A privacy-preserving medical service recommendation method in an electronic medical system

A medical service and electronic medical technology, applied in the field of privacy protection medical service recommendation, can solve the problems of consuming large computing resources, affecting accuracy, inapplicability, etc., achieving the effect of accurate and reasonable recommendation results and improving efficiency

Active Publication Date: 2021-10-15
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the recent research on privacy-preserving recommender systems, privacy-preserving methods can be divided into three types, the first one is based on secure multi-party computation, which consumes a lot of computing resources in the process of protecting privacy; the second The second method is to use random numbers to perturb sensitive data to protect privacy, but adding perturbed data will affect the accuracy of recommendations to a certain extent; the third method is to use pseudonyms to protect the user's real ID so that get privacy protection
However, in summary, the above three privacy protection methods are not suitable for our medical service recommendation scenario.
[0005] To sum up, the existing recommendation system mechanism and privacy protection methods cannot meet the needs of our medical service recommendation scenario

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A privacy-preserving medical service recommendation method in an electronic medical system
  • A privacy-preserving medical service recommendation method in an electronic medical system
  • A privacy-preserving medical service recommendation method in an electronic medical system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] This embodiment elaborates in detail the system model diagram on which the privacy protection medical service recommendation method in the electronic medical system of the present invention relies, as shown in figure 1 shown.

[0067] From figure 1 It can be seen that when a patient user wants to apply for medical services, the user can send a medical service request to the server through smart devices such as mobile phones, tablets, and computers. Acceptable thresholds are sent to the server.

[0068] The server uses the safe similarity matching method proposed by the present invention to calculate the similarity between the user and each doctor according to the user's needs and the doctor's information, and then screens out similarity satisfaction according to the acceptable threshold provided by the user. A part of doctors with threshold conditions. Finally, for a part of doctors screened out, the server recommends the doctor with the highest reputation score to th...

Embodiment 2

[0070] Compared with traditional medical service recommendation methods such as the medical service recommendation method in the FSSR paper by Cheng Huang et al., the FSSR recommendation method only recommends doctors based on the factor of similarity. Only consider the factor of similarity to make recommendations, and users will be matched with doctors who meet their basic needs, but the quality of doctors' services is unpredictable. The recommendation method we propose recommends doctors based on the two factors of similarity and doctor reputation score. The server first screens out a batch of doctors that meet the user's needs based on similarity, and then selects the doctor with the highest reputation score among these doctors for recommendation. To the user, the higher the reputation score, the better the service quality of the doctor. In terms of algorithmic efficiency, such as figure 2 As shown, when the number of doctors is 500, the time used by the FSSR recommendati...

Embodiment 3

[0072] For the calculation of the true value of multiple user feedback data, this scheme uses the Modified Paillier encryption algorithm to process the user feedback rating data. Compared with the PPTD scheme proposed by Miao et al., which uses the ThresholdPaillier encryption algorithm to process user data, it improves Efficiency of User Feedback Data Aggregation and Calculation of Truth. Such as image 3 As shown, when the number of users is 500, the time used by the PPTD scheme to calculate the true value is 652.23s, while the time used by our PPMR scheme to calculate the true value is 14.59s. In contrast, our scheme improves the calculation of the true value s efficiency. Specifically, the privacy-preserving truth-value discovery technology is divided into two stages: weight update and truth-value update, such as Figure 4 and Figure 5 As shown, the time used by our PPMR scheme is lower than that of the PPTD scheme in the weight update phase and the truth value update ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a method for recommending privacy-protected medical services in an electronic medical system, and belongs to the technical fields of medical service recommendation and privacy protection. The recommendation method mainly recommends according to the similarity between the user's needs and the doctor's information and the doctor's reputation score. Specifically, it includes three parts: similarity calculation, doctor recommendation, and doctor reputation score calculation. Similarity calculation means that the server calculates the similarity according to the user's demand vector and the doctor's personal information vector; doctor recommendation means that the server recommends a doctor based on the two factors of the similarity between the user's demand and doctor's information and the similarity of the doctor; the doctor's reputation score calculation That is, the server processes the user's feedback score on the doctor and updates the doctor's reputation score. The invention can realize the calculation of the similarity degree and reputation score under the ciphertext, and realize the privacy protection of the user's personal information in the recommendation process.

Description

technical field [0001] The invention relates to a privacy protection medical service recommendation method in an electronic medical system, and belongs to the technical field of medical service recommendation and privacy protection. Background technique [0002] With the continuous development and progress of electronic medical systems and recommendation systems, online electronic medical service recommendations have become an indispensable part of daily life. According to the information of different users and doctors, the online medical recommendation server can find a suitable doctor for each patient user. Specifically, patient users submit their needs to the server, and the server matches the user's needs with the doctor's personal information. Privacy is paramount. [0003] Many existing studies have been working on the performance of doctor recommendation systems. Some recommendation systems use credibility and reputation scores as the basis for recommendation. Credi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G16H40/20G06F21/62
CPCG06F21/6245G16H40/20
Inventor 徐畅王家琛祝烈煌张川
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products