Question and answer robot training method capable of intelligently distributing privacy
The invention discloses a question and answer robot training method capable of intelligently distributing privacy. The method comprises the following steps: constructing a data weight of data generated when each user fills in data and uploads the data; preprocessing all chat records in the group by...
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 | XIONG QIAOFENG XIONG CHANGCHUN LI HAILIANG LI GUOYUAN ZHANG FUGENG WU JIANGCHUAN LI MIAO WANG JINGGUI LIU ANG |
| description | The invention discloses a question and answer robot training method capable of intelligently distributing privacy. The method comprises the following steps: constructing a data weight of data generated when each user fills in data and uploads the data; preprocessing all chat records in the group by combining a keyword technology preprocessing technology and a data weight to obtain a sentence trunk and a data label of reference data; marking an uploader of the chat record, and uploading the chat record to a block chain as a chat robot training material when the system judges that the difference of privacy attention degrees between the two users who have pairwise chats is large; initializing user credibility according to the difference of privacy attention degrees between the users; and dynamically changing the credibility of the chat record uploader according to the similarity search technology and the scoring feedback of the user using the chat robot on the multi-dimensional scoring request, thereby protectin |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114020883A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114020883A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114020883A3</originalsourceid><addsrcrecordid>eNqNyrEKwjAQgOEuDqK-w_kAQmsdukpRnARBcCyX5FoP4iUkV6Vvr4IP4PDzL9-8uF1GyspBAMV9yi9KkIIJCpqQhWWAB-k9OLAY0XiC0AOLkvc8kKifwHHWxGbUL46Jn2inZTHr0Wda_b4o1sfDtT1tKIaOckRLQtq156ralduyaep9_Y95A8PSOsk</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Question and answer robot training method capable of intelligently distributing privacy</title><source>esp@cenet</source><creator>XIONG QIAOFENG ; XIONG CHANGCHUN ; LI HAILIANG ; LI GUOYUAN ; ZHANG FUGENG ; WU JIANGCHUAN ; LI MIAO ; WANG JINGGUI ; LIU ANG</creator><creatorcontrib>XIONG QIAOFENG ; XIONG CHANGCHUN ; LI HAILIANG ; LI GUOYUAN ; ZHANG FUGENG ; WU JIANGCHUAN ; LI MIAO ; WANG JINGGUI ; LIU ANG</creatorcontrib><description>The invention discloses a question and answer robot training method capable of intelligently distributing privacy. The method comprises the following steps: constructing a data weight of data generated when each user fills in data and uploads the data; preprocessing all chat records in the group by combining a keyword technology preprocessing technology and a data weight to obtain a sentence trunk and a data label of reference data; marking an uploader of the chat record, and uploading the chat record to a block chain as a chat robot training material when the system judges that the difference of privacy attention degrees between the two users who have pairwise chats is large; initializing user credibility according to the difference of privacy attention degrees between the users; and dynamically changing the credibility of the chat record uploader according to the similarity search technology and the scoring feedback of the user using the chat robot on the multi-dimensional scoring request, thereby protectin</description><language>chi ; eng</language><subject>CALCULATING ; 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=20220208&DB=EPODOC&CC=CN&NR=114020883A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220208&DB=EPODOC&CC=CN&NR=114020883A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>XIONG QIAOFENG</creatorcontrib><creatorcontrib>XIONG CHANGCHUN</creatorcontrib><creatorcontrib>LI HAILIANG</creatorcontrib><creatorcontrib>LI GUOYUAN</creatorcontrib><creatorcontrib>ZHANG FUGENG</creatorcontrib><creatorcontrib>WU JIANGCHUAN</creatorcontrib><creatorcontrib>LI MIAO</creatorcontrib><creatorcontrib>WANG JINGGUI</creatorcontrib><creatorcontrib>LIU ANG</creatorcontrib><title>Question and answer robot training method capable of intelligently distributing privacy</title><description>The invention discloses