Hybrid depth defect prediction method based on code snippet analysis
The invention relates to a hybrid depth defect prediction method based on code snippet analysis, and belongs to the technical field of computer software defect prediction. According to the method, firstly, based on a program slicing method of defect library key points, an open source software code u...
Gespeichert in:
Hauptverfasser: | , , , , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | GAO DONGYING LYU JUNFENG ZHANG PAN SHEN LIANG JIANG XIN XIE LEI REN YINGWEN SU RENJIE LAI FENGGANG |
description | The invention relates to a hybrid depth defect prediction method based on code snippet analysis, and belongs to the technical field of computer software defect prediction. According to the method, firstly, based on a program slicing method of defect library key points, an open source software code unit set containing defects is vectorized, and features are expressed as a vector form which can be processed by a deep learning model; then, based on a defect prediction method of hybrid deep learning, the classification and prediction capabilities of a hybrid deep model are improved, and a defect prediction classifier is obtained through training; and finally, defect prediction is performed on the open source software based on the trained defect prediction classifier, and target code snippets are outputted in a classified manner. According to the method, the pre-designed defect library key points are taken as the entry point of program slicing, the code snippets containing defect characteristics are extracted from |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN112035345A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN112035345A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN112035345A3</originalsourceid><addsrcrecordid>eNrjZHDxqEwqykxRSEktKMkAkmmpySUKBUWpKZnJJZn5eQq5qSUZ-SkKSYnFqSkKQH5yfkqqQnFeZkFBaolCYl5iTmVxZjEPA2taYk5xKi-U5mZQdHMNcfbQTS3Ij08tLkhMTs1LLYl39jM0NDIwNjU2MXU0JkYNAKaGMq0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Hybrid depth defect prediction method based on code snippet analysis</title><source>esp@cenet</source><creator>GAO DONGYING ; LYU JUNFENG ; ZHANG PAN ; SHEN LIANG ; JIANG XIN ; XIE LEI ; REN YINGWEN ; SU RENJIE ; LAI FENGGANG</creator><creatorcontrib>GAO DONGYING ; LYU JUNFENG ; ZHANG PAN ; SHEN LIANG ; JIANG XIN ; XIE LEI ; REN YINGWEN ; SU RENJIE ; LAI FENGGANG</creatorcontrib><description>The invention relates to a hybrid depth defect prediction method based on code snippet analysis, and belongs to the technical field of computer software defect prediction. According to the method, firstly, based on a program slicing method of defect library key points, an open source software code unit set containing defects is vectorized, and features are expressed as a vector form which can be processed by a deep learning model; then, based on a defect prediction method of hybrid deep learning, the classification and prediction capabilities of a hybrid deep model are improved, and a defect prediction classifier is obtained through training; and finally, defect prediction is performed on the open source software based on the trained defect prediction classifier, and target code snippets are outputted in a classified manner. According to the method, the pre-designed defect library key points are taken as the entry point of program slicing, the code snippets containing defect characteristics are extracted from</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2020</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20201204&DB=EPODOC&CC=CN&NR=112035345A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20201204&DB=EPODOC&CC=CN&NR=112035345A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>GAO DONGYING</creatorcontrib><creatorcontrib>LYU JUNFENG</creatorcontrib><creatorcontrib>ZHANG PAN</creatorcontrib><creatorcontrib>SHEN LIANG</creatorcontrib><creatorcontrib>JIANG XIN</creatorcontrib><creatorcontrib>XIE LEI</creatorcontrib><creatorcontrib>REN YINGWEN</creatorcontrib><creatorcontrib>SU RENJIE</creatorcontrib><creatorcontrib>LAI FENGGANG</creatorcontrib><title>Hybrid depth defect prediction method based on code snippet analysis</title><description>The invention relates to a hybrid depth defect prediction method based on code snippet analysis, and belongs to the technical field of computer software defect prediction. According to the method, firstly, based on a program slicing method of defect library key points, an open source software code unit set containing defects is vectorized, and features are expressed as a vector form which can be processed by a deep learning model; then, based on a defect prediction method of hybrid deep learning, the classification and prediction capabilities of a hybrid deep model are improved, and a defect prediction classifier is obtained through training; and finally, defect prediction is performed on the open source software based on the trained defect prediction classifier, and target code snippets are outputted in a classified manner. According to the method, the pre-designed defect library key points are taken as the entry point of program slicing, the code snippets containing defect characteristics are extracted from</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHDxqEwqykxRSEktKMkAkmmpySUKBUWpKZnJJZn5eQq5qSUZ-SkKSYnFqSkKQH5yfkqqQnFeZkFBaolCYl5iTmVxZjEPA2taYk5xKi-U5mZQdHMNcfbQTS3Ij08tLkhMTs1LLYl39jM0NDIwNjU2MXU0JkYNAKaGMq0</recordid><startdate>20201204</startdate><enddate>20201204</enddate><creator>GAO DONGYING</creator><creator>LYU JUNFENG</creator><creator>ZHANG PAN</creator><creator>SHEN LIANG</creator><creator>JIANG XIN</creator><creator>XIE LEI</creator><creator>REN YINGWEN</creator><creator>SU RENJIE</creator><creator>LAI FENGGANG</creator><scope>EVB</scope></search><sort><creationdate>20201204</creationdate><title>Hybrid depth defect prediction method based on code snippet analysis</title><author>GAO DONGYING ; LYU JUNFENG ; ZHANG PAN ; SHEN LIANG ; JIANG XIN ; XIE LEI ; REN YINGWEN ; SU RENJIE ; LAI FENGGANG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN112035345A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2020</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>GAO DONGYING</creatorcontrib><creatorcontrib>LYU JUNFENG</creatorcontrib><creatorcontrib>ZHANG PAN</creatorcontrib><creatorcontrib>SHEN LIANG</creatorcontrib><creatorcontrib>JIANG XIN</creatorcontrib><creatorcontrib>XIE LEI</creatorcontrib><creatorcontrib>REN YINGWEN</creatorcontrib><creatorcontrib>SU RENJIE</creatorcontrib><creatorcontrib>LAI FENGGANG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>GAO DONGYING</au><au>LYU JUNFENG</au><au>ZHANG PAN</au><au>SHEN LIANG</au><au>JIANG XIN</au><au>XIE LEI</au><au>REN YINGWEN</au><au>SU RENJIE</au><au>LAI FENGGANG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Hybrid depth defect prediction method based on code snippet analysis</title><date>2020-12-04</date><risdate>2020</risdate><abstract>The invention relates to a hybrid depth defect prediction method based on code snippet analysis, and belongs to the technical field of computer software defect prediction. According to the method, firstly, based on a program slicing method of defect library key points, an open source software code unit set containing defects is vectorized, and features are expressed as a vector form which can be processed by a deep learning model; then, based on a defect prediction method of hybrid deep learning, the classification and prediction capabilities of a hybrid deep model are improved, and a defect prediction classifier is obtained through training; and finally, defect prediction is performed on the open source software based on the trained defect prediction classifier, and target code snippets are outputted in a classified manner. According to the method, the pre-designed defect library key points are taken as the entry point of program slicing, the code snippets containing defect characteristics are extracted from</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | chi ; eng |
recordid | cdi_epo_espacenet_CN112035345A |
source | esp@cenet |
subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
title | Hybrid depth defect prediction method based on code snippet analysis |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T06%3A38%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=GAO%20DONGYING&rft.date=2020-12-04&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN112035345A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |