Event forewarning method based on regions and object information discovery

Abstract

The invention discloses an event forewarning method based on regions and object information discovery. The method comprises the steps of 1) filtering crawled webpage information to obtain non-junk webpage information correlated with food safety events, 2) analyzing words expressing places in the webpage information to obtain accurate place name words, and processing the webpage information based on a constructed event information body and classifying the webpage information into a region of successful matching, 3) processing the webpage information by virtue of a regression analysis model and determining the relevant object class of each webpage, and 4) obtaining a set of a set region and the webpage information of events of objects according to the region of the webpages and the relevant object classes, establishing characteristic parameters of events and regularly calculating the values of the characteristic parameters, and if the characteristic parameter value of one event continuously exceed a set threshold, forewarning on the event. The event forewarning method improves the accuracy and comprehensiveness of event forewarning, and guarantees the efficiency of food safety event forewarning.

Description

technical field [0001] The invention belongs to the field of information technology, and in particular relates to a method for performing specific processing on crawled Internet information, and performing early warning of events on the basis of information discovery on the area where the event occurs, the type of object, etc., and is mainly used in food safety events In the emergency handling of unconventional emergencies such as information monitoring and risk warning. Background technique [0002] In recent years, food safety incidents such as poisonous capsules, twice-cooked oil, clenbuterol, dyed steamed buns, plasticizers, and poisonous cucumbers have occurred frequently, which have not only caused extremely bad social impacts, but also brought a lot of economic losses. In order to avoid or minimize the harm caused by these food safety incidents, event-based risk early warning technology has begun to receive great attention. For event-based risk early warning, it is n...

AI Technical Summary

Problems solved by technology

In this regard, if the impact of various spam information in the information is not considered in the above method, the accuracy of information extraction technology is not high enough so far, and the category information obtained after keyword matching is directly regarded as the same event In the practice of information, there may be problems such as the inconsistency of the subject corresponding to the information. It is not surprising that the above method has insufficient performance.

Images