Internet-based medical user privacy protection system and method

Abstract

The invention discloses a medical user privacy protection system based on the Internet, and the system comprises a data collection end which collects data information through a medical loT device, encrypts and transmits the data information to an edge node, carries out the desensitization of data, and adds a privacy grading label; the privacy protection layer comprises an anonymization engine and a user terminal, and the user terminal starts the anonymization engine through biological recognition and the dynamic access token; and the secure storage layer forms an encrypted cloud database through blockchain storage and distributed storage, and accesses the encrypted cloud database through the identified and authenticated anonymization engine. The medical user privacy protection system based on the Internet can effectively protect the privacy of the medical user.

Description

Technical Field

[0001] The present invention relates to the field of medical privacy protection, and more specifically, to an Internet-based medical user privacy protection system and method. Background Art

[0002] With the rapid development of Internet technology, Internet medical services have gradually become popular, such as online health consultations, online follow-up consultations, and electronic medical record sharing. However, these services involve a large amount of sensitive personal information, such as patient history, diagnostic reports, etc., and data security and privacy protection have become key challenges.

[0003] Existing privacy protection technologies have limitations in terms of data security and performance, while emerging technologies such as blockchain and differential privacy technologies provide new ideas for solving these problems. Therefore, an Internet-based medical user privacy protection system and method are needed. Summary of the Invention

[0004] The purpose of the present invention is to provide an Internet-based medical user privacy protection system and method, and the Internet-based medical user privacy protection system can effectively protect the privacy of medical users.

[0005] To achieve the above purpose, the present invention provides an Internet-based medical user privacy protection system, which includes:

[0006] A data collection end, which collects user data information through medical IoT devices, encrypts and transmits it to an edge node, and adds a privacy classification label after data desensitization processing;

[0007] A privacy protection layer, including an anonymization engine and a user terminal, and the user terminal starts the anonymization engine through biometric identification and a dynamic access token;

[0008] A secure storage layer, which forms an encrypted cloud database through blockchain evidence storage and distributed storage, and accesses the encrypted cloud database through the anonymization engine after identification and authentication.

[0009] Preferably, it further includes an authorized access layer, and the authorized access layer is used for doctors or institutions to perform permission authentication and zero-knowledge proof and then conduct data usage auditing.

[0010] Preferably, it further includes an emergency channel, and the emergency channel is used to inject data through differential privacy noise in the way of aggregating public health events through federated learning.

[0011] Preferably, the desensitization processing is two-channel desensitization, including conventional medical data desensitization and gene data desensitization.

[0012] Preferably, the biometric identification includes fingerprint, voiceprint, and retina recognition.

[0013] The present invention also provides an Internet-based medical user privacy protection method, which uses the protection system described above and includes: collecting user data information through IoT devices, encrypting and transmitting it to an edge node, adding privacy classification labels after data desensitization processing, and then performing encrypted storage; the user accesses the encrypted data through biometric identification, and the doctor or institution conducts permission authentication and zero-knowledge proof before performing data usage auditing.

[0014] Preferably, when the emergency channel is activated, the spatio-temporal distribution of fever patients is automatically aggregated, and differential privacy noise with ε = 0.4 to 0.6 is added.

[0015] According to the above technical solution, the Internet-based medical user privacy protection system provided by the present invention can effectively protect the privacy of medical users.

[0016] Other features and advantages of the present invention will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification, and are used to explain the present invention together with the following specific implementation, but do not constitute a limitation to the present invention. In the drawings:

[0018] Figure 1 is a system architecture diagram of an Internet-based medical user privacy protection system;

[0019] Figure 2 is an authorized access layer architecture diagram;

[0020] Figure 3 is an emergency channel architecture diagram. DETAILED DESCRIPTION OF THE INVENTION

[0021] The following will describe in detail the specific implementation of the present invention with reference to the drawings. It should be understood that the specific implementation described herein is only for explaining and understanding the present invention, and is not used to limit the present invention.

[0022] In the present invention, unless otherwise stated, the orientation words contained in terms such as "up and down, left and right, front and back, inside and outside" only represent the orientation of the term in its normal use state, or the common name understood by those skilled in the art, and should not be regarded as a limitation to the term.

[0023] Refer to Figure 1-2 the Internet-based medical user privacy protection system shown, which includes:

[0024] A data acquisition end, which collects user data information through medical IoT devices, encrypts and transmits it to an edge node, and adds privacy classification labels after data desensitization processing;

[0025] A privacy protection layer, including an anonymization engine and a user terminal, where the user terminal activates the anonymization engine through biometric identification and a dynamic access token;

[0026] A secure storage layer forms an encrypted cloud database through blockchain evidence storage and distributed storage, and accesses the encrypted cloud database through the anonymization engine after identification and authentication.

