Biological characteristic matching method, device and system, electronic equipment and storage medium
Through the biometric matching process between the management end and the consumer end, it is ensured that biometrics are only compared and stored on the trusted management end, which solves the data leakage and abuse in biometric matching authentication and improves information security.
Patent Information
- Application Number
- CN202311724782.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-14
- Publication Date
- 2024-11-29
AI Technical Summary
During the biometric matching authentication process, there is a risk of biometric data leakage and abuse, and the security of personal information is threatened.
The management end provides a biometric extraction algorithm to the consumer end. After the consumer end performs feature extraction, the first biometric feature is sent to the management end for matching. After the management end completes the matching, the first biometric feature is deleted to ensure that the biometric feature is only on the trusted management end. Storage, consumer side has no storage permissions.
It effectively avoids the risk of biometric data leakage, ensures the security of personal information, prevents identity theft and fraud, and enhances data protection measures.
Smart Images

Figure CN119049138A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a biometric matching method, device, system, electronic device and storage medium. Background Art
[0002] Biometrics are widely used in identity recognition and authentication in various industries because they can indicate personal identity. More and more banks, enterprises, organizations and other institutions collect personal biometrics, perform identity recognition, and provide corresponding services based on the identity recognition results. However, in this identity recognition and authentication process, the organization and the individual directly collect and match biometrics, which may lead to unintentional or intentional abuse of biometrics. Personal information security is at risk of biometric data leakage in identity matching and authentication. Summary of the invention
[0003] The present application provides a biometric matching method, device, system, electronic device and storage medium. The management end sends the biometric extraction algorithm to the consumer end, and the consumer end extracts the first biometric feature and then performs biometric matching based on the first biometric feature and the second biometric feature pre-stored by the management end. The first biometric feature is deleted while the matching result is output, and the storage permission is restricted when the consumer end extracts the biometric feature, which solves the problem of biometric data leakage risk in the existing identity matching authentication process.
[0004] In a first aspect, the present application provides a biometric matching method, the method comprising:
[0005] Sending a preset biometric feature extraction algorithm to the consumer end;
[0006] Obtaining a biometric feature matching request returned by the consumer end, wherein the biometric feature matching request includes a first biometric feature obtained by the consumer end from the biometric feature collection data to be matched based on the biometric feature extraction algorithm, wherein the consumer end does not grant storage permission for the first biometric feature;
[0007] Matching the first biometric feature with a pre-stored second biometric feature to obtain a biometric feature matching result;
[0008] The biometric matching result is output to the consumer end.
[0009] Optionally, the biometric matching method provided by the present application further includes:
[0010] Obtaining a biometric record request, wherein the biometric record request includes biometric collection data to be recorded;
[0011] Feature extraction is performed on the biometric feature collection data to be recorded according to the biometric feature extraction algorithm to obtain a second biometric feature.
[0012] Optionally, the biometric matching method provided by the present application further includes:
[0013] Obtaining an authorization request sent by the consumer end, wherein the authorization request includes first authorization information;
[0014] Performing authorization matching according to the first authorization information and the second authorization information stored in advance to obtain an authorization matching result;
[0015] When the authorization matching result is that the first authorization information corresponds to the second authorization information, the biometric collection data to be matched after the authorization verification is determined.
[0016] Optionally, the biometric matching method provided by the present application further includes:
[0017] Matching the permission period with the validity period according to the request time node to obtain the permission period matching result;
[0018] Perform identity information matching according to the first identity information and the second identity information to obtain the identity information matching result;
[0019] A number check is performed according to the remaining number of times to obtain a number check result.
[0020] Optionally, the biometric matching method provided by the present application further includes:
[0021] Perform identity information matching according to the first identity information and the second identity information to obtain an identity information matching result;
[0022] When the identity information matching result is that the first identity information and the second identity information are consistent, the biometric feature collection data to be matched after the identity information is verified is determined.
[0023] Optionally, the biometric matching method provided by the present application further includes:
[0024] Perform distance calculation on the first eigenvector and the second eigenvector to obtain a distance calculation result;
[0025] Compare the distance calculation result with a preset vector distance threshold to obtain a distance comparison result;
[0026] Generate a biometric matching result based on the distance comparison result.
[0027] Optionally, the biometric matching method provided by the present application further includes:
[0028] According to the biometric feature extraction algorithm, one-dimensional vector processing is performed on the biometric feature collection data of the human face to be recorded to obtain a one-dimensional vector processing result;
[0029] Perform component analysis on the one-dimensional vector processing result through a covariance matrix to obtain the second facial biometric feature.
[0030] In a second aspect, the present application further provides a biometric management device, comprising:
[0031] A feature extraction algorithm sending module, used to send a preset biometric feature extraction algorithm to the consumer end;
[0032] a matching request acquisition module, configured to acquire a biometric matching request returned by the consumer end, wherein the biometric matching request includes a first biometric feature obtained by the consumer end from the biometric feature collection data to be matched based on the biometric feature extraction algorithm, wherein the consumer end does not grant storage permission for the first biometric feature;
[0033] A biometric matching module, used to match the first biometric with a pre-stored second biometric to obtain a biometric matching result;
[0034] The matching result processing module is used to output the biometric matching result to the consumer end.
[0035] In a third aspect, the present application also provides a biometric management system, including:
[0036] The consumer end is used to receive a preset biometric feature extraction algorithm sent by the consumer end, and based on a first biometric feature obtained by the biometric feature extraction algorithm from the biometric feature collection data to be matched, send a biometric feature matching request containing the first biometric feature to the management end, and receive the biometric feature matching result returned by the management end;
[0037] The management end trusted by the consumer end is used to send the biometric extraction algorithm to the consumer end, receive the biometric matching request returned by the consumer end, match the first biometric with a pre-stored second biometric to obtain the biometric matching result, and output the biometric matching result to the consumer end.
[0038] In a fourth aspect, the present application further provides an electronic device comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the biometric matching method as described in the first aspect are implemented.
[0039] In a fifth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the biometric matching method described in the first aspect are implemented.
