System for analyzing occurrences of logical concepts in text documents

摘要

A method for indexing, extracting, analyzing, and utilizing co-occurrences of logical concepts in text documents is disclosed. References to logical concepts are detected by a text processing procedure by detection of descriptors, e.g., names, also including abbreviations, from a hierarchical dictionary with names and synonyms for said logical concepts, or database identifiers. Co-occurring concepts are indexed and stored in a database as a list or a table. Analysis of co-occurrences detects expressed and implied relationships between co-occurring concepts based on statistical and lexical text analysis. The method includes a procedure to create domain-specific hierarchical dictionaries for logical concepts in a given domain.