Method for statistical text analysis

• US 6,477,524 B1
• Filed: 12/21/1999
• Issued: 11/05/2002
• Est. Priority Date: 08/18/1999
• Status: Active Grant

• Current Assignee: Sharp Laboratories of America Incorporated (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Laboratories of America Incorporated (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Qian, Richard, Taskiran, Cuneyt
• Primary Examiner(s): Coby, Frantz
• Application Number:
  US09/468,508
• Time in Patent Office: 1,050 Days
• Field of Search: 707/2, 707/3, 707/4, 707/5, 707/6
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3346 using probabilistic model
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

A method for retrieving relevant stories from a collection of stories. The method comprises the steps of identifying at least one query term, applying a cooccurrence matrix to the query term to provide a list of query terms, determining if a story in the collection contains any terms on the list of query terms, and then increasing a relevance measure if the story does contain words on the list of query words. If the relevance measure is higher than a threshold, the story is added to a list of relevant stories.

Claims

1. A method for retrieving relevant stories from a collection of stories, the method comprising:

identifying at least one query term;

applying an asymmetrical, cooccurrence matrix to the at least one query term to provide a list of query terms;

determining if a story in the collection contains any terms on the list of query terms;

increasing a relevance measure if the story does contain words on the list of query words; and

adding a story to a list of relevant stories if the relevance measure is higher than a threshold.

2. The method of claim 1, wherein identifying at least one query term further comprises using a user profile for obtaining the at least one query term.

3. The method of claim 1, wherein applying a cooccurrence matrix further comprises comparing a measure from the cooccurrence matrix to a threshold.

4. The method of claim 1, wherein the at least one query term is a single word.

5. The method of claim 1, wherein the at least one query term is a phrase and each word in the phrase is used as a query term.

6. The method of claim 1, wherein increasing a relevance measure further comprises:

determining a frequency of occurrence of the query term in the story;

comparing the frequency to a threshold; and

increasing the relevance measure based upon the comparing step.

7. The method of claim 1, wherein a directed graph is used to derive higher order associative information for each term in the matrix.

8. The method of claim 1, wherein the matrix is used to assist the user in formulating a query.

9. The method of claim 1, wherein the matrix is updated dynamically on the basis of new stories.