Disaster event description text processing method and device, equipment and storage medium

Abstract

The invention provides a disaster event description text processing method, device and equipment and a computer readable storage medium. The method comprises the steps of obtaining a description text of a target disaster event from a source terminal; based on a word segmentation model, performing word segmentation on the description text to obtain a plurality of keywords; based on a semantic generalization model, semantic generalization processing is conducted on the keywords, attribute concept words corresponding to the keywords are obtained, and the attribute concept words are used for describing attributes or categories of the keywords; based on an entity word database, entity matching is conducted on the attribute concept words, entity words corresponding to the attribute concept words are obtained, and the entity words are words associated with attributes or categories of the attribute concept words; and determining a generalization event description text according to the entity word, and sending the generalization event description text to a target terminal. The confidence coefficient of the generalized event description text is improved while the generalized event description text is obtained by constraining the generalization process of the description text. The invention further relates to a block chain technology, and the generalization event description text can be stored in a block chain.

Description

technical field [0001] The present application relates to the technical field of natural language processing, and in particular to a method, device, device and computer-readable storage medium for processing description text of disaster events. Background technique [0002] An event usually refers to the occurrence of some behavior or situation in which a participant participates, or a change in an objective state. Among them, the generalization or induction of specific events is called event generalization. The abstract events after generalization can provide certain support for downstream tasks such as event prediction and event extraction. In the related technologies of traditional natural disaster event generalization , the arguments in the structured event are often abstracted to a certain degree by high-dimensional events through the semantic network, and then the degree of generalization of the arguments in the event is constrained by predicate projection. The genera...

AI Technical Summary

Problems solved by technology

The generalized natural disaster events obtained by such methods have a large number of cases with low confidence

In addition, for event pairs with a certain relationship (such as causal relationship, sequential relationship, and sub-event relationship), after directly generalizing such methods, can the generalized natural disaster event pair still maintain the relationship between the two ends? The same kind of event relationship is difficult to guarantee

Images