Memory grounded conversational reasoning and question answering for assistant systems

In one embodiment, a method includes receiving a query from a user from a client system associated with the user, determining one or more initial memory slots based on the query, accessing a memory graph associated with the user which comprises a plurality of nodes and a plurality of edges connectin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shah, Pararth Paresh, Subba, Rajen, Moon, Seungwhan, Kumar, Anuj
Format: Patent
Sprache: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 Shah, Pararth Paresh
Subba, Rajen
Moon, Seungwhan
Kumar, Anuj
description In one embodiment, a method includes receiving a query from a user from a client system associated with the user, determining one or more initial memory slots based on the query, accessing a memory graph associated with the user which comprises a plurality of nodes and a plurality of edges connecting the nodes, and wherein one or more of the nodes correspond to one or more episodic memories of the user, respectively, and wherein each edge corresponds to a relationship between the connected nodes, selecting one or more candidate nodes from the memory graph by one or more machine-learning models based on the initial memory slots, generating a response based on the initial memory slots and episodic memories corresponding to the selected candidate nodes, and sending instructions for presenting the response to the client system in response to the query.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11657094B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11657094B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11657094B23</originalsourceid><addsrcrecordid>eNqNiksKwkAQBWfjQtQ7tAcQjF_cKoobV5p1aJKXMJB0x-mJkttrwAO4elTVG7v0hkZDT1XQTgoUlKu8EIyjV-GaAthUvFTEUtCzgw3hC_ZGGHSpgdjMW2SJZL1FNDZ1o5Jrw-y3Eze_nB-n6wKtZrCWcwhilt6TZLfdLw-b42r9z-cDkPk6ww</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Memory grounded conversational reasoning and question answering for assistant systems</title><source>esp@cenet</source><creator>Shah, Pararth Paresh ; Subba, Rajen ; Moon, Seungwhan ; Kumar, Anuj</creator><creatorcontrib>Shah, Pararth Paresh ; Subba, Rajen ; Moon, Seungwhan ; Kumar, Anuj</creatorcontrib><description>In one embodiment, a method includes receiving a query from a user from a client system associated with the user, determining one or more initial memory slots based on the query, accessing a memory graph associated with the user which comprises a plurality of nodes and a plurality of edges connecting the nodes, and wherein one or more of the nodes correspond to one or more episodic memories of the user, respectively, and wherein each edge corresponds to a relationship between the connected nodes, selecting one or more candidate nodes from the memory graph by one or more machine-learning models based on the initial memory slots, generating a response based on the initial memory slots and episodic memories corresponding to the selected candidate nodes, and sending instructions for presenting the response to the client system in response to the query.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2023</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=20230523&amp;DB=EPODOC&amp;CC=US&amp;NR=11657094B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230523&amp;DB=EPODOC&amp;CC=US&amp;NR=11657094B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Shah, Pararth Paresh</creatorcontrib><creatorcontrib>Subba, Rajen</creatorcontrib><creatorcontrib>Moon, Seungwhan</creatorcontrib><creatorcontrib>Kumar, Anuj</creatorcontrib><title>Memory grounded conversational reasoning and question answering for assistant systems</title><description>In one embodiment, a method includes receiving a query from a user from a client system associated with the user, determining one or more initial memory slots based on the query, accessing a memory graph associated with the user which comprises a plurality of nodes and a plurality of edges connecting the nodes, and wherein one or more of the nodes correspond to one or more episodic memories of the user, respectively, and wherein each edge corresponds to a relationship between the connected nodes, selecting one or more candidate nodes from the memory graph by one or more machine-learning models based on the initial memory slots, generating a response based on the initial memory slots and episodic memories corresponding to the selected candidate nodes, and sending instructions for presenting the response to the client system in response to the query.</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNiksKwkAQBWfjQtQ7tAcQjF_cKoobV5p1aJKXMJB0x-mJkttrwAO4elTVG7v0hkZDT1XQTgoUlKu8EIyjV-GaAthUvFTEUtCzgw3hC_ZGGHSpgdjMW2SJZL1FNDZ1o5Jrw-y3Eze_nB-n6wKtZrCWcwhilt6TZLfdLw-b42r9z-cDkPk6ww</recordid><startdate>20230523</startdate><enddate>20230523</enddate><creator>Shah, Pararth Paresh</creator><creator>Subba, Rajen</creator><creator>Moon, Seungwhan</creator><creator>Kumar, Anuj</creator><scope>EVB</scope></search><sort><creationdate>20230523</creationdate><title>Memory grounded conversational reasoning and question answering for assistant systems</title><author>Shah, Pararth Paresh ; Subba, Rajen ; Moon, Seungwhan ; Kumar, Anuj</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11657094B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2023</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>Shah, Pararth Paresh</creatorcontrib><creatorcontrib>Subba, Rajen</creatorcontrib><creatorcontrib>Moon, Seungwhan</creatorcontrib><creatorcontrib>Kumar, Anuj</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Shah, Pararth Paresh</au><au>Subba, Rajen</au><au>Moon, Seungwhan</au><au>Kumar, Anuj</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Memory grounded conversational reasoning and question answering for assistant systems</title><date>2023-05-23</date><risdate>2023</risdate><abstract>In one embodiment, a method includes receiving a query from a user from a client system associated with the user, determining one or more initial memory slots based on the query, accessing a memory graph associated with the user which comprises a plurality of nodes and a plurality of edges connecting the nodes, and wherein one or more of the nodes correspond to one or more episodic memories of the user, respectively, and wherein each edge corresponds to a relationship between the connected nodes, selecting one or more candidate nodes from the memory graph by one or more machine-learning models based on the initial memory slots, generating a response based on the initial memory slots and episodic memories corresponding to the selected candidate nodes, and sending instructions for presenting the response to the client system in response to the query.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US11657094B2
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Memory grounded conversational reasoning and question answering for assistant systems
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T20%3A19%3A05IST&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=Shah,%20Pararth%20Paresh&rft.date=2023-05-23&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11657094B2%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