User diagnosis and treatment information security management method and system applied to intelligent medical treatment

Through blockchain storage, independent learning privacy model, dynamic access control and zero-knowledge proof technology, combined with multi-factor authentication, the problems of data security and privacy protection in smart health care are solved, and efficient and fair data access control and security are achieved. Behavioral incentives ensure user privacy and data security.

CN119007905AInactive Publication Date: 2024-11-22YIBIN FIRST PEOPLES HOSPITAL

Patent Information

Application Number
CN202411085303.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the field of smart medical care, how to protect user privacy and medical data security while achieving efficient and impartial data access control, encourage user security behavior, and use zero-knowledge proof technology to enable users to not disclose any actual situation when verifying data ownership. medical information.

Method used

It adopts blockchain-based data storage, independent learning privacy protection model, role-based dynamic access control, security behavior incentive mechanism and zero-knowledge proof technology, and combines multi-factor authentication to achieve secure management of user diagnosis and treatment information.

Benefits of technology

Through blockchain storage encryption and decryption, independent learning and adjustment of privacy settings, dynamic permission management and security incentive mechanisms, data security and privacy are ensured, and users are encouraged to safe behavior, efficient and fair data access control, and meet user privacy needs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119007905A_ABST
    Figure CN119007905A_ABST
Patent Text Reader

Abstract

The invention discloses a user diagnosis and treatment information safety management method and system applied to intelligent medical treatment, belongs to the field of medical information secrecy, and can effectively protect the diagnosis and treatment information of a user by using data storage based on a block chain. Meanwhile, according to the method, the security of the diagnosis and treatment information of the user is further improved by establishing a privacy protection model with autonomous learning ability, performing role-based dynamic access control and establishing a security behavior incentive mechanism. Moreover, the method also utilizes a zero-knowledge proof technology to protect the privacy of the user. In addition, the system of the method can effectively achieve all the steps. On the basis, the invention further provides a method for carrying out user identity authentication by utilizing multi-factor identity authentication, so that the security and robustness of identity authentication are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of medical information confidentiality, and more specifically, relates to a user diagnosis and treatment information security management method and system applied to smart medical care. Background Art

[0002] In the current era of big data, the medical industry plays an important role in using large amounts of data to significantly improve the quality and efficiency of health care. With the rapid advancement of medical informatization, a large amount of diagnosis and treatment information is stored electronically, which provides great convenience for the realization of smart medical care. However, the sensitivity and privacy of medical data make it a target for hacker attacks and illegal use, and data security issues are becoming increasingly prominent. In order to protect the privacy of users, medical data usually needs to be encrypted for storage and transmission, but this poses many technical challenges.

[0003] In addition, since medical institutions, medical staff and patients have different needs in terms of information usage rights and authority management, how to achieve fair and effective data access control is also an important issue. Traditional role-based access control technology often cannot meet the dynamically changing needs in the medical field.

[0004] At the same time, how to encourage users to engage in safe behavior while protecting privacy is also an important issue that has no good solution. Most existing safe behavior incentive mechanisms often require users to actively participate, but the degree of user participation is often limited by their cognitive level and interests.

[0005] Finally, with the development of zero-knowledge proof technology, users can prove to a third party that they have certain information without revealing any actual information. However, the application of this method in the field of medical data is still in its infancy.

[0006] Therefore, studying a medical data security management method that can comprehensively address the above issues is of great significance to promoting the advancement of smart healthcare. Summary of the invention

[0007] The main technical problem solved by the present invention is how to achieve efficient and fair data access control while protecting user privacy and medical data security, encourage user safety behavior, and use zero-knowledge proof technology so that users do not need to disclose any actual medical information when verifying data ownership.

[0008] In order to achieve the above object, the present invention is implemented by adopting the following technical scheme: the user medical information security management method comprises:

[0009] Data storage based on blockchain: The user's medical information is stored on the blockchain, and the user can control his or her own medical information by controlling his or her own private key;

[0010] Establish a privacy protection model with self-learning capabilities: Use machine learning to identify and learn users’ privacy stances and behavior patterns, and automatically adjust the system’s privacy settings;

[0011] Role-based dynamic access control: dynamically adjust access rights based on the roles of medical staff and users;

[0012] Establish a safe behavior incentive mechanism: Provide users with incentives for privacy and security protection behaviors by adopting blockchain smart contracts;

[0013] Zero-knowledge proof: Users can perform zero-knowledge proof of their own medical information without revealing the actual medical information.

