Medical data infringement detection method and system based on image mapping

Abstract

The invention discloses a medical data infringement detection method and system based on image mapping, and belongs to the field of data security and privacy protection. A trusted execution environment processes medical data of a reporter and medical data of a reported person based on a normal range of a detection index; obtaining a data image of a reporter and a data image of a reported person; the trusted execution environment performs feature extraction on the data image of the reporter and the data image of the reported person to obtain feature sets of the two, performs similarity calculation based on the feature sets of the two to obtain a similarity score, and sends the similarity score to a trusted third party; and the credible third party judges whether infringement behaviors exist between the medical data of the reported person and the medical data of the reporter or not according to comparison of the similarity score and a set threshold value. According to the method, the characteristics which have higher robustness and can better represent different numerical data can be extracted so as to cope with the challenge that the data are modified, and the method has higher accuracy when similarity comparison is carried out.

Description

Technical Field

[0001] The present invention belongs to the field of data security and privacy protection, and in particular relates to a medical data infringement detection method and system based on image mapping. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] In today's digital age, the medical field has developed rapidly, generating a large amount of medical data with potential value. More and more users are willing to sell their medical data for economic benefits or to support medical research. In order to ensure the security and ownership of data transactions, users use blockchain technology to conduct transactions. Blockchain technology can effectively prevent data tampering and forgery during the transaction process through its decentralized and tamper-proof characteristics. Each transaction record will be stored in an encrypted form on the blockchain to ensure the transparency and credibility of the transaction.

[0004] However, in the process of data trading, since the physiological indicators of medical data may show high similarity between different individuals, traditional numerical data similarity detection methods (such as those based on statistical features, time dynamic regularization, etc.) are difficult to effectively distinguish these data, thereby increasing the risk of data infringement. In addition, when the data is partially modified or some unimportant information is deleted, conventional detection methods may not be able to accurately identify the true similarity of the data, providing opportunities for hidden data infringement. These problems lead to frequent unauthorized use and privacy leaks in data transactions. Summary of the invention

[0005] In order to overcome the deficiencies of the above-mentioned prior art, the present invention provides a medical data infringement detection method and system based on image mapping, which maps medical numerical data into images based on whether they are within the normal range in an SGX trusted execution environment, and performs infringement detection by judging the similarity of the images.

[0006] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0007] In a first aspect, the present invention provides a medical data infringement detection method based on image mapping, comprising:

[0008] The trusted third party obtains the medical data and decryption key ciphertext of the reporter and the reported person and signs them, obtains the normal range of each test indicator in the reporter's medical data, and sends the signed medical data and decryption key ciphertext of the reporter and the reported person, and the normal range of the test indicator to the trusted execution environment;

[0009] The trusted execution environment verifies the received data, and after successful verification, decrypts the medical data of the reporter and the person being reported based on the ciphertext to obtain the medical data of the reporter and the person being reported.

[0010] The trusted execution environment processes the medical data of the reporter and the medical data of the person being reported based on the normal range of the detection index to obtain the data image of the reporter and the data image of the person being reported;

[0011] The trusted execution environment extracts features from the data image of the reporter and the data image of the person being reported to obtain feature sets of the two, performs similarity calculation based on the feature sets of the two, obtains a similarity score and sends it to a trusted third party;

[0012] The trusted third party determines whether there is any infringement between the medical data of the person being reported and the medical data of the reporter based on a comparison of the similarity score with a set threshold.

[0013] Furthermore, the trusted execution environment verifies the received data by: verifying whether the data source is reliable based on the public key of the trusted third party, and verifying whether the data content is tampered with based on the hash value of the data.

[0014] Furthermore, the trusted execution environment processes the medical data of the reporter and the reported person based on the normal range of the detection indicator, specifically including:

[0015] Determine in turn whether the specific values ​​of each test indicator in the medical data of the reporter and the reported person are within the normal range of the test indicator;

[0016] If the detection value of a certain detection indicator is within the normal range, it will be mapped to a specific color system;

[0017] If the detection value of a certain detection indicator exceeds the normal range, it will be mapped to another contrasting color system;

[0018] Through the above mapping method, the medical data of the reporter and the medical data of the person being reported are converted into the data image of the reporter and the data image of the person being reported that reflect the data characteristics.

