Biometric identity verification method, client, server, device and system
By fitting the biometric model on the server side and sending functions to the client, offline biometric authentication is realized, network dependency problem is solved, and efficiency and accuracy are improved.
Patent Information
- Application Number
- CN202010908350.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-09-02
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2040-09-02
AI Technical Summary
In the state of incomplete communication network or offline, biometric authentication is difficult to implement, and the prior art has high computational complexity and low efficiency.
The biometric model is fitted through the server, and the biometric function is obtained and sent to the client with the biometric features. The client saves it locally to realize offline authentication, reduce computing complexity, and improve efficiency.
It realizes biometric authentication without network signals, improves the speed and accuracy of local authentication and reduces the computational complexity.
Smart Images

Figure CN112084476B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and more particularly to a biometric identity authentication method, client, server, device, and system. Background Art
[0002] With the development of artificial intelligence and computer vision technology, biometric authentication has been widely used in various fields as a new and convenient way of identity authentication. For example: face payment and fingerprint payment in financial scenarios, face authentication in civil aviation and high-speed rail scenarios, face access control and fingerprint access control in office scenarios, face authentication and fingerprint authentication in hotel accommodation scenarios, etc. Compared with traditional identity authentication methods based on card swiping or passwords, biometric identity authentication has the advantages of being fast, effective, and difficult to forge, so it has gradually become the mainstream way of identity authentication.
[0003] Generally, biometric identity authentication requires remote communication between the client and the server. How to perform biometric identity authentication in areas with imperfect communication networks or in offline states is a technical problem that urgently needs to be solved in this field. Summary of the invention
[0004] The purpose of the embodiments of this specification is to provide a biometric identity authentication method, client, server, device, storage medium and system to improve the accuracy and efficiency of biometric identity authentication.
[0005] In a first aspect, an embodiment of the present specification provides a biometric identity authentication method, the method comprising:
[0006] Receiving a biometric verification request, wherein the biometric verification request includes biometric information to be verified;
[0007] Performing biometric identification on the biometric information to be verified using a biometric identification function to obtain a biometric feature to be verified; wherein the biometric identification function is obtained and issued by the server after fitting a biometric identification model;
[0008] Calculating a feature distance between the biometric feature to be verified and the biometric sample feature received in advance and sent by the server; wherein the biometric sample feature is obtained after the server performs biometric recognition on the biometric sample information using the biometric recognition model;
[0009] Determine whether the identity verification request passes based on the feature distance.
[0010] In a second aspect, this specification provides a biometric identity authentication method, the method comprising:
[0011] Receiving biometric registration information uploaded by a client, wherein the biometric registration information includes biological sample information;
[0012] Performing image recognition on the biological sample information using a biological recognition model to obtain biological sample features corresponding to the biological sample information;
[0013] The biological sample feature and the biometric function obtained after fitting the biometric model are sent to the client, so that the client uses the biometric function and the biological sample feature to authenticate the received biometric verification request.
[0014] In a third aspect, this specification provides a biometric identity authentication client, including:
[0015] A verification request receiving module, used to receive a biometric verification request, wherein the biometric verification request includes biometric information to be verified;
[0016] A biometric identification module, used to perform biometric identification on the biometric information to be verified using a biometric identification function to obtain the biometric feature to be verified; wherein the biometric identification function is obtained and issued by the server after fitting the biometric identification model;
[0017] A feature distance calculation module, used to calculate the feature distance between the biometric feature to be verified and the biometric sample feature received in advance and sent by the server; wherein the biometric sample feature is obtained after the server performs biometric recognition on the biometric sample information using the biometric recognition model;
[0018] The identity authentication module is used to determine whether the identity authentication of the biometric authentication request is passed according to the feature distance.
[0019] In a fourth aspect, this specification provides a biometric identity authentication server, comprising:
[0020] A biometric image receiving module, used to receive biometric registration information uploaded by a client, wherein the biometric registration information includes biological sample information;
[0021] A biometric feature recognition module, used to perform image recognition on the biological sample information using a biometric recognition model to obtain biological sample features corresponding to the biological sample information;
[0022] The identification data sending module is used to send the biological sample characteristics and the biological recognition function obtained after fitting the biological recognition model to the client, so that the client uses the biometric recognition function and the biological sample characteristics to authenticate the received biometric verification request.
[0023] In a fifth aspect, an embodiment of the present specification provides a biometric identity authentication device, comprising at least one processor and a memory for storing processor executable instructions, wherein when the processor executes the instructions, the biometric identity authentication method described in the first aspect or the second method mentioned above is implemented.
[0024] In a sixth aspect, an embodiment of the present specification provides a computer-readable storage medium having computer instructions stored thereon, which, when executed, implement the biometric identity authentication method described in the first aspect or the second method above.
[0025] In a seventh aspect, an embodiment of the present specification provides a biometric identity authentication system, comprising: a server and a client; wherein the server comprises at least one processor and a memory for storing processor executable instructions, and when the processor executes the instructions, the method described in the second aspect is implemented, so as to provide the client with a biometric identification function for biometric identification and a biometric feature for identity authentication;
[0026] The client includes at least one processor and a memory for storing processor executable instructions. When the processor executes the instructions, it implements the method described in the first aspect above, which is used to perform biometric-based identity authentication on the user according to the biometric function and the biometric feature provided by the server.
[0027] The biometric identity authentication method, client, server, device, storage medium and system provided in this specification can use the server to fit the biometric model, obtain the biometric function, send the biometric function and biometric features to the client, and save them locally by the client. When the client receives the biometric verification request, the client can use the locally stored biometric function and biometric sample features to authenticate the user. When the client authenticates the user, it does not need to communicate with the server, but can directly use the locally stored data, realizing biometric identity authentication in an offline state, so that biometric identity authentication no longer depends on network signals. And fitting the biometric model into a biometric function reduces the complexity of calculation and improves the speed of local biometric recognition. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0029] Figure 1This is a schematic diagram of the overall process of biometric identity authentication in a scenario example of this manual;
[0030] Figure 2 It is a flowchart of an embodiment of a biometric identity authentication method provided in an embodiment of this specification;
[0031] Figure 3 is a flowchart of a biometric identity authentication method in another embodiment of the present specification;
[0032] Figure 4 is a flowchart of a biometric identity authentication method in another embodiment of the present specification;
[0033] Figure 5 This is a flow chart of face recognition identity authentication in a scenario example of this manual;
[0034] Figure 6 It is a schematic diagram of the module structure of an embodiment of a biometric identity authentication client provided in this specification;
[0035] Figure 7 It is a schematic diagram of the module structure of an embodiment of a biometric identity authentication server provided in this specification;
[0036] Figure 8 It is a hardware structure block diagram of a biometric identity authentication server in one embodiment of this specification. DETAILED DESCRIPTION
[0037] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.
[0038] Biometrics can be understood as a technology that uses the inherent physiological characteristics of the human body (such as fingerprints, facial images, irises, etc.) and behavioral characteristics (such as handwriting, voice, gait, etc.) to identify individuals through the close combination of computers, optics, acoustics, biosensors, and biostatistics principles. Biometrics is safer, more confidential, and more convenient than traditional identity authentication methods. It has the advantages of being difficult to forget, having good anti-counterfeiting performance, not easy to be forged or stolen, being "carryable", and being available anytime, anywhere.
[0039] General biometric identification technology requires matching the real-time collected biometric features with pre-stored biometric features to verify the user's identity. Usually, when performing biometric identity authentication, the client and the server need to communicate in real time. This specification embodiment provides a biometric identity authentication method, Figure 1 This is a schematic diagram of the overall process of biometric identity authentication in a scenario example in this manual. Figure 1 As shown, the biometric identity authentication process in the embodiment of this specification may include: the client first collects the user's biological sample information, and sends the collected biological sample information to the server. The server can use the biometric recognition model to perform biometric recognition on the biological sample information sample collected by the client to obtain the biological sample feature. The server can also fit the biometric recognition model to obtain the biometric recognition function, and send the biometric recognition function and the identified biological sample feature to the client, which is saved locally by the client. When the client receives the biometric verification request, it can collect the biometric information to be verified corresponding to the current biometric verification request, and use the biometric recognition function issued by the server to perform biometric recognition on the biometric information to be verified, obtain the biometric feature to be verified corresponding to the biometric verification request, and then compare the identified biometric feature to be verified with the biometric sample feature issued by the server, calculate the feature distance, and determine whether the identity authentication of the biometric verification request is passed based on the calculated feature distance.
[0040] In the biometric identity authentication method provided in this specification, the server can fit the biometric model to obtain the biometric function, send the biometric function and the biometric feature to the client, and the client can save it locally. When the client receives the biometric verification request, the client can use the locally stored biometric function and biometric feature to authenticate the user. When the client authenticates the user, it does not need to communicate with the server, but can directly use the locally stored data, thereby realizing biometric identity authentication in an offline state, so that the biometric identity authentication no longer depends on the network signal. In addition, the biometric model is fitted into the biometric function, which reduces the complexity of the calculation and improves the speed of local biometric recognition.
[0041] Figure 2It is a flowchart of an embodiment of a biometric identity authentication method provided in an embodiment of this specification. Although this specification provides method operation steps or device structures as shown in the following embodiments or drawings, more or fewer operation steps or module units may be included in the method or device based on routine or no creative labor. In the steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or drawings of this specification. When the method or module structure described is applied in an actual device, server or terminal product, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiment or drawings (for example, a parallel processor or multi-threaded processing environment, or even a distributed processing, server cluster implementation environment).
