test case with higher fitness as an optimal solution for output.
5. A test case multiplexing system based on spectral clustering, for implementing a test case multiplexing method based on a spectral clustering algorithm as set forth in any one of claims 1 to 4, comprising:
The input module is used for inputting the attribute and data information of the visual test cases of the items to be tested;
the retrieval module is used for carrying out retrieval matching on the attribute information of the tested item and the test case cluster;
the output module is used for combining the searched optimal test cases with the input test data and outputting test cases applicable to the items to be tested;
The creation module is used for creating a new test case by a tester when the test case which is the same or similar to the tested item is not matched, inputting the new test case into the test case database and generating a test case cluster.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410444426.XA CN118051442B (en) | 2024-04-15 | 2024-04-15 | Test case multiplexing method and system based on spectral clustering |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410444426.XA CN118051442B (en) | 2024-04-15 | 2024-04-15 | Test case multiplexing method and system based on spectral clustering |
Publications (2)
Publication Number | Publication Date |
---|---|
CN118051442A CN118051442A (en) | 2024-05-17 |
CN118051442B true CN118051442B (en) | 2024-06-25 |
Family
ID=91052269
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410444426.XA Active CN118051442B (en) | 2024-04-15 | 2024-04-15 | Test case multiplexing method and system based on spectral clustering |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118051442B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109933515A (en) * | 2017-12-18 | 2019-06-25 | 大唐移动通信设备有限公司 | A kind of optimization method and automatic optimizing equipment of regression test case collection |
CN114579430A (en) * | 2022-01-26 | 2022-06-03 | 中国人民解放军陆军工程大学 | Test case recommendation system and method based on pre-training language model |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111708703A (en) * | 2020-06-18 | 2020-09-25 | 深圳前海微众银行股份有限公司 | Test case set generation method, device, equipment and computer readable storage medium |
CN114741276A (en) * | 2021-12-21 | 2022-07-12 | 中国电子科技集团公司第十五研究所 | Method and device for multiplexing test cases of domestic operating system |
CN115576834A (en) * | 2022-10-28 | 2023-01-06 | 西安微电子技术研究所 | Software test multiplexing method, system, terminal and medium for supporting fault recovery |
CN116560984A (en) * | 2023-04-24 | 2023-08-08 | 南京大学 | Test case clustering grouping method based on call dependency graph |
-
2024
- 2024-04-15 CN CN202410444426.XA patent/CN118051442B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109933515A (en) * | 2017-12-18 | 2019-06-25 | 大唐移动通信设备有限公司 | A kind of optimization method and automatic optimizing equipment of regression test case collection |
CN114579430A (en) * | 2022-01-26 | 2022-06-03 | 中国人民解放军陆军工程大学 | Test case recommendation system and method based on pre-training language model |
Also Published As
Publication number | Publication date |
---|---|
CN118051442A (en) | 2024-05-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110888849B (en) | Online log analysis method and system and electronic terminal equipment thereof | |
CN109886294B (en) | Knowledge fusion method, apparatus, computer device and storage medium | |
Liu et al. | Empirical studies of a two-stage data preprocessing approach for software fault prediction | |
CN113761218B (en) | Method, device, equipment and storage medium for entity linking | |
CN111666350B (en) | Medical text relation extraction method based on BERT model | |
CN114579430A (en) | Test case recommendation system and method based on pre-training language model | |
US20050065919A1 (en) | Method and apparatus for document filtering capable of efficiently extracting document matching to searcher's intention using learning data | |
CN110688593A (en) | Social media account identification method and system | |
CN112633000A (en) | Method and device for associating entities in text, electronic equipment and storage medium | |
CN111753067A (en) | Innovative assessment method, device and equipment for technical background text | |
CN114049505B (en) | Method, device, equipment and medium for matching and identifying commodities | |
CN114912425A (en) | Presentation generation method and device | |
CN104598599A (en) | Method and system for removing name ambiguity | |
JP5780036B2 (en) | Extraction program, extraction method and extraction apparatus | |
CN118051442B (en) | Test case multiplexing method and system based on spectral clustering | |
CN116049376B (en) | Method, device and system for retrieving and replying information and creating knowledge | |
CN116578700A (en) | Log classification method, log classification device, equipment and medium | |
CN111723182A (en) | Key information extraction method and device for vulnerability text | |
CN115563515A (en) | Text similarity detection method, device and equipment and storage medium | |
CN116304012A (en) | Large-scale text clustering method and device | |
Lin et al. | High-order structure preserving graph neural network for few-shot learning | |
KR20220041337A (en) | Graph generation system of updating a search word from thesaurus and extracting core documents and method thereof | |
Pighin et al. | Reverse engineering of tree kernel feature spaces | |
Ebadat et al. | Proper noun semantic clustering using bag-of-vectors | |
Muhammad Fuad | Towards Normalizing the Edit Distance Using a Genetic Algorithms–Based Scheme |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |