Geological document feature lexical item sorting method and device based on graded lexical items

Abstract

The invention relates to a geological document feature lexical item sorting method based on graded lexical items. The method comprises the steps that range type parameter information is acquired; judging whether the range type parameter is the same as a preset first parameter or a preset second parameter or a preset third parameter or not; if so, acquiring range parameter information; based on therange type parameter information and the range parameter information, obtaining a preset first document set or a preset second document set or a preset third document set corresponding to the type parameter information and the range parameter information; obtaining word frequencies of feature lexical items in the first document set or the second document set or the third document set; based on the word frequency of the feature lexical items in the first document set or the second document set or the third document set and preset lexical item levels and level weights corresponding to the feature lexical items, obtaining feature values of the feature lexical items in the first document set or the second document set or the third document set; and based on the feature values of the feature word items, obtaining the feature word items corresponding to the first N feature values in the feature values.

Description

technical field [0001] The invention relates to the field of language processing, in particular to a method and device for sorting geological document feature terms based on hierarchical terms. Background technique [0002] The subject (or feature) of a geological document is determined by all terms in the document and their grammar, context dependencies, etc., among which terms play an important role. [0003] The terms in geological documents include geological named entities such as "XX fault", "XX mine", "XX rock", geological property terms such as "normal fault" and "rhyoline structure", and "2019 Common named entities such as "October 10, Year" and "Hunan Academy of Geological Sciences", basic geological terms such as "stratum", "structure", and "rock mass", and "control", "basis", and "area" , "feature" and other common word segmentations, different terms have different characterization functions on geological documents. [0004] At present, most Chinese text classi...

AI Technical Summary

Problems solved by technology

However, in the general term-document matrix, the number of occurrences of the term is purely used to represent the representation of the term to the topic of the document. The TextRank algorithm uses the relationship between local words (co-occurrence window) to sort the subsequent feature words. Reflect the difference in the importance of different terms to the topic

Images