[0042] A specific implementation example is Figure 2 As shown, in one embodiment of the biometric identity authentication method provided in this specification, the method can be applied on the client side, and the client can be a terminal device such as a computer, a tablet computer, a server, a smart wearable device, a vehicle-mounted device, etc. The method may include the following steps:
[0043] Step 202: Receive a biometric verification request, wherein the biometric verification request includes biometric information to be verified.
[0044] In the specific implementation process, when the user needs to use biometrics for identity authentication, a biometric verification request can be sent to the client. For example, when a user needs to make a facial recognition payment, the user can click on the facial recognition payment function option on the client to send a biometric verification trigger request to the client. The client will turn on the camera and collect the user's facial image data as the biometric information to be verified. It should be noted that the biometric verification request, biometric registration request, etc. in the embodiments of this specification may not only represent an instruction, but may represent a process. For example, in the above example, the user sends a biometric verification trigger request to the client, the client turns on the camera, and finally collects the user's facial image data. The entire process can be called the user sending a biometric verification request to the client.
[0045] The biometric information to be verified may be biometric information required for identity authentication, such as face image or face video data, fingerprint image, voice, iris image, handwriting image, etc., which is not specifically limited in the embodiments of this specification.
[0046] Step 204: Use a biometric recognition function to perform biometric recognition on the biometric information to be verified to obtain the biometric feature to be verified; wherein the biometric recognition function is obtained and issued by the server after fitting a biometric recognition model.
[0047] In the specific implementation process, the server can use historical data to build a biometric model in advance. The historical data can be the biometric information of multiple users collected by multiple clients or the biometric information of multiple users collected by one client, such as: face image or face video data, fingerprint image, sound, iris image, handwriting image, etc. After the biometric model is built, the biometric model is fitted to obtain the biometric function. Among them, the biometric model can be a machine learning model for identifying biometric features, such as: a model for biometrics such as face recognition, fingerprint recognition, and sound recognition. The historical face image, fingerprint image, sound data, etc. can be used for model training to build a biometric model. The specific type of the biometric model can be selected based on actual needs, such as: it can be a convolutional neural network model (CNN). The specific structure and type of the biometric model are not specifically limited in the embodiments of this specification. When fitting the biometric model, the biometric sample information and the biometric features output by the biometric model can be used to analyze the mapping relationship between the independent variable and the dependent variable, and the biometric model can be simplified and fitted into a simpler model or function. Alternatively, when fitting the biometric model to obtain the biometric function, the model distillation method can also be used. Model distillation can be understood as migrating the knowledge learned by a large model or multiple models to another lightweight single model for easy deployment. Simply put, it is to use a new small model to learn the prediction results of the large model. The model distillation method can be used to use a simple model or function, namely the biometric function, to learn the prediction results of the biometric model. In the embodiment of this specification, the server can obtain the biometric function after fitting the biometric model. The biometric function can also perform biometric identification on the biometric information to obtain the biometric feature. The complexity of the biometric function is less than that of the biometric model, and the calculation speed is faster than that of the biometric model.
[0048] The server can send the fitted biometric function to the client, which is saved locally by the client. When the client receives the biometric verification request sent by the user, the client can use the biometric function sent by the server to perform biometric identification on the biometric information to be verified in the biometric verification request locally on the client to obtain the biometric feature to be verified. Biometric identification can be understood as the process of extracting features from biometric information using a biometric model or a biometric function and converting the biometric information into a feature vector. Biometric features can be understood as feature vectors obtained by converting biometric information using a biometric model or a biometric function, which can represent the characteristic attributes in the biometric information.
[0049] Step 206: Calculate the feature distance between the biometric feature to be verified and the biometric sample feature received in advance and sent by the server; wherein the biometric sample feature is obtained after the server performs biometric recognition on the biometric sample information using the biometric recognition model.
[0050] In the specific implementation process, when the client receives a biometric verification request and uses the biometric recognition function sent by the server to perform biometric recognition on the biometric information to be verified in the biometric verification request, the identified biometric feature to be verified can be compared with the biometric sample feature sent by the server to calculate the feature distance between the biometric feature to be verified and the biometric sample feature. For example, the feature distance between the biometric feature to be verified and the biometric sample feature can be calculated using a similarity algorithm, etc. Of course, other methods can also be used to calculate the distance between two features, and the embodiments of this specification do not make specific limitations. In general, the biometric features identified by the biometric recognition model are more accurate than the biometric features identified by the biometric recognition function, and are closer to the actual situation of the user. The server can use the biometric recognition model to perform biometric recognition based on the biometric sample information uploaded by the client to obtain the biometric sample features and send them to the client as a biometric template when the client performs biometric identity authentication on the user.
[0051] Figure 3 FIG. 1 is a flow chart of a biometric identity authentication method in another embodiment of the present specification. Figure 3 As shown, in some embodiments of this specification, before receiving the biometric verification request, the method further includes:
[0052] Step 302: receiving a biometric registration request, wherein the biometric registration request includes biological sample information;
[0053] Step 304: Send the biological sample information to the server, so that the server uses the biological recognition model to perform biometric recognition on the biological sample information and obtain the biological sample feature;
[0054] Step 306: Receive the biological sample feature sent by the server.
[0055] In the specific implementation process, the biometric sample feature can be determined by the server based on the biometric sample information collected by the client. For example, when a user needs to use the biometric identity authentication function, he can perform biometric registration in the client. The client can collect the biometric sample information of the registered user, that is, the user sends a biometric registration request to the client. The client can send the user's biometric sample information to the server, and the server uses the biometric recognition model to perform biometric recognition on the biometric sample information, convert the biometric sample information into a corresponding feature vector, and obtain the biometric sample feature. The server can send the obtained biometric sample feature to the client for storage, so that the client can locally compare the biometric feature to be verified identified by the biometric recognition function with the biometric sample feature. For subsequent steps, see Figure 2 As shown. Among them, the server can also use the user's biological information in the biometric registration information received by the client as training data for biometric model training, perform model training, and then use the trained biometric model to identify the biological sample features corresponding to the biological sample information after the model training is completed. The embodiments of this specification do not specifically limit the construction time of the biometric model.
[0056] It should be noted that, in general, the biometric sample feature can be understood as the biometric feature standard of the client, and each client may correspond to one or more biometric sample features as the standard for subsequent biometric identity authentication of the client.
[0057] The embodiments of this specification use a biometric recognition model on the server side to perform biometric recognition on the biological sample information registered by the user in advance to obtain biological sample characteristics, and then send the identified biological sample characteristics to the client for storage, so that the client can directly perform biometric identity authentication locally without the need for an Internet connection, thereby realizing the function of performing biometric identity authentication offline.
[0058] Step 208: Determine whether the identity verification of the biometric verification request is successful based on the feature distance.
[0059] In the specific implementation process, the feature distance can represent the similarity between the biometric feature to be verified and the biological sample feature. After the client calculates the feature distance between the biometric feature to be verified and the biological sample feature, it can determine whether the identity authentication of the received biometric authentication request is passed based on the feature distance. For example: if the feature distance is less than a preset threshold, it can be determined that the identity authentication is passed, otherwise the identity authentication fails, or other methods are used to determine whether the identity authentication is passed, and the embodiments of this specification do not make specific limitations.
[0060] For example: when user A activates the face payment function, he can perform biometric registration in the client, and the client collects user A's face image sample and sends the collected user A's face image sample to the server. The server uses the face recognition model to perform feature recognition on the face image sample sent by the client, obtains the face sample features of user A, and sends the face sample features of user A to the client. When user A consumes and uses the face payment function to pay, the client receives the biometric verification request sent by user A. The client collects user A's current face image information, and uses the face recognition function sent by the server to perform biometric recognition on the collected user A's current face image information to obtain the biometric features to be verified. The client can compare the locally identified biometric features to be verified with the face sample features of user A sent by the server, calculate the feature distance between the two, and determine whether the identity authentication of the biometric verification request issued by user A is passed based on the calculated feature distance, so as to determine whether the current face payment request can be passed.
[0061] In the biometric identity authentication method provided in the embodiments of this specification, the server can fit the biometric model to obtain the biometric function, send the biometric function and the biometric feature to the client, and the client saves it locally. When the client receives the biometric verification request, the client can use the locally stored biometric function and the biometric sample feature to authenticate the user. When the client authenticates the user, it does not need to communicate with the server, but can directly use the locally stored data, thereby realizing biometric identity authentication in an offline state, so that the biometric identity authentication no longer depends on the network signal. In addition, the biometric model is fitted into the biometric function, which reduces the complexity of the calculation and improves the speed of local biometric recognition.
[0062] Based on the above embodiments, in some embodiments of this specification, the method may further include:
[0063] receiving a verification upper limit determined by the server based on the biometric recognition model and a verification lower limit determined by the server based on the biometric recognition function;
[0064] The determining, according to the characteristic distance, whether the identity authentication of the biometric authentication request is passed includes:
[0065] If the characteristic distance is greater than the verification lower limit and less than the verification upper limit, it is determined that the verification request identity verification is successful.
[0066] In the specific implementation process, the server can also determine the verification upper limit of the identity authentication based on the biometric recognition model. The verification upper limit can be understood as the recognition accuracy of the biometric recognition model, which can be determined based on the training data of the biometric recognition model. Of course, the calculation accuracy of the biometric recognition model can also be obtained by using the test data to determine the verification upper limit. Similarly, the server can also determine the verification lower limit of the identity authentication based on the biometric recognition function. The biometric recognition function is obtained based on the fitting of the biometric recognition model, and the biometric recognition accuracy of the biometric recognition function is less than the biometric recognition accuracy of the biometric recognition model. The verification lower limit can be understood as the recognition error between the recognition result of the biometric recognition function and the recognition result of the biometric recognition model, or the recognition accuracy of the biometric recognition function can also be used as the verification lower limit, which is not specifically limited in the embodiments of this specification. The server can send the determined verification upper limit and verification lower limit to the client. When the client calculates the feature distance between the biometric feature to be verified and the feature of the biological sample, the calculated feature distance can be compared with the verification upper limit and verification lower limit. If the feature distance is between the verification upper limit and verification lower limit, it is determined that the identity authentication of the biometric verification request is passed. Otherwise, it is determined that the identity authentication of the biometric verification request is not passed.