[0014] In one embodiment, the blockchain-based data storage includes:

[0015] Encrypt the user's medical information, create the encrypted information C in the form of a transaction, generate a hash value for the transaction, and use the user's private key Pr to sign the transaction hash value H to generate a digital signature;

[0016] Submit the transaction hash value H, digital signature S and user's public key Pu to the blockchain network, package them into a new block and add them to the end of the blockchain;

[0017] When a user obtains his or her own medical information, he or she finds the corresponding transaction on the blockchain, and then uses his or her own private key Pr to decrypt the data C in the transaction to obtain the original medical information m.

[0018] In one embodiment, the step of establishing a privacy protection model with autonomous learning capability includes:

[0019] Collect a large amount of user behavior data and user feedback on privacy protection;

[0020] The collected user behavior data is converted into feature vectors;

[0021] Convert the user's access frequency, access time, and queried disease diagnosis and treatment information into a feature vector X = [x1, x2, ..., xn];

[0022] A neural network model f is trained using the collected data and feature vectors. The model output Y = f(X) represents the user's expectation of privacy protection. 1 indicates that the user is willing to disclose his or her medical information, and 0 indicates that the user is unwilling to disclose his or her medical information.

[0023] The best model parameters are found through the adma optimization algorithm, so that the model output Y is close to the actual feedback of user privacy protection;

[0024] According to the model's prediction result Y, the system's privacy settings are automatically adjusted. If Y=1, the system automatically discloses the user's medical information; if Y=0, the system will not disclose the user's medical information.

[0025] In one embodiment, the role-based dynamic access control includes:

[0026] First, define various roles, including patients and doctors, and each role corresponds to different permissions and permission levels;

[0027] When users register, roles are assigned based on their actual identities;

[0028] Dynamically allocate and adjust permissions based on roles and the current medical environment. During the diagnosis and treatment phase, doctors have the permission to read and modify patient diagnosis and treatment data. This permission will be revoked when the diagnosis and treatment phase is over.

[0029] Every time a user accesses a resource, the system verifies the user's permissions;

[0030] Design a state transition matrix, where each row represents a role, each column represents a state, and the elements represent the permissions a role has when it is in a certain state;

[0031] Let R = {r1, r2, ..., rn} be the role set, S = {s1, s2, ..., sm} be the state set; define a state transition matrix M, where M[i][j] represents the authority of role ri in state sj;

[0032] At each time t, the roles of medical staff and patients are rt and rp respectively, and their permissions are obtained by referring to the state transfer matrix M, that is, permission = [M[rt][st], M[rp][sp]].

[0033] In one embodiment, the establishment of a safe behavior incentive mechanism includes:

[0034] Design and deploy a smart contract that rewards users with tokens if they regularly update their passwords or verify their medical information;

[0035] Monitor user behavior. When a user's behavior is found to be in line with the rules of the smart contract, the smart contract will be automatically triggered for execution.

[0036] When the contract is triggered, according to the preset rules, the system will automatically transfer the corresponding number of tokens to the user as a reward.

[0037] In one solution, the zero-knowledge proof includes the prover, the verifier, and the trusted third party. The specific process is as follows:

[0038] The proving party first submits its diagnosis and treatment data to a trusted third party;

[0039] The verifier submits a series of questions to the certifier, who answers them without revealing actual medical information.

[0040] The trusted third party verifies whether the prover knows the corresponding diagnosis and treatment data based on the prover's answer; after a specific probability interval is met, the verifier is convinced;

[0041] Its interaction process is expressed as:

[0042] The prover P submits one of the two graphs to the verifier V, denoted as graph G, and claims that he knows the other graph G';

[0043] The verifier selects two nodes on graph G and asks the prover to provide the corresponding two nodes on graph G';

[0044] The prover answered the positions of these two nodes on G';

[0045] The verifier repeats the above process until he knows that within a certain probability range, the range is 95%, he is sure that the prover understands the mapping relationship from graph G to G';

[0046] If two graphs are isomorphic, their adjacency matrices can be determined by some permutation, through P'AP = B, where A, B are the adjacency matrices of graphs G and G', and P is some permutation matrix.

