A method and system for user identification integrating multiple biometric features

Abstract

This invention relates to the field of user identification technology, and provides a user identification method and system integrating multiple biometric features. The method includes: receiving a user identification instruction and acquiring current user identification data; determining the type of biometric feature to be verified based on the current user identification data, wherein the obtained first biometric feature type is the most efficient biometric feature type for identifying the current user; extracting biometric data from the current user identification data based on the first biometric feature type to obtain a first biometric feature; and identifying the user's identity based on the first biometric feature. This eliminates the need for repeated attempts by the user, allows for the rapid extraction of sufficient biometric data from the best available equipment for identity comparison, and completes user identification, thereby improving the efficiency of user identification and optimizing the user's consumption experience.

Description

Technical Field

[0001] This invention relates to the field of user identification technology, and in particular to a user identification method and system integrating multiple biometric features. Background Technology

[0002] Consumer devices have undergone nearly 30 years of development in China, gradually evolving from simple card-swiping modes to modes that recognize fingerprints, palm prints, and faces. However, the content that current consumer devices can recognize is still relatively limited, and each biometric feature requires a dedicated recognition device, resulting in low efficiency in user identification and affecting the user's consumption experience. Summary of the Invention

[0003] This invention provides a user identification method integrating multiple biometric features, which solves the problem that existing consumer devices can only identify a single biometric feature, resulting in low efficiency in user identification and affecting the user's consumption experience.

[0004] The first aspect of this invention provides a user identification method integrating multiple biometric features, comprising:

[0005] Receive user identification instructions and obtain current user identification data; determine the type of biometric feature to be verified based on the current user identification data to obtain the first biometric feature type;

[0006] Based on the first biometric type, biometric data is extracted from the current user identification data to obtain the first biometric; the user's identity is identified based on the first biometric.

[0007] Preferably, the step of receiving the user identification instruction further includes:

[0008] Multiple sets of user identification sample data are acquired, and biometric data of each type are extracted to identify user posture features in each set of user identification sample data. The amount of biometric data of each type in each set of user identification sample data is calculated, and the correlation between the amount of biometric data of each type and the user posture features of the corresponding group is established.

[0009] Preferably, the step of determining the type of biometric feature to be verified based on the current user identification data to obtain the first biometric feature type specifically includes:

[0010] The user's posture is identified from the current user identification data to obtain the current user posture feature vector. Based on the current user posture feature vector, the user posture type with the largest feature data volume is predicted and set as the first biometric type.

[0011] Preferably, the step of determining the type of biometric feature to be verified based on the current user identification data to obtain the first biometric feature type specifically includes:

[0012] When the amount of predicted feature data for the first biometric type is less than a preset single decision parameter threshold, the current user posture feature vector is substituted into the biometric fusion prediction model to obtain multiple combinations of biometric types that satisfy the biometric fusion prediction model. The biometric fusion prediction model is specifically as follows:

[0013]

[0014] in, Let n be the unit vector of the nth biometric type. This is the current user pose feature vector. is the decision coefficient for the nth type of biometric data, and D is the threshold for the fusion decision parameter; the combination with the fewest biometric types is identified, and the corresponding biometric type is taken as the first biometric.

[0015] A second aspect of this application provides a user identification system integrating multiple biometric features, including:

[0016] The biometric selection module is used to receive user identification instructions, obtain current user identification data, determine the type of biometric feature to be verified based on the current user identification data, and obtain the first biometric feature type.

[0017] The user identity recognition module is used to extract biometric data from the current user identification data based on the first biometric type to obtain the first biometric; and to identify the user's identity based on the first biometric.

[0018] Preferably, the biometric selection module further includes, before receiving the user identification instruction:

[0019] Multiple sets of user identification sample data are acquired, and biometric data of each type are extracted to identify user posture features in each set of user identification sample data. The amount of biometric data of each type in each set of user identification sample data is calculated, and the correlation between the amount of biometric data of each type and the user posture features of the corresponding group is established.

