Multi-criterion decision-making-based multi-modal scene information uncertainty processing method and system

Abstract

The invention provides a multi-criterion decision-making-based multi-modal scene information uncertainty processing method and system. The method comprises the following steps: receiving multi-sourcescene information, and modeling the multi-source scene information based on a concept lattice; detecting uncertainty of the multi-source scene information after modeling according to preset thresholdinformation of a scene information knowledge base to obtain the multi-source scene information meeting preset requirements; based on a real-time strategy of multi-mode control, judging whether the scene information is the same type or not according to attributes related to the scene information type in the scene modeling information, and then selecting an uncertainty processing mode according to the type of the scene information; dynamically monitoring processing results of the same kind of scene information in real time; evaluating user satisfaction degree of processing results of the same kind of scene information based on a feedback correction mechanism of QoE. Feedback information of uncertainty processing is continuously obtained through the real-time feedback mechanism, and then real-time closed-loop adjustment is conducted on threshold value information, expert experience and weight parameters in the scene information knowledge base through the feedback information.

Description

technical field [0001] The invention belongs to the field of context-aware information processing, and in particular relates to a multi-criteria decision-making and multi-modal context information uncertainty processing method and system. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] With the maturity of communication technology, sensor technology and network technology, the situational awareness technology has also been developed rapidly, and the situational awareness system is gradually integrated into our daily life. Technology enables computer equipment to "perceive" the current situation, and the situation awareness system is a whole that performs reasoning and calculation on the perceived information and ensures that the intelligent system outputs reliable judgments. [0004] In the process of research and application of situation...

AI Technical Summary

Problems solved by technology

Due to the error-prone nature of sensors, the quality of collected situational information cannot be effectively guaranteed. With the development of various sensor devices and wireless networks, the amount of data acquired in various fields is increasing exponentially. The certainty will increase significantly, and the internal relationship of the data will become more complex, which will cause greater difficulties in accurately extracting complex and diverse useful information

The inventors found that traditional methods for dealing with uncertainty problems generally have the disadvantages of poor flexibility, high redundancy, and low degree of collaboration, and cannot accurately classify useful information

Images