[0040] In the technical solution provided by the present application, since the first biometric feature and the second biometric feature are compared internally, only the biometric feature matching result is output and displayed, and the biometric feature is only stored on the management end that is trusted by the production end and the consumer end. When the consumer end generates the first biometric feature, the storage permission is restricted and the first biometric feature cannot be stored. The management end deletes the first biometric feature after completing the feature matching, which further avoids the risk of leakage of the first biometric feature and ensures the security of personal information.
[0041] Specifically, in the technical solution provided by the present application, there will be no direct data or information interaction between the consumer end and the production end. Instead, the management end collects the collected data from the production end and extracts features to achieve biometric matching and storage. The consumer end processes the matched biometric collected data based on the biometric extraction algorithm provided by the management end to obtain the first biometric, but does not obtain the authority to store the first biometric, thereby avoiding the leakage of personal biometrics and ensuring information security during the personal biometric identification process.
[0042] The above description is only an overview of the technical solution provided by the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.
[0044] Figure 1 This is one of the schematic diagrams of the biometric matching method provided in the embodiments of the present application;
[0045] Figure 2 This is the second schematic diagram of the biometric matching method provided in the embodiment of the present application;
[0046] Figure 3 This is the third schematic diagram of the biometric matching method provided in the embodiment of the present application;
[0047] Figure 4 This is the fourth schematic diagram of the biometric matching method provided in the embodiment of the present application;
[0048] Figure 5 This is the fifth schematic diagram of the biometric matching method provided in the embodiment of the present application;
[0049] Figure 6 This is the sixth schematic diagram of the biometric matching method provided in the embodiment of the present application;
[0050] Figure 7 This is an example of a biometric management interaction process provided by this application;
[0051] Figure 8 is a schematic diagram of a biometric management device provided in an embodiment of the present application;
[0052] Fig. 9 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0053] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.
[0054] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.
[0055] In today's digital age, with the continuous development and popularization of biometric recognition technologies such as facial recognition, the acquisition, storage and use of human body information characteristics have become extremely easy. The abuse of biometric information such as human body information characteristics has brought many privacy and security risks.
[0056] First, human information features, especially facial information, have become a widely used authentication method in all walks of life. Finance, social media, public security and other fields are actively exploring the application of these technologies. However, the large-scale adoption of this technology also brings privacy issues. Personal facial data may be collected, stored and used at will by different companies, institutions and individuals, causing the risk of personal information leakage. Secondly, the abuse of human information features may lead to identity theft and fraud. Once malicious parties obtain personal facial information, they can use it to access protected personal accounts, systems or devices to obtain private data or commit fraud. In addition, it is becoming easier to forge faces, which may lead to the problem of fake identity. In addition, since the use of human information features is not always clearly regulated and regulated, the abuse problem also involves the issue of data security and privacy protection. Personal facial data may be sold to third parties for advertising purposes, facial recognition training, etc. This may lead to the infringement of personal privacy rights, and individuals have relatively weak control over these data. In addition, the large-scale collection and use of human information features may also raise social ethical issues. For example, the use of facial recognition technology in public places may result in an individual's actions being recorded and tracked for a long time, raising the issue of the balance between privacy rights and public safety.
[0057] In order to deal with the abuse of these technologies, society needs to formulate stricter laws and regulations to protect individual privacy and data rights. At the same time, the government and relevant organizations also need to strengthen data protection measures to ensure that user data is properly managed and securely protected. Individuals also need to be vigilant when using technology services and carefully choose to share their own human information characteristics to protect their own privacy security.
[0058] Among them, biometrics are widely used in banks, enterprises, organizations and other industries because they can indicate personal identity. More and more banks, enterprises, organizations and other institutions collect personal biometrics for identity recognition and provide corresponding services. However, this identity recognition method may cause institutions to store personal biometrics unintentionally or intentionally, and biometrics may be leaked and abused, infringing personal privacy, leading to identity theft, identity fraud and other cases.
[0059] In view of the problem of biometric leakage and abuse in the process of biometric matching and identification in the prior art, the present application provides a biometric extraction algorithm from the management end to the consumer end, so that the consumer end extracts the biometric collection data to be matched carried in the biometric matching request through the biometric extraction algorithm to obtain the first biometric feature and sends it to the management end. Among them, the consumer end does not obtain the storage permission of the first biometric feature. For example, the calculated first biometric feature can only be deleted, which avoids the trend of the first biometric feature being abused by the consumer end. Subsequently, the management end compares and matches the biometric feature according to the first biometric feature and the second biometric feature corresponding to the biometric collection data to be recorded pre-entered by the production end, and outputs and displays the biometric matching result. Since the first biometric feature and the second biometric feature are compared inside the management end, only the matching result can be obtained outside, and the first biometric feature cannot be obtained, so the biometric feature provided by the production end cannot be used for identity theft. Identity fraud and other illegal events. In addition, the second biometric feature provided by the production end is only stored in the management end trusted by the production end and the consumer end, which further ensures the security of the biometric data of the production end.
[0060] The biometric matching method, device, system, electronic device and non-volatile readable storage medium provided by the present application are described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.
[0061] The first embodiment of the present application relates to a biometric matching method, such as Figure 1 As shown in the figure, the management end used for trust between the production end and the consumer end includes:
[0062] Step 101: Send the preset biometric feature extraction algorithm to the consumer end:
[0063] Step 102: Obtain a biometric feature matching request returned by the consumer end, wherein the biometric feature matching request includes a first biometric feature obtained by the consumer end from the biometric feature collection data to be matched based on the biometric feature extraction algorithm, wherein the consumer end does not grant storage permission for the first biometric feature;
[0064] Step 103: Match the first biometric feature with the pre-stored second biometric feature to obtain a biometric feature matching result;
[0065] Step 104: output the biometric matching result to the consumer end.
