Event information mining and warning method

Abstract

The invention discloses an event information mining and warning method, and belongs to the technical field of information. The method comprises the following steps: step 1, an event information ontology is built, obtained internet information is filtered, and information corresponding to an event is obtained; step 2, classification is conducted to the filtered information basing on the instance name and attribute in the event information ontology; step 3, clustering is conducted to the classified information according to set features, invents contained in each type of information are obtained; step 4, event feature parameter values of information page number, page views, page forward number, information source area number, information source web site number and the like of each event are calculated at fixed period; and step 5, if a difference value between the feature parameter values of a certain event and the mean value of the period time before exceeds a pre-set threshold value, alarming is conducted to the event. The event information mining and warning method ensures accuracy and comprehensiveness of information discovery and alarming of food safety events, and improves the efficiency of alarming of food safety risks.

Description

technical field [0001] The present invention belongs to the field of information technology, and in particular relates to a method for processing Internet information acquired by crawling by using specific strategies and steps to discover and warn food safety incident information, which is mainly used in food safety incident information monitoring, risk early warning, etc. In the emergency response work of planned emergencies. Background technique [0002] In recent years, food safety incidents such as 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 necessary to discover information about these events in advance. [0003] With the ...

AI Technical Summary

Problems solved by technology

In this regard, if it is considered that the above method only considers news information and does not consider the current Web2.0 applications such as blog information, does not consider the impact of various spam information in the information, and the accuracy of information extraction technology is not enough so far. High, and the method of directly using the category information obtained after keyword matching as the same event information may have problems such as inconsistency of the subject corresponding to the information. It is not surprising that the above method has insufficient performance

Images