[0019] Furthermore, the trusted execution environment performs feature extraction on the data image of the reporter and the data image of the reported person to obtain feature sets of the two, specifically including: using a scale-invariant feature transformation algorithm to perform feature extraction on the data image of the reporter and the data image of the reported person to generate a robust feature set of the reporter's data and a robust feature set of the reported person's data.

[0020] Further, similarity calculation is performed based on the feature sets of the two, specifically including:

[0021] The robust feature set of the informant's data and the feature points in the robust feature set of the reported person's data are matched one by one through a brute force search method, and the best match between all feature points is found;

[0022] The distances between all matching points are used to calculate the average matching distance, which is then converted into a similarity score.

[0023] Furthermore, the trusted third party determines whether there is any infringement between the medical data of the person being reported and the medical data of the reporter based on the comparison of the similarity score with the set threshold, specifically including:

[0024] When the similarity score is higher than the set threshold, there is infringement. The trusted third party finds the registered user through the smart contract, determines the real owner of the data based on the registration timestamp, and punishes the infringer.

[0025] When the similarity score is below the set threshold, there is no infringement.

[0026] Furthermore, the infringement detection results are stored in the blockchain through smart contracts.

[0027] In a second aspect, the present invention provides a medical data infringement detection system based on image mapping, comprising:

[0028] The infringement reporting module is configured as follows: a trusted third party obtains and signs the medical data and decryption key ciphertext of the reporter and the reported person, obtains the normal range of each detection indicator in the reporter's medical data, and sends the signed medical data and decryption key ciphertext of the reporter and the reported person, and the normal range of the detection indicator to the trusted execution environment;

[0029] The data verification module is configured to: the trusted execution environment verifies the received data, and after successful verification, decrypts the medical data of the reporter and the reported person based on the ciphertext to obtain the medical data of the reporter and the reported person.

[0030] The data processing module is configured to: the trusted execution environment processes the medical data of the reporter and the medical data of the person being reported based on the normal range of the detection index to obtain the data image of the reporter and the data image of the person being reported;

[0031] The similarity calculation module is configured to: extract features from the data image of the reporter and the data image of the person being reported by the trusted execution environment to obtain feature sets of the two, calculate similarity based on the feature sets of the two, obtain a similarity score and send it to a trusted third party;

[0032] The infringement determination module is configured to: a trusted third party determines whether there is infringement between the medical data of the person being reported and the medical data of the reporter based on a comparison of the similarity score with a set threshold.

[0033] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in a medical data infringement detection method based on image mapping as described in the first aspect.

[0034] In a fourth aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in a medical data infringement detection method based on image mapping as described in the first aspect are implemented.

[0035] One or more of the above technical solutions have the following beneficial effects:

[0036] In the SGX trusted execution environment, the present invention maps the data into different specified color systems according to whether each medical numerical data is within the normal value range, and in the same color system, the numerical difference is intuitively reflected by the change of color, thereby generating an image reflecting the data characteristics, and judging whether there is infringement by performing similarity detection on the robustness characteristics of the image. Compared with the method of directly extracting features from numerical data, it can extract features that are more robust and more representative of different numerical data to cope with the challenge of data modification; compared with the method of directly mapping data into images, it has higher accuracy when performing similarity comparison, and can more accurately judge the similarity between two copies of data. It is suitable for scenarios of medical data transactions and infringement judgment, and can realize the authentication and supervision of the identity of the data owner during the transaction process, and provide efficient transaction data infringement detection. While ensuring that users have control over the data, the present invention effectively prevents data buyers and hospitals from privately selling the data owner's data, ensures the security and privacy of transaction data, ensures the legality of the data source, and prevents data from being abused.

