Method for predicting group events through event knowledge graph

Abstract

The invention discloses a method for predicting group events through an event knowledge graph, and relates to the technology of event knowledge graph mining and application. The method is implementedthrough the following technical scheme: the method comprises two stages of prediction model training and real-time prediction; in the prediction model training stage, historical structured event dataare used as input data to construct a historical event graph, a graph embedding network is adopted to learn vectorized representation of the event graph, and then whether an event occurs or not is predicted based on a classification network model established by a deep neural network. In the real-time prediction stage, real-time structured event data are used as input data to construct a real-timeevent graph, the real-time event graph is used as input data of a trained event prediction model, the event graph constructed by the real-time event data is input into the event prediction model, vectorized representation of the event graph is obtained, and then deep semantic information of the event data is mined and is converted into a dichotomy problem that an event occurs or does not occur, and a result with the maximum probability is taken as a prediction result of whether the event occurs or not.

Description

Technical field[0001]The invention relates to knowledge graph mining in the field of data mining, in particular to event knowledge graph mining and application technology, in particular to a group event prediction method based on event knowledge graph mining.Background technique[0002]Among the three words group, emergency and event, around the word "event", group and emergency are all attributive terms used to describe a certain state or a certain nature of the "event". Group emergencies refer to the behaviors and activities of actors with the same interest demands that, under certain time, space and psychological conditions, adopt spontaneous or organized methods of gathering crowds to conflict or confront public order and public safety. Because many events happen suddenly, or the subject of some events is group-like, some people put "emergency" and "event" together and describe it as an emergency; some people put "group" and "event" together to express As a "mass incident". Differ...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to solve the problems existing in the current group event prediction method such as single unstructured event data information, weak event correlation analysis ability, insufficient event feature mining, long prediction response time, and low early warning accuracy, etc., to provide a Based on the event graph, it can effectively realize event correlation analysis, important information mining, and real-time prediction and early warning group event prediction method

Images