Intention recognition method and system based on a blackboard model

Abstract

The invention relates to an intention recognition method and system based on a blackboard model, and the system comprises a blackboard module which is used for decomposing extracted feature parameters into a series of situation inference problems, and storing related data; a knowledge source module which comprises a plurality of mutually independent modules formed by professional domain knowledge and is used for solving various questions submitted by the blackboard; a control mechanism module used for scheduling each module and realizing interactive communication between the blackboard and the knowledge source module; a stimulation module used for calling related knowledge sources for reasoning from bottom to top according to the change of the content stored in each layer of blackboard, selecting knowledge with the highest matching degree with the questions asked by the blackboard from the knowledge sources to make an answer, and giving out a prediction result; a response module used for finding a corresponding matching chain table according to an intention prediction result generated by each layer of knowledge source; the judgment module is used for finding a node corresponding to a prediction object in the corresponding matching chain table and updating the node; and a judgment module used for judging the accumulated value of the node just processed by the response module.

Description

technical field [0001] The invention relates to the field of target recognition, in particular to an intention recognition method based on a blackboard model. Background technique [0002] Obtaining decision-making advantages and gaining control over the battlefield is one of the key conditions for victory in informationized warfare. However, in the informationized combat environment, there are many targets, coordinated relationships and frequent maneuvers. This makes it impossible for commanders to make timely and effective decisions in the face of massive information and rapidly changing battlefield situations. [0003] In order to assist the commander to implement combat command and gain decision-making advantages, it is necessary to use the command and decision-making system for information fusion, that is, to quickly and efficiently process and abstract multi-source information for subsequent situation assessment. [0004] In order to analyze intent, the first thing i...

AI Technical Summary

Problems solved by technology

This increases the difficulty and complexity of the prediction process, and for example, the model lacks the accumulation and correction of the prediction results, which reduces the accuracy of the prediction results

Images