Research and application of Web data collection technology for coal mine safety
Aiming at the hard to obtain data such as accidents and penalties required for mine safety analysis,the Web data published on the Internet was selected as the data source.Based on the analysis and summary of the visual characteristics of the Web query results page,a Web data extraction method(VDLE)based on vision and DOM tree was proposed.First,the visual block center of gravity offset was introduced to locate the data region,and then the spectral clustering algorithm was used to locate the node clusters with similar structure within the data region.The data records were located based on the diversity of text organization.The experimental results showed that the precision of VDLE extraction results was 99％,which was 8.51％higher than D-EEM and 4.32％higher than VIDE precision;the recall rate of VDLE extraction results was 98.75％,which was 13.33％higher than that of D-EEM and 8.17％higher than that of ViDE.On this basis,a coal mine safety Web data collection system was developed.The results of field experiments showed that the accident information collected by the system complemented and improved the reserve of mine safety information,laying a data foundation for mine safety analysis.
visualDOM treeWeb data extractioncoal mine safetyaccident analysis
万方数据
维普
