Smart city identity authentication system based on block chain technology

Abstract

The invention discloses a smart city identity authentication system based on a block chain technology. The smart city identity authentication system comprises a physiological signal acquisition terminal and a block chain system. The physiological signal acquisition terminal is provided with a user-defined module, supports a patient to check the type of identity authentication information, and then carries out preprocessing through an artificial intelligence algorithm to obtain structured data. The block chain system comprises a block chain network, a client, a digital signature module and an identity verification module. The digital signature module can verify the integrity and authenticity of the data; and the identity authentication module can perform identity verification based on structured data provided by the client. The system acquires identity information of a patient through the physiological signal acquisition terminal, performs preprocessing by adopting an artificial intelligence algorithm, and subsequently performs identity verification by utilizing a block chain system, so that secure access of privacy data is ensured.

Description

Technical Field

[0001] The present invention relates to the field of identity authentication, and in particular to a smart city identity authentication system based on blockchain technology. Background Art

[0002] In recent years, identity authentication and data privacy protection issues have caused trust barriers between patients and medical institutions, directly affecting the sustainable development of the medical system. This invention combines blockchain, cryptography and artificial intelligence technology, obtains the patient's identity information through the physiological signal acquisition terminal, and uses artificial intelligence algorithm + blockchain system for identity verification to ensure secure access to privacy data, greatly improving the efficiency of medical services.

[0003] Traditional identity authentication methods rely on passwords and biometrics, which have drawbacks such as poor security, low convenience, and insufficient privacy protection. For example, passwords are easily stolen or attacked, and although biometrics have improved in accuracy, they face the risk of data leakage. With the advancement of artificial intelligence technology, the generalization ability of the model has been greatly enhanced, and it can effectively extract the generalized features of face and voiceprint data. Therefore, blockchain + AI algorithms can be used in medical systems to achieve identity authentication. This method can effectively avoid the leakage of biological information and greatly improve the level of privacy protection.

[0004] At present, there are also some patent technologies related to identity authentication based on blockchain technology on the market, for example: Chinese patent CN202411676375.X discloses a blockchain-based electronic nursing medical record security management system, including a user management module, a blockchain encryption module, a data consistency verification module, a data integrity verification module, a data analysis and evaluation module, a data transmission module, and a data management module; the system performs identity authentication through blockchain to realize user information registration, login, authority allocation and cancellation functions. However, this system has obvious drawbacks, which are specifically manifested as follows: the blockchain network adopted by the present invention is based on private keys for identity authentication. When the private key is lost or stolen, the identity verification module cannot detect it in time, which will cause the risk of electronic medical record data leakage.

[0005] Chinese patent CN202410620084.2 discloses a virtual identity authentication device and its authentication method, including a video acquisition module, a central processing module and a projection display module. The patent obtains facial images through a camera, and then uses an algorithm to obtain facial data, and performs identity authentication through image comparison. Although the system implements identity authentication based on biometrics, the privacy protection during implementation is not strong, and the model training process uses a centralized framework, which has the risk of facial data leakage.

[0006] In order to improve the efficiency and security of identity authentication, the present invention provides a smart city identity authentication system based on blockchain technology, which realizes accurate identification of user identity through customizing the business logic of smart contracts, combining physiological signal acquisition terminals, artificial intelligence feature extraction algorithms and blockchain systems. Summary of the invention

[0007] In view of the above problems, the present invention provides a smart city identity authentication system based on blockchain technology, which obtains the patient's identity information through a physiological signal acquisition terminal, uses an artificial intelligence algorithm to extract features, and subsequently uses a blockchain system to verify the identity to ensure secure access to private data. The system is characterized in that it includes: a physiological signal acquisition terminal and a blockchain system:

[0008] The physiological signal acquisition terminal has a user-defined function, which supports patients to select the type of identity authentication information; the identity authentication information includes biological information and physiological data; the biological information includes voiceprints and facial images, which are pre-processed by artificial intelligence algorithms to obtain structured data, which is in the following form:

[0009] {

[0010] "Face image features": [

[0011] ["a11", "a12", "a13", ..., "a1n"],

[0012] ["a21", "a22", "a23", ..., "a2n"],

[0013] ["a31", "a32", "a33", ..., "a3n"], ... ]

