Identity authentication method, device, equipment, storage medium and program product
By dynamically adjusting the matching weights of identity authentication features, the problem of insufficient accuracy of identity authentication in different environments is solved, thereby improving the environmental adaptability and accuracy of identity authentication.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- INDUSTRIAL AND COMMERCIAL BANK OF CHINA
- Filing Date
- 2026-03-05
- Publication Date
- 2026-07-14
AI Technical Summary
In existing technologies, identity authentication methods based on multimodal biometrics are not accurate enough in different environments, leading to inaccurate identity authentication.
By acquiring the identity authentication features and environmental information of the authentication object, the matching weight of each feature is dynamically adjusted to adapt to different environmental conditions and improve the accuracy of identity authentication.
Improve the accuracy and reliability of identity authentication in different environments, enhance the environmental adaptability of identity authentication, and reduce the risk of misjudgment and incorrect judgment.
Smart Images
Figure CN122389013A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of biometric technology, and in particular to an identity authentication method, device, equipment, storage medium, and program product. Background Technology
[0002] In modern society, accurate identity authentication is required in various scenarios such as finance, government affairs, healthcare, and logistics. These scenarios include withdrawing money from bank ATMs, obtaining documents at government self-service terminals, picking up medicines at hospital self-service pharmacies, and retrieving packages from express delivery lockers. These scenarios place higher demands on the convenience and security of identity authentication.
[0003] In related technologies, fixed matching weights are used to perform comprehensive matching based on multimodal biometrics, such as facial features, fingerprint features, and iris features, in order to verify the identity of a person. However, this method has the problem of inaccurate identity authentication. Summary of the Invention
[0004] This application provides an identity authentication method, apparatus, device, storage medium, and program product to solve the technical problem of inaccurate identity authentication.
[0005] Firstly, this application provides an identity authentication method, including:
[0006] Obtain the authentication characteristics and authentication environment information of the authentication object;
[0007] The matching weights corresponding to the identity authentication features are determined based on the identity authentication environment information. The matching weights are used to represent the degree of contribution of the identity authentication features to identity authentication.
[0008] The identity authentication object is authenticated based on the identity authentication features and the matching weights corresponding to those features.
[0009] Secondly, this application provides an identity authentication device, comprising:
[0010] The acquisition module is used to acquire the authentication characteristics and authentication environment information of the authentication object.
[0011] The determination module is used to determine the matching weights corresponding to the identity authentication features based on the identity authentication environment information. The matching weights are used to represent the degree of contribution of the identity authentication features to identity authentication.
[0012] The authentication module is used to authenticate the identity of the object based on the identity authentication features and the matching weights corresponding to those features.
[0013] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;
[0014] The memory stores the instructions that the computer executes;
[0015] The processor executes computer execution instructions stored in memory, causing the processor to perform the methods described in the various possible implementations of the first aspect above.
[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the methods described in the various possible implementations of the first aspect above.
[0017] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed, implements the methods described in the various possible implementations of the first aspect above.
[0018] The authentication method provided in this application obtains the authentication features and environment information of the authentication object; determines the matching weight corresponding to the authentication feature based on the environment information, whereby the matching weight represents the contribution of the authentication feature to the authentication process; and performs authentication on the authentication object based on the authentication feature and its corresponding matching weight. This method adaptively adjusts the matching weight corresponding to the authentication feature based on the environment information, enhancing the environmental adaptability of authentication and improving its accuracy under different environmental conditions. Attached Figure Description
[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0020] Figure 1 A flowchart illustrating the identity authentication method provided in this application embodiment;
[0021] Figure 2 This is a schematic diagram of the structure of the identity authentication device provided in the embodiments of this application;
[0022] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.
[0023] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation
[0024] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0025] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for users to choose to authorize or refuse.
[0026] Furthermore, the technical solution involved in this application, which involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.) and the use of artificial intelligence technology for automated decision-making, and makes decisions that have a significant impact on personal rights based on the results of automated decision-making, provides users with corresponding operation entry points for users to choose to agree to or reject the results of automated decision-making; if the user chooses to reject, the process will proceed to the expert decision-making process.
[0027] It should be noted that the identity authentication methods, devices, equipment, storage media, and program products provided in this application can be used in the field of biometrics, or in any field other than biometrics. The application fields of the identity authentication methods, devices, equipment, storage media, and program products in this application are not limited.