[0047] On the other hand, a user diagnosis and treatment information security management system applied to smart medical care is provided, wherein the system is applicable to the method described, and the system comprises:

[0048] The first module is used to store the user's medical information on the blockchain, encrypt and verify the medical information through the user's private key to ensure the security and integrity of the data;

[0049] The second module is used to meet users’ privacy expectations by automatically learning and adjusting their privacy settings;

[0050] The third module is used to dynamically adjust the access rights of users according to their roles, ensuring that information is accessed by the right users at the right time and place;

[0051] The fourth module is used to incentivize users’ safe behaviors through blockchain smart contracts and encourage them to engage in safe behaviors;

[0052] The fifth module is used to use zero-knowledge proof technology, so that users can prove that they know their medical information without disclosing it, in order to protect their privacy;

[0053] The sixth module is used to utilize multi-factor authentication for user authentication, which improves the security and robustness of authentication through multiple factors such as phone devices, biometrics, and behavioral patterns.

[0054] In one solution, the sixth module includes four sub-steps: device binding, biometric registration, behavioral pattern recognition, and identity verification. The system automatically enrolls and learns the user's behavioral pattern and uses it in a multi-factor identity verification process.

[0055] Beneficial effects of the present invention:

[0056] The present invention provides a user medical information security management method and system applied to smart medical care, which stores and encrypts and decrypts the user's medical information through blockchain technology, thereby ensuring the security and integrity of medical data. A self-learning privacy protection model is adopted to automatically identify and adjust user privacy settings to meet the user's privacy needs. In addition, the system's role-based dynamic access control and security behavior incentive mechanism not only achieves the fairness and effectiveness of data access, but also encourages users to perform more secure behaviors. At the same time, the application of zero-knowledge proof technology allows users to verify data ownership without disclosing specific medical information. By integrating these measures, the system and method of the present invention can efficiently and effectively solve the problems of data security and privacy protection in the field of smart medical care, and has important practical value and broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is a flow chart of the method of the present invention;

[0058] Figure 2 This is a flowchart of data storage based on blockchain in the present invention;

[0059] Figure 3 A flow chart of a privacy protection model with autonomous learning capability is established for the present invention. DETAILED DESCRIPTION

[0060] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Typical embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described in the present invention. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0061] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0062] like Figure 1 As shown, the user diagnosis and treatment information security management method applied to smart medical care includes:

[0063] S1. Blockchain-based data storage: The user's medical information is stored on the blockchain, and the user can control his or her own medical information by controlling his or her own private key.

[0064] like Figure 2 As shown, the blockchain-based data storage includes:

[0065] S101, data encryption: First, encrypt the user's medical information. Assume that the plaintext information is m and the user's private key is Pr. The encrypted information C can be expressed as C = E (Pr, m), where E is an encryption function.

[0066] S102, create a transaction: create the encrypted information C in the form of a transaction. At the same time, generate a hash value H=Hash(C) of the transaction, and the hash value H will serve as the unique identifier of the transaction.

[0067] S103, transaction signature: Use the user's private key Pr to sign the transaction hash value H, and generate a digital signature S = Sign (Pr, H). The signature can ensure the non-repudiation and integrity of the transaction.

[0068] S104, transaction verification: Submit the transaction hash value H, digital signature S and user's public key Pu to the blockchain network. Nodes in the network can verify the digital signature S with the user's public key Pu. If the verification is successful, the transaction is accepted and forwarded.

[0069] S105. Packing into blocks: When enough transactions are verified and aggregated, they can be packaged into a new block and added to the end of the blockchain.

[0070] S106. Data decryption: When a user needs to obtain his or her own medical information, he or she only needs to find the corresponding transaction on the blockchain, and then use his or her own private key Pr to decrypt the data C in the transaction to obtain the original medical information m.

[0071] S2. Establish a privacy protection model with autonomous learning capabilities: Use machine learning to identify and learn users’ privacy stances and behavior patterns, and automatically adjust the system’s privacy settings.

