Method for automatically identifying address information

Abstract

The invention discloses a method for automatically identifying address information. Address information in characters to be identified is searched by carrying out matching on address data in an information point database established in advance and the characters to be identified, so that the condition that an identifying result is accurate and inerrant can be ensured. By correlating a concrete address and a character index, the address marked by the character index can be automatically identified; and moreover, concrete address information correlated with the character index is provided to a user, so that the use of the user is greatly convenient.

Description

technical field [0001] The invention relates to the technical field of text recognition, in particular to a method for extracting address information from text content. Background technique [0002] With the rapid development of Internet applications, there is an increasing demand for extracting various contact information from text content on computer browsers and mobile devices, such as extracting phone numbers, emails or address information from the text content. The accurate extraction of various contact information can make the user's Internet application more convenient and richer. [0003] The existing method for automatically identifying address information from text content mainly extracts address information containing specific characters such as "**路**号" through semantic analysis of the text content to be recognized. For example, when the text content to be recognized contains words such as "road, street, street" and numbers and "number" behind it, it is extracte...

AI Technical Summary

Problems solved by technology

Existing recognition methods require a strong semantic analysis function, but the recognition effect is often limited by the characteristics of the text to be analyzed, and often cannot accurately identify address information

Moreover, the existing recognition methods can only recognize address information similar to the standard expression of "No. 128, XX Road", but cannot recognize the abbreviation of commonly used address information such as "XX Cafe" corresponding to this address.

Images