[0028] The specific application scenarios of this application are those requiring identity authentication, such as withdrawing cash from bank ATMs, retrieving documents from government self-service terminals, picking up medicine at hospital self-service pharmacies, and retrieving packages from express delivery lockers. These scenarios place higher demands on the convenience and security of identity authentication. Current technologies employ multiple identity authentication information methods based on fixed matching weights to authenticate the target, resulting in poor environmental adaptability and inaccurate identity authentication.
[0029] The authentication method provided in this application adaptively adjusts the matching weights corresponding to authentication features based on authentication environment information, enabling efficient and accurate authentication of objects based on authentication features in different authentication environments, thereby improving the environmental adaptability and accuracy of authentication. It aims to solve the aforementioned technical problems of existing technologies.
[0030] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.
[0031] Figure 1 This is a flowchart illustrating the identity authentication method provided in an embodiment of this application. Figure 1 As shown, the identity authentication method provided in this application includes:
[0032] S101. Obtain the identity authentication characteristics and identity authentication environment information of the identity authentication object.
[0033] Specifically, identity authentication features can include biometric features such as finger vein patterns, facial features, iris patterns, and fingerprint patterns, as well as unique authentication features specific to the object being authenticated, such as digital identifiers. There can be one or more identity authentication features. Identity authentication environmental information includes the current ambient brightness, the distance to the object being authenticated, and the degree of occlusion in the feature recognition area.
[0034] S102. Determine the matching weights corresponding to the identity authentication features based on the identity authentication environment information. The matching weights are used to represent the degree of contribution of the identity authentication features to identity authentication.
[0035] It is understandable that different authentication features have varying processing efficiencies in different authentication environments. The core reason lies in the inherent differences in the technical acquisition requirements, data storage formats, and algorithm verification logic of features such as finger veins, faces, irises, and fingerprints. Furthermore, different authentication environments create variations in physical conditions, device computing power, network quality, and environmental interference. For example, fingerprint features are easily affected by environmental factors such as humidity and wear, resulting in significantly reduced acquisition and verification efficiency in dusty outdoor environments where hands are easily wet. Facial features are constrained by environmental conditions such as lighting, shooting angle, and obstructions, leading to a marked decrease in processing efficiency in low-light or backlit remote authentication environments. Iris features require extremely high precision in acquisition equipment and shooting distance, making rapid acquisition and verification difficult in simple authentication environments with limited equipment and space. Finger vein features are less affected by environmental interference and can maintain relatively stable acquisition efficiency even in complex physical environments, but they require specialized equipment, have complex algorithms, and thus have lower processing efficiency.
[0036] Therefore, to improve the efficiency and accuracy of identity authentication, the matching weights are adaptively adjusted based on the identity authentication environment information. For example, in bright lighting conditions, the matching weights of identity authentication features measured by optical sensors are increased; as the lighting becomes dim, the matching weights of identity authentication features measured by optical sensors are decreased, while the matching weights of other identity authentication features measured by non-optical sensors are increased, thereby improving the adaptability of identity authentication to the environment.
[0037] S103. Based on the identity authentication features and the matching weights corresponding to the identity authentication features, perform identity authentication on the identity authentication object.
[0038] Specifically, for cases with only one authentication feature, if the authentication feature collected in the current environment is found to be inaccurate based on the authentication environment information, the matching weight of the authentication feature will be reduced, and if the authentication fails, the authentication object will be prompted to use other authentication methods that are not affected by environmental factors, such as account-password authentication.
[0039] For scenarios where multiple authentication features are pre-set, matching weights are adaptively allocated based on the authentication environment information. For example, in low-light conditions, the matching weight of authentication features measured by optical sensors is reduced, while the matching weight of authentication features measured by non-optical sensors is increased. The authentication result is then determined by weighting the matching results of various authentication features.
[0040] The identity authentication method provided in this application, based on the adaptation rules between environmental features and various identity authentication features, dynamically and adaptively adjusts and optimizes the matching weights corresponding to different identity authentication features. It increases the matching weights of authentication features that are more complete, more stable in verification, and more effective in the current environment, while appropriately decreasing the matching weights of authentication features that are more susceptible to environmental interference and have reduced reliability. Through this dynamic weight adjustment mechanism, the identity authentication system can flexibly adapt to different environmental conditions, effectively enhancing the overall environmental adaptability and scenario adaptability of identity authentication. This fundamentally compensates for the shortcomings of a single weight mode in complex environments, significantly improving the accuracy and reliability of identity authentication under various differentiated environmental conditions.
