Address segmentation method and device

Abstract

The invention discloses an address segmentation method and device, and relates to the technical field of computers. A specific implementation mode of the method comprises the steps that all addressesto be matched are determined according to character strings of to-be-segmented addresses; traversing each address to be matched, so as to obtain a result array; and constructing a segmentation array based on the obtained result array so as to realize address segmentation. By virtue of the embodiment, the problem of information repetition and ambiguity of administrative regions can be solved, and standardized segmentation of the address can be realized with relatively high accuracy.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for address word segmentation. Background technique [0002] Address information is an effective description of a geographic location based on certain rules and combinations of keywords. Today, with the development of the Internet and logistics technology, a large number of online shopping users fill in address information online to ensure accurate analysis of contact addresses or timely and accurate delivery of goods. However, on the one hand, the address information is not standardized enough to be filled by the user itself, and on the other hand, the address information template and the address information filled in by the user are often redundant, resulting in insufficient standardization of user address information storage and a waste of storage space. In addition, it also poses a huge challenge to the address matching technology for analyzing user ris...

AI Technical Summary

Problems solved by technology

[0003] At present, some address word segmentation methods are based on the establishment of a set of hierarchical rule bases based on the standardized form of national standard addresses, such as first-level countries, second-level provinces, third-level cities..., and so on, and then through regular matching. Word segmentation address, once the user fills in irregularly and the keyword is missing, the accuracy rate is extremely low

There is also a combination of address dictionary and word segmentation rules to segment words. This method has improved both accuracy and efficiency compared to the past, and it also has the ability to clean address information (based on certain word segmentation rules), but Although the matching method relies on the tree model, the cost is still high, and the ability to deal with the repetition or ambiguity of administrative divisions (country, province, city, district level) is weak

There is also a method based on word frequency statistics to realize address word segmentation, but it is often misclassified due to address ambiguity

[0004] Considering the complex scene of address information, it is still difficult for the above methods to achieve standardized word segmentation of addresses with high accuracy.

Images