PREDICTING FUTURE POSSIBILITY OF BIAS IN AN ARTIFICIAL INTELLIGENCE MODEL

PREDICTING FUTURE POSSIBILITY OF BIAS IN AN ARTIFICIAL INTELLIGENCE MODEL

One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to predicting bias in an artificial intelligence (AI) model. A system can comprise a memory configured to store computer executable components; and a processor configured to exec...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bhide, Manish Anand, Goyal, Prateek
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
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 Bhide, Manish Anand
Goyal, Prateek
description One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to predicting bias in an artificial intelligence (AI) model. A system can comprise a memory configured to store computer executable components; and a processor configured to execute the computer executable components stored in the memory, wherein the computer executable components can comprise a data generation component that can generate a set of structured test data to test likelihood of an AI model generating biased outputs, based on analysis of payload logging data; and an alerting component that can alert a user of likelihood that the AI model will generate the biased outputs, wherein the alerting component can generate an alert in response to at least a first set of records approaching a defined threshold.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024111995A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024111995A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024111995A13</originalsourceid><addsrcrecordid>eNrjZPAMCHJ18XQO8fRzV3ALDQkNclUI8A8O9nTy9PEMiVTwd1Nw8nQMVvD0U3AEoqAQTzdPZ09HH6BAiKuPj6e7q5-zq4Kvv4urDw8Da1piTnEqL5TmZlB2cw1x9tBNLciPTy0uSExOzUstiQ8NNjIwMjE0NLS0NHU0NCZOFQDlNS39</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>PREDICTING FUTURE POSSIBILITY OF BIAS IN AN ARTIFICIAL INTELLIGENCE MODEL</title><source>esp@cenet</source><creator>Bhide, Manish Anand ; Goyal, Prateek</creator><creatorcontrib>Bhide, Manish Anand ; Goyal, Prateek</creatorcontrib><description>One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to predicting bias in an artificial intelligence (AI) model. A system can comprise a memory configured to store computer executable components; and a processor configured to execute the computer executable components stored in the memory, wherein the computer executable components can comprise a data generation component that can generate a set of structured test data to test likelihood of an AI model generating biased outputs, based on analysis of payload logging data; and an alerting component that can alert a user of likelihood that the AI model will generate the biased outputs, wherein the alerting component can generate an alert in response to at least a first set of records approaching a defined threshold.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2024</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&amp;date=20240404&amp;DB=EPODOC&amp;CC=US&amp;NR=2024111995A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240404&amp;DB=EPODOC&amp;CC=US&amp;NR=2024111995A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Bhide, Manish Anand</creatorcontrib><creatorcontrib>Goyal, Prateek</creatorcontrib><title>PREDICTING FUTURE POSSIBILITY OF BIAS IN AN ARTIFICIAL INTELLIGENCE MODEL</title><description>One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to predicting bias in an artificial intelligence (AI) model. A system can comprise a memory configured to store computer executable components; and a processor configured to execute the computer executable components stored in the memory, wherein the computer executable components can comprise a data generation component that can generate a set of structured test data to test likelihood of an AI model generating biased outputs, based on analysis of payload logging data; and an alerting component that can alert a user of likelihood that the AI model will generate the biased outputs, wherein the alerting component can generate an alert in response to at least a first set of records approaching a defined threshold.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPAMCHJ18XQO8fRzV3ALDQkNclUI8A8O9nTy9PEMiVTwd1Nw8nQMVvD0U3AEoqAQTzdPZ09HH6BAiKuPj6e7q5-zq4Kvv4urDw8Da1piTnEqL5TmZlB2cw1x9tBNLciPTy0uSExOzUstiQ8NNjIwMjE0NLS0NHU0NCZOFQDlNS39</recordid><startdate>20240404</startdate><enddate>20240404</enddate><creator>Bhide, Manish Anand</creator><creator>Goyal, Prateek</creator><scope>EVB</scope></search><sort><creationdate>20240404</creationdate><title>PREDICTING FUTURE POSSIBILITY OF BIAS IN AN ARTIFICIAL INTELLIGENCE MODEL</title><author>Bhide, Manish Anand ; Goyal, Prateek</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024111995A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Bhide, Manish Anand</creatorcontrib><creatorcontrib>Goyal, Prateek</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bhide, Manish Anand</au><au>Goyal, Prateek</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>PREDICTING FUTURE POSSIBILITY OF BIAS IN AN ARTIFICIAL INTELLIGENCE MODEL</title><date>2024-04-04</date><risdate>2024</risdate><abstract>One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to predicting bias in an artificial intelligence (AI) model. A system can comprise a memory configured to store computer executable components; and a processor configured to execute the computer executable components stored in the memory, wherein the computer executable components can comprise a data generation component that can generate a set of structured test data to test likelihood of an AI model generating biased outputs, based on analysis of payload logging data; and an alerting component that can alert a user of likelihood that the AI model will generate the biased outputs, wherein the alerting component can generate an alert in response to at least a first set of records approaching a defined threshold.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2024111995A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title PREDICTING FUTURE POSSIBILITY OF BIAS IN AN ARTIFICIAL INTELLIGENCE MODEL
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T22%3A27%3A09IST&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=Bhide,%20Manish%20Anand&rft.date=2024-04-04&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024111995A1%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