[0072] like Figure 3 As shown, the establishment of a privacy protection model with autonomous learning capability includes:

[0073] S201. Data collection: In order to learn about users’ privacy stance and behavior patterns, we first need to collect a large amount of user behavior data and user feedback on privacy protection.

[0074] S202, feature engineering: converting the collected user behavior data into meaningful feature vectors for use by machine learning models. For example, the user's access frequency, access time, queried disease and other medical information can be converted into a feature vector X = [x1, x2, ..., xn].

[0075] S203, model training: a model f is trained using the collected data and feature vectors, using a neural network machine learning algorithm for training. The output of the model Y = f (X) represents the user's expectation of privacy protection, with 1 indicating that the user is willing to disclose his or her medical information, and 0 indicating that the user is unwilling to disclose his or her medical information.

[0076] S204, finding the best model parameters through the adma optimization algorithm so that the output Y of the model is close to the actual feedback of the user's privacy protection;

[0077] S205, automatically adjust privacy settings: automatically adjust the privacy settings of the system according to the prediction result Y of the model. If Y=1, the system can automatically disclose the user's medical information; if Y=0, the system will not disclose the user's medical information.

[0078] Taking the neural network as the training model, its output can be expressed as Y = σ (WX + b), where σ indicates that the activation function is the ReLU function, W indicates the weight, X indicates the feature vector, and b indicates the bias. The update of weights and biases is mainly performed through the gradient descent algorithm, that is, W = W-ηδ / δW, b = b-ηδ / δb, where η is the learning rate, δ / δW and δ / δb respectively represent the partial derivatives of the loss function L with respect to the weight W and the bias b.

[0079] S3. Role-based dynamic access control: Dynamically adjust access rights based on the roles of medical personnel and users.

[0080] First, define various roles, such as patients, doctors, etc. Each role corresponds to different permissions and permission levels.

[0081] When users register, roles are assigned based on their actual identities.

[0082] Dynamically allocate and adjust permissions based on roles and the current medical environment. For example, during the diagnosis and treatment phase, doctors can have the permission to read and modify patient diagnosis and treatment data. Once the diagnosis and treatment phase is over, this permission will be revoked.

[0083] Each time a user accesses a resource, the system needs to verify the user's permissions. Only after the permission verification is passed can the user access the resource.

[0084] Design a state transition matrix, where each row represents a role, each column represents a state, and the elements represent the permissions a role has when it is in a certain state;

[0085] Let R = {r1, r2, ..., rn} be the role set, S = {s1, s2, ..., sm} be the state set; define a state transition matrix M, where M[i][j] represents the authority of role ri in state sj;

[0086] At each time t, the roles of medical staff and patients are rt and rp respectively, and their permissions are obtained by referring to the state transfer matrix M, that is, permission = [M[rt][st], M[rp][sp]].

[0087] S4. Establish a security behavior incentive mechanism: Provide users with incentives for privacy and security protection behaviors by adopting blockchain smart contracts. Including:

[0088] Smart contract design: In the blockchain, a smart contract is designed and deployed. This smart contract can write a series of rules, for example, if the user regularly updates his password or verifies his medical information, then the corresponding token will be rewarded. Tokens are usually used as a reward or incentive method to encourage users to actively participate in and maintain their data security, such as regularly updating passwords or verifying their medical information.

[0089] User behavior monitoring: The system will continuously monitor user behavior. When it is found that a user's behavior meets the rules of the smart contract, it will automatically trigger the smart contract for execution.

[0090] Smart contract execution: When the contract is triggered, according to the preset rules, the system will automatically transfer the corresponding number of tokens to the user as a reward.

[0091] Smart contracts are written in solidity. Ethereum smart contracts have features such as state variables, functions, and events. State variables are variables stored on the blockchain, functions are used to modify state variables, and events can be monitored externally. Each time a user completes a security behavior, the number of reward tokens he or she receives may be calculated according to a certain mathematical formula: numTokens = baseNum + bonusFactor * numSecurities, where baseNum is the base reward number, bonusFactor is the bonus factor, and numSecurities is the number of security behaviors completed by the user.

[0092] S5. Zero-knowledge proof: Users can perform zero-knowledge proof on their own medical information without revealing the actual medical information.

[0093] The zero-knowledge proof includes:

[0094] Submission: The prover first submits its diagnosis and treatment data to a trusted third party. This process can be carried out through a private channel to ensure the security of the data.

