Attention analysis method based on human intelligence, edge computing device and medium
By combining semantic segmentation technology in eye tracking technology, identifying the target object that the user is gazes and generating feedback information, the problem that the prior art cannot identify the content of the user's gazes is solved, achieving higher recognition accuracy and real-time interactive experience.
CN119672416APending Publication Date: 2025-03-21KINGFAR INTERNATIONAL INC
0 Cites 0 Cited by
Patent Information
- Application Number
- CN202411732398.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-28
- Publication Date
- 2025-03-21
AI Technical Summary
Technical Problem
The existing eye tracking technology cannot identify the specific object content of the user's gaze, limiting its application in more in-depth research and analysis.
Method used
The attention analysis method based on human intelligence is adopted, and the user's eye movement data is collected through eye movement tracking devices, and the visual data collected by the camera is semantic segmentation, matching the eye movement data and segmented areas to identify the target object being stared at by the user, and feedback information is generated based on the object's category information.
Benefits of technology
It realizes automatic recognition of the object categories of users' attention, improves recognition accuracy, and enhances real-time interactive experience.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention discloses an attention analysis method based on human intelligence, an edge computing device and a medium. The method comprises the following steps: collecting eye movement data of a user through an eye movement tracking device, and collecting visual data of a visual field range of the user through a camera; semantic segmentation is carried out on the visual data to obtain a plurality of segmentation areas representing the positions of all the objects in the visual data and category information of all the objects; matching the plurality of segmented regions according to the position of the eye movement data in the visual data to obtain a target object watched by the user; and generating feedback information based on the category information of the target object and feeding back to the user. According to the embodiment of the invention, the method can achieve the automatic recognition of the types of objects watched by a user, improves the recognition accuracy, and enhances the real-time interaction experience.
Need to check novelty before this filing date? Find Prior Art