[0066] Specifically, the biometric matching method provided in this application is applied to the management end that is trusted by both the production end and the consumer end. Among them, the production end is the owner of biometrics such as face, fingerprint, iris, sound wave, etc., and enjoys the ownership of these biometrics. It can provide image, audio and other collected data for biometric extraction, and authorize the use of the biometrics corresponding to these collected data to the management end, allowing the management end to perform biometric matching and biometric storage according to the biometrics provided by the production end. The consumer end is a natural person or organization or hiring company that needs to perform biometric verification on the production end, and needs to perform biometric verification and matching based on the new collected data provided by the production end, and provide corresponding services to the production end according to the matching results. The management end is the manager and storage of biometric information that is trusted and legal by both the production end and the consumer end, and provides a biometric matching algorithm to the consumer end, so that the consumer end can extract the biometrics to obtain the first biometric information and send it to the management end through the network after encryption. The management end matches the first biometric information with the biometrics pre-stored by the production end, and sends the matching result to the consumer end, so as to realize the output display of the matching result.
[0067] Specifically, the management end first provides a biometric feature extraction algorithm to the consumer end, and the consumer end extracts the biometric feature based on the biometric feature collection data to be matched provided by the production end to the consumer end, such as image, video, audio and other collection data representing the biometric feature, to obtain the first biometric feature information. At this time, the consumer end does not have the authority to save the first biometric feature information, and can only send the first biometric feature to the management end, for example, after encryption, to the management end through the network, and then delete the first biometric feature information. Subsequently, the management end performs feature matching based on the first biometric feature information returned by the consumer end and the pre-stored second biometric feature information, and outputs the feature matching result to the consumer end for subsequent use by the consumer end.
[0068] For example, the production end may be an individual who provides the collected data corresponding to the biometrics, the management end may be a legitimate public organization recognized by the government and the public, such as the public security department, and the consumption end may be an organization or company that needs to perform personal identity authentication based on the newly provided collected data, such as a bank or an employment company. The individual enters his or her own biometrics in advance through the place provided by the public security department, and the public security department stores and processes the biometrics entered by the individual. When the individual needs to prove his or her identity to the bank, the bank collects data from the individual and extracts the collected data through the biometric extraction method in the window or port provided by the public security department to obtain a new biometric. At this time, the bank does not have the storage permission for the new biometrics. After transmitting the biometrics to the public security department through the window or port provided by the public security department, the newly obtained biometrics are automatically deleted. The public security department matches the new biometrics with the biometrics previously stored by the individual at the public security department, and sends the matching results to the bank for the bank to make a judgment on identity verification. In addition, in order to further protect personal privacy and security, the public security department will also delete the newly received biometrics after completing the biometric matching, and only retain the biometrics previously provided by the individual.
[0069] In addition, the present application also provides a biometric matching method, in which the management end receives a biometric matching request sent by the consumer end, wherein the request sent by the consumer end also carries the biometric collection data to be matched provided by the production end to the consumer end for matching, such as images, videos, audio, etc., which are collection data representing biometrics.
[0070] After receiving the biometric collection data to be matched transmitted by the consumer end, the management end extracts the biometric feature representing the identity of the production end corresponding to the biometric collection data to be matched according to the pre-set feature extraction rules, as the first biometric feature, and performs feature matching between the first biometric feature and the second biometric feature pre-stored in the management end by the production end to obtain the biometric matching result. Finally, the management end outputs the biometric matching result to the consumer end.
[0071] For example, the production end can be an individual who provides the collected data corresponding to the biometrics, the management end can be a legitimate public organization recognized by the government and the public, such as the public security department, and the consumption end can be an organization or company that needs to perform personal identity authentication based on the newly provided collected data, such as a bank or an employment company. The individual enters his or her own biometrics in advance through the venue provided by the public security department, and the public security department stores and processes the biometrics entered by the individual. When the individual needs to prove his or her identity to the bank, the bank collects data from the individual and sends the collected data to the public security department through the window or port provided by the public security department. The public security department extracts the features of the newly received collected data, extracts new biometrics, and matches them with the biometrics previously stored by the individual at the public security department, and sends the matching results to the bank for the bank to make a judgment on identity verification.
[0072] Among them, in the biometric matching method provided by the present application, the second biometric feature pre-stored by the production end can directly send the second biometric feature extracted from the collected data to the management end, and the management end will store and preserve the second biometric feature, or the collected data can be directly sent to the management end, and the management end will extract the second biometric feature from the collected data according to a pre-set feature extraction rule. This application does not impose any restrictions.
[0073] It should be emphasized that in the biometric matching method provided in the present application, the types of the first biometric and the second biometric need to be completely consistent, for example, if the first biometric is a facial feature, the second biometric is also a facial feature. In addition, the feature extraction methods of the first biometric and the second biometric also need to be completely consistent, for example, if the first biometric is extracted from the collected data through eigenfaces, the second biometric is also extracted from the corresponding collected data through eigenfaces.
[0074] In addition, in the biometric matching method provided by the present application, the production end provides the biometric collection data to be recorded and the consumer end provides the biometric collection data to be matched, which can be achieved through mobile terminals such as 5G smartphones, or data collection and transmission can be carried out through fixed equipment, and this application does not impose any restrictions.
[0075] In the technical solution provided by the present application, the management end sends the biometric feature extraction algorithm to the consumer end, so that the consumer end can extract the feature to obtain the first biometric feature, and then perform biometric feature matching based on the first biometric feature and the second biometric feature pre-stored by the management end. The first biometric feature is deleted while the matching result is output, and the storage permission is restricted when the consumer end extracts the biometric feature. Since the first biometric feature and the second biometric feature are both compared internally, only the biometric feature matching result is output and displayed, and the biometric feature is only stored in the management end that is trusted by the production end and the consumer end. When the consumer end generates the first biometric feature, the storage permission is restricted and the first biometric feature cannot be stored. After completing the feature matching, the management end deletes the first biometric feature, which further avoids the risk of leakage of the first biometric feature and ensures personal information security.
[0076] Based on the above implementation, Figure 2 As shown, in the biometric matching method provided by the present application, before step 101, the method further includes:
[0077] Step 105: Obtain a biometric record request, wherein the biometric record request includes biometric collection data to be recorded;
[0078] Step 106: Extract the biometric feature data to be recorded according to the biometric feature extraction algorithm to obtain a second biometric feature.
