METHOD, DEVICE, AND SYSTEM FOR INFORMATION CLASSIFICATION

PROBLEM TO BE SOLVED: To provide the information classifying device which can classify information automatically with high precision. SOLUTION: A correlation matrix processing part 15 generates correlation matrixes by categories from a feature vector set showing features of a text for learning to ob...

Full description

Saved in:
Bibliographic Details
Main Authors MATSUNAGA TSUTOMU, KIDA HIROMI
Format Patent
LanguageEnglish
Published 18.06.1999
Edition6
Subjects
Online AccessGet full text

Cover

Loading…
Abstract PROBLEM TO BE SOLVED: To provide the information classifying device which can classify information automatically with high precision. SOLUTION: A correlation matrix processing part 15 generates correlation matrixes by categories from a feature vector set showing features of a text for learning to obtain a reference profile. A similarity processing part 18 calculates the projections of the feature vector set of a new text to be classified and reference profiles by the categories or a common reference profile to classify the new text. When the classification system is altered, correlation matrixes are generated again by the categories from the feature vector set of the corresponding text group and the reference profile regarding the altered category is updated. A common category processing part 17 puts mutually relative reference profiles together to generate a common category and a common reference profile and also updates a common category when the corresponding reference profile is generated or updated.
AbstractList PROBLEM TO BE SOLVED: To provide the information classifying device which can classify information automatically with high precision. SOLUTION: A correlation matrix processing part 15 generates correlation matrixes by categories from a feature vector set showing features of a text for learning to obtain a reference profile. A similarity processing part 18 calculates the projections of the feature vector set of a new text to be classified and reference profiles by the categories or a common reference profile to classify the new text. When the classification system is altered, correlation matrixes are generated again by the categories from the feature vector set of the corresponding text group and the reference profile regarding the altered category is updated. A common category processing part 17 puts mutually relative reference profiles together to generate a common category and a common reference profile and also updates a common category when the corresponding reference profile is generated or updated.
Author KIDA HIROMI
MATSUNAGA TSUTOMU
Author_xml – fullname: MATSUNAGA TSUTOMU
– fullname: KIDA HIROMI
BookMark eNrjYmDJy89L5WSw9HUN8fB30VFwcQ3zdHbVUXD0c1EIjgwOcfVVcPMPUvD0A5K-jiGe_n4Kzj6OwcGebp7OYC4PA2taYk5xKi-U5mZQdHMNcfbQTS3Ij08tLkhMTs1LLYn3CvAwNDQ0MzQzN3Q0JkYNAH8jKoo
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
Edition 6
ExternalDocumentID JPH11161671A
GroupedDBID EVB
ID FETCH-epo_espacenet_JPH11161671A3
IEDL.DBID EVB
IngestDate Fri Jul 19 15:42:18 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_JPH11161671A3
Notes Application Number: JP19970329934
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=19990618&DB=EPODOC&CC=JP&NR=H11161671A
ParticipantIDs epo_espacenet_JPH11161671A
PublicationCentury 1900
PublicationDate 19990618
PublicationDateYYYYMMDD 1999-06-18
PublicationDate_xml – month: 06
  year: 1999
  text: 19990618
  day: 18
PublicationDecade 1990
PublicationYear 1999
RelatedCompanies NTT DATA CORP
RelatedCompanies_xml – name: NTT DATA CORP
Score 2.500491
Snippet PROBLEM TO BE SOLVED: To provide the information classifying device which can classify information automatically with high precision. SOLUTION: A correlation...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Title METHOD, DEVICE, AND SYSTEM FOR INFORMATION CLASSIFICATION
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=19990618&DB=EPODOC&locale=&CC=JP&NR=H11161671A
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT8IwEL8gfr4pahQ_UhOzJxYZAzYeFgNtl7G4scgk-ETWfST6MIjM-O97a4b4oi99uCZN2_R317ve7wpwPyhpylmESENFoHYR2ioeZaGKWLQ1kUZ6L5HZFn7feem68968Bu8bLoysE_oliyMiomLEeyH19WobxGIyt3L9IN5QtHy0Q4spSUUXG6B5MhU2sngwYROqUGq5geI_Ww5iuq_1DW24A7t4jTZKNPDZqGSlrH6bFPsY9gIcLS9OoJbmDTikm5_XGnDgVQ_eDdiXGZrxGoUVCtenMPB46ExYizA-G1PeIkOfkenrNOQeQaeOjH1sPRl8IvRpiPrSrvjCZ3Bn85A6Ks5m8bP0hRtsJ66fQz1f5ukFkCQ1MvRtRJRFomvqZhSbiZ4YHdHOIj3utC-h-fc4zf86r-CoKkygauY11IuPz_QGzW4hbuV-fQPIl4Id
link.rule.ids 230,309,783,888,25576,76876
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT8IwEL8gfuCbokbxqyZmTywyBmw8LAbaLgPZWGQSfCLrPhJ9GERm_Pc9miG-6EsfrknTNv3d9a73uwLcd9c05TREpKEiUFsIbRWPslBFJBqaSEK9HctsC6_jvLSGs_asBO8bLoysE_oliyMioiLEey719XIbxGIyt3L1IN5QtHi0A4spcUEX66J5MhXWt7g_ZmOqUGoNfcV7thzEdEfrGFpvB3bxim2s0cCn_TUrZfnbpNhHsOfjaFl-DKUkq0KFbn5eq8KBWzx4V2FfZmhGKxQWKFydQNflgTNmdcL4dEB5nfQ8Riavk4C7BJ06MvCwdWXwidBRD_WlXfCFT-HO5gF1VJzN_Gfp86G_nbh-BuVskSXnQOLESNG3EWEaipapm2FkxnpsNEUjDfWo2biA2t_j1P7rvIWKE7ij-WjgPV3CYVGkQNXMKyjnH5_JNZrgXNzIvfsGDVaFEA
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=METHOD%2C+DEVICE%2C+AND+SYSTEM+FOR+INFORMATION+CLASSIFICATION&rft.inventor=MATSUNAGA+TSUTOMU&rft.inventor=KIDA+HIROMI&rft.date=1999-06-18&rft.externalDBID=A&rft.externalDocID=JPH11161671A