Disaster monitoring and analysis method for extracting internet multidimensional disaster information

Abstract

The invention provides a disaster monitoring and analysis method for extracting internet multidimensional disaster information. The method includes the steps of S1, performing real-time acquisition and preprocessing of multisource data; S2, constructing a disaster information extraction knowledge base with the assistance of a feature word multidimensional extension algorithm (FWME) to extract disaster loss information and emotional feedback information of affected people for acquiring multidimensional disaster information; S3, performing joint monitoring and analysis on a disaster area according to the multidimensional disaster information. Through the constructed disaster information extraction knowledge base, the disaster loss information and the emotional feedback information of affected people in the disaster process in the internet platform are accurately extracted, joint analysis is performed by combining the time and space dimensions, the disaster progress is described in detail, and the analysis result is also used for assisting in real-time disaster monitoring, disaster assessment and analysis, disaster rescue feedback, subsequent impact assessment and the like.

Description

technical field [0001] The invention relates to the technical field of disaster monitoring and analysis, in particular to extracting multi-dimensional disaster-related information based on Internet multi-source text data for disaster monitoring and analysis. Background technique [0002] my country is a disaster-prone country, and various disasters cause a large number of human and property losses every year. Traditional disaster monitoring methods such as satellite remote sensing, manual survey, etc. are often difficult to be effective in a timely manner due to the shortcomings of harsh implementation conditions and high costs. Moreover, some disaster information, such as the emotional feedback of the disaster audience, is difficult to obtain by traditional disaster monitoring methods, and this information is also extremely important in disaster monitoring and analysis. [0003] At present, many scholars monitor and analyze disaster situations based on social media, such as...

AI Technical Summary

Problems solved by technology

Traditional supervised learning methods not only require manual labeling of large-scale training corpora, but also mostly target text classification on a single topic.

However, the traditional rule-based method requires a lot of expert knowledge to summarize the extraction rules, and the portability is poor.

Images