Cognitive classification and prediction method and system based on eye movement track and deep learning

Abstract

The invention belongs to the technical field of eye movement track data processing, and discloses a cognitive classification and prediction method and system based on eye movement track and deep learning, and the method comprises the steps of collecting a face image of a user through camera equipment arranged on an intelligent terminal, such as a smart phone, and processing the collected face image of the user, and generating an eye movement language; and classifying and predicting eye movement tracks based on the generated eye movement language by using a pre-trained eye movement language model based on deep learning. The invention provides a system for analyzing, classifying and predicting eye movement tracks by using a deep learning language model. The system can be used as an analysis tool to provide an objective and continuous standard for early diagnosis and later treatment tracking of brain diseases such as neurodegenerative diseases, autism, mental diseases, cerebral concussion and the like; meanwhile, the invention can be widely applied to various cognitive researches such as natural language cognition, children cognition and lie detection.

Description

technical field [0001] The invention belongs to the technical field of eye movement track data processing, and in particular relates to a cognitive classification and prediction method and system based on eye movement track and deep learning. Background technique [0002] At present, Descartes said: "I think, therefore I am", and the cognitive function of the human brain is the basic dimension to measure people. The eyes are the windows of the soul. Studies have shown that among the information processed by the human brain, the image information collected by the eyes can reach more than 80%. From an evolutionary point of view, the evolution of the eyes has greatly promoted the development of the brain. Eye track (scanpath) is a strategy for biological image sampling of the external world. Under the pressure of evolution, this sampling strategy is efficient and spontaneous, which is the basis of the brain's cognition of the external world. [0003] When there is cognitive ...

AI Technical Summary

Problems solved by technology

[0014] The difficulty in solving the above problems and defects is as follows: 1) Since the mobile phone does not have an infrared camera of the eye tracker, the basic functions of the eye tracker must be completed on the mobile phone, and a deep learning method based on facial recognition must be used to determine the position of the eye gaze point. The use of this technical route requires a large amount of data for training; 2) Classification and prediction of the eye movement language converted from eye movement data, using the technical route of deep learning also requires a large amount of data for training

Images