A method, system and related device for detecting cognitive impairment
By acquiring and fusing the initial and supplementary features of the information to be detected in multiple modalities, the target fusion features are generated, and the problems of low efficiency and limited accuracy of cognitive impairment detection in the prior art are solved, and higher detection accuracy and information security are achieved.
CN118841139BActive Publication Date: 2025-03-28IFLYTEK CO LTD
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202411315276.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-20
- Publication Date
- 2025-03-28
- Estimated Expiration
- 2044-09-20
AI Technical Summary
Technical Problem
The existing cognitive impairment detection methods are inefficient and have limited accuracy, mainly due to the reliance on a single type of data for judgment.
Method used
By obtaining the information to be detected by multiple modal matching (such as painting data, expression audio data, video data and portrait data), the initial and supplementary features are extracted, and the target fusion features are generated by fusing these features, and the accurate detection results are finally obtained.
Benefits of technology
The accuracy and information security of cognitive impairment detection are improved, and by combining feature information from multiple modalities, a richer feature expression is generated, thereby improving the accuracy of the detection results.
✦ Generated by Eureka AI based on patent content.
Abstract
The present application discloses a method, system and related device for detecting cognitive impairment, which is applied to a detection unit and includes: obtaining information to be detected that matches multiple modalities and is sent by a target organization, and determining the initial features corresponding to the information to be detected; for each modality, extracting supplementary features that match the current modality from the initial features corresponding to other modalities; based on the supplementary features and the initial features corresponding to each modality, obtaining target fusion features; based on the target fusion features, obtaining detection results; wherein the detection results include target detection categories and target scores that match at least one evaluation scale. In the above manner, the present application can improve the accuracy of cognitive impairment detection and improve information security.
Need to check novelty before this filing date? Find Prior Art