Bad information identification method based on TextCNN-Bert fusion model algorithm

• Main Authors: PEI ZHUOXIONG, YIN WEI, YANG MIN, YANG JING
• Format: Patent
• Language: Chinese; English
• Published: 22.09.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides a bad information identification method based on a TextCNN-Bert fusion model algorithm, and belongs to the technical field of bad information identification based on a model algorithm. The technical problem to be solved is to provide an improvement of a method for identifying bad information by adopting a TextCNN-Bert fusion model algorithm. According to the technical scheme adopted for solving the technical problem, preprocessing of word segmentation, part-of-speech tagging and stop word removal is carried out on a to-be-recognized text, and the preprocessed text is input into a fusion model according to a sequence to be recognized; inputting the preprocessed text into a sensitive field theme recognition module in the fusion model for processing: if the sensitive field theme is recognized as false, judging that the sensitive field theme is irrelevant to the sensitive field, and outputting the text information as general text information; if the subject of the sensitive field is recogni