Cross-media intelligence target element association analysis system and association analysis method thereof

Abstract

The invention provides a cross-media intelligence target element association analysis system and an association analysis method thereof. The invention can remarkably improve the analysis ability of the target object and the application value of the analysis result to the user. The invention is realized by the following technical scheme: the user interactive operation module selects a decision treemodel corresponding to the purpose of information analysis, a goal-centered model of target elements is established, the user requirement information is sent into an association expansion processingmodule, Reads the target element model of the initial retrieval intelligence set according to the index, obtains the structured data of the attribute items of the intelligence data input into the database module, uses the domain prior knowledge and element expansion rules provided by the external data support module to carry out element expansion, and obtains the new extended target element and element expansion intelligence; Retrieves all the information, and outputs the correlation results of the target events to the support service module, and outputs the target analysis results including the target correlation and the target activity law.

Description

technical field [0001] The present invention relates to the field of intelligence information association analysis, in particular to an intelligence association analysis method for element information of a target event. Background technique [0002] With the rapid development of multimedia information technology and Internet technology, more and more multimedia information is flooding the entire network, and it becomes increasingly inseparable from various multimedia information in daily life. People can easily obtain these massive multimedia information, but finding the most relevant and interesting information often consumes a lot of manpower and material resources, and it is extremely difficult to distinguish the value of information. Among these media information, images often contain the largest amount of information and are also the most widely used media. However, image data is often heterogeneous, and its storage is also scattered, which causes a lot of trouble in h...

AI Technical Summary

Problems solved by technology

[0007] In view of the fact that the current cross-media retrieval algorithm does not make full use of the inherent semantic knowledge of events in different media and cannot solve the semantic gap in the cross-media retrieval process, the purpose of the present invention is to provide a more accurate analysis that can accurately measure cross-media The cross-media intelligence target element information association analysis system of data correlation can better find out the association relationship between media in the high-level semantic scope, analyze the potential high-level semantic association information between different media data, and find out the inherent relationship between images. similarity, and can effectively improve the accuracy and efficiency of cross-media retrieval, intelligence association and analysis methods for target event element information

Images