[0037] The present invention constructs a blockchain transaction platform, which generates ciphertext data with identity authentication and signs the ciphertext data and examination data when the patient seeks medical treatment, thereby linking the examination data with the ciphertext data, thereby preventing hospitals with a large amount of medical data from pretending to be patients and selling the data privately; SGX is used to verify the correctness of the patient's identity authentication data and key in plain text in a trusted execution environment, which neither leaks any relevant information of the plain text nor solves the problem of being unable to clearly authenticate the owner of the data; the key information is encrypted by SGX and stored by a trusted third party, thereby preventing a curious third party from viewing the user's key and then investigating the user's data, thereby ensuring the privacy of the data and solving the problem of limited SGX memory. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0039] Figure 1 is a flow chart of a medical data infringement detection method based on image mapping according to an embodiment of the present invention;

[0040] Figure 2 is an interactive diagram of a medical data infringement detection method based on image mapping according to an embodiment of the present invention;

[0041] Figure 3 It is a schematic diagram of a blockchain transaction platform according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0043] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0044] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0045] Terminology explanation:

[0046] SGX, software guard extensions, is an extension of the Intel instruction set architecture. It provides an encrypted trusted execution area in memory, with hardware security as a mandatory guarantee. It does not rely on the security status of firmware and software. The CPU protects data and privacy from malicious theft.

[0047] IPFS, the interplanetary file system, is a global, peer-to-peer distributed file transfer system. Its goal is to supplement the current Internet's hypertext transfer protocol and connect all computing devices with the same file system. The principle is to use content-based addresses instead of domain-based addresses, that is, users are not looking for a certain address but content stored somewhere. There is no need to verify the identity of the sender, but only the hash of the content, which can make data transmission faster, safer and more robust.

[0048] Embodiment 1

[0049] like Figure 1 As shown, this embodiment discloses a medical data infringement detection method based on image mapping, which includes the following steps:

[0050] S1: The trusted third party obtains and signs the medical data and decryption key ciphertext of the reporter and the reported person, obtains the normal range of each test indicator in the reporter's medical data, and sends the signed medical data and decryption key ciphertext of the reporter and the reported person, and the normal range of the test indicator to the trusted execution environment;

[0051] In this embodiment, the medical data infringement detection method based on image mapping is based on the use of blockchain technology for data transactions, and the publication of data descriptions, data ownership registration and data transactions are realized based on blockchain; through the on-chain and off-chain collaboration, the user's identity and decryption key are verified in the trusted execution environment SGX, and credentials are generated and key ciphertexts are stored with the help of a third party; infringement detection is performed in the trusted execution environment SGX.

[0052] Ciphertext refers to the ciphertext stored by a trusted third party. After the trusted execution environment encrypts the decoding key and other information, it will be sent to the trusted third party for storage, that is, the ciphertext.

[0053] The data owner registers the feature in the blockchain based on the hash value hash (FE) and the data description ID DS Preliminarily determine whether your data has been infringed. If so, provide your and the person being reported’s address and data identifier (Add i , ID DSi ) is sent to a trusted third party, where i = I represents the information of the reporter, i = H represents the information of the person being reported, Add i Refers to the ID of the data owner, and this definition also applies to the following content.

[0054] The trusted third party Download data from IPFS and get Refers to the two medical data ciphertexts of the reporter and the reported person, which are encrypted by the hospital using different symmetric keys K h encryption; Refers to the address where the reporter and the reported person store ciphertext data; use their own private key PK HD right ID DSi 、Add i , Signature, Generate and will The data are sent to SGX for infringement detection, where TA is the normal range of each detection indicator in the whistleblower’s medical data.

[0055] S2: The trusted execution environment verifies the received data. After successful verification, the medical data of the reporter and the reported person are decrypted based on the ciphertext to obtain the medical data of the reporter and the reported person.

[0056] In this embodiment, the trusted execution environment verifies the received data including: verifying whether the data source is reliable based on the public key of the trusted third party, and verifying whether the data content is tampered with based on the hash value of the data.

[0057] SGX first uses the public key PK of a trusted third party HD Verify the sign HD The correctness of the data to ensure the reliability of the data source; use your own private key SK SGX Decryption get calculate Hash value And judge with Are they equal? ​​If they are equal, it indicates that the data content has not been tampered with and the ciphertext is indeed the ciphertext of the verification decryption key.

