A doctor-patient privacy matching method based on secure computation in a digital health platform

CN122117202APending Publication Date: 2026-05-29XIDIAN UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
XIDIAN UNIV
Filing Date
2026-02-12
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Patient privacy protection schemes in digital health platforms pose a risk of privacy breaches. Existing technologies struggle to protect input privacy, process privacy, and outcome privacy while ensuring matching accuracy and real-time performance.

Method used

By adopting a service platform architecture that does not collude between the two parties, and through cryptographic primitives such as arithmetic secret sharing, Boolean secret sharing, Boolean to arithmetic share conversion, secure comparison and secure equivalence judgment, the system can accurately match patient symptom vectors with doctor professional vectors, thus protecting patient privacy information from being leaked.

Benefits of technology

This method achieves accurate Top-k doctor index retrieval without disclosing patient symptom vectors, similarity ranking processes, or the identities of Top-k results. It effectively protects patient privacy, reduces computational and communication overhead, and is suitable for practical digital healthcare scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122117202A_ABST
    Figure CN122117202A_ABST
Patent Text Reader

Abstract

The application provides a doctor-patient privacy matching method based on secure computation in a digital health platform, which is applied to a doctor-patient privacy matching system composed of a patient terminal, a first service platform and a second service platform, and the method comprises the following steps: the patient terminal performs secret sharing on a symptom vector, generates symptom vector secret shares and respectively sends the symptom vector secret shares to the first service platform and the second service platform; the first service platform and the second service platform calculate the similarity secret shares of each doctor based on the symptom vector shares received by the first service platform and the second service platform respectively, utilize a secure multi-party computation protocol, subsequently cooperatively perform secure order calculation, obtain the ranking order value secret shares corresponding to each doctor, and then cooperatively perform secure order retrieval according to each target order value in a preset Top-k order set to obtain the doctor index secret shares corresponding to each ranking and send the doctor index secret shares to the patient terminal; and the patient terminal combines the doctor index secret shares to reconstruct a plaintext Top-k doctor index set.
Need to check novelty before this filing date? Find Prior Art