[0016] "Voiceprint Features": [

[0017] ["b11", "b12", "b13", ..., "b1n"],

[0018] ["b21", "b22", "b23", ..., "b2n"],

[0019] ["b31", "b32", "b33", ..., "b3n"], ... ]

[0022] };

[0023] The physiological data includes ultrasound images, computer tomography, magnetic resonance imaging, heart rate, blood pressure and blood sugar data, which are subsequently pre-processed by artificial intelligence algorithms to obtain structured data, specifically;

[0024] {

[0025] "Heart rate": "Low",

[0026] "Systolic blood pressure": "Moderate",

[0027] "Blood sugar": "High",

[0028] "Ultrasound examination of organ morphology": "Normal",

[0029] "CT Lesion Size": "Small",

[0030] "MRI signal strength": "Normal",

[0031] };

[0032] The artificial intelligence algorithm is trained based on federated learning to effectively protect the privacy of medical data;

[0033] The blockchain system includes a blockchain network, a client, a digital signature module and an identity authentication module; the blockchain network adopts a private blockchain framework and realizes private access to medical data through role-based access control; the client is represented as a physiological signal acquisition terminal, which can make transaction requests to the blockchain to obtain the patient's electronic medical record; the digital signature module can verify the integrity and authenticity of the data; the identity authentication module can perform identity verification based on the structured data provided by the client, and the specific process is as follows:

[0034] S1: Initiate a transaction request: The client hashes the structured data and uploads it to the blockchain network for identity verification;

[0035] S2: Feature extraction: Convert the structured data provided by the client into biometric features, specifically:

[0036] { "Face image features":

[0037] { "fat": "moderate", "nose": "straight", "eyes": "big", "face shape": "oval face", "skin": "fair", "eyebrows": "thick", "lips": "thin", "chin": "pointed", "forehead": "wide"},

[0038] "Voiceprint Features":

[0039] { "voice": "high", "pitch": "high", "speed": "moderate", "timbre": "clear", "tone": "steady", "volume": "moderate", "accent": "standard"}

[0040] };

[0041] S3: Distance calculation: Perform feature comparison and calculate the distance between the requested data and the patient's medical features, specifically:

[0042]

[0043] in, It is expressed as feature weights, specifically:

[0044]

[0045] Expressed as feature comparison results, when the features are consistent,

[0046]

[0047] When the feature is not entered,

[0048]

[0049] When the feature comparison is inconsistent,

[0050]

[0051] in, Describe the penalty function;

[0052] S4: Identity verification: Verify the identity of the client, specifically:

[0053]

[0054] in, It is expressed as a threshold for identity authentication to ensure the security of user information.

[0055] The advantages of the present invention are:

[0056] 1. High degree of intelligence: It supports patients to customize the types of authentication information, and then implements identity authentication through artificial intelligence algorithm + blockchain, avoiding identity theft caused by loss of private keys;

[0057] 2. Strong privacy: This system does not provide original face data and voiceprint information during identity authentication. Through artificial intelligence algorithms, the intermediate structured data is passed to the blockchain for identity authentication, which has the advantage of strong privacy;

[0058] 3. High robustness: using spatial distance Perform identity authentication by design The value of ensures that the system has a fault-tolerant mechanism and can adapt to slight differences in biometric features. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the present invention, and do not constitute a limitation of the embodiments of the present invention.

[0060] Figure 1 : A smart city identity authentication system framework based on blockchain technology.

[0061] Figure 2 :System implementation architecture of blockchain.

[0062] Figure 3 : Implementation framework of identity authentication.