[0058] S3: The trusted execution environment processes the medical data of the reporter and the reported person based on the normal range of the detection indicator to obtain the data image of the reporter and the data image of the reported person;

[0059] In this embodiment, the medical data of the reporter and the reported person are processed, specifically including:

[0060] Determine in turn whether the specific values ​​of each test indicator in the medical data of the reporter and the reported person are within the normal range of the test indicator;

[0061] If the detection value of a certain detection indicator is within the normal range, it will be mapped to a specific color system;

[0062] If the detection value of a certain detection indicator exceeds the normal range, it will be mapped to another contrasting color system;

[0063] Through the above mapping method, the medical data of the reporter and the medical data of the person being reported are converted into the data image of the reporter and the data image of the person being reported that reflect the data characteristics.

[0064] Specifically, SGX uses Decryption get SGX According to Data i The specific values ​​of each test indicator in the TA are determined to determine whether they are within the normal range defined by TA, so as to classify the data; if a test value is within the normal range, it is mapped to a specific color system; if the test value exceeds the normal range, it is mapped to another contrasting color system; this process is performed on the Data in turn. i To further reflect the differences in data, each test item corresponds to an independent color system, and different item data are mapped to different color groups. Even in the same color system, subtle changes in specific test values ​​will be reflected through color brightness. i The data in is converted into an image image that reflects the characteristics of the data i .

[0065] S4: The trusted execution environment extracts features from the data image of the reporter and the data image of the person being reported to obtain feature sets of the two, performs similarity calculation based on the feature sets of the two, obtains a similarity score, and sends it to a trusted third party;

[0066] In this embodiment, the feature sets of the two are obtained, specifically including: using the scale-invariant feature transform (SIFT) algorithm to extract features from the data image of the reporter and the data image of the reported person, and generating a robust feature set of the reporter's data and a robust feature set of the reported person's data.

[0067] The similarity calculation is performed based on the feature sets of the two, specifically including: matching the feature points in the robust feature set of the reporter's data and the robust feature set of the reported person's data one by one through a brute force search method, and finding the best match between all feature points; calculating the average value of the matching distance through the distance between all matching points, and then converting it into a similarity score.

[0068] Specifically, SGX has a I and image HThe two images are feature extracted using the SIFT algorithm to identify the key points in each image and their corresponding local features, generating a robust feature set FE that can represent the core structure and information of the image. i , and for FE i Generate hash value hash(FE i ). FE is searched by brute force method I and FE H The feature points in the two feature sets are matched one by one, and the best match between all feature points in the two images is found; the average value of the matching distance is calculated through the distance between these matching points (best match), and then converted into a similarity score Simil; SGX converts (ID DSI , ID DSH , Simil, hash FEI , hash FEH ,) is returned to the trusted third party.

[0069] S5: The trusted third party determines whether there is any infringement between the medical data of the person being reported and the medical data of the reporter based on the comparison of the similarity score with the set threshold.

[0070] In this embodiment, the trusted third party determines whether there is any infringement between the medical data of the person being reported and the medical data of the reporter based on the comparison of the similarity score with the set threshold, specifically including: when the similarity score is higher than the set threshold, there is infringement, the trusted third party finds the registered user through the smart contract, determines the true owner of the data based on the registration timestamp, and punishes the infringer; when the similarity score is lower than the set threshold, there is no infringement.

[0071] Specifically, the trusted third party determines the similarity of the data based on whether the Simil is lower than the set threshold, thereby determining whether there is infringement between the two pieces of data; when it is higher than the set threshold, there is infringement, and the trusted third party registers the data ownership registry based on the smart contract. Find a registered user, or Add i Find the registered user and determine the real owner of the data based on the registration timestamp, and add the infringer H Finally, through the smart contract Stored in the blockchain; if there is no infringement, The information will be stored in the blockchain, and part of the whistleblower’s deposit will be deducted as the detection fee.

[0072] In this embodiment, medical data is traded on the blockchain trading platform. The construction of the blockchain trading platform is as follows:

[0073] 1. Hospital

[0074] 1. Hospital identity authentication: The hospital applies for qualification review from a trusted third party (such as a national or local health department); after the trusted third party successfully reviews the hospital, it creates an account for the hospital identity in the blockchain and obtains the hospital address Add h ; Add h , review status and other information are uploaded to the blockchain; the hospital generates its own public key PK h and private key SK h , by calling the smart contract to Add h and PK h The above realizes off-chain qualification review and on-chain identity registration.

