Text content security detection method based on deep learning
The invention relates to a text content security detection method based on deep learning. The method comprises an algorithm part, and a corresponding detector is a convolutional neural network framework. The overall architecture of the algorithm adopts a long short term memory (LSTM) network, and th...
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 | JIN MEI SHEN QIAN WANG LEI XUE JINGFANG ZHANG LIGUO HUANG WENHAN QIN QIAN MENG ZIJIE |
description | The invention relates to a text content security detection method based on deep learning. The method comprises an algorithm part, and a corresponding detector is a convolutional neural network framework. The overall architecture of the algorithm adopts a long short term memory (LSTM) network, and the structure is a recurrent neural network, is simple to implement and has a long-term memory function; on the basis, an attention mechanism is further added, limited resources of a computer can be efficiently utilized through the mechanism, parallelism can be achieved during use, and the accuracy can be improved under the condition that network parameters are reduced. Besides, a residual structure is added to the algorithm part, so that a learning result is more sensitive to fluctuation change of network weight, and meanwhile, a residual result is more sensitive to fluctuation of data. According to the method, a depth-based method is provided, different text content detectors can be constructed by changing model pa |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN113901801A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN113901801A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN113901801A3</originalsourceid><addsrcrecordid>eNrjZLANSa0oUUjOzytJzStRKE5NLi3KLKlUSEktSU0uyczPU8hNLcnIT1FISixOTVEA8lNSUwsUclITi_Iy89J5GFjTEnOKU3mhNDeDoptriLOHbmpBfnxqcUFicmpeakm8s5-hobGlgaGFgaGjMTFqADL8MDY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Text content security detection method based on deep learning</title><source>esp@cenet</source><creator>JIN MEI ; SHEN QIAN ; WANG LEI ; XUE JINGFANG ; ZHANG LIGUO ; HUANG WENHAN ; QIN QIAN ; MENG ZIJIE</creator><creatorcontrib>JIN MEI ; SHEN QIAN ; WANG LEI ; XUE JINGFANG ; ZHANG LIGUO ; HUANG WENHAN ; QIN QIAN ; MENG ZIJIE</creatorcontrib><description>The invention relates to a text content security detection method based on deep learning. The method comprises an algorithm part, and a corresponding detector is a convolutional neural network framework. The overall architecture of the algorithm adopts a long short term memory (LSTM) network, and the structure is a recurrent neural network, is simple to implement and has a long-term memory function; on the basis, an attention mechanism is further added, limited resources of a computer can be efficiently utilized through the mechanism, parallelism can be achieved during use, and the accuracy can be improved under the condition that network parameters are reduced. Besides, a residual structure is added to the algorithm part, so that a learning result is more sensitive to fluctuation change of network weight, and meanwhile, a residual result is more sensitive to fluctuation of data. According to the method, a depth-based method is provided, different text content detectors can be constructed by changing model pa</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2022</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=20220107&DB=EPODOC&CC=CN&NR=113901801A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,778,883,25551,76302</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220107&DB=EPODOC&CC=CN&NR=113901801A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>JIN MEI</creatorcontrib><creatorcontrib>SHEN QIAN</creatorcontrib><creatorcontrib>WANG LEI</creatorcontrib><creatorcontrib>XUE JINGFANG</creatorcontrib><creatorcontrib>ZHANG LIGUO</creatorcontrib><creatorcontrib>HUANG WENHAN</creatorcontrib><creatorcontrib>QIN QIAN</creatorcontrib><creatorcontrib>MENG ZIJIE</creatorcontrib><title>Text content security detection method based on deep learning</title><description>The invention relates to a text content security detection method based on deep learning. The method comprises an algorithm part, and a corresponding detector is a convolutional neural network framework. The overall architecture of the algorithm adopts a long short term memory (LSTM) network, and the structure is a recurrent neural network, is simple to implement and has a long-term memory function; on the basis, an attention mechanism is further added, limited resources of a computer can be efficiently utilized through the mechanism, parallelism can be achieved during use, and the accuracy can be improved under the condition that network parameters are reduced. Besides, a residual structure is added to the algorithm part, so that a learning result is more sensitive to fluctuation change of network weight, and meanwhile, a residual result is more sensitive to fluctuation of data. According to the method, a depth-based method is provided, different text content detectors can be constructed by changing model pa</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLANSa0oUUjOzytJzStRKE5NLi3KLKlUSEktSU0uyczPU8hNLcnIT1FISixOTVEA8lNSUwsUclITi_Iy89J5GFjTEnOKU3mhNDeDoptriLOHbmpBfnxqcUFicmpeakm8s5-hobGlgaGFgaGjMTFqADL8MDY</recordid><startdate>20220107</startdate><enddate>20220107</enddate><creator>JIN MEI</creator><creator>SHEN QIAN</creator><creator>WANG LEI</creator><creator>XUE JINGFANG</creator><creator>ZHANG LIGUO</creator><creator>HUANG WENHAN</creator><creator>QIN QIAN</creator><creator>MENG ZIJIE</creator><scope>EVB</scope></search><sort><creationdate>20220107</creationdate><title>Text content security detection method based on deep learning</title><author>JIN MEI ; SHEN QIAN ; WANG LEI ; XUE JINGFANG ; ZHANG LIGUO ; HUANG WENHAN ; QIN QIAN ; MENG ZIJIE</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN113901801A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</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>JIN MEI</creatorcontrib><creatorcontrib>SHEN QIAN</creatorcontrib><creatorcontrib>WANG LEI</creatorcontrib><creatorcontrib>XUE JINGFANG</creatorcontrib><creatorcontrib>ZHANG LIGUO</creatorcontrib><creatorcontrib>HUANG WENHAN</creatorcontrib><creatorcontrib>QIN QIAN</creatorcontrib><creatorcontrib>MENG ZIJIE</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>JIN MEI</au><au>SHEN QIAN</au><au>WANG LEI</au><au>XUE JINGFANG</au><au>ZHANG LIGUO</au><au>HUANG WENHAN</au><au>QIN QIAN</au><au>MENG ZIJIE</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Text content security detection method based on deep learning</title><date>2022-01-07</date><risdate>2022</risdate><abstract>The invention relates to a text content security detection method based on deep learning. The method comprises an algorithm part, and a corresponding detector is a convolutional neural network framework. The overall architecture of the algorithm adopts a long short term memory (LSTM) network, and the structure is a recurrent neural network, is simple to implement and has a long-term memory function; on the basis, an attention mechanism is further added, limited resources of a computer can be efficiently utilized through the mechanism, parallelism can be achieved during use, and the accuracy can be improved under the condition that network parameters are reduced. Besides, a residual structure is added to the algorithm part, so that a learning result is more sensitive to fluctuation change of network weight, and meanwhile, a residual result is more sensitive to fluctuation of data. According to the method, a depth-based method is provided, different text content detectors can be constructed by changing model pa</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | chi ; eng |
recordid | cdi_epo_espacenet_CN113901801A |
source | esp@cenet |
subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
title | Text content security detection method based on deep learning |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T04%3A24%3A08IST&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=JIN%20MEI&rft.date=2022-01-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN113901801A%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 |