[0063] Figure 4 : An implementation framework for federated learning. DETAILED DESCRIPTION

[0064] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0065] Implementation Example 1

[0066] Attached Figure 1 A smart city identity authentication system framework based on blockchain technology is demonstrated. The patient's identity information is obtained through a physiological signal acquisition terminal, and an artificial intelligence algorithm is used for feature extraction. The blockchain system is then used for identity verification to ensure secure access to private data. The system is characterized by: a physiological signal acquisition terminal and a blockchain system:

[0067] The physiological signal acquisition terminal has a user-defined function, which supports patients to select the type of identity authentication information; the identity authentication information includes biological information and physiological data; the biological information includes voiceprints and facial images, which are pre-processed by artificial intelligence algorithms to obtain structured data, which is in the following form:

[0068] {

[0069] "Face image features": [

[0070] ["a11", "a12", "a13", ..., "a1n"],

[0071] ["a21", "a22", "a23", ..., "a2n"],

[0072] ["a31", "a32", "a33", ..., "a3n"], ... ]

[0075] "Voiceprint Features": [

[0076] ["b11", "b12", "b13", ..., "b1n"],

[0077] ["b21", "b22", "b23", ..., "b2n"],

[0078] ["b31", "b32", "b33", ..., "b3n"], ... ]

[0081] };

[0082] The physiological data includes ultrasound images, computer tomography, magnetic resonance imaging, heart rate, blood pressure and blood sugar data, which are subsequently pre-processed by artificial intelligence algorithms to obtain structured data, specifically;

[0083] {

[0084] "Heart rate": "Low",

[0085] "Systolic blood pressure": "Moderate",

[0086] "Blood sugar": "High",

[0087] "Ultrasound examination of organ morphology": "Normal",

[0088] "CT Lesion Size": "Small",

[0089] "MRI signal strength": "Normal",

[0090] };

[0091] The artificial intelligence algorithm is trained based on federated learning to effectively protect the privacy of medical data;

[0092] The blockchain system includes a blockchain network, a client, a digital signature module and an identity authentication module; Figure 2The system implementation architecture of blockchain is demonstrated. The blockchain network adopts a private blockchain framework, and realizes private access to medical data through role-based access control; the client is represented as a physiological signal acquisition terminal, which can make transaction requests to the blockchain to obtain the patient's electronic medical record; the digital signature module can verify the integrity and authenticity of the data; the identity authentication module can perform identity verification based on the structured data provided by the client, and the specific process is as follows:

[0093] S1: Initiate a transaction request: The client hashes the structured data and uploads it to the blockchain network for identity verification;

[0094] S2: Feature extraction: Convert the structured data provided by the client into biometric features, specifically:

[0095] { "Face image features":

[0096] { "fat": "moderate", "nose": "straight", "eyes": "big", "face shape": "oval face", "skin": "fair", "eyebrows": "thick", "lips": "thin", "chin": "pointed", "forehead": "wide"},

[0097] "Voiceprint Features":

[0098] { "voice": "high", "pitch": "high", "speed": "moderate", "timbre": "clear", "tone": "steady", "volume": "moderate", "accent": "standard"}

[0099] };

[0100] S3: Distance calculation: Perform feature comparison and calculate the distance between the requested data and the patient's medical features, specifically:

[0101]

[0102] in, It is expressed as feature weights, specifically:

[0103]

[0104] Expressed as feature comparison results, when the features are consistent,

[0105]

[0106] When the feature is not entered,

[0107]

[0108] When the feature comparison is inconsistent,

[0109]

[0110] in, Describe the penalty function;

[0111] S4: Identity verification: Verify the identity of the client, specifically:

[0112]

[0113] in, It is expressed as a threshold for identity authentication to ensure the security of user information.

[0114] Implementation Example 2

[0115] Attached Figure 3 The implementation framework of identity authentication is shown. In the blockchain system, each transaction needs to be verified by a digital signature to ensure that the initiator of the transaction is legitimate and that the transaction content has not been tampered with during transmission. Digital signatures are implemented through public key encryption algorithms. The transaction initiator uses his own private key to encrypt the transaction data and generate a signature; the receiver uses the initiator's public key to decrypt and verify the validity of the signature. The specific implementation steps are as follows:

[0116] S1: Data preprocessing: The server-side structured data is encrypted and signed. The specific process is as follows:

[0117] {

[0118] "Face image features": [[0.23, 0.45, 0.67, ..., 0.12], [0.89, 0.34, 0.56,..., 0.78], ... ],

[0119] "Voiceprint features": [[0.56, 0.12, 0.34, ..., 0.90], [0.67, 0.23, 0.45, ...,0.56], ... ]

[0120] }.