[0067] In the embodiments of the present specification, during identity authentication, not only the recognition accuracy of the biometric model is considered, but also the verification lower limit is obtained by using the biometric function fitted by the biometric model. During identity authentication, the verification upper limit and the verification lower limit are comprehensively considered, which can not only ensure the reliability of the biometric identity authentication result, but also prevent the client from directly copying the biometric features as the biometric features in the verification stage, thereby avoiding the theft of biological sample features, resulting in errors in biometric identity authentication, causing losses to users, and causing leakage of user privacy information.
[0068] On the basis of the above embodiments, in some embodiments of this specification, when receiving the biological sample feature, the verification upper limit, and the verification lower limit sent by the server, the method includes:
[0069] Receive confidential information sent by the server, wherein the confidential information includes the encrypted biological sample feature obtained by the server encrypting the biological sample feature with the public key and the public key, or the confidential information includes the encrypted biological sample feature obtained by the server encrypting the biological sample feature with the public key, the encrypted verification upper limit obtained by encrypting the verification upper limit with the public key, the encrypted verification lower limit obtained by encrypting the verification lower limit with the public key, and the public key.
[0070] In a specific implementation process, after obtaining the biological sample characteristics of the user during registration, the server may encrypt the biological sample characteristics, the verification upper limit, and the verification lower limit, and then send the obtained encrypted biological sample characteristics, the encrypted verification upper limit, and the encrypted verification lower limit. In one embodiment, the server sends the encrypted biological sample characteristics and the corresponding public key to the client for storage, so as to avoid the client being attacked and causing the user's biological characteristics to be stolen, resulting in inaccurate user identity authentication. In another embodiment, the server may send the encrypted biological sample characteristics, the encrypted verification upper limit, the encrypted verification lower limit, and the public key used for encryption as secret information to the client for storage, so that the client can directly verify the user's identity locally, and can avoid the client being attacked and causing the user's biological characteristics to be stolen, resulting in inaccurate user identity authentication. Among them, the encryption method for the biological sample characteristics, the verification upper limit, and the verification lower limit can be a homomorphic encryption algorithm, and the server can generate a homomorphic encryption key, and the key can include a public key and a private key, and the public key can be used to encrypt the biological sample characteristics, the verification upper limit, and the verification lower limit. When the encrypted biological sample characteristics, the encrypted verification upper limit, and the encrypted verification lower limit are sent to the client, the public key used for encryption is sent to the client for storage, and the private key is saved by the server itself.
[0071] In the embodiments of this specification, the server uses an encryption algorithm to encrypt the biological sample features, the upper verification limit, and the lower verification limit, and sends the encrypted information to the client for storage, so as to prevent the client from being attacked, resulting in the theft of the data required for biometric identity authentication, and causing biometric identity authentication errors. At the same time, the encryption process is performed on the server side, which can reduce the encryption and verification time of the client, and improve the reliability and efficiency of offline biometric identity authentication.
[0072] On the basis of the above embodiments, in some embodiments of this specification, when the secret information includes the encrypted biological sample feature obtained by the server encrypting the biological sample feature using a public key and the public key, the calculating the feature distance between the biological feature to be verified and the biological sample feature sent by the server in advance includes:
[0073] Encrypting the biometric feature to be verified by using the public key to obtain an encrypted biometric feature to be verified;
[0074] Calculating an encrypted feature distance between the encrypted biometric feature to be verified and the encrypted biometric sample feature;
[0075] The determining, according to the characteristic distance, whether the identity authentication of the biometric authentication request is passed includes:
[0076] Sending the encrypted feature distance to the server;
[0077] Receive the identity authentication result of the biometric authentication request determined by the server by comparing the encryption feature distance with an encryption verification upper limit and an encryption verification lower limit.
[0078] In the specific implementation process, when the client calculates the feature distance between the biometric feature to be verified and the biometric sample feature, it can use the public key sent by the server to encrypt the biometric feature to be verified to obtain the encrypted biometric feature to be verified. Then perform the encrypted distance calculation to calculate the encrypted feature distance between the encrypted biometric feature to be verified and the encrypted biometric sample feature, such as: the similarity between the encrypted biometric feature to be verified and the encrypted biometric sample feature can be calculated. After calculating the encrypted feature distance, the client can send the calculated encrypted feature distance to the server, and the server can compare the encrypted feature distance with the encryption verification upper limit and the encryption verification lower limit obtained by using public key encryption to determine the identity authentication result of the current biometric verification request. For example: if the server finds that the encryption feature distance is between the encryption verification upper limit and the encryption verification lower limit after comparison, it can be determined that the user's identity authentication is passed, and the identity authentication result can be sent to the client for the client to perform the next business processing.
[0079] In the embodiments of this specification, the server encrypts the user's biometric sample features and sends them to the client to prevent the client from being attacked and causing the user's biometric information to be stolen. At the same time, the client can calculate the encrypted feature distance between the biometric feature to be verified and the biometric sample feature based on the encrypted biometric sample features, public key, etc. sent by the server. The client only needs to send the calculated encrypted feature distance to the server, and the server can verify the user's identity without sending the collected user's biometric information to the server. The encrypted feature distance is generally a numerical value, and the data transmission volume is relatively small, far less than the transmission volume of the user's biometric information. In the case of poor network communication but not completely without network, the user identity recognition function can also be realized, and the security of the user's privacy information can be ensured.
[0080] On the basis of the above embodiments, in some embodiments of this specification, when the secret information includes the encrypted biological sample feature, the encrypted verification upper limit, the encrypted verification lower limit and the public key, the calculating of the feature distance between the biological feature to be verified and the biological sample feature received in advance and sent by the server includes:
[0081] Encrypting the biometric feature to be verified by using the public key to obtain an encrypted biometric feature to be verified;
[0082] Calculating an encrypted feature distance between the encrypted biometric feature to be verified and the encrypted biometric sample feature;
[0083] The determining, according to the characteristic distance, whether the identity authentication of the biometric authentication request is passed includes:
[0084] Whether the identity verification of the biometric verification request is passed is determined according to the encryption feature distance, the encryption verification upper limit, and the encryption verification lower limit.
[0085] In the specific implementation process, when calculating the feature distance between the biometric feature to be verified and the biometric sample feature, the client can use the public key sent by the server to encrypt the biometric feature to be verified to obtain the encrypted biometric feature to be verified. Then perform the encrypted distance calculation to calculate the encrypted feature distance between the encrypted biometric feature to be verified and the encrypted biometric sample feature, such as: the similarity between the encrypted biometric feature to be verified and the encrypted biometric sample feature can be calculated. After calculating the encrypted feature distance, it can be determined whether the identity authentication of the biometric verification request is passed based on the encrypted feature distance, the encryption verification upper limit, and the encryption verification lower limit. For example, if the encryption feature distance is between the encryption verification upper limit and the encryption verification lower limit, it is determined that the identity authentication of the biometric verification request is passed, otherwise it is determined that the identity authentication of the biometric verification request is not passed.
[0086] The embodiments of this specification store secret biometric features, verification upper and lower limits on the client, so that the client can perform secret distance comparison locally, and achieve the purpose of user identity authentication even without a communication network. At the same time, it prevents information leakage and biometric verification errors caused by malicious attacks.
[0087] Based on the above embodiments, in some embodiments of this specification, the method further includes:
[0088] After completing identity authentication for the biometric verification request, when it is determined that the communication status is normal, receiving the updated encryption information returned by the server after receiving the updated encryption information request.
[0089] In the specific implementation process, after the client completes the identity authentication of a biometric verification request, when it is determined that the communication status is normal, such as: when the user arrives in an area with good network communication status, the server can use the updated public key to update the secret information sent to the client and resend the updated secret information to the client. For example, the biometric sample characteristics, the verification upper limit, and the verification lower limit can be re-encrypted, and the encrypted biometric sample characteristics obtained after the re-encryption and the updated public key can be sent to the client as the updated secret information, or the encrypted biometric sample characteristics, the encrypted verification upper limit, the encrypted verification lower limit, and the updated public key obtained after the re-encryption can be sent to the client as the updated secret information.
[0090] In the embodiments of the present specification, after completing an identity authentication, the encryption key and related confidential data are updated when the communication is restored, so as to avoid the client being attacked and causing the confidential data in the client to be leaked, thereby improving the accuracy and reliability of biometric identity authentication.
[0091] Figure 4 is a flowchart of a biometric identity authentication method in another embodiment of this specification, such as Figure 4 As shown, the method can be applied in a server, and the method may include:
[0092] Step 402: Receive biometric registration information uploaded by the client, where the biometric registration information includes biological sample information.
[0093] In the specific implementation process, when a user needs to use the biometric identity authentication function, he can perform biometric registration in the client, and the client can collect the biometric sample information of the registered user, that is, the user sends a biometric registration request to the client. The client can send the biometric registration information including the user's biometric sample information to the server.
[0094] Step 404: Use a biometric recognition model to perform image recognition on the biological sample information to obtain biological sample features corresponding to the biological sample information.
