A GCN-Based Trend Forecasting Method for Important Events

Abstract

The invention discloses a GCN-based major event trend prediction method. The invention acquires structured event information data from a relational database, constructs an event semantic association graph, and selects a time slice granularity to segment a partial graph; the GCN-based trend prediction model model is input as node vectors and adjacency matrices of multiple local event semantic association graphs , the output is the trend level. This method enhances the semantic understanding of the text, and the prediction accuracy is better than the method of constructing features based on expert knowledge. The method of the invention has the advantages of high timeliness, strong universality, etc., and has broad application prospects in the prediction of major event trend levels.

Description

technical field [0001] The invention relates to the application field of natural language processing and knowledge graph, and relates to a method for constructing a semantic association graph from event information data and extracting event graph features, and extracting graph features through a graph convolution network to predict the trend level of major events . Background technique [0002] In the field of international political relations research, major events generally refer to a type of event that will have a major impact on countries or regions. The major event trend prediction divides the event development trend into different levels, and uses the events that have occurred to predict the future trend level. At present, the main research methods can be divided into two categories: quantitative analysis based on event data analysis and machine learning classification. [0003] Traditional methods rely on expert knowledge to construct domain thematic data and quantif...

AI Technical Summary

Problems solved by technology

At present, the method of automatic feature extraction mainly adopts the distribution characteristics of the subject words. This method only considers the word frequency feature, and further analyzes the news reports through the event extraction technology to obtain the core elements such as the initiator, recipient, and event type of each event. Use event type frequency information to construct semantic and event fusion features. This method of merging event features has tried to use event data to improve document semantic understanding. When counting event type frequency information, the initiator and recipient are restricted. However, only the frequency information of high-frequency events is considered, and the event information data is not fully utilized, which splits the relationship between words or event attributes, and there is still a problem of insufficient understanding of the semantics of document features. Therefore, it is necessary to consider organizing and utilizing in a new form Event information data, document event semantic association information in rich features

Images