[0121] S2: Hash encryption: To ensure that the data has not been tampered with, the server first hashes the original data. During the implementation process, the hash algorithm uses SHA-256. The specific results are:

[0122] Hash value: 4b6f6bb6727e94b39c7b2ee123c1c76a320e5b5c3a5411eb1355ed08363bb118.

[0123] S3: Digital signature: Use the RSA private key to generate a digital signature. The result after obtaining the signature is:

[0124] 7b6d8e8230b1352a3cfb0a24934c6f4e4ef0b5b92cc4903273cbb3b5f94e5c4 c097e9200d55a96db4bbeb59a1c9d9e77442c76e5bc02219503f600f1db68184 6e0d559f56c48dbd9264b8f8e3d1abf14c3c6c8bc037539b163a139cf9f5a48 ed629ec19701942f5e393d11f5b0db6f5e4c0de79cc95394464d4f9a08ed7e7.

[0125] The specific program code is:

[0126] from Crypto.PublicKey import RSA

[0127] from Crypto.Signature import pkcs1_15

[0128] from Crypto.Hash import SHA256

[0129] # Load the private key

[0130] private_key = RSA.import_key(open('private.pem').read())

[0131] # Create a SHA-256 hash object

[0132] hash_object = SHA256.new(data_str.encode())

[0133] # Sign the hash value using the private key

[0134] signature = pkcs1_15.new(private_key).sign(hash_object).

[0135] S4. Encrypted transmission: AES CBC mode is used for encryption during implementation. The data is divided into fixed-size blocks and an initialization vector (IV) is used to ensure that the same data has different encryption results. The encrypted data is:

[0136] 56a7d8baffd4b47d7f9ef7b21c4f2d34917c8f7b94a22c309c2c7f464598d6e8 1b32285db53965f768f0a4bbd4d0f0c99acb2b3b45c7a9ee51c084eeb9f7d933.

[0137] The specific code is:

[0138] from Crypto.Cipher import AES

[0139] from Crypto.Util.Padding import pad

[0140] import os

[0141] aes_key = os.urandom(16)

[0142] # Initialization vector (IV) for AES encryption

[0143] iv = os.urandom(16)

[0144] # Convert raw data into byte stream

[0145] data_bytes = data_str.encode()

[0146] # Encrypt using AES (CBC mode)

[0147] cipher_aes = AES.new(aes_key, AES.MODE_CBC, iv)

[0148] encrypted_data = cipher_aes.encrypt(pad(data_bytes, AES.block_size)).

[0149] S5: Send request: Send data to the blockchain smart contract module. The specific content is:

[0150] {

[0151] "Encrypted Data":

[0152] "56a7d8baffd4b47d7f9ef7b21c4f2d34917c8f7b94a22c309c2c7f464598d6e8 1b32285db53965f768f0a4bbd4d0f0c99acb2b3b45c7a9ee51c084eeb9f7d933",

[0153] "Signature Data":

[0154] "7b6d8e8230b1352a3cfb0a24934c6f4e4ef0b5b92cc4903273cbb3b5f94e5c4 c097e9200d55a96db4bbeb59a1c9d9e77442c76e5bc02219503f600f1db681846 e0d559f56c48dbd9264b8f8e3d1abf14c3c6c8bc037539b163a139cf9f5a48ed 629ec19701942f5e393d11f5b0db6f5e4c0de79cc95394464d4f9a08ed7e7e7",

[0155] "Timestamp": "2024-06-08T15:30:00Z",

[0156] "Sender": "Server ID",

[0157] "IV": "9c4f7c65b0f9d0101c6e0148fa78e77d"

[0158] }.

[0159] S6: Receiver verification and decryption: The receiver uses the server’s public key to verify the signature and ensure the integrity and origin of the data.

[0160] S7: Feature extraction: Convert the decrypted data into biometric features, specifically:

[0161] {

[0162] "Face image features": {

[0163] "nose": "straight",

[0164] "eyes": "big"

[0165] },

[0166] "Voiceprint Features": {

[0167] "sound": "shrill"

[0168] },

[0169] "Heart rate": 72,

[0170] "Systolic blood pressure": 120,

[0171] "Diastolic blood pressure": 80

[0172] }.