[0041] Optionally, the identity authentication features include a first identity authentication feature measured by an optical sensor and a second identity authentication feature measured by a non-optical sensor. The matching weights corresponding to the identity authentication features are determined based on the identity authentication environment information, including:
[0042] The measurement accuracy of the optical sensor is determined based on the identity authentication environment information;
[0043] If the measurement accuracy is less than the accuracy threshold, reduce the matching weight corresponding to the first identity authentication feature and increase the matching weight corresponding to the second identity authentication feature.
[0044] First, the collected identity authentication environment information is comprehensively analyzed, quantitatively evaluated, and integrated. Combining the working principle and environmental adaptability of the optical sensor, the actual accuracy of feature measurement under the current environmental conditions is accurately determined. Second, the determined actual measurement accuracy of the optical sensor is compared with the system's preset accuracy threshold. If the detection result shows that the actual measurement accuracy is less than the preset accuracy threshold, it indicates that the current environment has significantly interfered with the optical sensor's measurement work, leading to a decrease in the reliability of the first identity authentication feature it collects. In this case, the system will automatically perform a weight adjustment operation, appropriately reducing the matching weight corresponding to the first identity authentication feature, while correspondingly increasing the matching weight corresponding to the second identity authentication feature, which is measured by a non-optical sensor and is less affected by the current environment. This ensures that the weight allocation for identity authentication aligns with the actual environment, guaranteeing the rationality of feature matching and the reliability of the authentication results.
[0045] The identity authentication method provided in this application determines the measurement accuracy of optical sensors by using identity authentication environment information and dynamically adjusts the matching weights of corresponding authentication features of optical and non-optical sensors. This allows the identity authentication system to adaptively adjust the feature weight allocation according to the actual environmental conditions, effectively avoiding feature acquisition and verification deviations caused by environmental interference of optical sensors, strengthening the authentication contribution of non-optical sensor features in adverse environments, significantly improving the environmental adaptability and anti-interference capability of identity authentication, ensuring the accuracy, stability and reliability of identity authentication judgment under various environmental conditions, and making the authentication logic more in line with the objective needs of actual application scenarios.
[0046] Optionally, the identity authentication features include facial features and non-facial features. The matching weights corresponding to the identity authentication features are determined based on the identity authentication environment information, including:
[0047] Based on the identity authentication environment information, determine the degree of facial occlusion of the identity authentication target;
[0048] If the degree of face occlusion is greater than the occlusion threshold, the matching weight corresponding to the face feature is reduced, and the matching weight corresponding to the non-face feature is increased.
[0049] Specifically, the system comprehensively analyzes, extracts features from, and quantifies the acquired full-scale identity authentication environment information. It combines this with factors such as potential occlusion sources, shooting angles, and scene occlusion conditions to accurately determine the actual degree of facial occlusion of the identity authentication subject in the current environment. Next, this actual degree of facial occlusion is compared with a pre-set facial occlusion threshold. If the actual degree of occlusion exceeds the threshold, it indicates that the completeness of facial feature collection, information validity, and verification reliability are significantly affected in the current environment. In this case, the system automatically performs dynamic weight adjustment, appropriately reducing the matching weight of facial features in the overall identity authentication process while correspondingly increasing the matching weight of non-facial features that are less affected by the current facial occlusion environment and have higher information validity. This achieves a scientific allocation of authentication feature weights, ensuring that the identity authentication logic is adapted to the actual current environment.
[0050] The identity authentication method provided in this application determines the degree of face occlusion of the authentication object by combining identity authentication environment information, and dynamically adjusts the matching weights of facial features and non-facial features based on the comparison result of the occlusion degree and a preset threshold. When the degree of face occlusion exceeds the threshold, the weight of facial features is reduced and the weight of non-facial features is increased. This can effectively avoid problems such as incomplete feature collection and inaccurate verification results caused by face occlusion, reduce the interference of adverse environments on identity authentication, make the weight allocation of authentication features more in line with the objective conditions of the actual scenario, and give full play to the authentication value of non-facial features in such scenarios. This improves the scenario adaptability and anti-interference ability of the identity authentication system, and ensures the accuracy, stability and reliability of identity authentication judgment in different environments.
