Multimedia file identification method and device, server and storage medium
The invention relates to a multimedia file identification method and device, a server and a storage medium. The method comprises the following steps: inputting a plurality of multimedia files into a target identification model; dividing the plurality of multimedia files into a plurality of batches a...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| 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 | CAO XIAOLUN |
| description | The invention relates to a multimedia file identification method and device, a server and a storage medium. The method comprises the following steps: inputting a plurality of multimedia files into a target identification model; dividing the plurality of multimedia files into a plurality of batches according to a preset batching mode through the target identification model, carrying out convolutioncalculation on the multiple batches of multimedia files through multiple convolution kernels of the target recognition model, processing convolution calculation results through a full connection layer, and outputting recognition results of the multiple multimedia files; wherein the preset batching mode is obtained by training based on a plurality of sample multimedia files and each convolution kernel of the target identification model. Faster convolution calculation speed can be obtained under the condition of limited hardware resources, so that the multimedia file identification efficiencyis improved on the whole.
本 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN110929623A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN110929623A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN110929623A3</originalsourceid><addsrcrecordid>eNqNi80KwjAQBnPxIOo7rHcF24LQoxRFED15L0vypS7kpyRpn18UH8DTwDCzVLf75Ip4GGGy4kBiEIpY0VwkBvIor2iIgyGDWTR2lJFmpK_KJSYeQJ9_8mu1sOwyNj-u1PZyfnbXPcbYI4-sEVD67lFVh7Zuj3Vzav5p3lpjNVk</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Multimedia file identification method and device, server and storage medium</title><source>esp@cenet</source><creator>CAO XIAOLUN</creator><creatorcontrib>CAO XIAOLUN</creatorcontrib><description>The invention relates to a multimedia file identification method and device, a server and a storage medium. The method comprises the following steps: inputting a plurality of multimedia files into a target identification model; dividing the plurality of multimedia files into a plurality of batches according to a preset batching mode through the target identification model, carrying out convolutioncalculation on the multiple batches of multimedia files through multiple convolution kernels of the target recognition model, processing convolution calculation results through a full connection layer, and outputting recognition results of the multiple multimedia files; wherein the preset batching mode is obtained by training based on a plurality of sample multimedia files and each convolution kernel of the target identification model. Faster convolution calculation speed can be obtained under the condition of limited hardware resources, so that the multimedia file identification efficiencyis improved on the whole.
本</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</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=20200327&DB=EPODOC&CC=CN&NR=110929623A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200327&DB=EPODOC&CC=CN&NR=110929623A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CAO XIAOLUN</creatorcontrib><title>Multimedia file identification method and device, server and storage medium</title><description>The invention relates to a multimedia file identification method and device, a server and a storage medium. The method comprises the following steps: inputting a plurality of multimedia files into a target identification model; dividing the plurality of multimedia files into a plurality of batches according to a preset batching mode through the target identification model, carrying out convolutioncalculation on the multiple batches of multimedia files through multiple convolution kernels of the target recognition model, processing convolution calculation results through a full connection layer, and outputting recognition results of the multiple multimedia files; wherein the preset batching mode is obtained by training based on a plurality of sample multimedia files and each convolution kernel of the target identification model. Faster convolution calculation speed can be obtained under the condition of limited hardware resources, so that the multimedia file identification efficiencyis improved on the whole.
本</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNi80KwjAQBnPxIOo7rHcF24LQoxRFED15L0vypS7kpyRpn18UH8DTwDCzVLf75Ip4GGGy4kBiEIpY0VwkBvIor2iIgyGDWTR2lJFmpK_KJSYeQJ9_8mu1sOwyNj-u1PZyfnbXPcbYI4-sEVD67lFVh7Zuj3Vzav5p3lpjNVk</recordid><startdate>20200327</startdate><enddate>20200327</enddate><creator>CAO XIAOLUN</creator><scope>EVB</scope></search><sort><creationdate>20200327</creationdate><title>Multimedia file identification method and device, server and storage medium</title><author>CAO XIAOLUN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN110929623A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2020</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>CAO XIAOLUN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CAO XIAOLUN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Multimedia file identification method and device, server and storage medium</title><date>2020-03-27</date><risdate>2020</risdate><abstract>The invention relates to a multimedia file identification method and device, a server and a storage medium. The method comprises the following steps: inputting a plurality of multimedia files into a target identification model; dividing the plurality of multimedia files into a plurality of batches according to a preset batching mode through the target identification model, carrying out convolutioncalculation on the multiple batches of multimedia files through multiple convolution kernels of the target recognition model, processing convolution calculation results through a full connection layer, and outputting recognition results of the multiple multimedia files; wherein the preset batching mode is obtained by training based on a plurality of sample multimedia files and each convolution kernel of the target identification model. Faster convolution calculation speed can be obtained under the condition of limited hardware resources, so that the multimedia file identification efficiencyis improved on the whole.
本</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN110929623A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Multimedia file identification method and device, server and storage medium |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T22%3A48%3A40IST&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=CAO%20XIAOLUN&rft.date=2020-03-27&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN110929623A%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 |