[0079] Specifically, in the biometric matching method provided by the present application, before performing biometric matching, the production end sends a biometric recording request to the management end, and the biometric recording request received by the management end also carries the biometric collection data to be recorded provided by the production end. Subsequently, the management end extracts features from the biometric collection data to be recorded in the biometric recording request to obtain the second biometric corresponding to the production end. Among them, the feature extraction method of the second biometric needs to be consistent with the first biometric.
[0080] On the basis of the above implementation, since the present application can also extract the second biometric feature by the management end alone, the production end cannot obtain the second biometric feature either, thus avoiding the risk of biometric feature leakage. Moreover, the algorithm for extracting biometric features from the collected data is only known to the management end, and neither the production end nor the consumer end can understand the specific algorithm in the biometric feature extraction process, and thus cannot extract biometric features based on the collected data, further avoiding the risk of biometric feature data leakage.
[0081] Based on the above implementation, in the biometric matching method provided by the present application, step 101 includes:
[0082] Step 111: Obtain an authorization request sent by the consumer end, wherein the authorization request includes first authorization information;
[0083] Step 112: performing authorization matching according to the first authorization information and the pre-stored second authorization information to obtain an authorization matching result;
[0084] Step 113: When the authorization matching result is that the first authorization information corresponds to the second authorization information, the biometric feature extraction algorithm is sent to the consumer end.
[0085] Specifically, the first authorization information includes the first identity information and the request time node, the second authorization information also includes the second identity information, the validity period and the remaining number of times, the authorization matching result includes the authority period matching result, the identity information matching result and the number of times verification result, and step 112 includes:
[0086] Step 114: Match the permission period with the validity period according to the request time node to obtain the permission period matching result;
[0087] Step 115: performing identity information matching according to the first identity information and the second identity information to obtain the identity information matching result;
[0088] Step 116: Perform a number check according to the remaining number of times to obtain a number check result.
[0089] Among them, Figure 3 As shown, the first authorization information includes the request time node, and the second authorization information includes the validity period. In the biometric matching method provided by the present application, before step 101, it also includes:
[0090] Step 107: Match the permission period according to the request time node and the validity period to obtain a permission period matching result;
[0091] Step 108: When the authority period matching result is that the request time node is within the validity period, determine the biometric collection data to be matched after the period verification.
[0092] Specifically, in the biometric matching method provided by the present application, before matching the first biometric and the second biometric, it is also necessary to perform authority authentication on the consumer end and the production end corresponding to the biometric matching request and the biometric record request respectively. Only the biometric collection data to be matched that meets the authority authentication can the subsequent biometric extraction action be performed.
[0093] Among them, the authority authentication can be carried out through the request time node carried by the biometric matching request and the validity period carried by the biometric recording request to perform the authority period matching authentication. The biometric recording request sent by the production end to the management end not only carries the biometric collection data to be recorded, but also carries the validity period of the biometric collection data to be recorded. When the management end records the second biometric, it also stores its corresponding validity period. The authorization request sent by the consumer end to the management end carries the request time node for initiating the matching request. Before extracting the first biometric, the management end first matches the request time node with the validity period for the authority period. When the request time node falls within the validity period, it means that the consumer end sending the request is allowed to perform biometric matching at this time; when the request time node falls outside the validity period, it means that the consumer end sending the request is not allowed to perform biometric matching at this time, so as to extract the biometrics of the biometric collection to be matched that falls within the validity period after the period verification, and participate in the subsequent biometric matching action.
[0094] In addition, in the biometric matching method provided by the present application, the biometric matching action can also be managed by the number of times. When the production end pre-enters the authorization period, the number of biometric matching is also limited. Each time a match is completed, the number of times is reduced according to the actual needs of the user. When the number of times is reduced to 0, feature matching can no longer be performed based on the biometric provided by the production end. Among them, the effective condition for the number of times reduction can be determined based on the result of a successful match, or it can be directly determined based on the number of matches. For example, after successfully matching to the number of times pre-specified by the production end, the biometric provided by the production end is abolished so that it no longer participates in the match. It is also possible that when the biometric provided by the production end reaches the number of times pre-specified by the production end, the biometric provided by the production end is abandoned so that it no longer participates in the match.
[0095] In addition, when the production end sends a biometric record request, it can also limit the authorization type of the biometric information, such as limiting it to facial information or fingerprint information. Subsequent feature matching can only be performed when the collected data in the biometric matching request sent by the consumer end is consistent with the collected data type recorded by the production end.
[0096] For example, the production end sends a biometric record request to the management end. The biometric record request carries the biometric collection data to be recorded and the authorization information that needs to be recorded by the management end. The authorization information carries information such as the authorization period, authorization type, and number of authorizations. The authorization period indicates the period of use of the biometrics on the production end, such as "May 1, 2023 to April 30, 2024", the authorization type indicates the authorization type of the biometrics on the production end, such as "face information", and the number of authorizations indicates the number of times the biometrics on the production end are used, such as "query matching times 1 time", and is set to reduce the number of queries once for each match. After the management end records and stores all the biometrics and authorization information in the biometric record request from the production end, it receives four biometric matching requests sent by the consumer end. The request time node of the first biometric matching request is "May 1, 2022". The management end finds that the request time node falls outside the deadline, and does not perform feature extraction processing on the biometric collection data to be matched; the request time node of the second biometric matching request is "May 1, 2023". The management end finds that the request time node falls outside the deadline, but the type of the second biometric matching request is "iris information", which is different from the type pre-stored on the production end, and does not perform feature extraction processing on the biometric collection data to be matched; the request time node of the third biometric matching request is "May 1, 2023", and the request information is "face information". The management end performs feature extraction processing on the biometric collection data to be matched to obtain the first biometric, but the difference between the first biometric and the second biometric pre-stored on the production end is greater than the preset threshold, the match fails, and the number of matches is deducted; the request time node of the fourth biometric matching request is "May 1, 2023", and the request information is "face information", but the number of biometric uses has been deducted to zero at this time, so no biometric extraction and matching actions are performed.
