Identification method of user operation intention and cognitive state in human-computer interaction

Abstract

The present invention discloses an identification method of user operation intention and cognitive state in human-computer interaction. The method comprises the following steps: collecting eye movement characteristic data and electroencephalogram signal data of users in a human-computer interaction process; pre-processing the collected data and respectively dividing into a training set and a testset; and using the training set to train an SVM classifier and then using the optimized classifier to classify the test set to obtain corresponding operation intention and cognitive state. The identification method can identify operation requirements in the interaction process, provides a basis for adaptive adjustment of interfaces, at the same time, can judge the cognitive state of the interaction process and ensures reliability of completion of interaction tasks.

Description

technical field [0001] The invention belongs to the technical field of ergonomics, and in particular relates to a method for identifying user operation intentions and cognitive states in human-computer interaction. Background technique [0002] In many fields such as aviation flight operation, weapon equipment operation, CNC machine tool operation, manufacturing operation system monitoring and operation, operators need to complete a large number of interactive tasks, process massive amounts of information, and have high requirements for timeliness and accuracy. This has caused great burden to the operator's physiology and psychology. In addition, long-term high-intensity operations have continuously reduced the work efficiency of operators, and the rate of operational errors has continued to increase. However, the existing system has a low level of intelligence and cannot perceive the operational needs of operators, which reduces the efficiency and reliability of interactiv...

AI Technical Summary

Problems solved by technology

[0002] In many fields such as aviation flight operation, weapon equipment operation, CNC machine tool operation, manufacturing operation system monitoring and operation, operators need to complete a large number of interactive tasks, process massive amounts of information, and have high requirements for timeliness and accuracy. This has caused a great burden on the operator's physiology and psychology.

In addition, long-term high-intensity operations have continuously reduced the work efficiency of operators, and the rate of operational errors has continued to increase.

However, the existing system has a low level of intelligence and cannot perceive the operational needs of operators, which reduces the efficiency and reliability of interactive tasks.

[0003] In addition, the operator may be in a different cognitive state during the process of completing the human-computer interaction task: in the on-duty task, since the operator only needs to roughly monitor the entire interface, it is very easy to be "out of the loop" due to the monotony of the task

Once an alarm occurs, the operator needs to deal with the abnormal situation quickly, and it is very easy to cause "stress" due to the tension of the task

If it is impossible to monitor the cognitive state of the operator in real time, give a warning when "out of the loop", and provide information assistance when "stressed", it will be difficult to guarantee the reliability and efficiency of the human-computer interaction process

Images