[0095] Questioning and answering: The verifier submits a series of questions to the certifier, who then answers them. The certifier does not need to disclose actual medical information during this process.

[0096] Verification: The trusted third party verifies whether the prover knows the corresponding diagnosis and treatment data based on the prover’s answer. After a certain probability interval is met, the verifier is convinced.

[0097] Its interaction process can be expressed as:

[0098] 1. Submission: The prover (P) submits one of the two graphs (denoted as graph G) to the verifier (V) and claims that he knows the other graph (G'). Graph G is an abstract concept that expresses a certain relationship or problem through graph theory. These graphs can be of any type, such as directed graphs, undirected graphs, weighted graphs, bipartite graphs, etc.

[0099] In the verification process of zero-knowledge proof, graph G plays an important role. The principle of zero-knowledge proof is that the prover P (Prover) claims that he knows the answer to a question (for example, graph G' is an isomorphic graph of graph G), but does not want to tell the answer directly to the verifier V (Verifier).

[0100] In this process, the prover P only needs to provide enough evidence (such as graph G and random response) to convince the verifier V that he does know the graph G' without revealing the specific information of graph G'. This can protect the prover P's information from being leaked, and make the verifier V believe that the prover P knows the correct answer. This is the basic idea of ​​zero-knowledge proof.

[0101] 2. Question: The verifier selects two nodes on graph G and asks the prover to give the corresponding two nodes on graph G'.

[0102] 3. Answer: The prover answered the positions of these two nodes on G'.

[0103] 4. Verification: The verifier repeats the above process until he knows that within a certain probability range, the range is 95%, he is sure that the prover understands the mapping relationship from graph G to graph G'. The probability range means that by repeating the same test many times, the verifier V reaches a certain level of confidence in whether the prover P really understands the mapping relationship from graph G to graph G'. In other words, this is a way to measure the minimum uncertainty that the verifier can accept.

[0104] This probability range is usually determined based on specific application requirements or the requirements of the verifier. The verifier V sets this probability range to 95%, that is, through repeated verification, as long as the prover P can answer the question correctly in 95% of the scenarios, the verifier V will accept the prover P's statement.

[0105] If two graphs are isomorphic, their adjacency matrices can be determined by some permutation, through P'AP = B, where A, B are the adjacency matrices of graphs G and G', and P is some permutation matrix.

[0106] Embodiment 2:

[0107] A user diagnosis and treatment information security management system applied to smart medical care, the system is applicable to the method described, and the system includes:

[0108] The first module is used to store the user's medical information on the blockchain, encrypt and verify the medical information with the user's private key, and ensure the security and integrity of the data. This module will store the user's medical information on the blockchain and encrypt the medical information with the user's private key to prevent unauthorized access. In addition, the information encrypted in this way can only be decrypted with the corresponding private key, which improves the security and integrity of the data.

[0109] The second module is used to meet users’ privacy expectations by automatically learning and adjusting their privacy settings;

[0110] The third module dynamically sets access rights based on the user's role. The system is able to identify the user's role (such as patient, doctor, etc.) and assign access rights appropriately based on the role. This ensures that information is only accessed by authorized users at the appropriate time and place.

[0111] The fourth module encourages users to engage in safe behavior through blockchain smart contracts. For example, regular password updates or regular account audits can earn rewards from smart contracts. This incentive mechanism can effectively improve users' awareness of safety precautions.

[0112] The fifth module uses zero-knowledge proof technology to protect user privacy. Users can use zero-knowledge proof technology to prove that they know their medical information without disclosing it.

[0113] The sixth module is used to perform user authentication using multi-factor authentication, which improves the security and robustness of authentication through multiple factors such as phone devices, biometrics and behavioral patterns. It includes four sub-steps: device binding, biometric registration, behavioral pattern recognition and identity authentication. The system automatically enrolls and learns the user's behavioral pattern and uses it in the multi-factor authentication process.

[0114] Embodiment three:

[0115] Suppose there is a user A whose medical information is "suffering from high blood pressure". First, encrypt the medical information to generate an encrypted information C. Then, use blockchain technology to generate a digital signature S based on user A's private key Pr, and submit the data containing the transaction hash value H, digital signature S and the user's public key Pu to the blockchain network. This data will be packaged into a new block and added to the end of the blockchain to form a verifiable and tamper-proof transaction record.

