WIPO logo
Mobile | Deutsch | Español | Français | 日本語 | 한국어 | Português | Русский | 中文 | العربية |
PATENTSCOPE

Search International and National Patent Collections
World Intellectual Property Organization
Search
 
Browse
 
Translate
 
Options
 
News
 
Login
 
Help
 
Machine translation
1. (WO2000026795) METHOD FOR CONTENT-BASED FILTERING OF MESSAGES BY ANALYZING TERM CHARACTERISTICS WITHIN A MESSAGE
Latest bibliographic data on file with the International Bureau   

Pub. No.:    WO/2000/026795    International Application No.:    PCT/US1999/024359
Publication Date: 11.05.2000 International Filing Date: 18.10.1999
Chapter 2 Demand Filed:    23.05.2000    
IPC:
G06F 17/27 (2006.01)
Applicants: JUSTSYSTEM PITTSBURGH RESEARCH CENTER, INC. [US/US]; 4616 Henry Street Pittsburgh, PA 15213 (US)
Inventors: KANTROWITZ, Mark; (US).
MCCALLUM, Andrew; (US).
BERNSTEIN, Evan; (US)
Agent: BYRNE, Richard, L.; Webb Ziesenheim Logsdon Orkin & Hanson, P.C. 700 Koppers Building 436 Seventh Avenue Pittsburgh, PA 15219-1818 (US)
Priority Data:
09/183,871 30.10.1998 US
Title (EN) METHOD FOR CONTENT-BASED FILTERING OF MESSAGES BY ANALYZING TERM CHARACTERISTICS WITHIN A MESSAGE
(FR) PROCEDE DE FILTRAGE DE MESSAGES SUR LA BASE DU CONTENU, PAR ANALYSE DES CARACTERISTIQUES DES TERMES A L'INTERIEUR DU MESSAGE
Abstract: front page image
(EN)A computer implemented method for document classification or filtering of junk messages comprises the steps of computing the sum of the product of the frequency of occurrence with an assigned term weight for every term from a term lexicon that also appears in the message, normalizing the resulting sum by dividing the result by the total number of words (or the number of unique words) in the document and assigning a score to the document based on the normalized sum.
(FR)Cette invention se rapporte à un procédé informatisé de classification de documents ou de filtrage de messages poubelles, qui consiste à calculer la somme du produit de la fréquence d'occurrence avec une pondération attribuée à chaque terme provenant d'un lexique de termes apparaissant également dans le message, à normaliser la somme ainsi calculée en divisant le résultat par le nombre total de mots (ou le nombre de mots uniques) dans le document, et à attribuer une notation aux documents sur la base de la somme ainsi normalisée.
Designated States: AE, AL, AM, AT, AU, AZ, BA, BB, BG, BR, BY, CA, CH, CN, CR, CU, CZ, DE, DK, DM, EE, ES, FI, GB, GD, GE, GH, GM, HR, HU, ID, IL, IN, IS, JP, KE, KG, KP, KR, KZ, LC, LK, LR, LS, LT, LU, LV, MA, MD, MG, MK, MN, MW, MX, NO, NZ, PL, PT, RO, RU, SD, SE, SG, SI, SK, SL, TJ, TM, TR, TT, TZ, UA, UG, UZ, VN, YU, ZA, ZW.
African Regional Intellectual Property Organization (GH, GM, KE, LS, MW, SD, SL, SZ, TZ, UG, ZW)
Eurasian Patent Organization (AM, AZ, BY, KG, KZ, MD, RU, TJ, TM)
European Patent Office (AT, BE, CH, CY, DE, DK, ES, FI, FR, GB, GR, IE, IT, LU, MC, NL, PT, SE)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GW, ML, MR, NE, SN, TD, TG).
Publication Language: English (EN)
Filing Language: English (EN)