Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Cross-media event extraction method

An event extraction, cross-media technology, applied in special data processing applications, instruments, electronic digital data processing, etc., can solve the problem of not yet discovered methods for comprehensive news media and social network data event extraction, and achieve a wide range of content coverage, large scale effect

Active Publication Date: 2017-03-08
INST OF INFORMATION ENG CAS
View PDF4 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

No method has been found for event extraction in integrated news media and social network data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Cross-media event extraction method
  • Cross-media event extraction method
  • Cross-media event extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] This method provides a cross-media event extraction method, which is used to quickly generate fine-grained structured event data based on news media and social network related information after a specific category of major events, including data extraction, event summary framework, Event feature extraction and event fusion. Hereinafter, the present invention will be described in detail in conjunction with specific embodiments, wherein the extraction of social network events is taken as an example of researching microblog data. It should be understood that this embodiment is only used to explain the present invention and not limit the scope of the present invention.

[0022] refer to figure 1 Shown is a schematic flow diagram of the cross-media event extraction method of the present invention, including the following steps:

[0023] (1) Set up the seed event feature database and the required knowledge data, including the database of entity elements such as specific orga...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a cross-media event extraction method. The cross-media event extraction method comprises the steps of setting a seed event feature library and required knowledge data; collecting a news webpage from a trusted news source and extracting a news text and metadata information; extracting event factor information from each news text and generating an initial event collection; calculating the degree of importance of each factor of an initial event in an portrayed event and generating an initial general event framework; searching a social network message text based on each factor in the initial general event framework and generating a candidate message collection; filtering the candidate messages based on the similarity of a general framework of the candidate messages and the general event framework to obtain a message queue corresponding to the initial event; and generating complete event data by using the event factors in the initial general event framework and the event factors which exist in the message queue but do not exist in the initial general framework. The cross-media event extraction method can realize accurate extraction of important events in an environment with massive cross-media data.

Description

technical field [0001] The invention relates to an event extraction method in a cross-media data environment based on news media and social networks, and belongs to the field of information extraction. Background technique [0002] Scientific quantitative analysis of news event data has been applied in social research such as situational awareness, emergency response, and risk warning. Event data (Event Data) records a human activity in a specific scene, including multiple elements such as the subject and object involved, the act, time, place, type, sociological attributes, etc., and is usually expressed in the form of a multigroup. An atomic description of the real world. The representation categories of event elements can be divided into digital type, descriptive type, assertive type, etc. Digital type data usually represents the quantitative information in the event, descriptive type data is usually a keyword classified with event elements, and assertive type data is use...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/30G06Q50/00G06F17/27
CPCG06F16/3344G06F40/30G06Q50/01
Inventor 尹芷仪薛聪向继查达仁王雷
Owner INST OF INFORMATION ENG CAS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products