[0095] In the specific implementation process, after receiving the biometric registration information uploaded by the client, the server uses the biometric recognition model to perform biometric recognition on the biological sample information, converts the biological sample information into a corresponding feature vector, and obtains the biological sample feature. The biometric recognition model can be constructed using historical data, and the historical data can be the user's biological information collected by the client, such as: face image, fingerprint image, voice, iris image, handwriting image, etc.
[0096] It should be noted that the biometric model can be constructed by using historical data collected by multiple clients for model training before the server receives the biological sample information collected when the user registers and uploaded by the client. Alternatively, when receiving the biological sample information collected when the user registers and uploaded by the client, the biological information of the user in the biometric registration information received by the client is used as training data for biometric model training to train the model, and after the model training is completed, the trained biometric model is used to identify the biological sample features corresponding to the biological sample information. The embodiments of this specification do not specifically limit the construction time of the biometric model.
[0097] Step 406: Send the biological sample feature and the biometric function obtained after fitting the biometric model to the client, so that the client uses the biometric function and the biological sample feature to authenticate the received biometric verification request.
[0098] In the specific implementation process, the server can use historical data to construct a biometric model in advance, then fit the biometric model to obtain a biometric function, and then send the obtained biological sample features and the biometric function to the client for storage, so that the client can compare the biological features to be verified identified by the biometric function with the biological sample features locally. Among them, the process of fitting the biometric model to obtain the biometric function can refer to the records of the above embodiment, which will not be repeated here. Of course, the server can receive biological sample information uploaded by multiple clients, and after performing biometric identification using the biometric model, send the identified biological sample features to the corresponding client as a biometric template for identity authentication.
[0099] The biometric identity authentication method provided in the embodiments of this specification uses a biometric recognition model to perform biometric recognition on the biological sample information registered by the user on the server side in advance to obtain the biological sample characteristics, and then sends the identified biological sample characteristics to the client for storage. At the same time, the server can also fit the biometric recognition model to obtain a biometric recognition function, and send the biometric recognition function to the client. When the client receives the biometric verification request, the client can use the locally stored biometric recognition function and biometric characteristics to authenticate the user. When the client authenticates the user, it does not need to communicate with the server, but can directly use the locally stored data, thereby realizing biometric identity authentication in an offline state, so that biometric identity authentication no longer depends on network signals. In addition, the biometric recognition model is fitted into a biometric recognition function, which reduces the complexity of the calculation and improves the speed of local biometric recognition.
[0100] Based on the above embodiments, in some embodiments of this specification, the method may further include:
[0101] Determine an upper verification limit based on the biometric recognition model, and determine a lower verification limit based on the biometric recognition function;
[0102] The verification upper limit and the verification lower limit are sent to the client, so that after receiving the biometric verification request, the client uses the biometric recognition function, the biological sample feature, the verification upper limit and the verification lower limit to authenticate the biometric verification request.
[0103] In the specific implementation process, the server can also determine the verification upper limit of the identity authentication based on the biometric recognition model. The verification upper limit can be understood as the recognition accuracy of the biometric recognition model, which can be determined based on the training data of the biometric recognition model. Of course, the calculation accuracy of the biometric recognition model can also be obtained by using the test data to determine the verification upper limit. Similarly, the server can also determine the verification lower limit of the identity authentication based on the biometric recognition function. The biometric recognition function is obtained based on the fitting of the biometric recognition model, and the biometric recognition accuracy of the biometric recognition function is less than the biometric recognition accuracy of the biometric recognition model. The verification lower limit can be understood as the recognition error between the recognition result of the biometric recognition function and the recognition result of the biometric recognition model, or the recognition accuracy of the biometric recognition function can also be used as the verification lower limit, which is not specifically limited in the embodiments of this specification. The server can send the determined verification upper limit and verification lower limit to the client. When the client calculates the feature distance between the biometric feature to be verified and the feature of the biological sample, the calculated feature distance can be compared with the verification upper limit and verification lower limit. If the feature distance is between the verification upper limit and verification lower limit, it is determined that the identity authentication of the biometric verification request is passed. Otherwise, it is determined that the identity authentication of the biometric verification request is not passed.
[0104] In the embodiments of the present specification, during identity authentication, not only the recognition accuracy of the biometric model is considered, but also the verification lower limit is obtained by using the biometric function fitted by the biometric model. During identity authentication, the verification upper limit and the verification lower limit are comprehensively considered, which can not only ensure the reliability of the biometric identity authentication result, but also prevent the client from directly copying the biometric features as the biometric features in the verification stage, thereby avoiding the theft of biological sample features, resulting in errors in biometric identity authentication and the resulting losses to users.
[0105] On the basis of the above embodiments, in some embodiments of this specification, when the biological sample feature, the biometric function obtained after fitting the biometric model, the verification upper limit, and the verification lower limit are sent to the client, the method includes:
[0106] Generate an encryption key, and use the public key in the encryption key to encrypt the biometric sample feature, the verification upper limit, and the verification lower limit respectively, to obtain the encrypted biometric sample feature, the encrypted verification upper limit, and the encrypted verification lower limit respectively, and send the encrypted biometric sample feature and the public key as confidential information to the client, or send the encrypted biometric sample feature, the encrypted verification upper limit, the encrypted verification lower limit, and the public key in the encryption key as confidential information to the client, so that after receiving the biometric verification request, the client uses the confidential information to authenticate the identity of the biometric verification request.
[0107] In a specific implementation process, after obtaining the biological sample characteristics of the user during registration, the server may encrypt the biological sample characteristics, the verification upper limit, and the verification lower limit, and then send the obtained encrypted biological sample characteristics, the encrypted verification upper limit, and the encrypted verification lower limit. In one embodiment, the server sends the encrypted biological sample characteristics and the corresponding public key to the client for storage to avoid the user's biological characteristics being stolen due to attacks on the client, resulting in inaccurate user identity authentication. In another embodiment, the server may send the encrypted biological sample characteristics, the encrypted verification upper limit, the encrypted verification lower limit, and the public key used for encryption as secret information to the client for storage, so that the client can directly verify the user's identity locally, and can avoid the user's biological characteristics being stolen due to attacks on the client, resulting in inaccurate user identity authentication. Among them, the encryption method for the biological sample characteristics, the verification upper limit, and the verification lower limit can be a homomorphic encryption algorithm, and the server can generate a homomorphic encryption key, and the key can include a public key and a private key, and the public key can be used to encrypt the biological sample characteristics, the verification upper limit, and the verification lower limit. When the encrypted biological sample characteristics, the encrypted verification upper limit, and the encrypted verification lower limit are sent to the client, the public key used for encryption is sent to the client for storage.
[0108] In the embodiments of this specification, the server uses an encryption algorithm to encrypt the biological sample features, the upper verification limit, and the lower verification limit, and sends the encrypted information to the client for storage, so as to prevent the client from being attacked, resulting in the theft of the data required for biometric identity authentication, and causing biometric identity authentication errors. At the same time, the encryption process is performed on the server side, which can reduce the encryption and verification time of the client, and improve the reliability and efficiency of offline biometric identity authentication.
[0109] Based on the above embodiments, in some embodiments of this specification, the method further includes:
[0110] The public key and the private key in the encryption key are updated, the secret information is updated using the updated public key to obtain updated secret information, and the updated secret information is sent to the client.
[0111] In the specific implementation process, after the client completes the identity authentication of a biometric verification request, the server can update the public key and private key, and use the updated public key to re-encrypt the biometric sample characteristics, verification upper limit, and verification lower limit. When it is determined that the communication status is normal, such as: when the user arrives in an area with good network communication status, the server can use the updated public key to update the confidential information sent to the client. For example, the biometric sample characteristics, verification upper limit, and verification lower limit can be re-encrypted, and the encrypted biometric sample characteristics obtained after re-encryption and the updated public key can be sent to the client as updated confidential information, or the encrypted biometric sample characteristics obtained after re-encryption, the encrypted verification upper limit, the encrypted verification lower limit, and the updated public key can be sent to the client as updated confidential information.
[0112] In the embodiments of the present specification, after completing an identity authentication, the encryption key and related confidential data are updated when the communication is restored, so as to avoid the client being attacked and causing the confidential data in the client to be leaked, thereby improving the accuracy and reliability of biometric identity authentication.
[0113] Based on the above embodiments, in some embodiments of this specification, before receiving the biometric registration information uploaded by the client, the method further includes:
[0114] Receive biological sample information collected by the client;
[0115] Using the biological sample information to perform model training and construct the biometric recognition model;
[0116] Inputting the biological fitting information into the biological recognition model to obtain biological characteristic model data output by the biological recognition model;
[0117] The biometric recognition model is fitted according to the biometric fitting information and the biometric feature model data to obtain the biometric recognition function.
[0118] In the specific implementation process, the server can pre-construct a biometric model, and then use the biometric sample information collected by the client to train the biometric model until the model converges and the biometric model is constructed. Then the biological fitting information is input into the constructed biometric model, and the biometric model outputs the biological model data. The model is fitted using the biological fitting information and the biological model data output by the biometric model to obtain the biometric function. Among them, the biological sample information can be biological information collected by one or more clients, such as: face image, fingerprint image, iris image, sound, etc. The biological fitting information can be the same as the biological sample information, or it can be biological information re-collected by the client, which is not specifically limited in the embodiments of this specification. The specific forms of the biometric model and the biometric function can refer to the records of the above embodiments, and will not be repeated here.
[0119] Based on the above embodiments, in some embodiments of this specification, the determining of the verification upper limit based on the biometric recognition model and the determining of the verification lower limit based on the biometric recognition function include:
[0120] Determining the verification upper limit according to the recognition accuracy of the biometric recognition model;
[0121] Inputting the biometric fitting information into the biometric recognition function to obtain biometric feature fitting data;
[0122] Calculating the recognition error corresponding to the biometric recognition function according to the biometric fitting data and the biometric model data;
[0123] The verification lower limit is determined according to the identification error.