[0097] On the basis of the above-mentioned implementation methods, since the biometric matching method provided in this application can also judge the authorization information before matching authentication, it determines whether the consumer end is authorized based on the preset deadline of the production end and the request time node of the consumer end, thereby further avoiding the abuse of biometric matching actions and ensuring the data security and personal privacy of the production end.
[0098] Based on the above implementation, Figure 4 As shown, the first authorization information includes the first identity information, and the second authorization information includes the second identity information. In the biometric matching method provided by the present application, before step 101, it also includes:
[0099] Step 109: performing identity information matching according to the first identity information and the second identity information to obtain an identity information matching result;
[0100] Step 110: When the identity information matching result is that the first identity information and the second identity information are consistent, determine the biometric feature collection data to be matched after the identity information is verified.
[0101] Specifically, in the biometric matching method provided by the present application, before matching the first biometric and the second biometric, it is also necessary to perform authority authentication on the consumer end and the production end corresponding to the biometric matching request and the biometric record request respectively. Only the biometric collection data to be matched that meets the authority authentication can the subsequent biometric extraction action be performed.
[0102] Among them, the authority authentication can be performed through the first identity information carried in the biometric matching request and the second identity information carried in the biometric recording request. The biometric recording request sent by the production end to the management end carries not only the biometric collection data to be recorded, but also the second identity information. While recording the second biometric, the management end also stores the corresponding second identity information. Similarly, the biometric matching request sent by the consumer end to the management end carries not only the biometric collection data to be matched, but also the first identity information. Before extracting the first biometric, the management end first authenticates the first identity information and the second identity information. When the first identity information and the second identity information can match, it means that the consumer end sending the request at this time is consistent with the consumer end authorized by the production end, and the first biometric corresponding to the biometric collection data to be matched can be matched with the second biometric pre-stored by the production end; when the first identity information and the second identity information cannot match, it means that the consumer end sending the request at this time is inconsistent with the consumer end authorized by the production end, and the first biometric corresponding to the biometric collection data to be matched cannot be matched with the second biometric pre-stored by the production end. Thus, the biometrics to be matched corresponding to the identity are collected for biometric extraction and participate in subsequent biometric matching actions.
[0103] It should be emphasized that in the biometric matching method provided by the present application, the first identity information and the second identity information can be completely identical, and the identification code provided by the production end as the second identity information is completely consistent with the identification code provided by the consumer end as the first identity information, for example, both use personal ID number, enterprise social unified credit code and other information to mark the identity information, or the production end can predetermine the first identity information that can match the second identity information. Specifically, when the production end sends the second identity information to the management end, it also determines the first identity information that is allowed to match. For example, when an individual uploads the collected data to the public security department for extracting biometrics, the extracted biometrics are restricted to be used only for bank identification. When the bank performs personal identity authentication as a consumer end, the bank provides the first identity information indicating its own identity. When the management end determines that the first identity information is indeed a bank and is within the scope of personal restrictions, the corresponding biometrics are collected and matched. When the management end determines that the first identity information does not belong to the bank, but to other enterprises and individuals, and does not belong to the personal permission scope as the production end, the biometric extraction and judgment action is not performed.
[0104] Similarly, when the consumer sends the first identity information to the management end, it also determines the second identity information that is allowed to match. For example, before the bank uploads the collected data to the public security department to extract biometrics, it will also limit the extracted biometrics to correspond to the identity information of the production end. For example, the biometrics correspond to multiple personal ID numbers. When the management end determines that the pre-stored second identity information cannot correspond to multiple ID numbers, the management end determines that the collected data transmitted by the bank "does not exist" and does not belong to the individual pre-registered and stored in the public security department, and does not perform biometric extraction and judgment.
[0105] For example, the production end sends a biometric record request to the management end. The biometric record request carries the biometric collection data to be recorded and the authorization information that needs to be recorded by the management end. The authorization information carries information such as the authorization object and the authorization type. The authorization object information indicates the identification code of the production end, such as "44XXXX19980101XXXX" and the identification code of the consumer end, such as "9134182485354232XM". After the management end records and stores all the biometrics and authorization information in the biometric record request of the production end, it receives three biometric matching requests sent by the consumer end. The first biometric matching request also carries the identity information "9134182485354231XM" indicating the consumer. The management end matches the identity information provided by the consumer with the identity information pre-stored by the production end. It is found that the match does not occur, so the feature extraction process is not performed on the biometric collection data to be matched. The second biometric matching request carries the identity information "9134182485354232XM" indicating the consumer, but it also carries the identity information "44XXXX19980102XXXX" of the production end that needs to be matched. Although the consumer The identity of the end can match the authorization information, but the production end of the second identity information carried in the biometric matching request is inconsistent with the production end of the pre-stored information. After it is found that the comparison cannot be made, the feature extraction processing of the biometric collection data to be matched is not performed; the second identity information carried in the third biometric matching request includes both the production end identification code "44XXXX19980101XXXX" and the consumer end identification code "9134182485354232XM". After comparison, the management end finds that they are exactly the same, and continues with subsequent biometric extraction and biometric comparison actions.
[0106] On the basis of the above-mentioned implementation methods, since the biometric matching method provided in this application can also judge the authorization information before matching authentication, it determines whether the consumer end is authorized based on the second identity information preset by the production end and the first identity information of the consumer end, thereby further avoiding the abuse of biometric matching actions and ensuring the data security and personal privacy of the production end.
[0107] Based on the above implementation, Figure 5 As shown, the first biometric feature includes a first feature vector, and the second biometric feature includes a second feature vector. In the biometric feature matching method provided in the present application, step 103 includes:
[0108] Step 131, performing distance calculation on the first eigenvector and the second eigenvector to obtain a distance calculation result;
[0109] Step 132: Compare the distance calculation result with a preset vector distance threshold to obtain a distance comparison result;
[0110] Step 133: Generate a biometric matching result based on the distance comparison result.
