SYSTEMS AND METHODS FOR IMPROVED AUTOMATED CONVERSATIONS WITH INTENT AND ACTION RESPONSE GENERATION
Systems and methods for generating intents for a response is provided. The tokens of the response is encoded into a dense vector space as a plurality of vectors. Name entities are extracted, and individual sentences and paragraphs are both classified in response to the vectors. In addition to the to...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
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 | Gainor, Macgregor S Ginstrom, Ryan Francis Gouge, Connor Mack Jonnalagadda, Siddhartha Reddy |
description | Systems and methods for generating intents for a response is provided. The tokens of the response is encoded into a dense vector space as a plurality of vectors. Name entities are extracted, and individual sentences and paragraphs are both classified in response to the vectors. In addition to the tokens being represented in the vector space, the sentences and paragraphs may be represented in the vector space. The entities and intents are then used to determine an action for the system according to a policy that is optimized for. Annotations may be requested when the classifications are below thresholds, and these annotations may be employed in the action determination process. Annotation includes receiving an annotation work in an annotation queue, prioritizing the annotations, and sending the highest priority annotations to the annotator in order. This is used to update the production annotation database. |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2020143247A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2020143247A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2020143247A13</originalsourceid><addsrcrecordid>eNqNi8EKwjAQRHvxIOo_LHgW2rTgOSRbk0OSkt1WPJVS4km0UP8fa_EDPM0w7802G-lGjI5Aeg0O2QRNUIcI1jUxdKhBthyc5KWp4DuMJNkGT3C1bMB6Rs_rWarvDhGpWTDCBT3G1d1nm_vwmNPhl7vsWCMrc0rTq0_zNIzpmd59SyIXeVGVojrLovzP-gA16zWo</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>SYSTEMS AND METHODS FOR IMPROVED AUTOMATED CONVERSATIONS WITH INTENT AND ACTION RESPONSE GENERATION</title><source>esp@cenet</source><creator>Gainor, Macgregor S ; Ginstrom, Ryan Francis ; Gouge, Connor Mack ; Jonnalagadda, Siddhartha Reddy</creator><creatorcontrib>Gainor, Macgregor S ; Ginstrom, Ryan Francis ; Gouge, Connor Mack ; Jonnalagadda, Siddhartha Reddy</creatorcontrib><description>Systems and methods for generating intents for a response is provided. The tokens of the response is encoded into a dense vector space as a plurality of vectors. Name entities are extracted, and individual sentences and paragraphs are both classified in response to the vectors. In addition to the tokens being represented in the vector space, the sentences and paragraphs may be represented in the vector space. The entities and intents are then used to determine an action for the system according to a policy that is optimized for. Annotations may be requested when the classifications are below thresholds, and these annotations may be employed in the action determination process. Annotation includes receiving an annotation work in an annotation queue, prioritizing the annotations, and sending the highest priority annotations to the annotator in order. This is used to update the production annotation database.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</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=20200507&DB=EPODOC&CC=US&NR=2020143247A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200507&DB=EPODOC&CC=US&NR=2020143247A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Gainor, Macgregor S</creatorcontrib><creatorcontrib>Ginstrom, Ryan Francis</creatorcontrib><creatorcontrib>Gouge, Connor Mack</creatorcontrib><creatorcontrib>Jonnalagadda, Siddhartha Reddy</creatorcontrib><title>SYSTEMS AND METHODS FOR IMPROVED AUTOMATED CONVERSATIONS WITH INTENT AND ACTION RESPONSE GENERATION</title><description>Systems and methods for generating intents for a response is provided. The tokens of the response is encoded into a dense vector space as a plurality of vectors. Name entities are extracted, and individual sentences and paragraphs are both classified in response to the vectors. In addition to the tokens being represented in the vector space, the sentences and paragraphs may be represented in the vector space. The entities and intents are then used to determine an action for the system according to a policy that is optimized for. Annotations may be requested when the classifications are below thresholds, and these annotations may be employed in the action determination process. Annotation includes receiving an annotation work in an annotation queue, prioritizing the annotations, and sending the highest priority annotations to the annotator in order. This is used to update the production annotation database.</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>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNi8EKwjAQRHvxIOo_LHgW2rTgOSRbk0OSkt1WPJVS4km0UP8fa_EDPM0w7802G-lGjI5Aeg0O2QRNUIcI1jUxdKhBthyc5KWp4DuMJNkGT3C1bMB6Rs_rWarvDhGpWTDCBT3G1d1nm_vwmNPhl7vsWCMrc0rTq0_zNIzpmd59SyIXeVGVojrLovzP-gA16zWo</recordid><startdate>20200507</startdate><enddate>20200507</enddate><creator>Gainor, Macgregor S</creator><creator>Ginstrom, Ryan Francis</creator><creator>Gouge, Connor Mack</creator><creator>Jonnalagadda, Siddhartha Reddy</creator><scope>EVB</scope></search><sort><creationdate>20200507</creationdate><title>SYSTEMS AND METHODS FOR IMPROVED AUTOMATED CONVERSATIONS WITH INTENT AND ACTION RESPONSE GENERATION</title><author>Gainor, Macgregor S ; Ginstrom, Ryan Francis ; Gouge, Connor Mack ; Jonnalagadda, Siddhartha Reddy</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2020143247A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2020</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>Gainor, Macgregor S</creatorcontrib><creatorcontrib>Ginstrom, Ryan Francis</creatorcontrib><creatorcontrib>Gouge, Connor Mack</creatorcontrib><creatorcontrib>Jonnalagadda, Siddhartha Reddy</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Gainor, Macgregor S</au><au>Ginstrom, Ryan Francis</au><au>Gouge, Connor Mack</au><au>Jonnalagadda, Siddhartha Reddy</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>SYSTEMS AND METHODS FOR IMPROVED AUTOMATED CONVERSATIONS WITH INTENT AND ACTION RESPONSE GENERATION</title><date>2020-05-07</date><risdate>2020</risdate><abstract>Systems and methods for generating intents for a response is provided. The tokens of the response is encoded into a dense vector space as a plurality of vectors. Name entities are extracted, and individual sentences and paragraphs are both classified in response to the vectors. In addition to the tokens being represented in the vector space, the sentences and paragraphs may be represented in the vector space. The entities and intents are then used to determine an action for the system according to a policy that is optimized for. Annotations may be requested when the classifications are below thresholds, and these annotations may be employed in the action determination process. Annotation includes receiving an annotation work in an annotation queue, prioritizing the annotations, and sending the highest priority annotations to the annotator in order. This is used to update the production annotation database.</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | eng |
recordid | cdi_epo_espacenet_US2020143247A1 |
source | esp@cenet |
subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
title | SYSTEMS AND METHODS FOR IMPROVED AUTOMATED CONVERSATIONS WITH INTENT AND ACTION RESPONSE GENERATION |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T22%3A06%3A02IST&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=Gainor,%20Macgregor%20S&rft.date=2020-05-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2020143247A1%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 |