Neural-network-based self-learning semantic detection method and system

Abstract

The invention discloses a neural-network-based self-learning semantic detection method and system. The method includes the steps: 101, a dictionary base is imported to segment filenames to be recognized so as to obtain keywords in the filenames, and a probability item of each keyword is calculated on the basis of a Bayesian algorithm; the probability items are analyzed and acquired on the basis of judgment results of good or bad filenames; 102, a product of multiplying a product of probabilities of all keywords occurring in good semantic string names and prior probabilities of the good semantic string names is obtained; a product of multiplying a product of probabilities of all keywords occurring in bad semantic string names and prior probabilities of bad semantic string names is obtained; 103, the two products are compared; if the product item of the good semantic string is larger than that of the bad semantic strings, the strings are determined as to have good semantics; if not, the strings are determined to have bad semantics; judgment results are stored in a storage medium.

Description

technical field [0001] The invention belongs to the field of network information processing and analysis, in particular to the field of automatic determination of the nature and tendency of text information content, and in particular to a neural network-based self-learning semantic detection method and system. Background technique [0002] The automatic processing and analysis technology of network information is an important part of realizing the analysis, detection and management of network content, and it is of great significance to the construction of network content processing and security system. [0003] Due to the continuous development of network technology and the continuous improvement of bandwidth provided by operators, users can easily access and download various information on the network. Information dissemination provides new convenience. In recent years, the dissemination of harmful information such as obscenity, pornography and reactionary information is p...

AI Technical Summary

Problems solved by technology

From the perspective of system composition, the existing discriminant system basically only has a word segmentation module and a discriminant module. It performs simple word segmentation, and then checks whether bad keywords are included to judge the attributes of the file name. The success rate is often not high.

Images