a question and answer robot training method capable of intelligently distributing privacy. The method comprises the following steps: constructing a data weight of data generated when each user fills in data and uploads the data; preprocessing all chat records in the group by combining a keyword technology preprocessing technology and a data weight to obtain a sentence trunk and a data label of reference data; marking an uploader of the chat record, and uploading the chat record to a block chain as a chat robot training material when the system judges that the difference of privacy attention degrees between the two users who have pairwise chats is large; initializing user credibility according to the difference of privacy attention degrees between the users; and dynamically changing the credibility of the chat record uploader according to the similarity search technology and the scoring feedback of the user using the chat robot on the multi-dimensional scoring request, thereby protectin</description><subject>CALCULATING</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>eNqNyrEKwjAQgOEuDqK-w_kAQmsdukpRnARBcCyX5FoP4iUkV6Vvr4IP4PDzL9-8uF1GyspBAMV9yi9KkIIJCpqQhWWAB-k9OLAY0XiC0AOLkvc8kKifwHHWxGbUL46Jn2inZTHr0Wda_b4o1sfDtT1tKIaOckRLQtq156ralduyaep9_Y95A8PSOsk</recordid><startdate>20220208</startdate><enddate>20220208</enddate><creator>XIONG QIAOFENG</creator><creator>XIONG CHANGCHUN</creator><creator>LI HAILIANG</creator><creator>LI GUOYUAN</creator><creator>ZHANG FUGENG</creator><creator>WU JIANGCHUAN</creator><creator>LI MIAO</creator><creator>WANG JINGGUI</creator><creator>LIU ANG</creator><scope>EVB</scope></search><sort><creationdate>20220208</creationdate><title>Question and answer robot training method capable of intelligently distributing privacy</title><author>XIONG QIAOFENG ; XIONG CHANGCHUN ; LI HAILIANG ; LI GUOYUAN ; ZHANG FUGENG ; WU JIANGCHUAN ; LI MIAO ; WANG JINGGUI ; LIU ANG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114020883A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>XIONG QIAOFENG</creatorcontrib><creatorcontrib>XIONG CHANGCHUN</creatorcontrib><creatorcontrib>LI HAILIANG</creatorcontrib><creatorcontrib>LI GUOYUAN</creatorcontrib><creatorcontrib>ZHANG FUGENG</creatorcontrib><creatorcontrib>WU JIANGCHUAN</creatorcontrib><creatorcontrib>LI MIAO</creatorcontrib><creatorcontrib>WANG JINGGUI</creatorcontrib><creatorcontrib>LIU ANG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>XIONG QIAOFENG</au><au>XIONG CHANGCHUN</au><au>LI HAILIANG</au><au>LI GUOYUAN</au><au>ZHANG FUGENG</au><au>WU JIANGCHUAN</au><au>LI MIAO</au><au>WANG JINGGUI</au><au>LIU ANG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Question and answer robot training method capable of intelligently distributing privacy</title><date>2022-02-08</date><risdate>2022</risdate><abstract>The invention discloses a question and answer robot training method capable of intelligently distributing privacy. The method comprises the following steps: constructing a data weight of data generated when each user fills in data and uploads the data; preprocessing all chat records in the group by combining a keyword technology preprocessing technology and a data weight to obtain a sentence trunk and a data label of reference data; marking an uploader of the chat record, and uploading the chat record to a block chain as a chat robot training material when the system judges that the difference of privacy attention degrees between the two users who have pairwise chats is large; initializing user credibility according to the difference of privacy attention degrees between the users; and dynamically changing the credibility of the chat record uploader according to the similarity search technology and the scoring feedback of the user using the chat robot on the multi-dimensional scoring request, thereby protectin</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN114020883A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Question and answer robot training method capable of intelligently distributing privacy |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T14%3A15%3A16IST&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=XIONG%20QIAOFENG&rft.date=2022-02-08&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114020883A%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 |