Extraction method of case information in webpage

Abstract

The invention discloses an extraction method of case information in a webpage. A case attribute knowledge base is built; the knowledge base comprises a case information type special noun set, a qualifier set, a forbidden word set and a case body special modifier set; word segmentation is carried out to a text; an article is segmented into a plurality of whole sentences; corresponding rules are translated in combination with the word sets in the knowledge base; when learning that the words in the word sets corresponding to the rules appear through scanning, the sentence patterns of the words satisfy a certain rule, and there is no forbidden word in the sentence, it is indicated that the sentence satisfies the rule; and the related fields of a court are extracted according to the field positions restricted in the rule. According to the method of the invention, the targeted case information is extracted through a method of combining rules and word count sets; and the case extracted by the method has relatively high accuracy.

Description

technical field [0001] The invention relates to the technical field of Internet information collection, in particular to a method for extracting case information in web pages. Background technique [0002] With the rapid development of the Internet, webpage information has become a huge source of information release and dissemination, and the webpage information is still increasing rapidly, and the webpage may contain a large amount of information required by users, for example, for a certain case Judgment time, judgment result, etc. [0003] In practical applications, in order to provide users with webpage information in a targeted manner, useful information is generally extracted from existing webpages by means of webpage information extraction, and the extracted information is provided to users. In the prior art, when web page information is extracted, methods such as keyword matching can be used. Specifically, when extracting webpage information through the keyword mat...

AI Technical Summary

Problems solved by technology

Applying the above method can extract some relevant informatics from the target webpage, but due to the large amount of information contained in the webpage, there may be multiple information matching the preset keywords, which may cause the extracted The information contains redundant information or wrong information, which affects user experience

When the extracted information contains redundant information, if you want to remove the redundant information, you need to perform secondary processing on the extracted information, and the efficiency of information extraction is low.

Images