Neural network-based scholarship user portrait information extraction method and model

Abstract

The invention relates to a neural network-based scholarship user portrait information extraction method, which comprises the following steps of: carrying out text preprocessing on a webpage, and carrying out structure adjustment and entity labeling on the webpage; constructing Word library tables for all the text nodes and characters thereof of the identified webpage; Extracting context features of the text nodes and the front and rear nodes, and then training a text node sequence to obtain a word vector h containing node sequence context information; And performing decoding calculation on theword vector output, correspondingly obtaining the score of each word vector on the target tag, calculating the tag probability distribution of the node sequence, decoding a model output result, obtaining an optimal prediction tag sequence when the target function is minimum, completing model construction, and performing model training. According to the method, end-to-end training of the model canbe realized, and the problem of long-term dependency between target extraction entities is effectively solved by utilizing the sequence memory characteristic of the LSTM network.

Description

technical field [0001] The invention relates to the field of image information extraction, in particular to a neural network-based method and model for extracting user image information of scholars. Background technique [0002] With the rapid development of applications such as the Internet, mobile Internet, and the Internet of Things, the amount of global data has increased significantly, and user portraits have become one of the most important applications in the context of big data technology. As the first step in user portrait extraction, user information extraction lays the foundation for subsequent user portrait mining and analysis, and largely determines the accuracy and completeness of the final model. In recent years, with the development of big data technology, many studies on user information extraction models have emerged. In terms of information extraction for scholars, most of the current research is to abstract it into a sequence labeling (Sequence Label) pr...

AI Technical Summary

Problems solved by technology

The extraction method of manually written rules needs to write specific rules for each type of page, and depends on specific domain knowledge, so the versatility is very poor; although traditional machine learning methods have improved this problem to a certain extent, they still cannot Ways to handle text nodes with long distances in web pages well

As Web pages become more and more diverse and complex, these problems are becoming more and more prominent, and the existing methods cannot well realize the information extraction of scholars and users.

Images