[0124] In the specific implementation process, the server can determine the verification upper limit of the identity authentication based on the recognition accuracy of the biometric recognition model, and can determine it based on the training data of the biometric recognition model. Of course, the calculation accuracy of the biometric recognition model can also be obtained by using test data to determine the verification upper limit. The server can also input the biological fitting information into the biometric recognition function to obtain the biological feature fitting data output by the biometric recognition function, and then compare the biological feature model data output by the biometric recognition model based on the biological fitting information and the biological feature fitting data output by the biometric recognition function, calculate the biometric recognition error value between the biometric recognition function and the biometric recognition model, and determine the verification lower limit based on the calculated biometric recognition error value. The server can send the determined verification upper limit and verification lower limit to the client. After the client calculates the feature distance between the biometric feature to be verified and the biometric sample feature, it can compare the calculated feature distance with the verification upper limit and verification lower limit. If the feature distance is between the verification upper limit and verification lower limit, it is determined that the identity authentication of the biometric verification request is passed. Otherwise, it is determined that the identity authentication of the biometric verification request is not passed.
[0125] In the embodiments of the present specification, during identity authentication, not only the recognition accuracy of the biometric model is considered, but also the verification lower limit is obtained by using the biometric function fitted by the biometric model. During identity authentication, the verification upper limit and the verification lower limit are comprehensively considered, which can not only ensure the reliability of the biometric identity authentication result, but also prevent the client from directly copying the biometric features as the problem of biometric feature verification in the verification stage, thereby avoiding the theft of biological sample features, resulting in errors in biometric identity authentication and losses to users.
[0126] Figure 5 This is a flow chart of face recognition identity authentication in a scenario example of this manual, such as Figure 5 As shown, the process of performing face recognition using the biometric identity authentication method in the embodiment of this specification may include:
[0127] Step 1: Face recognition model training
[0128] 1.1 Model Training
[0129] The server builds a face recognition model and uses the face image information collected by the client as training data D. After multiple forward propagations and backward propagations, the model gradually converges to obtain the final model M(D). The verification upper limit of the model is t.
[0130] The face recognition model can use the convolutional neural network model CNN. CNN can be understood as a multi-layer artificial neural network specially designed to process two-dimensional input data. Each layer in the network is composed of multiple two-dimensional planes, and each plane is composed of multiple independent neurons. The neurons of two adjacent layers are connected to each other, and there is no connection between the neurons in the same layer. The basic structure of CNN consists of an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. There are generally several convolutional layers and pooling layers, which are set in an alternating manner, that is, a convolutional layer is connected to a pooling layer, and a convolutional layer is connected after the pooling layer, and so on.
[0131] 1.2 Model Fitting
[0132] According to the input image data D1 and the facial feature data X output by the face recognition model, the model M(D) is fitted to obtain the fitting function F(D), where F(D)≈X. Then, using statistical information, the verification lower limit δ of |F(D)-X| is obtained.
[0133] Step 2: Face Registration
[0134] 2.1 Generating Face Representation
[0135] The user registers face recognition information on a mobile phone or other client, and the local client device collects face data and sends the face image information to the remote server. The server calculates the face representation X' through the model M(D). The face representation is a compact and discriminable feature vector converted from a face image through a trained recognition model, which can also be called a face template.
[0136] 2.2 Face Representation Encryption
[0137] The server generates a homomorphic encryption key<pk,sk> , where the public key is pk and the private key is sk. The face representation X' is encrypted using the homomorphic encryption algorithm to obtain<X’> , encrypt the threshold to get <t>and <δ>.
[0138] 2.3 Model and dense feature delivery
[0139] The server sends the public key pk, model fitting function F(D), and secret state feature<X’> , threshold upper limit <t>And the lower threshold <δ> are sent to the client.
[0140] Step 3: Face verification
[0141] 3.1 Generate facial features
[0142] When performing face verification, the client collects the user's face image D~ and uses the model fitting function F(D) to obtain the face feature X~ that needs to be verified.
[0143] 3.2 Obtaining feature distance
[0144] The client uses the homomorphic encryption public key pk to encrypt the feature X~<X~> , and then calculate the dense Hamming distance between the face representation and the face feature to be verified <d>Of course, according to actual needs, other methods for calculating the distance between two features can also be used to obtain the distance between the face representation and the face feature to be verified, such as: Euclidean distance, cosine similarity, etc. to calculate the distance between the face representation and the face feature to be verified, which is not specifically limited in the embodiments of this specification.
[0145] 3.3 Compare and verify
[0146] Using the homomorphic encryption comparison algorithm, we get <d>The relationship between the verification upper limit and the verification lower limit is as follows: <d> < <t>, the verification passes, otherwise the verification fails.
[0147] Step 4: Key Update
[0148] After completing step 3 once using key pk, when the communication status is normal, repeat steps 2.2-2.3 to update the secret information stored in the client.
[0149] The method provided in the embodiment of this specification reduces the complexity of calculation by fitting a deep CNN network and sending it to the client, thereby improving the local calculation speed of the client, and can realize offline face recognition. By outputting statistics of the fitting function and using the fitting error, the lower limit of the threshold passed in the face verification stage is obtained, thereby preventing the copying and attack of the secret face features in the verification process, and improving the security of the verification stage. The face representation is stored in the client in the form of ciphertext, and even if it is stolen, the plaintext information cannot be obtained, and a secret distance comparison is performed to prevent information leakage and malicious attacks. The encryption process is performed on the server side, thereby reducing the client verification time. After completing a face verification, when the communication returns to normal, the key and its related secret data are updated to prevent the forgery of face features and reduce the risk of attack.
[0150] In this specification, each embodiment of the above method is described in a progressive manner, and the same or similar parts between the embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments. For relevant parts, refer to the partial description of the method embodiment.
[0151] Based on the biometric identity authentication method described above, one or more embodiments of this specification also provide a client and server for biometric identity authentication. The client and server may include a system (including a distributed system), software (application), module, component, server, client, etc. that uses the method described in the embodiment of this specification and is combined with a device for necessary implementation hardware. Based on the same innovative concept, the client and server in one or more embodiments provided in the embodiment of this specification are as described in the following embodiments. Since the implementation scheme and method for solving the problem of the client and server are similar, the implementation of the specific client and server in the embodiment of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can implement a combination of software and / or hardware for predetermined functions. Although the client and server described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.
[0152] Specifically, Figure 6 is a schematic diagram of the module structure of an embodiment of a biometric identity authentication client provided in this specification. The client can be understood as the client in the above embodiment, such as Figure 6 As shown, the biometric authentication client provided in this specification may include:
[0153] A verification request receiving module 61, configured to receive a biometric verification request, wherein the biometric verification request includes biometric information to be verified;
[0154] A biometric identification module 62, configured to perform biometric identification on the biometric information to be verified using a biometric identification function to obtain a biometric feature to be verified; wherein the biometric identification function is obtained and issued by the server after fitting a biometric identification model;
[0155] The feature distance calculation module 63 is used to calculate the feature distance between the biological feature to be verified and the biological sample feature received in advance and sent by the server; wherein the biological sample feature is obtained after the server performs biometric identification on the biological sample information using the biometric identification model;
[0156] The identity verification module 64 is used to determine whether the identity verification of the biometric verification request is successful based on the characteristic distance.
[0157] In the biometric identity authentication client provided in the embodiments of this specification, the server can fit the biometric model to obtain the biometric function, send the biometric function and the biometric feature to the client, and the client saves it locally. When the client receives the biometric verification request, the client can use the locally stored biometric function and the biometric sample feature to authenticate the user. When the client authenticates the user, it does not need to communicate with the server, but can directly use the locally stored data, thereby realizing biometric identity authentication in an offline state, so that the biometric identity authentication no longer depends on the network signal. In addition, the biometric model is fitted into the biometric function, which reduces the complexity of the calculation and improves the speed of local biometric recognition.
[0158] In some embodiments of this specification, the client further includes a verification threshold receiving module, which is used to:
[0159] receiving a verification upper limit determined by the server based on the biometric recognition model and a verification lower limit determined by the server based on the biometric recognition function;
[0160] The determining, according to the characteristic distance, whether the identity authentication of the biometric authentication request is passed includes:
[0161] If the characteristic distance is greater than the verification lower limit and less than the verification upper limit, it is determined that the verification request identity verification is successful.
[0162] The biometric identity authentication client provided in the embodiments of this specification not only considers the recognition accuracy of the biometric model during identity authentication, but also uses the biometric function fitted by the biometric model to obtain the verification lower limit. During identity authentication, the verification upper limit and the verification lower limit are comprehensively considered, which can not only ensure the reliability of the biometric identity authentication results, but also prevent the client from directly copying the biometric features as the problem of biometric feature verification in the verification stage, thereby avoiding the theft of biological sample features, resulting in errors in biometric identity authentication and losses to users.
[0163] In some embodiments of this specification, the client further includes a registration module for:
[0164] Before receiving the biometric verification request, receiving a biometric registration request, wherein the biometric registration request includes biometric sample information;
[0165] Sending the biological sample information to the server, so that the server obtains the biological sample feature after performing biometric recognition on the biological sample information using the biometric recognition model;
[0166] Receive the biological sample feature sent by the server.
[0167] The biometric identity authentication client provided in the embodiments of this specification performs biometric identification on the biological sample information registered by the user using a biometric identification model on the server side in advance to obtain biological sample characteristics, and then sends the identified biological sample characteristics to the client for storage, so that the client can directly perform biometric identity authentication locally without the need for an Internet connection, thereby realizing the function of performing biometric identity authentication offline.