[0111] Specifically, in the biometric matching method provided by the present application, a first feature vector can be obtained from the biometric collection data of the face to be matched as the first biometric feature, and a second feature vector can be obtained from the biometric collection data to be recorded as the second biometric feature by extracting a biometric vector, wherein the extraction method of the first feature vector and the second feature vector needs to be completely consistent. Subsequently, the management end calculates the distance between the first feature vector and the second feature vector to obtain a distance calculation result, and compares the pre-set vector distance threshold. When the distance calculation result is less than the vector distance threshold, it indicates that the first biometric corresponding to the first feature vector and the second biometric corresponding to the second feature vector have high similarity, for example, the personal collection data provided by the bank or enterprise is consistent with the collection data pre-entered by the individual, which can prove that the information provider is the person himself, and generate the corresponding biometric matching result; when the distance calculation result is greater than the vector distance threshold, it indicates that the first biometric corresponding to the first feature vector and the second biometric corresponding to the second feature vector are greatly different, for example, the personal collection data provided by the bank or enterprise is inconsistent with the collection data pre-entered by the individual, which cannot prove that the information provider is the person himself, and generate the corresponding biometric matching result.
[0112] Among them, the first feature vector and the second feature vector can also obtain the similarity calculation result between the vectors through similarity calculation. When the similarity calculation result is greater than a preset similarity threshold, it means that the first biometric feature corresponding to the first feature vector and the second biometric feature corresponding to the second feature vector are highly similar. For example, the personal collection data provided by the bank or enterprise is consistent with the collection data pre-entered by the individual, which can prove that the information provider is the person himself, and generate the corresponding biometric matching result; when the similarity calculation result is less than the similarity threshold, it means that the first biometric feature corresponding to the first feature vector and the second biometric feature corresponding to the second feature vector are very different. For example, the personal collection data provided by the bank or enterprise is inconsistent with the collection data pre-entered by the individual, and it cannot be proved that the information provider is the person himself, and the corresponding biometric matching result is generated.
[0113] On the basis of the above-mentioned implementation manner, since the biometric matching method provided in the present application can determine the biometric matching result by means of feature vector distance calculation, the accuracy of the biometric matching is ensured.
[0114] Based on the above implementation, Figure 6 As shown, the biometric feature collection data to be recorded includes the face biometric feature collection data to be recorded, and the second biometric feature includes the second face biometric feature. In the biometric feature matching method provided in the present application, step 106 includes:
[0115] Step 161: Perform one-dimensional vector processing on the facial biometric feature collection data to be recorded according to the biometric feature extraction algorithm to obtain a one-dimensional vector processing result;
[0116] Step 162: Perform component analysis on the one-dimensional vector processing result through a covariance matrix to obtain the second facial biometric feature.
[0117] Specifically, in the biometric matching method provided by the present application, taking the biometric extraction of facial information as an example, feature vectors of the first facial biometric and the second facial biometric can be collected respectively by using eigenfaces and neural base area visual processing:
[0118] After obtaining the biometric data to be matched, the facial data is first collected and processed into images of the same size containing the face. Then, one-dimensional vectors are processed and averaged to obtain the one-dimensional vector processing results. Then, principal component analysis is performed, and the one-dimensional vector processing results are analyzed by covariance matrix processing to obtain eigenvalues and eigenvectors. The changes in these data represent the changes in facial features. Subsequently, each eigenvector is extracted and matched one-to-one with the identity information corresponding to the biometric data to be matched, such as ID, and saved.
[0119] Similarly, after obtaining the biometric feature collection data to be recorded and generating the corresponding feature value and feature vector, each feature vector is matched one-to-one with the ID corresponding to the biometric feature collection data to be recorded and saved.
[0120] Finally, the two feature vectors are compared in distance or similarity to obtain a comparison result, thereby achieving a matching effect of biometric features.
[0121] It should be emphasized that the biometric matching method provided by the present application is not limited to the biometric feature of face information, but can also match information on biometric information such as fingerprint information provided by the production end and fingerprint information, iris information, voice wave or voiceprint information provided by the consumer end. For example, when the collected data provided by the production end is fingerprint data, the fingerprint image can be extracted from the collected data by optical image acquisition, such as optical correlation tomography or ultrasonic scanning, and the fingerprint image is divided into sub-graphs, and the feature vectors of each sub-graph after division are extracted respectively, so as to obtain the fingerprint feature vector corresponding to the first biometric feature and the fingerprint feature vector corresponding to the second biometric feature, thereby realizing the fingerprint recognition and matching function.
[0122] When the production end provides iris information, the technical solution provided by the present application can locate the area where the human eye is located from the collected image, such as the face image, through the pre-trained neural network model, and extract the corresponding image, and then extract the image fiber where the human eye is located. Color and other information and generate an iris feature vector, thereby respectively obtaining the iris feature vector corresponding to the first biometric feature and the iris feature vector corresponding to the second biometric feature, thereby realizing the iris recognition and matching function.
[0123] When the production end provides voiceprint or voiceprint information, the technical solution provided in the present application can extract the feature vector of the voiceprint based on the voiceprint information through a pre-prepared neural network model, so as to obtain the voiceprint feature vector corresponding to the first biometric feature and the voiceprint feature vector corresponding to the second biometric feature, thereby realizing the voiceprint recognition and matching functions.
[0124] On the basis of the above-mentioned implementation modes, since the biometric matching method provided by the present application can collect and match feature vectors of various different biometric features such as face, fingerprint, iris, voiceprint, etc., the application scope of the present application is expanded and the versatility of the present application is improved.
[0125] Based on the above implementation, Figure 7 As shown, this application also provides an example of a biometric management interaction process:
[0126] The producer is a natural person or authorized person who owns the biometrics. He / she sends facial information, fingerprint information, iris information, voiceprint information and other biometric information to the manager as the regulatory department, so that the manager can save the producer's biometrics. The manager not only provides a place and method to extract the producer's biometric collection data to be recorded, but also saves and processes the source data such as the biometric collection data to be recorded, and processes the collected data through its own algorithm to obtain the producer's second biometric and other sequence information, and also stores and processes the second biometric. In addition, the manager also provides windows and interfaces for producers to set and update authorization information, such as the user's identity ID, biometric type, biometric validity period, and number of biometric uses.