[0075] 2. Deployment algorithm: Deploy symmetric encryption and signature algorithms in hospital inspection equipment to generate secret information that only the patient (data owner) knows and signs, and the hospital cannot modify it. D Add with hospital address h Stored in the blockchain, the smart contract deploys the two algorithms into the trusted execution environment SGX.

[0076] 2. Data Owner (Patient)

[0077] 1. Generate the patient's identity authentication ciphertext: When the patient is examined, enter the encryption key PK p and plaintext data M for identity authentication; check device encryption M and generate ciphertext data for identity authentication The device uses its own private key SK D Right D p Signature, Generate

[0078] 2. Get data: When the data owner (patient) requests his or her medical data, the hospital will HD ,sign infor , C HK , S D , D p , PK, S h} is sent to the data owner. HD The symmetric key K h Encrypt the ciphertext of medical data Data, C HK The public key PK of the data owner is used u Encrypted data details infor and K h The ciphertext, sign inforis the result of the ring signature of infor, PK is the set of all hospital public keys in the ring signature, S h It is SK used in hospitals h Signature of the relevant content. After the data owner verifies the correctness of the transmitted content, C HD Store in IPFS and return the storage address Add D . Add D It is the storage address of the ciphertext data in IPFS. After the data owner receives the ciphertext data from the hospital, it will be verified. After successful verification, the ciphertext data will be stored, and this address is the storage address of the ciphertext data.

[0079] 3. Publish data description: The data owner publishes the data description in the smart contract and obtains the data description identifier ID DS , that is, publish the data information to be sold in the smart contract. And deposit a certain amount of security deposit into the smart contract. The security deposit is used in the subsequent process. When it is determined that there is no infringement, part of the security deposit of the reporter (that is, the data owner) is deducted as a reward for the infringement detection process.

[0080] The data owner and the trusted third party perform remote authentication with the Enclave in SGX and establish a secure channel.

[0081] 4. Apply for verification information: The data owner uses the SGX public key PK SGX Encrypted TX, TX = {K h , C HD ,infor,PK,sign infor , ID DS , S D , PK p , M, D p},get And calculate its hash hash (C tra ). Through the secure channel, {C tra , hash(C tra )} is sent to SGX for key verification and credential generation.

[0082] 5. Verify key and authentication ciphertext: SGX computes C tra The hash value hash(C tra ′), and hash(C tra ) to verify the integrity of the data; use PK to verify the signature sign infor The correctness of the data source is determined by the reliability of the data source; use your own private key SK SGX Decryption C tra , using the obtained K hDecrypted C HD , get the relevant parameters and Data′; calculate Data′ and C HD The hash values ​​hash(Data′), hash(C HD ), respectively determine whether the plaintext hash value and ciphertext hash value in infor are the same, to verify the integrity of the data, the correctness of the decryption key, and the association between Data and infor; SGX uses the public key PK of the stored device D Successfully verified signature S D After the correctness is confirmed, the identity authentication key PK sent by the data owner is used p Right D p Decrypt and get Calculate and compare hsah(M) and hsah(M′) to verify the identity of the data owner.

[0083] 6. Generate credentials and store keys: After successful verification, SGX generates a certificate for the data owner, including Add o 、ID DS , PK's credential; use your own private key SK SGX Sign the cred and generate Sign SGXP and cred are returned to the data owner; SGX uses its own private key SK SGX Encryption K h , hash(C HD ), ID DS , Add o , get Enc SGX =Enc SGX (K h ||hash(C HD )||ID DS ||Add o ), and calculate its hash value hash(Enc SGX ); through the secure channel {Enc SGX 、ID DS 、hash(Enc SGX )} is sent to a trusted third party, which will store it. SGX Represents ciphertext, which is the result of SGX encrypting data with its own private key, and can be called the ciphertext of decryption key information.

[0084] 7. Register data ownership: The data owner sends {Add D , hash(C HD ), PK, sign SGXP ,cred,hash(FE),Addo , ID DS}, to register data ownership, where FE is the feature of medical numerical data (the specific generation process is described in S4); smart contract verification sign SGXP Confirm the user's identity and key storage; check whether the PK′ in cred is consistent with the PK, and whether the public key in PK corresponds to the registered hospital; after successful verification, register the data for the data owner.