[0051] Optionally, before authenticating the object being authenticated, the following steps are also included:
[0052] Obtain the liveness information of the object being authenticated;
[0053] The identity verification object is determined to be a living person based on the liveness feature information.
[0054] Specifically, using dedicated feature acquisition equipment and compliant acquisition methods, the liveness information of the identity authentication object is accurately obtained. This type of information consists of unique features that characterize the physiological liveness attributes of the object, possessing the core characteristics of being uncopyable and real-time, effectively distinguishing real live individuals from forged carriers such as photos, videos, and models. The collected liveness information is then fed into a pre-set liveness detection algorithm model for professional analysis and verification. Through feature matching, dynamic verification, and other technical means, the authenticity and validity of the feature information are accurately identified. Finally, based on the verification results, the identity authentication object is determined to be a real live individual, completing the pre-verification of liveness detection.
[0055] The identity authentication method provided in this application determines that the identity authentication object is a living person before performing identity authentication, thus laying a solid security foundation for subsequent formal identity authentication operations, avoiding the authentication risk of forgery and impersonation from the source, and ensuring the security and authenticity of the entire identity authentication process.
[0056] Optionally, identity authentication is performed on the object based on the identity authentication features and the matching weights corresponding to those features, including:
[0057] Determine the matching degree between the identity authentication and the authentication information in the preset storage space;
[0058] The credibility of identity authentication is determined by the product of the matching degree and the matching weight.
[0059] If the authentication credibility is greater than the credibility threshold, then the authentication of the object is deemed successful.
[0060] Specifically, after collecting identity authentication features and dynamically allocating matching weights, a formal identity verification operation will be conducted on the identity authentication object by combining various identity authentication features and their corresponding matching weights. First, the collected feature information of the identity authentication object is compared and similarity calculated dimension-by-dimensionally with the object's standard authentication information pre-stored in the system's preset storage space to accurately determine the actual matching degree of each feature in the identity authentication process. Second, according to the weighted calculation rules, the actual matching degree of each identity authentication feature is multiplied by its corresponding matching weight, and all calculation results are summarized to determine the overall identity authentication credibility of the object in this verification. This credibility is a core indicator for quantifying the degree of identity matching, comprehensively reflecting the authentication contribution and overall matching effect of each feature in the current environment. Finally, the calculated overall identity authentication credibility is compared with a preset credibility threshold. If the result shows that the identity authentication credibility is greater than the preset credibility threshold, it indicates that the overall result of this identity verification meets the system's authentication standard, and the identity authentication process for the object is directly determined to have passed, completing the entire identity verification process.
[0061] The identity authentication method provided in this application combines various identity authentication features and corresponding dynamic matching weights to conduct identity authentication. It first calculates the matching degree between features and pre-stored information, then multiplies the matching degree by the weight to obtain the overall authentication credibility. Finally, it uses a credibility threshold as the authentication pass criterion. This approach ensures that the identity authentication result fully considers the actual adaptability and authentication contribution of different features in the current environment, avoiding the bias of single feature matching or equal weight judgment. Furthermore, it forms an objective and unified authentication credibility index through quantitative calculation, providing clear quantitative basis for authentication judgment and effectively improving the scientific, accurate, and objective nature of identity authentication judgment. Simultaneously, using a credibility threshold as the pass standard accurately controls the pass line of the authentication result, ensuring the reliability of the authentication pass result and significantly reducing the risk of misjudgment or incorrect judgment due to environmental interference or feature failure. This allows identity authentication to achieve accurate and stable verification judgment in various environments.
[0062] Optionally, there are at least two authentication features. The authentication credibility is determined by the product of the matching degree and the matching weight, including:
[0063] The product of the matching degree and the matching weight is determined as the feature recognition degree;
[0064] The credibility of identity authentication is determined by summing the feature recognition scores corresponding to the identity authentication features.