[0020] Preferably, in the biometric selection module, the type of biometric to be verified is determined based on the current user identification data to obtain a first biometric type, specifically including:

[0021] The user's posture is identified from the current user identification data to obtain the current user posture feature vector. Based on the current user posture feature vector, the user posture type with the largest feature data volume is predicted and set as the first biometric type.

[0022] Preferably, in the biometric selection module, the type of biometric to be verified is determined based on the current user identification data to obtain a first biometric type, specifically including:

[0023] When the amount of predicted feature data for the first biometric type is less than a preset single decision parameter threshold, the current user posture feature vector is substituted into the biometric fusion prediction model to obtain multiple combinations of biometric types that satisfy the biometric fusion prediction model. The biometric fusion prediction model is specifically as follows:

[0024]

[0025] in, Let n be the unit vector of the nth biometric type. This is the current user pose feature vector. is the decision coefficient for the nth type of biometric data, and D is the threshold for the fusion decision parameter; the combination with the fewest biometric types is identified, and the corresponding biometric type is taken as the first biometric.

[0026] A third aspect of this application provides a user identification method and device integrating multiple biometric features, the device comprising a processor and a memory:

[0027] The memory is used to store program code and transmit the program code to the processor;

[0028] The processor is configured to execute, according to instructions in the program code, a multi-biometric integrated user identification method as described in any of the first aspects of the present invention.

[0029] The fourth aspect of this application provides a computer-readable storage medium for storing program code for executing a multi-biometric integrated user identification method according to any one of the first aspects of the present invention.

[0030] As can be seen from the above technical solutions, the present invention has the following advantages:

[0031] By receiving user identification instructions, the system obtains current user identification data; based on the current user identification data, it determines the type of biometric feature to be verified, and the resulting first biometric feature type is the most efficient biometric feature type for identifying the current user; based on the first biometric feature type, it extracts biometric data from the current user identification data to obtain the first biometric feature; based on the first biometric feature, it identifies the user's identity without requiring the user to repeat attempts, and can quickly extract sufficient biometric data for identity comparison using the best available equipment to complete user identification, thereby improving the efficiency of user identification and optimizing the user's consumption experience. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a flowchart of a user identification method that integrates multiple biometric features.

[0034] Figure 2 This is a structural diagram of a user identification system that integrates multiple biometric features. Detailed Implementation

[0035] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0036] This invention provides a user identification method integrating multiple biometric features, which solves the problem that existing consumer devices can only identify a single biometric feature, resulting in low efficiency in user identification and affecting the user's consumption experience.

[0037] Please see Figure 1 , Figure 1 This is the first flowchart of a user identification method integrating multiple biometric features provided in an embodiment of the present invention.

[0038] S100: Receive user identification instruction, obtain current user identification data; determine the biometric type to be verified based on the current user identification data, and obtain the first biometric type;

[0039] It should be noted that the user identification device in this embodiment integrates multiple types of biometric identification components, enabling the identification and extraction of various biometric data. For example, biometric features such as faces, fingerprints, and palm prints need to be identified and extracted from image-type user identification data. When a user identification command is received, the user to be identified has activated the user identification device. However, because this device integrates multiple biometric features, it needs to select the biometric feature most suitable for the current user's intent verification or verification, and determine the optimal biometric feature type corresponding to the current user's identification data. For example, when the current user opens their palm and triggers the data acquisition unit of the user identification device with their finger... In some cases, the device acquires current user identification data that includes images of fingers, palms, or even the user's face. The user's intention is to identify the user's fingerprint type biometrics. In this case, the biometric type to be verified can be determined to be fingerprint, and the fingerprint biometric type can be set as the first biometric type. However, there may be cases where the user originally wanted to identify their fingerprint, but there are stains on their fingers, making it difficult to extract fingerprint biometrics that can be used to identify the user's identity. In this case, the palm print should be set as the first biometric type based on the image of the current user identification data, or other biometric types such as voiceprint, face, iris, hand shape, gait, handwriting, skin infrared reflection, etc. should be set in the integrated identity recognition device.