[0116] In the self-learning privacy protection model, the feature vector X is set to [X1, X2, X3] based on the behavior data and privacy protection willingness of user A. Then, through the training of the neural network model and the adma optimization algorithm, the optimal model parameters are found to make the output value Y close to the actual needs of the user for privacy protection.

[0117] In terms of permission control, user A is defined as a patient in the hospital, and his access rights are dynamically adjusted according to the needs of the current medical environment. For example, when a doctor treats user A, the doctor will be granted permission to read and modify user A's medical data, and this permission will be revoked after the treatment is completed.

[0118] In order to encourage users to protect privacy and data security, users will be given corresponding rewards through blockchain smart contracts. For example, if user A regularly updates his password or verifies his medical information, the system will reward user A with a certain number of tokens.

[0119] User A does not need to disclose his or her medical information and can prove his or her knowledge of the information through zero-knowledge proof technology, which further protects the user's privacy.

[0120] Finally, authentication is performed through multiple methods such as phone device information, biometrics (such as fingerprint or facial recognition), and user behavior patterns to ensure that only genuine users can gain access.

[0121] Therefore, based on the above description, the smart medical user medical information security management method can effectively ensure the security and privacy of user medical information.

[0122] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0123] It should be understood that the detailed description of the technical solutions of the present invention by means of the preferred embodiments is illustrative rather than restrictive. A person skilled in the art may modify the technical solutions described in the embodiments, or replace some of the technical features by equivalents, based on reading the specification of the present invention; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A user diagnosis and treatment information security management method applied to smart medical care, characterized by: The user medical information security management method includes: Data storage based on blockchain, storing the user's medical information on the blockchain, and controlling their own medical information by controlling their own private keys; Establish a privacy protection model with self-learning capabilities, use machine learning models to identify and learn users' privacy stances and behavior patterns, and automatically adjust the system's privacy settings; Role-based dynamic access control dynamically adjusts access rights according to the roles of medical staff and users; Establish a security behavior incentive mechanism to provide users with incentives for privacy and security protection behaviors through the use of blockchain smart contracts; Zero-knowledge proof: users can provide zero-knowledge proof of their own medical information without revealing the actual medical information.

2. According to a method for secure management of user diagnosis and treatment information applied to smart medical care according to claim 1, it is characterized by: The blockchain-based data storage includes: Encrypt the user's medical information, create the encrypted information C in the form of a transaction, generate a hash value for the transaction, and use the user's private key Pr to sign the transaction hash value H to generate a digital signature; Submit the transaction hash value H, digital signature S and user's public key Pu to the blockchain network, package them into a new block and add them to the end of the blockchain; When a user obtains his or her own medical information, he or she finds the corresponding transaction on the blockchain, and then uses his or her own private key Pr to decrypt the data C in the transaction to obtain the original medical information m.

3. According to a method for secure management of user diagnosis and treatment information applied to smart medical care according to claim 1, it is characterized by: The establishment of a privacy protection model with autonomous learning capability includes: Collect a large amount of user behavior data and user feedback on privacy protection; The collected user behavior data is converted into a feature vector, and the user's access frequency, access time, and queried disease diagnosis and treatment information are converted into a feature vector X = [x1, x2, ..., xn]; A neural network model f is trained using the collected data and feature vectors. The model output Y = f(X) represents the user's expectation of privacy protection. 1 indicates that the user is willing to disclose his or her medical information, and 0 indicates that the user is unwilling to disclose his or her medical information. The best model parameters are found through the adma optimization algorithm, so that the model output Y is close to the user's feedback on privacy protection; According to the model's prediction result Y, the system's privacy settings are automatically adjusted. If Y=1, the system automatically discloses the user's medical information; if Y=0, the user's medical information is not disclosed.

