Electric power field table column labeling method based on text classification

• Main Authors: GUO MING, ZHANG YULUO, ZHANG YUNJU, YANG QIANG, SHI QIHONG, XING MIAOMIAO, SHI HUJUN
• Format: Patent
• Language: Chinese; English
• Published: 08.10.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses an electric power field table column labeling method based on text classification, which comprises the following steps of: 1, collecting relevant table text corpora in the electric power field, extracting an entity or a sentence from each row in a table, searching the entity by utilizing a search engine, and obtaining a search result corresponding to the entity; 2, extracting anchor texts from search result entries to form abstracts, and filtering the abstracts by using a power field keyword library to filter out abstracts which do not contain power field keywords so as to form contexts of content elements of the cells; 3, inputting the context of the cell into a classifier based on a pre-training model, obtaining the category to which the cell element belongs, and performing classification marking; and 4, for one column in the table, determining a column label of the column according to the category to which the cell content elements in the column belong. The technical problem that in