[0085] 3. Data Buyers

[0086] 1. Transaction data: When a data buyer purchases data from a data owner through a smart contract, the data owner o , C bh ,cred,Add D , ID DS , hash(C bh ), sign SGXP} is sent to the smart contract, where C bh The public key PK of the data buyer is used b Encryption K h The ciphertext, r o The private key SK of the data owner is used o C bh Signature, ID DS Is the corresponding data description; smart contract verification sign SGXP and Add o and ID DS After the content is consistent with the corresponding content in cred, the transaction is carried out with the data buyer.

[0087] Compared with the prior art that does not use blockchain, the present invention realizes the release of on-chain data description, data ownership registration, hospital qualification inspection, data transaction, data ownership traceability and storage of transaction records based on blockchain, and realizes the verification and storage of keys, user identity verification and data infringement detection by the on-chain and off-chain collaboration. The infringement results are stored on the chain, making the whole process open and transparent, and can correctly judge the infringement, and it has non-repudiation and traceability, protecting the rights and interests of data owners and preventing data abuse. Compared with the prior art that uses blockchain, the present invention maps medical numerical data into images according to whether they are in the normal range in the SGX trusted execution environment, and performs infringement detection by judging the similarity of the images.

[0088] The present invention discloses a medical data infringement detection method and system based on image mapping, which supports the authentication of user identities, verification and storage of decryption keys outside the chain; realizes the release of data descriptions, data ownership registration and data transactions based on blockchain; verifies the user's identity and decryption key in an SGX-based trusted execution environment through on-chain and off-chain collaboration, generates credentials and uses a third party to store key ciphertext; maps medical numerical data into images based on whether they are in a normal range in an SGX-based trusted execution environment, and performs infringement detection through image similarity judgment. The present invention is suitable for scenarios of medical data transactions and infringement judgments, can realize the authentication and supervision of the identity of data sellers during the transaction process, and provide efficient transaction data infringement detection. While ensuring that users have control over the data, the solution effectively prevents data buyers and hospitals from selling patient data privately, ensures the security and privacy of transaction data, ensures the legality of data sources, and prevents data from being abused.

[0089] Embodiment 2

[0090] This embodiment provides a medical data infringement detection system based on image mapping, including:

[0091] The infringement reporting module is configured as follows: a trusted third party obtains and signs the medical data and decryption key ciphertext of the reporter and the reported person, obtains the normal range of each detection indicator in the reporter's medical data, and sends the signed medical data and decryption key ciphertext of the reporter and the reported person, and the normal range of the detection indicator to the trusted execution environment;

[0092] The data verification module is configured to: the trusted execution environment verifies the received data, and after successful verification, decrypts the medical data of the reporter and the reported person based on the ciphertext to obtain the medical data of the reporter and the reported person.

[0093] The data processing module is configured to: the trusted execution environment processes the medical data of the reporter and the medical data of the person being reported based on the normal range of the detection index to obtain the data image of the reporter and the data image of the person being reported;

[0094] The similarity calculation module is configured to: extract features from the data image of the reporter and the data image of the person being reported by the trusted execution environment to obtain feature sets of the two, calculate similarity based on the feature sets of the two, obtain a similarity score and send it to a trusted third party;

[0095] The infringement determination module is configured to: a trusted third party determines whether there is infringement between the medical data of the person being reported and the medical data of the reporter based on a comparison of the similarity score with a set threshold.

[0096] Embodiment 3

[0097] The purpose of this embodiment is to provide a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of embodiment 1 when executing the program.

[0098] Embodiment 3

[0099] The purpose of this embodiment is to provide a computer-readable storage medium, a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps of the method of embodiment 1 are performed.

[0100] The steps involved in the apparatus of the above embodiments 3 and 4 correspond to the method embodiment 1, and the specific implementation method can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method of the present invention.