[0040] The user identification device can use a Linux system-based main control board to control the collection, storage, and comparison verification of biometric features and various card swipe data, the data parsing and transmission of the QR code module, the interaction with the customer display linkage board, the interactive display of the main display screen, and the charging functions of various modes; and the main control board implements embedded programs, the program functions of which include "transaction query, transaction parameters, user management, data management, system management, network management, device self-test, information query" and other functions closely related to the charging of the consumer interface.

[0041] S200: Extract biometric data from the current user identification data based on the first biometric type to obtain the first biometric; identify the user's identity based on the first biometric.

[0042] It should be noted that in the aforementioned steps, the first biometric type to be identified and extracted was determined based on the current user identification data, but the biometric feature was not extracted. In this step, the corresponding biometric identification component will be called according to the first biometric type to extract the first biometric feature from the current user identification data. That is, the aforementioned step S100 is equivalent to preprocessing the current user identification data. The extracted first biometric feature is the most effective biometric feature type for identity recognition in the current user identification data. For example, if a user intends to identify their fingerprint biometric feature, but their finger is dirty, it is difficult to complete the identity recognition. A single device needs to repeatedly perform fingerprint recognition until the user cleans their finger and collects enough fingerprint biometric feature data. However, after the aforementioned preprocessing steps select the first biometric feature type in the integrated device, the user does not need to try repeatedly. The best device is called to quickly extract enough biometric feature data for identity comparison and complete the user identity recognition.

[0043] In this embodiment, by receiving a user identification instruction, current user identification data is obtained; based on the current user identification data, the type of biometric feature to be verified is determined, and the obtained first biometric feature type is the most efficient biometric feature type for identifying the current user; based on the first biometric feature type, biometric data is extracted from the current user identification data to obtain the first biometric feature; the user's identity is identified based on the first biometric feature, eliminating the need for repeated attempts by the user. The best device can be called to quickly extract sufficient biometric data for identity comparison, thereby completing user identification, improving the efficiency of user identification, and optimizing the user's consumption experience.

[0044] The above is a detailed description of the first embodiment of a multi-biometric feature integrated user identification method provided in this application. The following is a detailed description of the second embodiment of a multi-biometric feature integrated user identification method provided in this application.

[0045] In this embodiment, a multi-biometric integrated user identification method is further provided. Before receiving the user identification instruction in the aforementioned step S100, the method further includes:

[0046] Multiple sets of user identification sample data are acquired, and biometric data of each type are extracted to identify user posture features in each set of user identification sample data. The amount of biometric data of each type in each set of user identification sample data is calculated, and the correlation between the amount of biometric data of each type and the user posture features of the corresponding group is established.

[0047] It should be noted that user identification data from each instance of user identification in different postures are used as samples to form multiple sets of user identification sample data. The postures in each set of sample data can include the user extending a finger, palm, or facial posture, etc. All types of biometric recognition components within the user identification device are activated on the sample data to extract all types of biometric data. For the user postures in the user identification sample data, user posture features are identified, and these features are assigned directionality based on the user's limbs and movements. A pre-trained vectorized regression neural network model can be used to directly obtain the user posture feature vector after inputting the recognition data detected by images or other devices. Simultaneously, unit vectors are also set for different biometric types. That is, the component of the user posture feature vector in the direction of the unit vector of a certain biometric type reflects the amount of data of that type of biometric feature contained in the user posture; the larger the component, the more feature data there is. Based on the biometric data and user posture features of each type in the multiple sets of user identification sample data, the correlation between the amount of data of each type of biometric data and the user posture features of the corresponding group is calculated, resulting in the unit vector of each type of biometric data.

