Multi-source information fusion method and system of surgical robot and storage medium
The principal components of the surgical robot's visual images, motion data, and force data are extracted through a three-layer principal component analysis network, which solves the problem of redundant data interference and improves the efficiency and accuracy of surgical status assessment.
CN120636746APending Publication Date: 2025-09-12XIEHE HOSPITAL ATTACHED TO TONGJI MEDICAL COLLEGE HUAZHONG SCI & TECH UNIV
0 Cites 0 Cited by
Patent Information
- Application Number
- CN202510635102.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-16
- Publication Date
- 2025-09-12
AI Technical Summary
Technical Problem
The existing technology lacks the interference elimination of redundant data during the surgical robot evaluation process, which affects the evaluation results and efficiency.
Method used
A three-layer principal component analysis network is used to extract principal component information from visual images, motion data, and force data, which are combined into multi-source information for evaluating surgical status. Convolutional networks and mutual supervision structures are used to improve the accuracy and synchronization of information extraction.
Benefits of technology
It eliminates the interference of redundant data during the status assessment process, improves the efficiency and accuracy of the assessment, and provides a more accurate surgical status assessment.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention relates to the technical field of surgical process evaluation, in particular to a multi-source information fusion method and system of a surgical robot and a storage medium, and the method comprises the following steps: carrying out the principal component information extraction of visual images, motion data and force sense data obtained in a surgical operation process through a three-layer principal component analysis network, correspondingly obtaining visual information representing the operation state in the visual image, motion information representing the operation state in the motion data and force sense information representing the operation state in the force sense data; visual information, motion information, and haptic information are combined into multi-source information for assessing surgical conditions. According to the method, principal component information extraction is carried out on the visual image, the motion data and the force sense data through the three-layer principal component analysis network, information highly related to the operation state is screened out from the original data, interference of redundant data is eliminated in the state evaluation process, and finally the efficiency and precision of state evaluation can be improved.
Need to check novelty before this filing date? Find Prior Art