Field word identification method and device

Abstract

The embodiment of the invention discloses a field word identification method and device. In the scheme provided by the embodiment of the invention, a search engine serves as the basis, and the field key word of a field to which a field word to be identified possibility belongs is determined according to the search result of the field word to be identified by the search engine; the score of the field word to be identified, which belongs to the field, is calculated according to the information of the pre-determined field key words and the search result; the score is compared with the field conformity threshold value of the field; and according to a comparison result, whether the field word to be identified belongs to the field is determined. The scheme provided by the embodiment obtains linguistic data having great correlation degree with the field word to be identified by using the characteristics of the search engine, thereby greatly improving the identification speed and accuracy of the field word.

Description

technical field [0001] The present invention relates to the field of information recognition, in particular to a method and device for field word recognition. Background technique [0002] Domain words refer to characteristic words with a strong text representation function, that is, they can clearly express the content characteristics of the text (such as domain category, theme, central meaning, etc.). Field words can be divided into field common words and field specific words according to the field circulation of words. [0003] Common words in the field are basic words representing the field, representing the centroid characteristics of this type of field, such as "games, teams" in sports; field-specific words are highly specific and highly differentiated, and can distinguish the detailed characteristics of the field For example, "World Boxing Council, Boxing Champion" in the sports category can not only distinguish the sports category from other categories, but also dis...

AI Technical Summary

Problems solved by technology

[0006] The inventor found through research on the existing technology that the rule-based method actually uses linguistic rules to identify and extract terms. Since linguistic rules are difficult to find, especially in today's highly developed Internet, the expression methods are becoming more and more diverse. , the linguistic rules are even more difficult to find. At present, it is mainly to use artificial intelligence to discover linguistic rules, and then use them in automatic computer recognition. This method makes the recognition speed of domain words slow and lags behind the development of information seriously Accuracy is also limited by the degree of human cognition; the recognition performance of domain words based on statistical methods depends on the performance of the algorithm model and the amount of information provided by the text corpus

Although the optimization of models and algorithms can improve the performance of recognition to a certain extent, because the text corpus often contains domain words in multiple fields, this intersectionality will bring great difficulties to the recognition of domain words.

Images