[0048] Step S100, which involves determining the type of biometric feature to be verified based on the current user identification data to obtain the first biometric feature type, specifically includes:

[0049] The user posture of the current user identification data is identified to obtain the current user posture feature vector. Based on the current user posture feature vector, the user posture type with the largest feature data volume is predicted and set as the first biometric type.

[0050] It should be noted that after extracting the current user posture feature vector from the current user identification data and calculating the components of the current user posture feature vector in the unit vector of each type of biometric feature, the biometric feature type with the largest component value is taken as the first biometric feature type. Predicting that the biometric feature type contains the largest amount of biometric feature data can perform user identification most efficiently.

[0051] Step S100, which involves determining the type of biometric feature to be verified based on the current user identification data to obtain the first biometric feature type, specifically includes:

[0052] When the amount of predicted feature data for the first biometric type is less than a preset single decision parameter threshold, the current user posture feature vector is substituted into the biometric fusion prediction model to obtain multiple combinations of biometric types that satisfy the biometric fusion prediction model. The biometric fusion prediction model is specifically as follows:

[0053]

[0054] in, Let n be the unit vector of the nth biometric type. This is the current user pose feature vector. is the decision coefficient for the nth type of biometric data, and D is the threshold for the fusion decision parameter; the combination with the fewest biometric types is identified, and the corresponding biometric type is taken as the first biometric.

[0055] It should be noted that in multi-biometric integrated identity recognition devices, if a single biometric feature cannot meet the user identification requirements, a multi-biometric feature fusion identification method can be adopted. When the predicted feature data volume of the first biometric feature type is less than the preset single decision parameter threshold, it can be considered as the biometric feature with the largest predicted biometric data volume, which cannot complete user identification. Therefore, multiple biometric features need to be combined to achieve identity recognition. The single decision parameter threshold is set according to the needs of biometric recognition. After substituting the current user posture feature vector into the biometric fusion prediction model, the effect of user identification after extracting biometric features from the current user identification data using multiple biometric features and then using decision-level fusion can be predicted. In the biometric fusion prediction model, the fusion decision parameter threshold D is used to evaluate whether the combination can complete user identification. Decision-level fusion makes the final judgment by fusing the decision results of different features. For example, fingerprints and irises can be used for identification separately, and their decision results can be fused to obtain a more reliable identification result. Each biometric feature requires a different number of features to complete its corresponding identification. Therefore, the corresponding biometric data volume decision coefficient is constructed according to the proportion of features required for different biometric features.

[0056] Calculate the current user pose feature vector Unit vector of the nth biometric type When considering the components, if a certain biometric data cannot be extracted from the current user identification data, the component will be zero or negative, but it can still form a combination of biometric types. When identifying the combination with the fewest biometric types, this biometric type will be eliminated. The biometric types of the combination that can achieve user identification through decision fusion and requires the fewest biometric types will be used as the first biometric, so that the corresponding biometric identification components are called in the next step, thereby improving the efficiency of user identification. The first biometric in this step must contain the biometric type with the largest amount of biometric data.

[0057] Because consumer devices have both an operating end and a consumer end, dual-screen different display can be used on user identification devices. That is, two screens display different interface content according to needs. This involves different human-computer interaction operations and display content on different display ends. In addition to improving the intuitive experience at the functional level, it also better reflects the application and conversion of data delivery content, function setting menus, and image and video stream display technologies.