[0127] Among them, producers can also use their own unique identification codes, such as ID number, organization code, social unified credit code and other information to match biometric information. When the unique identification code attached to the biometric matching request issued by the consumer corresponds to it, the matching result output by the administrator can be obtained.
[0128] After the producer completes the entry of his or her own biometrics, the consumer or user, such as a natural person, company or organization, initiates a biometric matching request to the administrator, first using the interface and method provided by the administrator to query the authorization information, and when the consumer's identity ID, biometric type, biometric validity period, and number of biometric uses meet the authorization requirements set by the producer, the biometric matching action is performed, and the biometric matching result after the administrator's matching is received. Among them, the consumer can also obtain the authorization result fed back by the administrator, and re-initiate the biometric matching request based on the authorization result, which is not limited in this application.
[0129] For example, the producer sets and updates the permission information of biometric features through the interface provided by the administrator, such as a window and the Internet. The permission information set by the producer includes but is not limited to the authorization object, such as the consumer's identity code, the type of authorization information, such as facial information or fingerprint information, the authorization validity period, such as "May 1, 2023 to April 30, 2024" and the number of authorizations, such as "10 times". The final permission information example is as follows: "The producer (identification code 44XXXX19980101XXXX) authorizes the consumer (identification code 9134182485354232XM) to query and match facial information 10 times between May 1, 2023 and April 30, 2024".
[0130] Before consumers need to match the biometric data to be matched, they first query whether they are authorized through the interface provided by the administrator. When the consumer's identity ID is inconsistent and the biometric type is inconsistent, the administrator determines that there is no authorization; when the consumer's time node is not within the time limit, the biometric information cannot be verified. When the consumer meets the above authority requirements, the administrator sends authorization information to the consumer and provides the consumer with a biometric extraction algorithm. The consumer extracts features from the biometric data to be matched according to the biometric extraction algorithm provided by the administrator to obtain the first biometric information. The consumer then sends the first biometric information to the administrator and deletes the first biometric information. The administrator matches the first biometric with the second biometric information to obtain a biometric matching result. Finally, the administrator sends the biometric matching result to the consumer and deletes the first biometric information obtained based on the biometric data to be matched.
[0131] The second embodiment of the present application relates to a biometric management device, which is applied to a management end trusted by a production end and a consumer end, such as Figure 8 As shown, including:
[0132] A feature extraction algorithm sending module 201 is used to send a preset biometric feature extraction algorithm to the consumer end;
[0133] A matching request acquisition module 202, configured to acquire a biometric matching request returned by the consumer end, wherein the biometric matching request includes a first biometric feature obtained by the consumer end from the biometric feature collection data to be matched based on the biometric feature extraction algorithm, wherein the consumer end does not grant storage permission for the first biometric feature;
[0134] A biometric matching module 203, configured to match the first biometric with a pre-stored second biometric to obtain a biometric matching result;
[0135] The matching result processing module 204 is used to output the biometric matching result to the consumer end.
[0136] On the basis of the above implementation, the biometric management device provided by the present application further includes:
[0137] A biometric record request acquisition module, used to acquire a biometric record request, wherein the biometric record request includes biometric collection data to be recorded;
[0138] The second feature extraction module is used to extract features from the biometric feature collection data to be recorded according to the biometric feature extraction algorithm to obtain a second biometric feature.
[0139] On the basis of the above implementation, in the biometric management device provided by the present application, the feature extraction algorithm sending module 201 includes:
[0140] An authorization request obtaining unit, configured to obtain an authorization request sent by the consumer end, wherein the authorization request includes first authorization information;
[0141] An authorization result matching unit, used to perform authorization matching according to the first authorization information and the pre-stored second authorization information to obtain an authorization matching result;
[0142] An algorithm sending unit is used to send the biometric feature extraction algorithm to the consumer end when the authorization matching result is that the first authorization information corresponds to the second authorization information.
[0143] On the basis of the above implementation, in the biometric management device provided by the present application, the authorization result matching unit includes:
[0144] A term matching subunit, configured to match the authority term according to the request time node and the validity period to obtain the authority term matching result;
[0145] an identity matching subunit, configured to perform identity information matching according to the first identity information and the second identity information to obtain the identity information matching result;
[0146] The number verification subunit is used to perform number verification according to the remaining number of times to obtain a number verification result.
[0147] On the basis of the above implementation, the first authorization information includes the request time node, and the second authorization information includes the validity period. The biometric management device provided by the present application also includes:
[0148] The validity period matching module is used to match the permission period according to the request time node and the validity period to obtain the permission period matching result;
[0149] The validity period verification module is used to determine the biometric collection data to be matched after the validity period verification when the permission period matching result is that the request time node is within the validity period.
[0150] On the basis of the above implementation, the first authorization information includes the request time node, and the second authorization information includes the validity period. The biometric management device provided by the present application also includes:
[0151] An identity information matching module, used to perform identity information matching according to the first identity information and the second identity information to obtain an identity information matching result;
[0152] The identity information verification module is used to determine the biometric feature collection data to be matched after the identity information is verified when the identity information matching result is that the first identity information and the second identity information are consistent.
[0153] On the basis of the above implementation, the first biometric feature includes a first feature vector, and the second biometric feature includes a second feature vector. In the biometric feature management device provided by the present application, the biometric feature matching module 203 includes:
[0154] A distance calculation unit, used for performing distance calculation on the first eigenvector and the second eigenvector to obtain a distance calculation result;
[0155] A distance comparison unit is used to compare the distance calculation result with a preset vector distance threshold to obtain a distance comparison result;
[0156] The result generating unit is used to generate a biometric feature matching result according to the distance comparison result.