[0168] In some embodiments of this specification, the verification threshold receiving module is specifically used to:
[0169] When receiving the confidential information sent by the server, the confidential information includes the encrypted biological sample feature obtained by the server encrypting the biological sample feature with the public key and the public key, or the confidential information includes the encrypted biological sample feature obtained by the server encrypting the biological sample feature with the public key, the encrypted verification upper limit obtained by encrypting the verification upper limit with the public key, the encrypted verification lower limit obtained by encrypting the verification lower limit with the public key, and the public key.
[0170] In the biometric identity authentication client provided in the embodiments of this specification, the server uses an encryption algorithm to encrypt the biological sample characteristics, the upper limit of verification, and the lower limit of verification, and sends the encrypted information to the client for storage, so as to prevent the client from being attacked, resulting in the theft of the data required for biometric identity authentication, and causing biometric identity authentication errors. At the same time, the encryption process is performed on the server side, which can reduce the encryption and verification time of the client, and improve the reliability and efficiency of offline biometric identity authentication.
[0171] In some embodiments of this specification, the feature distance calculation module is specifically used to:
[0172] Encrypting the biometric feature to be verified by using the public key to obtain an encrypted biometric feature to be verified;
[0173] Calculating an encrypted feature distance between the encrypted biometric feature to be verified and the encrypted biometric sample feature;
[0174] The identity authentication module is specifically used for:
[0175] Sending the encrypted feature distance to the server;
[0176] The receiving server compares the encryption feature distance with an encryption verification upper limit and an encryption verification lower limit to determine an identity authentication result of the biometric verification request.
[0177] In the embodiment of this specification, the server encrypts the user's biological sample features and sends them to the client to prevent the client from being attacked and causing the user's biometric information to be stolen. At the same time, the client can calculate the encrypted feature distance between the biometric feature to be verified and the biometric sample feature based on the encrypted biometric sample features, public key, etc. sent by the server. The client only needs to send the calculated encrypted feature distance to the server, and the server can verify the user's identity without sending the collected user's biometric information to the server. The encrypted feature distance is generally a numerical value, and the data transmission volume is relatively small, far less than the transmission volume of the user's biometric information. In the case of poor network communication, the user identity recognition function can also be realized, and the security of the user's privacy information can be ensured.
[0178] In some embodiments of this specification, the feature distance calculation module is specifically used to:
[0179] Encrypting the biometric feature to be verified by using the public key to obtain an encrypted biometric feature to be verified;
[0180] Calculating an encrypted feature distance between the encrypted biometric feature to be verified and the encrypted biometric sample feature;
[0181] The determining, according to the characteristic distance, whether the identity authentication of the biometric authentication request is passed includes:
[0182] Whether the identity verification of the biometric verification request is passed is determined according to the encryption feature distance, the encryption verification upper limit, and the encryption verification lower limit.
[0183] The biometric identity authentication client provided in the embodiments of this specification prevents information leakage and biometric verification errors caused by malicious attacks by storing secret biometric features, verification upper limits, and verification lower limits on the client and then performing secret distance comparison.
[0184] In some embodiments of this specification, the client further includes an update encryption information receiving module, which is used to:
[0185] After completing identity authentication for the biometric authentication request, when it is determined that the communication status is normal, receiving the updated confidentiality information returned by the server.
[0186] The biometric identity authentication client provided in the embodiments of this specification, after completing an identity authentication, updates the encryption key and related confidential data when communication is restored, thereby preventing the client from being attacked and causing leakage of confidential data in the client, and improving the accuracy and reliability of biometric identity authentication.
[0187] Figure 7 is a schematic diagram of the module structure of an embodiment of a biometric identity authentication server provided in this specification. The server can be understood as the server in the above embodiment, such as Figure 7 As shown, the biometric authentication server provided in this specification may include:
[0188] A biometric image receiving module 71, configured to receive biometric registration information uploaded by a client, wherein the biometric registration information includes biometric sample information;
[0189] A biometric feature recognition module 72, configured to perform image recognition on the biological sample information using a biometric recognition model to obtain biological sample features corresponding to the biological sample information;
[0190] The identification data sending module 73 is used to send the biological sample characteristics and the biological recognition function obtained after fitting the biological recognition model to the client, so that the client can use the biometric recognition function and the biological sample characteristics to authenticate the received biometric verification request.
[0191] The biometric identity authentication server provided in the embodiments of this specification uses a biometric recognition model to perform biometric recognition on the biological sample information registered by the user on the server side in advance to obtain the biological sample characteristics, and then sends the identified biological sample characteristics to the client for storage. At the same time, the server can also fit the biometric recognition model to obtain a biometric recognition function, and send the biometric recognition function to the client. When the client receives the biometric verification request, the client can use the locally stored biometric recognition function and biometric characteristics to authenticate the user. When the client authenticates the user, it does not need to communicate with the server, but can directly use the locally stored data, thereby realizing biometric identity authentication in an offline state, so that biometric identity authentication no longer depends on network signals. In addition, the biometric recognition model is fitted into a biometric recognition function, which reduces the complexity of the calculation and improves the speed of local biometric recognition.
[0192] In some embodiments of this specification, the identification data sending module is also used to:
[0193] Determine an upper verification limit based on the biometric recognition model, and determine a lower verification limit based on the biometric recognition function;
[0194] The verification upper limit and the verification lower limit are sent to the client, so that after receiving the biometric verification request, the client uses the biometric recognition function, the biological sample feature, the verification upper limit and the verification lower limit to authenticate the biometric verification request.
[0195] The biometric identity authentication server provided in the embodiments of this specification not only considers the recognition accuracy of the biometric model during identity authentication, but also uses the biometric function fitted by the biometric model to obtain the verification lower limit. During identity authentication, the verification upper limit and the verification lower limit are comprehensively considered, which can not only ensure the reliability of the biometric identity authentication results, but also prevent the client from directly copying the biometric features as the problem of biometric feature verification in the verification stage, thereby avoiding the theft of biological sample features, resulting in errors in biometric identity authentication and losses to users.
[0196] In some embodiments of this specification, the identification data sending module is specifically used for:
[0197] Generate an encryption key, and use a public key in the encryption key to encrypt the biological sample feature, the verification upper limit, and the verification lower limit, respectively, to obtain an encrypted biological sample feature, an encrypted verification upper limit, and an encrypted verification lower limit, respectively;
[0198] The encrypted biometric sample feature and the public key are sent to the client as confidential information, or the encrypted biometric sample feature, the encryption verification upper limit, the encryption verification lower limit and the public key in the encryption key are sent to the client as confidential information, so that after receiving the biometric verification request, the client uses the confidential information to authenticate the biometric verification request.
[0199] The biometric authentication server provided in the embodiments of this specification uses an encryption algorithm to encrypt biological sample features, verification upper limits, and verification lower limits, and sends the encrypted information to the client for storage, thereby preventing the client from being attacked, resulting in the theft of data required for biometric authentication, and causing biometric authentication errors. At the same time, the encryption process is performed on the server side, which can reduce the encryption and verification time of the client, and improve the reliability and efficiency of offline biometric authentication.
[0200] In some embodiments of this specification, the server further includes an encryption information updating module, which is used to:
[0201] The public key and the private key in the encryption key are updated, the secret information is updated using the updated public key to obtain updated secret information, and the updated secret information is sent to the client.
[0202] The biometric identity authentication server provided in the embodiment of this specification, after completing an identity authentication, updates the encryption key and related confidential data when the communication is restored, thereby preventing the client from being attacked and causing the confidential data in the client to be leaked, thereby improving the accuracy and reliability of biometric identity authentication.
[0203] It should be noted that the client and server described above may also include other implementations according to the description of the corresponding method embodiment. The specific implementation methods may refer to the description of the corresponding method embodiment, which will not be described one by one here.
[0204] The embodiment of this specification also provides a biometric identity authentication device, including: at least one processor and a memory for storing processor executable instructions, and the processor implements the biometric identity authentication method of the above embodiment when executing the instructions, such as:
[0205] Receiving a biometric verification request, wherein the biometric verification request includes biometric information to be verified;
[0206] Performing biometric identification on the biometric information to be verified using a biometric identification function to obtain a biometric feature to be verified; wherein the biometric identification function is obtained and issued by the server after fitting a biometric identification model;
[0207] Calculating a feature distance between the biometric feature to be verified and the biometric sample feature received in advance and sent by the server; wherein the biometric sample feature is obtained after the server performs biometric recognition on the biometric sample information using the biometric recognition model;
[0208] Determine whether the identity verification request passes based on the feature distance.
[0209] or, receiving biometric registration information uploaded by a client, wherein the biometric registration information includes biological sample information;
[0210] Performing image recognition on the biological sample information using a biological recognition model to obtain biological sample features corresponding to the biological sample information;
[0211] The biological sample feature and the biometric function obtained after fitting the biometric model are sent to the client, so that the client uses the biometric function and the biological sample feature to authenticate the received biometric verification request.
[0212] See also Figure 1 , the embodiment of this specification also provides a biometric identity authentication system, comprising: a server and a client; wherein the server comprises at least one processor and a memory for storing processor executable instructions, and when the processor executes the instructions, the method executed by the server side is implemented to provide the client with a biometric identification function for biometric identification and a biometric feature for identity authentication;
[0213] The client includes at least one processor and a memory for storing processor executable instructions. When the processor executes the instructions, it implements the method executed by the client side, which is used to perform biometric-based identity authentication on the user according to the biometric function and the biometric feature provided by the server.