[0058] A customer display linkage board is set up at the operation terminal for operators to quickly control the built-in key input and control the main display screen. It links with the underlying Linux system main control board to achieve real-time dual-screen interaction, allowing for the setting of various charging parameters, feedback on charging status, and quick modification of various charging modes. The main control module implements embedded programs with menu functions closely related to operator control, including "consumption mode, charging statistics, equipment testing, receipt printing, and key control." The main display screen connects to the customer display linkage board and keypad board to display the current device's communication status, consumption status (consumption mode, consumption amount, transaction success / failure status), recent transaction records, etc., in real time. Operators can quickly modify consumption modes, consumption amounts, and perform transaction error correction, view transaction statistics, and control external USB receipt printers via built-in or external keyboards. The customer display screen, through Linux... The system's underlying main control board is connected to a touchscreen to display various consumption modes (input consumption, fixed-amount consumption, bookkeeping consumption, product consumption, per-use consumption, transaction correction, cash top-up, QR code top-up, etc.) and consumption mode settings. It also displays human-computer interaction and touch confirmation when consumers use various identities (face, palm print, fingerprint, card, QR code) (displaying transaction user information, such as photo, name, employee number, consumption amount, account balance, etc.), real-time display of IPC video stream, user data management of the billing system, network parameter settings for communication with the backend, and device operating status display.

[0059] The user identification device can also be equipped with a functional communication board for controlling the device's power supply, power on / off, and communication with external devices. This communication board integrates a charging / discharging circuit, a power-on control circuit, an RJ45 Ethernet communication interface, a USB input device, USB communication, an external USB receipt printer, and an external electronic scale. The operation area features a button control zone, which connects to the customer display linkage board. This allows operators to quickly modify consumption patterns, transaction amounts, and correct transaction errors; view transaction statistics; control the external USB receipt printer; and control the input of various settings and display functions on the customer display linkage board.

[0060] The entire device mainly uses the Linux system-based main control board and the customer display linkage board as the core control components, and completes the linkage with other components through the built-in embedded program to meet the application requirements of different application scenarios.

[0061] The above is a detailed description of a multi-biometric integrated user identification method provided by the first aspect of this application. The following is a detailed description of an embodiment of a multi-biometric integrated user identification system provided by the second aspect of this application.

[0062] Please see Figure 2 , Figure 2 This is a structural diagram of a multi-biometric integrated user identification system. This embodiment provides a multi-biometric integrated user identification system, including:

[0063] The biometric selection module 10 is used to receive user identification instructions, obtain current user identification data, determine the type of biometric feature to be verified based on the current user identification data, and obtain the first biometric feature type.

[0064] User identity recognition module 20 is used to extract biometric data from the current user identification data based on the first biometric type to obtain the first biometric; and to identify the user identity based on the first biometric.

[0065] The biometric selection module 10 further includes the following components before receiving the user identification instruction:

[0066] Multiple sets of user identification sample data are acquired, and biometric data of each type are extracted to identify user posture features in each set of user identification sample data. The amount of biometric data of each type in each set of user identification sample data is calculated, and the correlation between the amount of biometric data of each type and the user posture features of the corresponding group is established.

[0067] In the biometric selection module 10, the type of biometric feature to be verified is determined based on the current user identification data to obtain the first biometric feature type, which specifically includes:

[0068] The user's posture is identified from the current user identification data to obtain the current user posture feature vector. Based on the current user posture feature vector, the user posture type with the largest feature data volume is predicted and set as the first biometric type.

[0069] In the biometric selection module 10, the type of biometric feature to be verified is determined based on the current user identification data to obtain the first biometric feature type, which specifically includes:

[0070] When the amount of predicted feature data for the first biometric type is less than a preset single decision parameter threshold, the current user posture feature vector is substituted into the biometric fusion prediction model to obtain multiple combinations of biometric types that satisfy the biometric fusion prediction model. The biometric fusion prediction model is specifically as follows:

[0071]

[0072] in, Let n be the unit vector of the nth biometric type. This is the current user pose feature vector. is the decision coefficient for the nth type of biometric data, and D is the threshold for the fusion decision parameter; identify the combination with the fewest biometric types and take the corresponding biometric type as the first biometric.

[0073] A third aspect of this application also provides a multi-biometric integrated user identification method device, including a processor and a memory: wherein the memory is used to store program code and transmit the program code to the processor; the processor is used to execute the above-mentioned multi-biometric integrated user identification method according to the instructions in the program code.

