Text feature judgment method and device based on neural network and storage medium

Abstract

The embodiment of the invention discloses a text feature judgment method and device based on a neural network and a storage medium, and the method comprises the steps: distributing identification information for identification characters, generating character identification associated data, and the identification characters comprising at least one of a Chinese character, a punctuation character, anumeric character and an English character; acquiring a text training set, the text set comprising multiple training texts and training text features corresponding to each training text, and each training text being composed of one or more identification characters; generating a curve coordinate graph corresponding to each training text according to the character identifier associated data; taking the curve coordinate graph as an input, taking the corresponding training text feature as an output, and training by using a neural network to obtain a text feature judgment template; and obtaininga to-be-recognized text, and judging the to-be-recognized text according to the text feature judgment template to determine text features. According to the scheme, the text content is deeply analyzed,the obtained text features are high in accuracy, and meanwhile the judgment efficiency is improved.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, and in particular to a neural network-based text feature judgment method, device and storage medium. Background technique [0002] With the development of technologies such as social networks, e-commerce, and mobile Internet, blogs, forums, and social service networks such as Dianping have produced a large number of user-participated, valuable and emotional content such as people, events, and products. Text comment data information, the rapid expansion of these text comment data information, all express people's various emotional colors and emotional tendencies, such as joy, anger, sorrow, joy, criticism, praise, etc. Fully mining and in-depth analysis of such text comment data information can better understand the views and positions of netizens, so as to better assist decision-making in various fields such as public opinion management and control, business decision...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, when the text is processed to judge the text features (such as the emotional features represented by the text), the accuracy is low, and the judgment effect and judgment efficiency are poor

Images