4. According to a method for secure management of user diagnosis and treatment information applied to smart medical care according to claim 1, it is characterized by: The role-based dynamic access control includes: First, define various roles, including patients and doctors, and each role corresponds to different permissions and permission levels; When users register, roles are assigned based on their actual identities; Dynamically allocate and adjust permissions based on roles and the current medical environment. During the diagnosis and treatment phase, doctors have the permission to read and modify patient diagnosis and treatment data. When the diagnosis and treatment phase is over, the permission will be revoked. Every time a user accesses a resource, the system verifies the user's permissions; Design a state transition matrix, where each row represents a role, each column represents a state, and the elements represent the permissions a role has when it is in a certain state; Let R = {r1, r2, ..., rn} be the role set, S = {s1, s2, ..., sm} be the state set; define a state transition matrix M, where M[i][j] represents the authority of role ri in state sj; At each time t, the roles of medical staff and patients are rt and rp respectively, and their permissions are obtained by referring to the state transfer matrix M, that is, permission = [M[rt][st], M[rp][sp]].

5. According to a method for secure management of user diagnosis and treatment information applied to smart medical care according to claim 1, it is characterized by: The establishment of a safety behavior incentive mechanism includes: Design and deploy a smart contract that rewards users with tokens if they regularly update their passwords or verify their medical information; Monitor user behavior. When a user's behavior is found to be in line with the rules of the smart contract, the smart contract will be automatically triggered for execution. When the contract is triggered, according to the preset rules, the system will automatically transfer the corresponding number of tokens to the user as a reward.

6. A user diagnosis and treatment information security management method applied to smart medical care according to claim 1, characterized in that: The zero-knowledge proof includes the prover, the verifier, and the trusted third party. The specific process is as follows: The proving party first submits its diagnosis and treatment data to a trusted third party; The verifier submits a series of questions to the certifier, who answers them without revealing actual medical information. The trusted third party verifies whether the prover knows the corresponding diagnosis and treatment data based on the prover's answer; after a specific probability interval is met, the verifier is convinced; Its interaction process is expressed as: The prover P submits one of the two graphs to the verifier V, denoted as graph G, and claims that he knows the other graph G'; The verifier selects two nodes on graph G and asks the prover to provide the corresponding two nodes on graph G'; The prover answered the positions of these two nodes on G'; The verifier repeats the above process until he knows that within a certain probability range, the range is 95%, he is sure that the prover understands the mapping relationship from graph G to G'; If two graphs are isomorphic, their adjacency matrices can be determined by some permutation, through P'AP = B, where A, B are the adjacency matrices of graphs G and G', and P is some permutation matrix.

7. A user diagnosis and treatment information security management system applied to smart medical care, the system is applicable to the method according to any one of claims 1 to 6, characterized in that: The system comprises: The first module is used to store the user's medical information on the blockchain, encrypt and verify the medical information through the user's private key to ensure the security and integrity of the data; The second module is used to meet users’ privacy expectations by automatically learning and adjusting their privacy settings; The third module is used to dynamically adjust the access rights of users according to their roles, ensuring that information is accessed by the right users at the right time and place; The fourth module is used to incentivize users’ safe behaviors through blockchain smart contracts and encourage them to engage in safe behaviors; The fifth module is used to use zero-knowledge proof technology, so that users can prove that they know their medical information without disclosing it, in order to protect their privacy; The sixth module is used to utilize multi-factor authentication for user authentication, which improves the security and robustness of authentication through multiple factors such as phone devices, biometrics, and behavioral patterns.

8. A user diagnosis and treatment information security management system for smart medical care according to claim 7, characterized in that: The sixth module includes four sub-steps: device binding, biometric registration, behavior pattern recognition and identity authentication. The system automatically enrolls and learns the user's behavior pattern and uses it in the multi-factor identity authentication process.

Citation Information

Patent Citations

  • Security industry token value-added method based on block chain

    CN110827053A

  • Block chain intelligent medical system

    CN115134378A

  • Electronic medical record sharing and verifiable system based on block chain

    CN115314225A

  • Emergency treatment electronic medical record management system and management method

    CN116631564A

  • Medical industry data security supervision system based on block chain

    CN116776389A

Cited By

  • Health data processing method and system based on distributed account book library

    CN120126655A

  • Remote medical identity management method and system based on multi-factor authentication and dynamic trust evaluation

    CN120296721A

  • Time-sensitive network flow scheduling method based on 5g network

    CN120456332A

  • A time-sensitive network traffic scheduling method based on a 5g network

    CN120456332B