[0157] On the basis of the above implementation, the biometric feature collection data to be recorded includes the face biometric feature collection data to be recorded, and the second biometric feature includes the second face biometric feature. In the biometric feature management device provided by the present application, the second feature extraction module includes:
[0158] A one-dimensional vector processing unit, used to perform one-dimensional vector processing on the facial biometric feature collection data to be recorded according to the biometric feature extraction algorithm to obtain a one-dimensional vector processing result;
[0159] A covariance component analysis unit is used to perform component analysis on the one-dimensional vector processing result through a covariance matrix to obtain the second facial biometric feature.
[0160] A third embodiment of the present application relates to a biometric management system, comprising:
[0161] The consumer end is used to receive a preset biometric feature extraction algorithm sent by the consumer end, and based on a first biometric feature obtained by the biometric feature extraction algorithm from the biometric feature collection data to be matched, send a biometric feature matching request containing the first biometric feature to the management end, and receive the biometric feature matching result returned by the management end;
[0162] The management end trusted by the consumer end is used to send the biometric extraction algorithm to the consumer end, receive the biometric matching request returned by the consumer end, match the first biometric with a pre-stored second biometric to obtain the biometric matching result, and output the biometric matching result to the consumer end.
[0163] A fourth embodiment of the present application relates to an electronic device, such as Fig. 9 As shown, including:
[0164] at least one processor 301; and,
[0165] A memory 302 is communicatively connected to the at least one processor 301; wherein,
[0166] The memory 302 stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor 301 so that the at least one processor 301 can implement the biometric matching method described in the first embodiment of the present application.
[0167] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.
[0168] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.
[0169] The fifth embodiment of the present application relates to a non-volatile computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the biometric matching method described in the first embodiment of the present application is implemented.
[0170] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.
[0171] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the application disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.
[0172] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A biometric matching method, characterized in that: Applied to a management end trusted by a consumer end, the method comprises: Sending a preset biometric feature extraction algorithm to the consumer end; Obtaining a biometric feature matching request returned by the consumer end, wherein the biometric feature matching request includes a first biometric feature obtained by the consumer end from the biometric feature collection data to be matched based on the biometric feature extraction algorithm, wherein the consumer end does not grant storage permission for the first biometric feature; Matching the first biometric feature with a pre-stored second biometric feature to obtain a biometric feature matching result; The biometric matching result is output to the consumer end.
2. The method according to claim 1, characterized in that Before matching the first biometric feature with a pre-stored second biometric feature to obtain a biometric feature matching result, the method further includes: Obtaining a biometric record request, wherein the biometric record request includes biometric collection data to be recorded; The biometric feature collection data to be recorded is subjected to feature extraction according to the biometric feature extraction algorithm to obtain the second biometric feature.
3. The method according to claim 1, characterized in that The sending of the preset biometric feature extraction algorithm to the consumer terminal comprises: Obtaining an authorization request sent by the consumer end, wherein the authorization request includes first authorization information; Performing authorization matching according to the first authorization information and the pre-stored second authorization information to obtain an authorization matching result; When the authorization matching result is that the first authorization information corresponds to the second authorization information, the biometric feature extraction algorithm is sent to the consumer end.
4. The method according to claim 3, characterized in that The first authorization information includes the first identity information and the request time node, the second authorization information also includes the second identity information, the validity period and the remaining number of times, the authorization matching result includes the authority period matching result, the identity information matching result and the number of times verification result, and the authorization matching result obtained by performing authorization matching based on the first authorization information and the pre-stored second authorization information includes: Matching the permission period with the validity period according to the request time node to obtain the permission period matching result; Perform identity information matching according to the first identity information and the second identity information to obtain the identity information matching result; A number check is performed according to the remaining number of times to obtain a number check result.
5. The method according to claim 1, characterized in that The first biometric feature includes a first feature vector, the second biometric feature includes a second feature vector, and the matching of the first biometric feature with the pre-stored second biometric feature to obtain a biometric feature matching result includes: Performing distance calculation on the first eigenvector and the second eigenvector to obtain a distance calculation result; Compare the distance calculation result with a preset vector distance threshold to obtain a distance comparison result; The biometric feature matching result is generated according to the distance comparison result.
6. The method according to claim 2, characterized in that The biometric feature collection data to be recorded includes face biometric feature collection data to be recorded, the second biometric feature includes a second face biometric feature, and the feature extraction of the biometric feature collection data to be recorded according to the biometric feature extraction algorithm to obtain the second biometric feature includes: According to the biometric feature extraction algorithm, one-dimensional vector processing is performed on the biometric feature collection data of the human face to be recorded to obtain a one-dimensional vector processing result; Perform component analysis on the one-dimensional vector processing result through a covariance matrix to obtain the second facial biometric feature.
7. A biometric management device, characterized in that: The management end used for consumer trust includes: A feature extraction algorithm sending module, used to send a preset biometric feature extraction algorithm to the consumer end; a matching request acquisition module, configured to acquire a biometric matching request returned by the consumer end, wherein the biometric matching request includes a first biometric feature obtained by the consumer end from the biometric feature collection data to be matched based on the biometric feature extraction algorithm, wherein the consumer end does not grant storage permission for the first biometric feature; A biometric matching module, used to match the first biometric with a pre-stored second biometric to obtain a biometric matching result; The matching result processing module is used to output the biometric matching result to the consumer end.
8. A biometric management system, characterized in that: include: The consumer end is used to receive a preset biometric feature extraction algorithm sent by the consumer end, and based on a first biometric feature obtained by the biometric feature extraction algorithm from the biometric feature collection data to be matched, send a biometric feature matching request containing the first biometric feature to the management end, and receive the biometric feature matching result returned by the management end; The management end trusted by the consumer end is used to send the biometric extraction algorithm to the consumer end, receive the biometric matching request returned by the consumer end, match the first biometric with a pre-stored second biometric to obtain the biometric matching result, and output the biometric matching result to the consumer end.
9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the biometric matching method according to any one of claims 1 to 6 are implemented.
10. A readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the biometric matching method according to any one of claims 1 to 6 is implemented.
