| The seriousness of major road traffic accidents and the consequences make road safety become a social problem that can not be ignored.Traffic accident information system has been widely used as an important tool for data collection,analysis and processing.In order to exploit the text information in the traffic accident information system better,we can obtain more valuable information to serve the accident analysis and injury prevention,and provide effective reference for the prevention of accident prevention.In the essay,we aim at developing a tool for text mining which can shorten the time of information procession,enhance the extraction ratio and improve the accuracy of identification.According to the Chinese Specifications for Road Traffic Management Information Collection,the authors build a systematic semantics set for preprocessing of the descriptive texts in the traffic accident information.The set comprises 12 items and 185 standard words,which are standard words and codes extracted from the fundamental traffic accident information defined in the standards of National Public Security.The authors extract 8156 severe traffic accidents collected between 2004 and 2014 from the Accident Query System operated by State Administration of Work Safety.Then we apply the semantics set to analyze the descriptive text in the traffic information.And the 2383 traffic accident data with administrative road type information were screened out.The data were classified according to the provincial administrative area,time,accident form,vehicle type and road type,and the safety level of the road was classified respectively.Also,we use correlation analysis to find the relations between traffic safety level and economical developing level,terrain ladder,and population density.The results show: The data of the traffic accident in the accident inquiry system contains a lot of potential information resources and should be fully utilized.The vocabulary collection based on the relevant laws and regulations can help to extract the relevant information in the text data more accurately.On different road types the safety level is different,and it is necessary to consider the road type in the development of the traffic accident defense measures.The clustering analysis is more scientific to classify the road safety level.The correlation analysis proves the safety level of the road and the economic,terrain and population density between the correlations.It is helpful to understand the mechanism of occurrence,but also provides an objective and direct basis for the development of traffic accident prevention measures,and contributes to the reduction of the traffic accident rate. |
