DETERMINING CORE GEOGRAPHICAL INFORMATION IN A DOCUMENT

摘要

A method determines core geographical information in a document by computing a score for each geographical name found in the document. The computation of the score uses the appearance frequency of the respective geographical name and positional weights assigned to various types of appearance positions of the geographical name in the document. The system determines the core geographical information in the document based on the scores of the geographical names found in the document. The method may further compute aggregated scores of geographical regions related to the geographical names and determine the core geographical information using both the aggregated scores of geographical regions and the scores of individual geographical names to increase accuracy.

主权项

1. A method for determining core geographical information in a document, the method comprising:
identifying appearances of a plurality of geographical names in the document; determining one or more frequencies of each geographical name's appearances in the document; assigning one or more positional weights to each geographical name according to positions of the geographical name's appearances in the document; computing a score of each geographical name based on the one or more frequencies and the one or more positional weights of the respective geographical name; and determining the core geographical information in the document based on the scores of the plurality of geographical names.