Multi-field-oriented power lexicon construction method

Abstract

The invention discloses an electric power lexicon construction method oriented to multiple fields, which overcomes the defects in the prior art and comprises the following steps: step 1, collecting electric power related documents, extracting character information of the electric power related documents, enumerating all text segments in the character information, and enabling the length of each text segment to be smaller than a set threshold value; 2, the text fragments are filtered according to lexical related statistical indexes, the filtered text fragments are candidate new words, and all the candidate new words form a candidate word bank; 3, comparing the candidate new words in the candidate word bank with the common vocabularies, if the candidate new words are the common vocabularies, abandoning the candidate new words, If the candidate new words are not the common vocabularies, defining the candidate new words as formal new words; and 4, all the formal new words form a professional lexicon.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a multi-field-oriented electric power thesaurus construction method. Background technique [0002] The existing construction of electric power thesaurus is generally selected through manual screening, and there are the following problems: [0003] (1) A large number of professional data resources of electric power texts have not been utilized [0004] The power industry has accumulated a large amount of text data, including text fragments in the power grid database, power-related documents on the internal and external networks, such as power science and technology papers, project reports, power regulations, power operation manuals, etc. These textual data and unstructured data have not yet been be fully utilized. [0005] (2) The application of artificial intelligence lacks the support of the professional subject database of electric power [0006] Thesaurus is a colle...

AI Technical Summary

Problems solved by technology

[0004] The power industry has accumulated a large amount of text data, including text fragments in the power grid database, power-related documents on the internal and external networks, such as power science and technology papers, project reports, power regulations, power operation manuals, etc. These textual data and unstructured data have not yet been fully utilized

[0005] (2) The application of artificial intelligence lacks the support of the professional subject database of electric power

[0007] (3) Lack of a set of power lexicon production and operation management mechanism covering identification, error correction, generation, and service application

At present, a large part of the accumulation of many professional lexicons relies on the way experts and others sort out and confirm them. There is a lack of a set of online management mechanisms for professional vocabulary generation, management, and external services from identification, error correction, generation to service applications, which accelerates professional development. The accumulation of corpus facilitates the use of artificial intelligence applications

Images