×

Process for determination of text relevancy

  • US 5,694,592 A
  • Filed: 08/28/1995
  • Issued: 12/02/1997
  • Est. Priority Date: 11/05/1993
  • Status: Expired due to Term
First Claim
Patent Images

1. A computer implemented method of creating similarity coefficients between sequences of words in documents that are being searched in a database by a natural word query without parsing the query words nor the words in the documents, and without removing any of the query words and any of the words in the documents, the method comprising the steps of:

  • (a) branching out the meanings of each and every word in a natural word query into respective probabilities of occurrence for each of the meanings in the natural word query;

    (b) branching out the meanings of words in a document searched by the natural word query into respective probabilities of occurrence for each of the meanings of the words in each of the documents;

    (c) determining a similarity coefficient between the probabilities of occurrence of words in the natural language query and the probabilities of occurrence of the words in the document;

    (d) repeating steps (a) to (c) for each additional document searched by the natural language query; and

    (e) ranking the documents being searched in order of their similarity coefficients without parsing of the natural language query and the documents, and without removing any words from the natural language query nor from the documents.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×