METHOD OF INFERRING SPATIAL MEANING TO TEXT

• US 20080114736A1
• Filed: 10/30/2007
• Published: 05/15/2008
• Est. Priority Date: 02/22/2000
• Status: Abandoned Application

• Current Assignee: Nokia Corporation
• Original Assignee: Metacarta, Inc.
• Inventors: RAUCH, Erik M., FRANK, John R.
• Application Number:
  US11/929,715
• Publication Number:
  US 20080114736A1
• Time in Patent Office: Days
• US Class Current: 707/3
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/338 Presentation of query results
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06F 16/954 Navigation, e.g. using categorised browsing
• 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 707/99937 Sorting
• CPC Class Codes: Y10S 707/99938 Concurrency, e.g. lock management in shared database
• CPC Class Codes: Y10S 707/99939 Privileged access
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99944 Object-oriented database structure
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

A computer-implemented method involving a corpus of documents, the method involving: analyzing the documents in the corpus of documents to identify known spatial identifiers, each of the known spatial identifiers identifying a corresponding spatial location; analyzing the corpus of documents to identify a specific text that is not a known spatial identifier; analyzing the corpus of documents to assess a degree of association between the specific text and one or more known spatial identifiers; and if the degree of association between the specific text and a known spatial identifier is sufficiently high, associating the specific text with the spatial location identified by that known spatial identifier.

Claims

1. A computer-implemented method involving a corpus of documents, said method comprising:

analyzing the documents in the corpus of documents to identify known spatial identifiers, each of said known spatial identifiers identifying a corresponding spatial location;

analyzing the corpus of documents to identify a specific text string that is not a known spatial identifier;

analyzing the corpus of documents to assess a degree of association between said specific text string and one or more known spatial identifiers; and

if the degree of association between said specific text string and a known spatial identifier is sufficiently high, associating said specific text string with the spatial location identified by that known spatial identifier.

2. The method of claim 1, wherein analyzing the corpus of documents to assess the degree of association involves statistically analyzing correlations.

3. The method of claim 1, where the degree of association between the specific text string and a known spatial identifier is measured by determining a frequency with which the specific text string and the known spatial identifier occurs in the same document among the corpus of documents.

4. The method of claim 1, wherein said specific text string is a specific word.

5. The method of claim 1, wherein said specific text string is a specific phrase.