Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO1997038382) METHOD OF AUTOMATICALLY CLASSIFYING A TEXT APPEARING IN A DOCUMENT WHEN SAID TEXT HAS BEEN CONVERTED INTO DIGITAL DATA
Latest bibliographic data on file with the International Bureau   

Pub. No.: WO/1997/038382 International Application No.: PCT/DE1997/000583
Publication Date: 16.10.1997 International Filing Date: 21.03.1997
Chapter 2 Demand Filed: 08.08.1997
IPC:
G06F 17/30 (2006.01) ,G06F 19/00 (2006.01) ,G06K 9/68 (2006.01) ,G06K 9/72 (2006.01) ,G06Q 10/00 (2006.01)
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
F
ELECTRIC DIGITAL DATA PROCESSING
17
Digital computing or data processing equipment or methods, specially adapted for specific functions
30
Information retrieval; Database structures therefor
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
F
ELECTRIC DIGITAL DATA PROCESSING
19
Digital computing or data processing equipment or methods, specially adapted for specific applications
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
K
RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9
Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62
Methods or arrangements for recognition using electronic means
68
using sequential comparisons of the image signals with a plurality of reference, e.g. addressable memory
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
K
RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9
Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62
Methods or arrangements for recognition using electronic means
72
using context analysis based on the provisionally recognised identity of a number of successive patterns, e.g. a word
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
Q
DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
10
Administration; Management
Applicants:
BLOCK, Hans-Ulrich [DE/DE]; DE (UsOnly)
BRÜCKNER, Thomas [DE/DE]; DE (UsOnly)
SIEMENS AKTIENGESELLSCHAFT [DE/DE]; Wittelsbacherplatz 2 D-80333 München, DE (AllExceptUS)
Inventors:
BLOCK, Hans-Ulrich; DE
BRÜCKNER, Thomas; DE
Priority Data:
196 13 400.503.04.1996DE
Title (EN) METHOD OF AUTOMATICALLY CLASSIFYING A TEXT APPEARING IN A DOCUMENT WHEN SAID TEXT HAS BEEN CONVERTED INTO DIGITAL DATA
(FR) PROCEDE DE CLASSIFICATION AUTOMATIQUE D'UN TEXTE REPORTE SUR UN DOCUMENT APRES AVOIR ETE TRANSFORME EN DONNEES NUMERIQUES
(DE) VERFAHREN ZUR AUTOMATISCHEN KLASSIFIKATION EINES AUF EINEM DOKUMENT AUFGEBRACHTEN TEXTES NACH DESSEN TRANSFORMATION IN DIGITALE DATEN
Abstract:
(EN) The text to be classified is compared with the contents of a relevance lexicon in which the significant words of the texts to be classified are stored according to text class and their relevance for the text classes. The blurred quantity (fuzzy quantity) which indicates the occurrence per text class of the significant words of the text to be classified and their relevance for the text class is calculated. A probability calculation determines the degree of probability with which the fuzzy quantity occurs per class for the class in question. The class with the highest degree of probability is selected and the text is assigned to this class.
(FR) Le texte à classé est comparé au contenu d'un lexique de pertinence dans lequel sont stockés les mots significatifs des textes à classer par catégorie de textes et selon leur pertinence pour les catégories de textes. La quantité imprécise (quantité floue) qui indique l'apparition par catégorie de textes et la pertinence pour la catégorie de textes des mots significatifs du texte à classer, est calculée. Un calcul de probabilité permet d'obtenir la probabilité avec laquelle la quantité floue intervient par catégorie pour la catégorie correspondante. La catégorie présentant la plus grande probabilité est sélectionnée et le texte est affecté à cette catégorie.
(DE) Der zu klassifizierende Text wird mit dem Inhalt eines Relevanzlexikons verglichen, in dem die signifikanten Wörter der zu klassifizierenden Texte pro Textklasse und deren Relevanz für die Textklassen gespeichert ist. Es wird die unscharfe Menge (Fuzzymenge) berechnet, die für die signifikanten Worte des zu klassifizierenden Textes deren Auftreten pro Textklasse und deren Relevanz für die Textklasse angibt. Mit einer Wahrscheinlichkeitsberechnung wird ermittelt, mit welcher Wahrscheinlichkeit die Fuzzymenge pro Klasse für die entsprechende Klasse auftritt. Die Klasse mit der höchsten Wahrscheinlichkeit wird ausgewählt und dieser Klasse der Text zugeordnet.
Designated States: JP, US
European Patent Office (EPO) (AT, BE, CH, DE, DK, ES, FI, FR, GB, GR, IE, IT, LU, MC, NL, PT, SE)
Publication Language: German (DE)
Filing Language: German (DE)