[0214] Among them, there can be multiple clients, and the server can send to each client the biometric function obtained by fitting the biometric model and the information required for identity authentication, such as the biological sample characteristics identified by the biometric model based on the biological information collected during user registration of each client, so that each client can directly perform biometric-based identity authentication locally.
[0215] It should be noted that the above-mentioned device and system may also include other implementation modes according to the description of the method embodiment. The specific implementation modes may refer to the description of the relevant method embodiment, which will not be described one by one here.
[0216] The biometric identity authentication device provided in this specification can also be used in a variety of data analysis and processing systems. The system or server or terminal or device can be a separate server, or it can include a server cluster, system (including distributed system), software (application), actual operation device, logic gate circuit device, quantum computer, etc. that uses one or more of the methods or one or more embodiments of the system or server or terminal or device of this specification and a terminal device combined with necessary implementation hardware. The detection system for checking the difference data may include at least one processor and a memory storing computer executable instructions, and the processor implements the steps of the method described in any one or more of the above embodiments when executing the instructions.
[0217] The method embodiments provided in the embodiments of this specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a server as an example, Figure 8 1 is a hardware structure block diagram of a biometric identity authentication server in one embodiment of this specification. The computer terminal may be a biometric identity authentication server or a biometric identity authentication device in the above embodiment. Figure 8 The server 10 shown may include one or more (only one is shown in the figure) processors 100 (the processor 100 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a non-volatile memory 200 for storing data, and a transmission module 300 for communication functions. Those skilled in the art will understand that Figure 8 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 8 More or fewer components shown in the figure may also include other processing hardware, such as a database or multi-level cache, GPU, or other hardware with Figure 8 Different configurations shown.
[0218] The non-volatile memory 200 can be used to store software programs and modules of application software, such as program instructions / modules corresponding to the biometric identity authentication method in the embodiment of this specification. The processor 100 executes various functional applications and resource data updates by running the software programs and modules stored in the non-volatile memory 200. The non-volatile memory 200 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the non-volatile memory 200 may further include a memory remotely arranged relative to the processor 100, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a bureau and a network, a mobile communication network, and combinations thereof.
[0219] The transmission module 300 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission module 300 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 300 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0220] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0221] The methods or devices described in the above embodiments provided in this specification can implement business logic through computer programs and record them on storage media, and the storage media can be read and executed by computers to achieve the effects of the solutions described in the embodiments of this specification, such as:
[0222] Receiving a biometric verification request, wherein the biometric verification request includes biometric information to be verified;
[0223] Performing biometric identification on the biometric information to be verified using a biometric identification function to obtain a biometric feature to be verified; wherein the biometric identification function is obtained and issued by the server after fitting a biometric identification model;
[0224] Calculating a feature distance between the biometric feature to be verified and the biometric sample feature received in advance and sent by the server; wherein the biometric sample feature is obtained after the server performs biometric recognition on the biometric sample information using the biometric recognition model;
[0225] Determine whether the identity verification request passes based on the feature distance.
[0226] or, receiving biometric registration information uploaded by a client, wherein the biometric registration information includes biological sample information;
[0227] Performing image recognition on the biological sample information using a biological recognition model to obtain biological sample features corresponding to the biological sample information;
[0228] The biological sample feature and the biometric function obtained after fitting the biometric model are sent to the client, so that the client uses the biometric function and the biological sample feature to authenticate the received biometric verification request.
[0229] The storage medium may include a physical device for storing information, which is usually a medium that digitizes the information and then stores it in an electrical, magnetic or optical manner. The storage medium may include: a device that stores information in an electrical energy manner, such as various memories, such as RAM, ROM, etc.; a device that stores information in a magnetic energy manner, such as a hard disk, a floppy disk, a magnetic tape, a magnetic core memory, a magnetic bubble memory, a USB flash drive; a device that stores information in an optical manner, such as a CD or a DVD. Of course, there are other readable storage media, such as quantum memory, graphene memory, etc.
[0230] The above-mentioned biometric identity authentication method or device provided in the embodiments of this specification can be implemented by a processor in a computer executing corresponding program instructions, such as using the C++ language of the Windows operating system to implement it on a PC, on a Linux system, or other systems such as Android and iOS system programming languages to implement it on a smart terminal, as well as based on the processing logic of a quantum computer.
[0231] It should be noted that the device, computer storage medium, and system described in the specification may also include other implementation methods according to the description of the relevant method embodiments. The specific implementation methods can refer to the description of the corresponding method embodiments, which will not be described one by one here.
[0232] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0233] The embodiments of this specification are not limited to complying with industry communication standards, standard computer resource data update and data storage rules, or the situations described in one or more embodiments of this specification. Certain industry standards or slightly modified implementation plans based on the implementation described in the custom method or embodiment can also achieve the same, equivalent or similar, or predictable implementation effects after deformation of the above-mentioned embodiments. The embodiments obtained by using these modified or deformed data acquisition, storage, judgment, processing methods, etc. can still fall within the scope of the optional implementation plans of the embodiments of this specification.
[0234] In the 1990s, it was very clear whether the improvement of a technology was a hardware improvement (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or a software improvement (improvement of the method flow). However, with the development of technology, many improvements in the method flow today can be regarded as direct improvements in the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs. The original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.
[0235] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.
[0236] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a vehicle-mounted human-computer interaction device, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0237] Although one or more embodiments of the present specification provide method operation steps as described in the embodiments or flow charts, more or less operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiments is only one way of executing the order of many steps, and does not represent a unique execution order. When the device or terminal product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, an environment of a parallel processor or multi-threaded processing, or even a distributed resource data update environment). The term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or equipment including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, product or equipment. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or equipment including the elements. The first, second, etc. words are used to represent the name, and do not represent any specific order.
[0238] For the convenience of description, the above devices are described in various modules according to their functions. Of course, when implementing one or more of the present specification, the functions of each module can be implemented in the same or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0239] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable resource data update device to produce a machine, so that instructions executed by the processor of the computer or other programmable resource data update device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0240] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable resource data update device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0241] These computer program instructions may also be loaded onto a computer or other programmable resource data updating device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions executed on the computer or other programmable device for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0242] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0243] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0244] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage, graphene storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0245] It should be understood by those skilled in the art that one or more embodiments of the present specification may be provided as a method, system or computer program product. Therefore, one or more embodiments of the present specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, one or more embodiments of the present specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0246] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0247] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. In the description of this specification, the description of the reference term "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this specification. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.
[0248] The above description is only an example of one or more embodiments of the present specification and is not intended to limit one or more embodiments of the present specification. For those skilled in the art, one or more embodiments of the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims.< / t> < / d> < / d> < / d> < / t> < / t>
Claims
1. A biometric identity verification method, the method comprising: Receiving a biometric verification request, wherein the biometric verification request includes biometric information to be verified; The biometric information to be verified is biometrically identified by using a biometric identification function to obtain a biometric feature to be verified; wherein the biometric identification function is obtained by: using the biometric sample information and the biometric feature output by the biometric identification model, analyzing the mapping relationship between the independent variable and the dependent variable, simplifying the biometric identification model and fitting it to the biometric identification function; Calculating a feature distance between the biometric feature to be verified and the biometric sample feature received in advance and sent by the server; wherein the biometric sample feature is obtained after the server performs biometric recognition on the biometric sample information using the biometric recognition model; Determining whether the identity verification request for biometric verification is passed according to the characteristic distance; Receiving a verification upper limit determined by the server based on the biometric recognition model and a verification lower limit determined by the server based on the biometric recognition function; the verification upper limit is the recognition accuracy of the biometric recognition model; the verification lower limit is the recognition error between the recognition result of the biometric recognition function and the recognition result of the biometric recognition model, or the recognition accuracy of the biometric recognition function; The determining whether the identity verification of the biometric verification request is passed according to the characteristic distance includes: if the characteristic distance is greater than the verification lower limit and less than the verification upper limit, determining that the identity verification of the verification request is passed.
2. The method according to claim 1, before receiving the biometric verification request, the method further comprises: receiving a biometric registration request, wherein the biometric registration request includes biological sample information; Sending the biological sample information to the server, so that the server obtains the biological sample feature after performing biometric recognition on the biological sample information using the biometric recognition model; Receive the biological sample feature sent by the server.
3. The method according to claim 1, when receiving the biological sample feature, the verification upper limit, and the verification lower limit sent by the server, the method comprises: Receive confidential information sent by the server, wherein the confidential information includes the encrypted biological sample feature obtained by the server encrypting the biological sample feature with the public key and the public key, or the confidential information includes the encrypted biological sample feature obtained by the server encrypting the biological sample feature with the public key, the encrypted verification upper limit obtained by encrypting the verification upper limit with the public key, the encrypted verification lower limit obtained by encrypting the verification lower limit with the public key, and the public key.
4. The method according to claim 3, when the secret information includes the encrypted biological sample feature obtained by the server encrypting the biological sample feature using a public key and the public key, the calculating the feature distance between the biological feature to be verified and the biological sample feature received in advance and sent by the server comprises: Encrypting the biometric feature to be verified by using the public key to obtain an encrypted biometric feature to be verified; Calculating an encrypted feature distance between the encrypted biometric feature to be verified and the encrypted biometric sample feature; The determining, according to the characteristic distance, whether the identity authentication of the biometric authentication request is passed includes: Sending the encrypted feature distance to the server; Receive the identity authentication result of the biometric authentication request determined by the server by comparing the encryption feature distance with an encryption verification upper limit and an encryption verification lower limit.