[0074] A fourth aspect of this application provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code for executing the above-described multi-biometric integrated user identification method.

[0075] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described apparatus and equipment can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0077] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0078] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0079] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, 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 storage medium 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 described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0080] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A user identification method integrating multiple biometric features, characterized in that... include: Acquire multiple sets of user identification sample data, extract various types of biometric data respectively, and identify user posture features in each set of user identification sample data; Calculate the amount of each type of biometric data in each group of user identification sample data, and establish the correlation between the amount of each type of biometric data and the user posture features of the corresponding group. Receive user identification instructions and obtain current user identification data; determine the type of biometric feature to be verified based on the current user identification data to obtain the first biometric feature type, which specifically includes: The user's posture is identified from the current user identification data to obtain the current user posture feature vector. Based on the current user posture feature vector, the user posture type with the largest feature data volume is predicted and set as the first biometric type. When the predicted feature data volume of the first biometric type is less than a preset single decision parameter threshold, the current user posture feature vector is substituted into the biometric fusion prediction model to obtain multiple combinations of biometric types that satisfy the biometric fusion prediction model. Specifically, the biometric fusion prediction model is as follows: ； in, The unit vector for the nth biometric type is obtained by assigning directionality to the user's posture features based on the user's limbs and movements, and then setting different biometric types. The current user posture feature vector is represented by the component of the user posture feature vector in the unit vector direction of a certain biometric feature type. This component reflects the amount of data of that type of biometric feature contained in the user posture. The larger the component, the more feature data there is. Let be the decision coefficient for the nth type of biometric data volume. The corresponding biometric data volume decision coefficients are constructed based on the required proportions of different biometric features. To fuse decision parameter thresholds; identify the combination with the fewest number of biometric types and use the corresponding biometric type as the first biometric; Based on the first biometric type, biometric data is extracted from the current user identification data to obtain the first biometric; the user's identity is identified based on the first biometric.

2. A user identification system integrating multiple biometric features, characterized in that, include: The biometric selection module is used to acquire multiple sets of user identification sample data, extract various types of biometric data, and identify user posture features in each set of user identification sample data. Calculate the data volume of each type of biometric data in each group of user identification sample data, establish the correlation between the data volume of each type of biometric data and the user posture features of the corresponding group, receive user identification instructions, and obtain the current user identification data; determine the type of biometric feature to be verified based on the current user identification data to obtain the first biometric feature type, which specifically includes: The user's posture is identified from the current user identification data to obtain the current user posture feature vector. Based on the current user posture feature vector, the user posture type with the largest feature data volume is predicted and set as the first biometric type. When the predicted feature data volume of the first biometric type is less than a preset single decision parameter threshold, the current user posture feature vector is substituted into the biometric fusion prediction model to obtain multiple combinations of biometric types that satisfy the biometric fusion prediction model. Specifically, the biometric fusion prediction model is as follows: ； in, The unit vector for the nth biometric type is obtained by assigning directionality to the user's posture features based on the user's limbs and movements, and then setting different biometric types. The current user posture feature vector is represented by the component of the user posture feature vector in the unit vector direction of a certain biometric feature type. This component reflects the amount of data of that type of biometric feature contained in the user posture. The larger the component, the more feature data there is. Let be the decision coefficient for the nth type of biometric data volume. The corresponding biometric data volume decision coefficients are constructed based on the required proportions of different biometric features. To fuse decision parameter thresholds; identify the combination with the fewest number of biometric types and use the corresponding biometric type as the first biometric; The user identity recognition module is used to extract biometric data from the current user identification data based on the first biometric type to obtain the first biometric; and to identify the user's identity based on the first biometric.

3. A user identification device integrating multiple biometric features, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the user identification method integrating multiple biometric features as described in claim 1 according to the instructions in the program code.

4. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code for executing the user identification method integrating multiple biometric features as described in claim 1.

Images