[0027] Through the implementation of the above technical solutions, the Internet-based medical user privacy protection system effectively protects the privacy of medical users through data desensitization, encrypted transmission, access control, etc.

[0028] For example: the ID number or bank card number is encrypted by AES-256 and desensitized by hashing; the diagnosis record is processed by retaining ICD and deleting free text; random noise of ±4-6% is added to the physiological indicators.

[0029] In this embodiment, it further includes an authorized access layer, which is used for doctors or institutions to perform permission authentication and zero-knowledge proof and then conduct data usage auditing. Through such a setting, doctors or institutions can only access and conduct data usage auditing when authorized.

[0030] In this embodiment, it further includes an emergency channel, which is used to inject data through differential privacy noise in the way of aggregating public health events through federated learning. Through the horizontal federation of local training models in each hospital, Paillier homomorphic encryption is adopted, and for the vertical federation of cross-institutional feature alignment, the PSI protocol is used to prevent data leakage.

[0031] In this embodiment, the desensitization process is dual-channel desensitization, including conventional medical data desensitization and gene data desensitization. Conventional medical data: K-anonymization + L-diversification, gene data: using a gene fuzzification algorithm (GRCh38 reference genome mapping).

[0032] In this embodiment, in order to further provide a biometric identification method, the biometric identification includes fingerprint, voiceprint, and retina recognition.

[0033] The present invention also provides an Internet-based medical user privacy protection method, which uses the above protection system and includes: collecting user data information through IoT devices, encrypting and transmitting it to an edge node, adding a privacy classification label after data desensitization processing, and then performing encrypted storage; users access encrypted data through biometric identification, and doctors or institutions perform permission authentication and zero-knowledge proof and then conduct data usage auditing.

[0034] In this embodiment, when the emergency channel is activated, the spatio-temporal distribution of febrile patients is automatically aggregated, and differential privacy noise with ε = 0.4 to 0.6 is added.

[0035] The preferred embodiments of the present invention have been described in detail above in conjunction with the accompanying drawings. However, the present invention is not limited to the specific details in the above embodiments. Within the scope of the technical concept of the present invention, various simple modifications can be made to the technical solutions of the present invention, and these simple modifications all fall within the protection scope of the present invention.

[0036] In addition, it should be noted that, in the various specific technical features described in the above specific embodiments, they can be combined in any appropriate manner without conflict. To avoid unnecessary repetition, the present invention will not separately describe various possible combination methods.

[0037] Furthermore, any combination can be made between different embodiments of the present invention, as long as it does not violate the idea of the present invention, and it should also be regarded as the content disclosed by the present invention.

Claims

1. An Internet-based medical user privacy protection system, characterized in that, The medical user privacy protection system includes: A data collection end, which collects user data information through medical IoT devices, encrypts and transmits it to an edge node, adds a privacy classification label after data desensitization processing; A privacy protection layer, including an anonymization engine and a user terminal, and the user terminal starts the anonymization engine through biometric identification and a dynamic access token; A secure storage layer, which forms an encrypted cloud database through blockchain evidence storage and distributed storage, and accesses the encrypted cloud database through the anonymization engine after identification and authentication; 2. The Internet-based medical user privacy protection system according to claim 1, characterized in that It further includes an authorized access layer, which is used for doctors or institutions to conduct data usage audits after permission authentication and zero-knowledge proof; 3. The internet-based medical user privacy protection system according to claim 1, wherein It further includes an emergency channel, which is used to inject data through differential privacy noise in the way of federated learning aggregation for public health events; 4. The Internet-based medical user privacy protection system according to claim 1, characterized in that The desensitization processing is dual-channel desensitization, including conventional medical data desensitization and gene data desensitization; 5. The Internet-based medical user privacy protection system according to claim 1, wherein The biometric identification includes fingerprint, voiceprint, and retina identification; 6. A method for protecting the privacy of medical users based on the Internet, characterized in that, The medical user privacy protection method uses the protection system described in any one of claims 1-5, and includes: collecting user data information through IoT devices, encrypting and transmitting it to an edge node, adding a privacy classification label after data desensitization processing, and then performing encrypted storage; the user accesses the encrypted data through biometric identification, and doctors or institutions conduct data usage audits after permission authentication and zero-knowledge proof; 7. The method for protecting the privacy of medical users based on the Internet according to claim 6, wherein, When the emergency channel is started, it automatically aggregates the spatio-temporal distribution of fever patients and adds differential privacy noise with ε = 0.4-0.6.

Images