5. The method according to claim 3, when the secret information includes the encrypted biological sample feature, the encrypted verification upper limit, the encrypted verification lower limit and the public key, the calculating the feature distance between the biological feature to be verified and the biological sample feature received in advance and sent by the server comprises: Encrypting the biometric feature to be verified by using the public key to obtain an encrypted biometric feature to be verified; Calculating an encrypted feature distance between the encrypted biometric feature to be verified and the encrypted biometric sample feature; The determining, according to the characteristic distance, whether the identity authentication of the biometric authentication request is passed includes: Whether the identity verification of the biometric verification request is passed is determined according to the encryption feature distance, the encryption verification upper limit, and the encryption verification lower limit.
6. The method of claim 3, further comprising: After completing identity authentication for the biometric authentication request, when it is determined that the communication status is normal, receiving the updated confidentiality information returned by the server.
7. A biometric identity verification method comprising: Receiving biometric registration information uploaded by a client, wherein the biometric registration information includes biological sample information; Performing image recognition on the biological sample information using a biological recognition model to obtain biological sample features corresponding to the biological sample information; The biological sample feature and the biological recognition function are sent to the client, so that the client uses the biological recognition function and the biological sample feature to authenticate the received biological verification request; the biological recognition function is obtained by: using the biological sample information and the biological features output by the biometric recognition model, analyzing the mapping relationship between the independent variable and the dependent variable, and simplifying the biometric recognition model to fit the biometric recognition function; Determining the recognition accuracy of the biometric recognition model as a verification upper limit; Determine the recognition error between the recognition result of the biometric recognition function and the recognition result of the biometric recognition model, or the recognition accuracy of the biometric recognition function as a verification lower limit; The verification upper limit and the verification lower limit are sent to the client, so that after receiving the biometric verification request, the client uses the biometric recognition function, the biological sample feature, the verification upper limit and the verification lower limit to authenticate the biometric verification request.
8. The method according to claim 7, when sending the biological sample feature, the biological recognition function obtained after fitting the biological recognition model, the verification upper limit, and the verification lower limit to the client, the method comprises: Generate an encryption key, and use a public key in the encryption key to encrypt the biological sample feature, the verification upper limit, and the verification lower limit, respectively, to obtain an encrypted biological sample feature, an encrypted verification upper limit, and an encrypted verification lower limit, respectively; The encrypted biometric sample feature and the public key are sent to the client as confidential information, or the encrypted biometric sample feature, the encryption verification upper limit, the encryption verification lower limit and the public key in the encryption key are sent to the client as confidential information, so that after receiving the biometric verification request, the client uses the confidential information to authenticate the biometric verification request.
9. The method of claim 8, further comprising: The public key and the private key in the encryption key are updated, the secret information is updated using the updated public key to obtain updated secret information, and the updated secret information is sent to the client.
10. The method according to claim 7, before receiving the biometric registration information uploaded by the client, the method further comprises: Receive biometric sample information collected by the client; Using the biometric sample information to perform model training and construct the biometric model; Inputting the biological fitting information into the biological recognition model to obtain biological characteristic model data output by the biological recognition model; The biometric recognition model is fitted according to the biometric fitting information and the biometric feature model data to obtain the biometric recognition function.
11. The method according to claim 10, wherein determining an upper verification limit based on the biometric recognition model and determining a lower verification limit based on the biometric recognition function comprises: Determining the verification upper limit according to the recognition accuracy of the biometric recognition model; Inputting the biometric fitting information into the biometric recognition function to obtain biometric feature fitting data; Calculating the recognition error corresponding to the biometric recognition function according to the biometric fitting data and the biometric model data; The verification lower limit is determined according to the identification error.
12. A biometric authentication client comprising: A verification request receiving module, used to receive a biometric verification request, wherein the biometric verification request includes biometric information to be verified; A biometric identification module, used to perform biometric identification on the biometric information to be verified using a biometric identification function to obtain the biometric features to be verified; wherein the biometric identification function is obtained by: using the biometric sample information and the biometric features output by the biometric identification model, analyzing the mapping relationship between the independent variable and the dependent variable, simplifying the biometric identification model and fitting it to the biometric identification function; A feature distance calculation module, used to calculate the feature distance between the biometric feature to be verified and the biometric sample feature received in advance and sent by the server; wherein the biometric sample feature is obtained after the server performs biometric recognition on the biometric sample information using the biometric recognition model; An identity verification module, used to determine whether the identity verification request for biometric verification is passed according to the characteristic distance; A verification threshold receiving module, used to: receive a verification upper limit determined by the server based on the biometric recognition model and a verification lower limit determined by the server based on the biometric recognition function; the verification upper limit is the recognition accuracy of the biometric recognition model; the verification lower limit is the recognition error between the recognition result of the biometric recognition function and the recognition result of the biometric recognition model, or the recognition accuracy of the biometric recognition function; The identity authentication module is specifically used to: if the feature distance is greater than the verification lower limit and less than the verification upper limit, determine that the identity authentication of the verification request is passed.
13. The client according to claim 12, further comprising a registration module, configured to: Before receiving the biometric verification request, receiving a biometric registration request, wherein the biometric registration request includes biometric sample information; Sending the biological sample information to the server, so that the server obtains the biological sample feature after performing biometric recognition on the biological sample information using the biometric recognition model; Receive the biological sample feature sent by the server.
14. The client according to claim 12, wherein the verification threshold receiving module is specifically used for: When receiving the biological sample feature, the verification upper limit, and the verification lower limit sent by the server, receive the confidential information sent by the server, the confidential information including the encrypted biological sample feature obtained by the server encrypting the biological sample feature with the public key and the public key, or the confidential information includes the encrypted biological sample feature obtained by the server encrypting the biological sample feature with the public key, the encrypted verification upper limit obtained by encrypting the verification upper limit with the public key, the encrypted verification lower limit obtained by encrypting the verification lower limit with the public key, and the public key.
15. The client according to claim 14, wherein the feature distance calculation module is specifically used for: Encrypting the biometric feature to be verified by using the public key to obtain an encrypted biometric feature to be verified; Calculating an encrypted feature distance between the encrypted biometric feature to be verified and the encrypted biometric sample feature; The identity authentication module is specifically used for: Sending the encrypted feature distance to the server; Receive the identity authentication result of the biometric authentication request determined by the server by comparing the encryption feature distance with an encryption verification upper limit and an encryption verification lower limit.
16. The client according to claim 14, wherein the feature distance calculation module is specifically used for: Encrypting the biometric feature to be verified by using the public key to obtain an encrypted biometric feature to be verified; Calculating an encrypted feature distance between the encrypted biometric feature to be verified and the encrypted biometric sample feature; The identity authentication module is specifically used for: Whether the identity verification of the biometric verification request is passed is determined according to the encryption feature distance, the encryption verification upper limit, and the encryption verification lower limit.
17. The client according to claim 14, further comprising an update encryption information receiving module, configured to: After completing identity authentication for the biometric authentication request, when it is determined that the communication status is normal, receiving the updated confidentiality information returned by the server.
18. A biometric authentication server comprising: A biometric image receiving module, used to receive biometric registration information uploaded by a client, wherein the biometric registration information includes biological sample information; A biometric feature recognition module, used to perform image recognition on the biological sample information using a biometric recognition model to obtain biological sample features corresponding to the biological sample information; An identification data sending module is used to send the biological sample characteristics and the biological recognition function to the client, so that the client uses the biological recognition function and the biological sample characteristics to authenticate the received biological verification request; the biological recognition function is obtained by: using the biological sample information and the biological characteristics output by the biological recognition model, analyzing the mapping relationship between the independent variable and the dependent variable, simplifying the biological recognition model and fitting it to the biological recognition function; The identification data sending module is also used to: determine the identification accuracy of the biometric identification model as a verification upper limit; Determine the recognition error between the recognition result of the biometric recognition function and the recognition result of the biometric recognition model, or the recognition accuracy of the biometric recognition function as the verification lower limit; send the verification upper limit and the verification lower limit to the client, so that after receiving the biometric verification request, the client uses the biometric recognition function, the biological sample feature, the verification upper limit and the verification lower limit to authenticate the identity of the biometric verification request.
19. The server according to claim 18, wherein the identification data sending module is specifically used for: Generate an encryption key, and use a public key in the encryption key to encrypt the biological sample feature, the verification upper limit, and the verification lower limit, respectively, to obtain an encrypted biological sample feature, an encrypted verification upper limit, and an encrypted verification lower limit, respectively; The encrypted biometric sample feature and the public key are sent to the client as confidential information, or the encrypted biometric sample feature, the encryption verification upper limit, the encryption verification lower limit and the public key in the encryption key are sent to the client as confidential information, so that after receiving the biometric verification request, the client uses the confidential information to authenticate the biometric verification request.
20. The server according to claim 19, further comprising an encryption information updating module, configured to: The public key and the private key in the encryption key are updated, the secret information is updated using the updated public key to obtain updated secret information, and the updated secret information is sent to the client.
21. A biometric identity verification device comprising: At least one processor and a memory for storing processor-executable instructions, wherein when the processor executes the instructions, the method according to any one of claims 1-6 or 7-11 is implemented.
22. A computer-readable storage medium having computer instructions stored thereon, wherein the instructions, when executed, implement the steps of the method of any one of claims 1-6 or 7-11.
23. A biometric identity verification system comprising: A server and a client; wherein the server comprises at least one processor and a memory for storing processor executable instructions, and when the processor executes the instructions, the method according to any one of claims 7 to 11 is implemented to provide the client with a biometric recognition function for biometric recognition and a biometric feature for identity authentication; The client includes at least one processor and a memory for storing processor executable instructions. When the processor executes the instructions, it implements the method described in any one of claims 1-6, which is used to perform biometric-based identity authentication on the user according to the biometric function and the biometric feature provided by the server.