[0173] S8: Distance calculation and identity authentication.

[0174] Implementation Example 3

[0175] Attached Figure 4 The implementation framework of federated learning is demonstrated. The patient's physiological data and biometrics are private data. During the project implementation, the FedAvg algorithm is used to train the artificial intelligence model. The specific implementation steps are as follows:

[0176] S1: Initialize the global model: The central server selects a convolutional neural network as the initial model;

[0177] S2: Local training: Medical institutions train models based on private databases;

[0178] S3: Upload model update: upload the model parameters obtained by medical institution training to the central server;

[0179] S4: Model aggregation: After receiving the model parameters from multiple medical institutions, the central server uses the FedAvg algorithm to perform weighted averaging on the model parameters, specifically:

[0180]

[0181] in, are the parameters of the global model, It is Model training parameters for each medical institution, is the weight, is the number of medical institutions;

[0182] S5: Sending the new model: The central server sends the aggregated new model to the medical institution as the initial model for the next round of training;

[0183] S6: Repeated iteration: Through iterative optimization, an identity authentication model with excellent performance is finally obtained;

[0184] S7: Model evaluation and validation.

[0185] The specific implementation method described above provides a detailed description of the objectives, technical solutions and beneficial effects of the present invention. It should be understood that the above is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A smart city identity authentication system based on blockchain technology, which obtains the patient's identity information through a physiological signal acquisition terminal, uses artificial intelligence algorithm + blockchain system for identity verification, and ensures secure access to private data, characterized by: Contains: Physiological signal acquisition terminal and blockchain system: The physiological signal acquisition terminal has a user-defined function, which supports patients to select the type of identity authentication information; the identity authentication information includes biological information and physiological data; the biological information includes voiceprints and facial images, which are pre-processed by artificial intelligence algorithms to obtain structured data, specifically: { "Face image features":[ ["a11", "a12", "a13", ..., "a1n"], ["a21", "a22", "a23", ..., "a2n"], ["a31", "a32", "a33", ..., "a3n"], ... ]， "Voiceprint features":[ ["b11", "b12", "b13", ..., "b1n"], ["b21", "b22", "b23", ..., "b2n"], ["b31", "b32", "b33", ..., "b3n"], ... ] }； The physiological data includes ultrasound images, computer tomography, magnetic resonance imaging, heart rate, blood pressure and blood sugar data, which are subsequently pre-processed by artificial intelligence algorithms to obtain structured data, specifically; { "Heart rate": "Low", "Systolic blood pressure": "Moderate", "Blood sugar": "High", "Ultrasound examination of organ morphology": "Normal", "CT Lesion Size": "Small", "MRI signal strength": "Normal", }； The artificial intelligence algorithm is trained based on federated learning to effectively protect the privacy of medical data; The blockchain system includes a blockchain network, a client, a digital signature module and an identity authentication module; the blockchain network adopts a private blockchain framework and realizes private access to medical data through role-based access control; the client is represented as a physiological signal acquisition terminal, which can make transaction requests to the blockchain to obtain the patient's electronic medical record; the digital signature module can verify the integrity and authenticity of the data; the identity authentication module can perform identity verification based on the structured data provided by the client, and the specific process is as follows: S1: Initiate a transaction request: The client hashes the structured data and uploads it to the blockchain network for identity verification; S2: Feature extraction: Convert the structured data provided by the client into biometric features, specifically: { "Face image features": {"weight": "moderate","nose": "straight","eyes": "big","face shape": "oval face","skin": "fair","eyebrows": "thick","lips": "thin","chin": "pointed","forehead": "wide"}, "Voiceprint Features": { "voice": "high", "pitch": "high", "speed": "moderate", "timbre": "clear", "tone": "smooth", "volume": "moderate", "accent": "standard"} }； S3: Distance calculation: Perform feature comparison and calculate the distance between the requested data and the patient's medical features, specifically: in, It is expressed as feature weights, specifically: Expressed as feature comparison results, when the features are consistent, When the feature is not entered, When the feature comparison is inconsistent, in, Describe the penalty function; S4: Identity verification: Verify the identity of the client, specifically: in, It is expressed as a threshold for identity authentication to ensure the security of user information.

Images