[0101] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0102] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0103] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A medical data infringement detection method based on image mapping, characterized in that: include: The trusted third party obtains the medical data and decryption key ciphertext of the reporter and the reported person and signs them, obtains the normal range of each test indicator in the reporter's medical data, and sends the signed medical data and decryption key ciphertext of the reporter and the reported person, and the normal range of the test indicator to the trusted execution environment; The trusted execution environment verifies the received data, and after successful verification, decrypts the medical data of the reporter and the reported person based on the ciphertext to obtain the medical data of the reporter and the reported person; The trusted execution environment processes the medical data of the reporter and the medical data of the person being reported based on the normal range of the detection index to obtain the data image of the reporter and the data image of the person being reported; The trusted execution environment extracts features from the data image of the reporter and the data image of the person being reported to obtain feature sets of the two, performs similarity calculation based on the feature sets of the two, obtains a similarity score and sends it to a trusted third party; The trusted third party determines whether there is any infringement between the medical data of the person being reported and the medical data of the reporter based on a comparison of the similarity score with a set threshold.

2. A medical data infringement detection method based on image mapping as claimed in claim 1, characterized in that: The trusted execution environment verifies the received data by: verifying whether the data source is reliable based on the public key of the trusted third party, and verifying whether the data content is tampered with based on the hash value of the data.

3. The medical data infringement detection method based on image mapping as claimed in claim 1, characterized in that: The trusted execution environment processes the medical data of the reporter and the medical data of the person being reported based on the normal range of the detection indicator, specifically including: Determine in turn whether the specific values ​​of each test indicator in the medical data of the reporter and the reported person are within the normal range of the test indicator; If the detection value of a certain detection indicator is within the normal range, it will be mapped to a specific color system; If the detection value of a certain detection indicator exceeds the normal range, it will be mapped to another contrasting color system; Through the above mapping method, the medical data of the reporter and the medical data of the person being reported are converted into the data image of the reporter and the data image of the person being reported that reflect the data characteristics.

4. The medical data infringement detection method based on image mapping as claimed in claim 1, characterized in that: The trusted execution environment performs feature extraction on the data image of the reporter and the data image of the reported person to obtain feature sets of the two, specifically including: using a scale-invariant feature transformation algorithm to extract features from the data image of the reporter and the data image of the reported person to generate a robust feature set of the reporter's data and a robust feature set of the reported person's data.

5. A medical data infringement detection method based on image mapping as claimed in claim 4, characterized in that: The similarity calculation is performed based on the feature sets of the two, specifically including: The robust feature set of the informant's data and the robust feature set of the reported person's data are matched one by one through a brute force search method, and the best match between all feature points is found; The distances between all matching points are used to calculate the average matching distance, which is then converted into a similarity score.

6. The medical data infringement detection method based on image mapping as claimed in claim 1, characterized in that: The trusted third party determines whether there is any infringement between the medical data of the person being reported and the medical data of the reporter based on the comparison of the similarity score with the set threshold, including: When the similarity score is higher than the set threshold, there is infringement. The trusted third party finds the registered user through the smart contract, determines the real owner of the data based on the registration timestamp, and punishes the infringer. When the similarity score is below the set threshold, there is no infringement.

7. A medical data infringement detection method based on image mapping as claimed in claim 6, characterized in that: The infringement detection results are stored in the blockchain through smart contracts.

8. A medical data infringement detection system based on image mapping, characterized in that: include: The infringement reporting module is configured as follows: a trusted third party obtains and signs the medical data and decryption key ciphertext of the reporter and the reported person, obtains the normal range of each detection indicator in the reporter's medical data, and sends the signed medical data and decryption key ciphertext of the reporter and the reported person, and the normal range of the detection indicator to the trusted execution environment; The data verification module is configured to: verify the received data in a trusted execution environment, and after successful verification, decrypt the medical data of the reporter and the reported person based on the ciphertext to obtain the medical data of the reporter and the reported person; The data processing module is configured to: the trusted execution environment processes the medical data of the reporter and the medical data of the person being reported based on the normal range of the detection index to obtain the data image of the reporter and the data image of the person being reported; The similarity calculation module is configured to: extract features from the data image of the reporter and the data image of the person being reported by the trusted execution environment to obtain feature sets of the two, calculate similarity based on the feature sets of the two, obtain a similarity score and send it to a trusted third party; The infringement determination module is configured to: a trusted third party determines whether there is infringement between the medical data of the person being reported and the medical data of the reporter based on a comparison of the similarity score with a set threshold.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of a medical data infringement detection method based on image mapping as described in any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the medical data infringement detection method based on image mapping as described in any one of claims 1-7 are implemented.

Images