[0065] Specifically, the identity authentication process employs at least two types of identity authentication features. When determining the overall credibility of identity authentication based on the product of the matching degree of each feature and its corresponding matching weight, a standardized step-by-step calculation logic is followed. First, for each type of identity authentication feature, the actual matching degree obtained by comparing it with standard authentication information in a preset storage space is multiplied by the matching weight dynamically assigned to that feature based on the current environment information. The result of this single calculation is determined as the independent feature recognition degree for that type of feature. This indicator can accurately quantify the actual contribution value and effective recognition degree of a single type of identity authentication feature to the overall identity authentication in the current environment. Second, the feature recognition degrees corresponding to all feature types participating in this identity authentication are summed. The accumulated result of all single-type feature recognition degrees is used as the overall credibility of this identity authentication. Through the comprehensive summation of multi-dimensional feature recognition degrees, a comprehensive quantitative evaluation of the matching situation of the identity authentication object is achieved, allowing the overall credibility to fully reflect the comprehensive authentication effect of various features in the current environment.
[0066] The identity authentication method provided in this application, in scenarios employing two or more identity authentication features, obtains the feature recognition score by multiplying the matching degree of a single feature by its corresponding weight, and then sums all feature recognition scores to obtain the overall identity authentication credibility. This approach can accurately quantify the actual authentication contribution of each feature in combination with the current environment through multiplication operations, strongly correlating the recognition value of a single feature with the environmental weight. Furthermore, it can achieve comprehensive integration of multi-dimensional feature authentication results through summation operations, fully combining the authentication advantages of various features and compensating for the limitations of single features. Simultaneously, the quantification operation logic is clear and standardized, allowing the overall identity authentication credibility to comprehensively and objectively reflect the comprehensive matching effect of multiple features in the current environment, avoiding the one-sidedness of single-feature judgment, further improving the accuracy, scientificity, and reliability of identity authentication results, and making the multi-feature fusion authentication mode more suitable for the actual application needs of complex environments.
[0067] The present application provides an embodiment of physical item collection using the authentication method of the present application, including the following steps:
[0068] User registration: Placing a finger in the collection area triggers the pressure sensor to activate the near-focus iris imaging module, recording the face and iris. Data collection is performed during SMS notification and agreement signing. Customer information is entered, binding order quantity data, and linking the customer's finger vein to their account. The system dynamically adjusts infrared light intensity to compensate for pressure deformation; liveness detection is performed; subcutaneous blood flow thermograms and blood oxygenation signals, as well as face and iris information, are simultaneously captured; and a database is established.
[0069] Identity authentication: Identify identity information, collect data during SMS notification and agreement signing; identify veins, face, and iris, the system responds and initiates a verification request; automatically adjust the matching coefficients of veins, face, and iris according to the identity authentication method in the above embodiment; check whether the finger vein information is consistent with the vein, face, and iris information bound to the logged-in user; determine whether the finger vein information bound to the customer is consistent, and if so, activate the order information corresponding to the user account.
[0070] Physical delivery: After identity verification, the target compartment unlocks, and the lifting tray delivers the item to the retrieval port; the compartment automatically closes after the laser sensor detects that a person's hand has left.
[0071] Figure 2 This is a schematic diagram of the identity authentication device provided in an embodiment of this application. Figure 2 As shown, the identity authentication device 20 provided in this embodiment includes:
[0072] The acquisition module 201 is used to acquire the identity authentication characteristics and identity authentication environment information of the identity authentication object;
[0073] The determination module 202 is used to determine the matching weights corresponding to the identity authentication features based on the identity authentication environment information. The matching weights are used to represent the degree of contribution of the identity authentication features to identity authentication.
[0074] The authentication module 203 is used to authenticate the identity of the object based on the identity authentication features and the matching weights corresponding to the identity authentication features.
[0075] Optionally, the authentication features include a first authentication feature measured based on an optical sensor and a second authentication feature measured based on a non-optical sensor. The determining module 202 is specifically used for:
[0076] The measurement accuracy of the optical sensor is determined based on the identity authentication environment information;
[0077] If the measurement accuracy is less than the accuracy threshold, reduce the matching weight corresponding to the first identity authentication feature and increase the matching weight corresponding to the second identity authentication feature.
[0078] Optionally, the identity authentication features include facial features and non-facial features, and the determination module 202 is specifically used for:
[0079] Based on the identity authentication environment information, determine the degree of facial occlusion of the identity authentication target;
[0080] If the degree of face occlusion is greater than the occlusion threshold, the matching weight corresponding to the face feature is reduced, and the matching weight corresponding to the non-face feature is increased.
