SYSTEM AND METHOD FOR SPATIAL SALIENCY EXPLANATION FOR TIME SERIES MODELS

Example aspects include techniques for spatial saliency explanation for Time Series machine learning models. These techniques may include identifying, based on a token-based importance method, a plurality of tokens of a predefined importance to a machine learning (ML) inference. In addition, the tec...

Full description

Saved in:
Bibliographic Details
Main Authors LOHIA, Pranay Kumar, PANWAR, Naveen, PATRO, Badri Narayana
Format Patent
LanguageEnglish
French
Published 08.08.2024
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Example aspects include techniques for spatial saliency explanation for Time Series machine learning models. These techniques may include identifying, based on a token-based importance method, a plurality of tokens of a predefined importance to a machine learning (ML) inference. In addition, the techniques may generating frequency distribution information based on the plurality of tokens of the predefined importance, and generating, based on the frequency distribution information, quantile information for the plurality' of tokens of a predefined importance. Further, the techniques may include calculating spatial saliency information based on the frequency distribution information and quantile information, the spatial saliency information including a spatial saliency value for a. quantile of the quantile information, and presenting the spatial saliency information via a graphical user interface. Des aspects donnés à titre d'exemple comprennent des techniques d'explication de relief spatial pour des modèles d'apprentissage automatique de série chronologique. Ces techniques peuvent consister à identifier, sur la base d'un procédé d'importance basé sur un jeton, une pluralité de jetons d'une importance prédéfinie par rapport à une inférence d'apprentissage automatique (ML). De plus, les techniques peuvent générer des informations de distribution de fréquence sur la base de la pluralité de jetons de l'importance prédéfinie et générer, sur la base des informations de distribution de fréquence, des informations de quantile pour la pluralité de jetons d'une importance prédéfinie. En outre, les techniques peuvent consister à calculer des informations de relief spatial sur la base des informations de distribution de fréquence et des informations de quantile, les informations de relief spatial comprenant une valeur de relief spatial pour un quantile des informations de quantile, et à présenter les informations de relief spatial par le biais d'une interface utilisateur graphique.
AbstractList Example aspects include techniques for spatial saliency explanation for Time Series machine learning models. These techniques may include identifying, based on a token-based importance method, a plurality of tokens of a predefined importance to a machine learning (ML) inference. In addition, the techniques may generating frequency distribution information based on the plurality of tokens of the predefined importance, and generating, based on the frequency distribution information, quantile information for the plurality' of tokens of a predefined importance. Further, the techniques may include calculating spatial saliency information based on the frequency distribution information and quantile information, the spatial saliency information including a spatial saliency value for a. quantile of the quantile information, and presenting the spatial saliency information via a graphical user interface. Des aspects donnés à titre d'exemple comprennent des techniques d'explication de relief spatial pour des modèles d'apprentissage automatique de série chronologique. Ces techniques peuvent consister à identifier, sur la base d'un procédé d'importance basé sur un jeton, une pluralité de jetons d'une importance prédéfinie par