Computing method for generating creative points by automatic classification and filtration of motivational vocabularies

Abstract

The invention relates to a computing method for generating creative points by automatic classification and filtration of motivational vocabularies; an automatic classification and filtration method based on Bayesian network computing is applied to the generation of creative points; motivational vocabulary corpus information is acquired through crawler algorithm, the acquired information is clustered by establishing a vector space model, correlation between the motivational vocabularies is computed by Bayesian network on such basis, and the motivational vocabularies are subjected to classification and filtration for generation according to phrases or sentence structures based on ontology theory. Experimental results show that the modified method used in the classification and filtration of motivational vocabularies is higher in classification and filtration precision and better in efficiency than traditional classification and filtration methods, and has certain advantages.

Description

technical field [0001] The invention relates to a method for calculating creative points generated through automatic classification and filtering of motivational vocabulary. Background technique [0002] With the rapid development of computer technology and the increasing popularity of the Internet, the amount of information available to users is increasing exponentially [1] , which greatly enriches the information environment in which users live, but at the same time causes problems such as information overload and increases the difficulty for users to obtain the required motivation vocabulary [2] . Automatic classification and filtering, as the simplest and most effective solution, is considered a key technology for processing and organizing large amounts of data [3] , and the calculation of its creative points is the most effective method for judging the pros and cons of automatic classification and filtering methods. It has become an urgent problem in this field and ha...

AI Technical Summary

Problems solved by technology

However, there is a problem of long classification time; literature [7] proposes an automatic classification and filtering method based on information feedback, which selects SNoW as the specific subject classification algorithm on the basis of existing classification algorithms, and proposes information feedback and threshold filtering strategies In order to achieve the purpose of accurately filtering irrelevant words, realize the automatic classification and filtering of motivational words

Although this method can realize the automatic classification and filtering of motivational vocabulary, there is a problem that the classification and filtering effect is not good; literature [8] proposes an automatic classification and filtering method based on heuristic rules, which uses the basis of word segmentation and feature extraction for motivational vocabulary In the above, the NB classifier is used for classification and filtering to realize the automatic classification and filtering of motivation vocabulary, but there is a problem of low classification and filtering accuracy; literature [9] proposes a classification and filtering method based on latent semantic index and support vector machine, and establishes motivation vocabulary. On the basis of the vocabulary information filtering model, the steps of preprocessing, feature dimensionality reduction, training, and filtering have been followed to achieve automatic classification and filtering of motivational vocabulary, but there is a problem of incomplete filtering information

Images