[0081] Optionally, before authenticating the object to be authenticated, the authentication module 203 is also used for:
[0082] Obtain the liveness information of the object being authenticated;
[0083] The identity verification object is determined to be a living person based on the liveness feature information.
[0084] Optionally, authentication module 203 is specifically used for:
[0085] Determine the matching degree between the identity authentication and the authentication information in the preset storage space;
[0086] The credibility of identity authentication is determined by the product of the matching degree and the matching weight.
[0087] If the authentication credibility is greater than the credibility threshold, then the authentication of the object is deemed successful.
[0088] Optionally, there are at least two authentication features, and authentication module 203 is also used for:
[0089] The product of the matching degree and the matching weight is determined as the feature recognition degree;
[0090] The credibility of identity authentication is determined by summing the feature recognition scores corresponding to the identity authentication features.
[0091] The identity authentication device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.
[0092] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 As shown, the electronic device 30 provided in this embodiment includes at least one processor 301 and a memory 302. Optionally, the electronic device 30 further includes a communication interface 303. The processor 301, memory 302, and communication interface 303 are connected via a communication bus 304.
[0093] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.
[0094] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.
[0095] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.
[0096] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.
[0097] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.
[0098] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.
[0099] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.
[0100] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.
[0101] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.
Claims
1. An identity authentication method, characterized in that, include: Obtain the authentication characteristics and authentication environment information of the authentication object; The matching weight corresponding to the identity authentication feature is determined based on the identity authentication environment information, and the matching weight is used to represent the degree of contribution of the identity authentication feature to identity authentication; The identity authentication object is authenticated based on the identity authentication features and the matching weights corresponding to the identity authentication features.
2. The identity authentication method according to claim 1, characterized in that, The identity authentication features include a first identity authentication feature measured based on an optical sensor and a second identity authentication feature measured based on a non-optical sensor. Determining the matching weight corresponding to the identity authentication feature based on the identity authentication environment information includes: Based on the identity authentication environment information, determine the measurement accuracy of the optical sensor; If the measurement accuracy is less than the accuracy threshold, the matching weight corresponding to the first identity authentication feature is reduced, and the matching weight corresponding to the second identity authentication feature is increased.
3. The identity authentication method according to claim 1, characterized in that, The identity authentication features include facial features and non-facial features. The matching weights corresponding to the identity authentication features are determined based on the identity authentication environment information, including: Based on the identity authentication environment information, determine the degree of face occlusion of the identity authentication object; If the degree of face occlusion is greater than the occlusion threshold, the matching weight corresponding to the face feature is reduced, and the matching weight corresponding to the non-face feature is increased.
4. The identity authentication method according to any one of claims 1 to 3, characterized in that, Before authenticating the identity of the object being authenticated, the process also includes: Obtain the liveness feature information of the authentication object; The identity authentication object is determined to be a living person based on the liveness feature information.
5. The identity authentication method according to any one of claims 1 to 3, characterized in that, The step of authenticating the identity object based on the identity authentication features and the matching weights corresponding to the identity authentication features includes: Determine the degree of matching between the identity authentication and the authentication information in the preset storage space; The credibility of identity authentication is determined by multiplying the matching degree by the matching weight. If the credibility of the identity authentication is greater than the credibility threshold, then the identity authentication of the authenticated object is determined to be successful.
6. The identity authentication method according to claim 5, characterized in that, The identity authentication features are at least two types, and the determination of identity authentication credibility based on the product of the matching degree and the matching weight includes: The product of the matching degree and the matching weight is determined as the feature recognition degree; The credibility of the identity authentication is determined by summing the feature recognition scores corresponding to the identity authentication features.
7. An identity authentication device, characterized in that, include: The acquisition module is used to acquire the authentication characteristics and authentication environment information of the authentication object. The determining module is used to determine the matching weight corresponding to the identity authentication feature based on the identity authentication environment information, wherein the matching weight is used to represent the degree of contribution of the identity authentication feature to identity authentication; The authentication module is used to authenticate the identity object based on the identity authentication features and the matching weights corresponding to the identity authentication features.
8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 6.
10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.