rapport à une inférence d'apprentissage automatique (ML). De plus, les techniques peuvent générer des informations de distribution de fréquence sur la base de la pluralité de jetons de l'importance prédéfinie et générer, sur la base des informations de distribution de fréquence, des informations de quantile pour la pluralité de jetons d'une importance prédéfinie. En outre, les techniques peuvent consister à calculer des informations de relief spatial sur la base des informations de distribution de fréquence et des informations de quantile, les informations de relief spatial comprenant une valeur de relief spatial pour un quantile des informations de quantile, et à présenter les informations de relief spatial par le biais d'une interface utilisateur graphique.
Author LOHIA, Pranay Kumar
PATRO, Badri Narayana
PANWAR, Naveen
Author_xml – fullname: LOHIA, Pranay Kumar
– fullname: PANWAR, Naveen
– fullname: PATRO, Badri Narayana
BookMark eNrjYmDJy89L5WTwDI4MDnH1VXD0c1HwdQ3x8HdRcPMPUggOcAzxdPRRCHb08XT1c45UcI0I8HH0Awr6-4EVhHj6uioEuwZ5ugYr-Pq7uPoE8zCwpiXmFKfyQmluBmU31xBnD93Ugvz41OKCxOTUvNSS-HB_IwMjE0MzY1NLY0dDY-JUAQASqi_S
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
DocumentTitleAlternate SYSTÈME ET PROCÉDÉ D'EXPLICATION DE RELIEF SPATIAL POUR DES MODÈLES DE SÉRIE CHRONOLOGIQUE
ExternalDocumentID WO2024163593A1
GroupedDBID EVB
ID FETCH-epo_espacenet_WO2024163593A13
IEDL.DBID EVB
IngestDate Fri Aug 23 06:56:15 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
French
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_WO2024163593A13
Notes Application Number: WO2024US13746
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240808&DB=EPODOC&CC=WO&NR=2024163593A1
ParticipantIDs epo_espacenet_WO2024163593A1
PublicationCentury 2000
PublicationDate 20240808
PublicationDateYYYYMMDD 2024-08-08
PublicationDate_xml – month: 08
  year: 2024
  text: 20240808
  day: 08
PublicationDecade 2020
PublicationYear 2024
RelatedCompanies MICROSOFT TECHNOLOGY LICENSING, LLC
RelatedCompanies_xml – name: MICROSOFT TECHNOLOGY LICENSING, LLC
Score 3.554375
Snippet Example aspects include techniques for spatial saliency explanation for Time Series machine learning models. These techniques may include identifying, based on...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Title SYSTEM AND METHOD FOR SPATIAL SALIENCY EXPLANATION FOR TIME SERIES MODELS
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240808&DB=EPODOC&locale=&CC=WO&NR=2024163593A1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1bS8MwFD6MeX3TqXiZElD6VrxkvexhSNdkbNKuxVbdnkabpSBIN1zFv-9J3HRPe8yFQxL4cs6XnHwBuKEWneYP9tS0CwR5izrCzO-pMF1pFa7Scyv0LxHh0O6_tJ5G1qgGH6u3MFon9FuLIyKiBOK90vv1_P8Qi-ncysVt_o5Vs8de2mHGkh0rva4712DdDo8jFvmG7yNvM4bPug1DD6tNPeRKWxhIOwoP_LWr3qXM151K7wC2Y7RXVodQk2UD9vzV32sN2A2XV94N2NE5mmKBlUscLo5gkIyTlIfEGzIS8rQfMYJsjiSxlw68gCReoI6OxoSP4sD7FbzVHdJByEmC3I0nJIwYD5JjuO7x1O-bOLrJ32JM3qL1qdATqJezUp4CeXDktK304yXGFKKVuUVmO1km3bZwqJDOGTQ3WTrf3HwB-6qoU9_cJtSrzy95ie64yq_0Kv4ASuCGww
link.rule.ids 230,309,783,888,25576,76876
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1bS8MwFD6MeZlvOhUvUwNK34q6rpc9DOnajFZ7w0bdnkrbpSBIN1zFv-9p3HRPe80JIQl8Oec7OfkCcKOoyjTralNZKxDkPUXP5exeyWWDq4VR67kV4pcIP9Ccl97jWB034GP1FkbohH4LcUREVI54r8R5Pf9PYtmitnJxm71j0-xhxAa2tGTHtV7XnSHZwwGNQju0JMtC3iYFz8KGoYfaV0zkSlsYZOs1HujrsH6XMl93KqN92I5wvLI6gAYv29CyVn-vtWHXX155t2FH1GjmC2xc4nBxCG48iRn1iRnYxKfMCW2CbI7Ekclc0yOx6dWpowmh48gzfwVvRQfm-pTEyN1oTPzQpl58BNcjyixHxtklf5uRvIXrS1GOoVnOSn4CpKvzab_Wj-cYU-S91ChSTU9TbvRzXcm5fgqdTSOdbTZfQcthvpd4bvB0Dnu1SZTBGR1oVp9f_AJdc5Vdih39AckCibY
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=SYSTEM+AND+METHOD+FOR+SPATIAL+SALIENCY+EXPLANATION+FOR+TIME+SERIES+MODELS&rft.inventor=LOHIA%2C+Pranay+Kumar&rft.inventor=PANWAR%2C+Naveen&rft.inventor=PATRO%2C+Badri+Narayana&rft.date=2024-08-08&rft.externalDBID=A1&rft.externalDocID=WO2024163593A1