Multi-biological feature integrated user identity recognition method and system

Abstract

The invention relates to the technical field of user identity recognition, and provides a multi-biological feature integrated user identity recognition method and system, and the method comprises the steps: obtaining current user recognition data through receiving a user identity recognition instruction; determining a to-be-verified biological feature type according to the current user identification data, wherein the obtained first biological feature type is the biological feature type with the highest current user identification identity efficiency; performing biological feature data extraction on the current user identification data based on the first biological feature type to obtain a first biological feature; the user identity is recognized according to the first biological feature, repeated attempts of the user are not needed, the optimal equipment can be called to quickly extract enough biological feature data for identity comparison, user identity recognition is completed, the user identity recognition efficiency is improved, and the consumption experience of the user is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of user identity recognition, and in particular, to a user identity recognition method and system integrating multiple biometrics. Background Art

[0002] Consumer devices have experienced nearly thirty years of development in China, gradually evolving from a simple card - swiping mode to a mode of recognizing fingerprints, palm prints, faces, etc. However, the content that current consumer devices can recognize is still relatively single, and each biometric requires a dedicated recognition device, resulting in low efficiency of user identity recognition and affecting the user consumption experience. Summary of the Invention

[0003] The present invention provides a user identity recognition method integrating multiple biometrics, which is used to solve the problem in the prior art that the biometrics that consumer devices can recognize are single, resulting in low efficiency of user identity recognition and affecting the user consumption experience.

[0004] In a first aspect of the present invention, a user identity recognition method integrating multiple biometrics is provided, including: Receiving a user identity recognition instruction, and obtaining current user recognition data; determining the type of biometric to be verified according to the current user recognition data to obtain a first biometric type; Extracting biometric data from the current user recognition data based on the first biometric type to obtain a first biometric; and recognizing the user identity according to the first biometric.

[0005] Preferably, before receiving the user identity recognition instruction, it further includes: Obtaining multiple groups of user recognition sample data, respectively extracting biometric data of each type, and recognizing the user posture features in each group of user recognition sample data; calculating the data volume of biometric data of each type in each group of user recognition sample data, and establishing an association relationship between the data volume of biometric data of each type and the user posture features of the corresponding group.

[0006] Preferably, the determining the type of biometric to be verified according to the current user recognition data to obtain a first biometric type specifically includes: Recognizing the user posture of the current user recognition data to obtain a current user posture feature vector, predicting the user posture type with the largest feature data volume according to the current user posture feature vector, and setting it as the first biometric type.

[0007] Preferably, the determining the type of biometric to be verified according to the current user recognition data to obtain a first biometric type specifically includes: When the amount of predicted feature data of the first biometric type is less than the preset single decision parameter threshold, substitute the current user posture feature vector into the biometric fusion prediction model to obtain multiple groups of biometric type combinations that satisfy the biometric fusion prediction model. The biometric fusion prediction model is specifically as follows:

[0008] Among them, is the unit vector of the nth biometric type, is the current user posture feature vector, is the decision coefficient of the biometric data volume of the nth type, and D is the fusion decision parameter threshold; identify the combination with the least number of biometric types, and use the corresponding biometric type as the first biometric.

[0009] The second aspect of this application provides a multi-biometric integrated user identity recognition system, including: A biometric selection module, configured to receive a user identity recognition instruction, obtain current user recognition data; determine the biometric type to be verified according to the current user recognition data, and obtain the first biometric type; A user identity recognition module, configured to extract biometric data from the current user recognition data based on the first biometric type to obtain the first biometric; identify the user identity according to the first biometric.

[0010] Preferably, in the biometric selection module, before receiving the user identity recognition instruction, it further includes: Obtain multiple groups of user recognition sample data, respectively extract biometric data of each type, and identify the user posture features in each group of user recognition sample data; calculate the data volume of biometric data of each type in each group of user recognition sample data, and establish the correlation between the data volume of biometric data of each type and the corresponding group of user posture features.

[0011] Preferably, in the biometric selection module, determining the biometric type to be verified according to the current user recognition data and obtaining the first biometric type specifically includes: Identify the user posture of the current user recognition data to obtain the current user posture feature vector, predict the user posture type with the largest amount of predicted feature data according to the current user posture feature vector, and set it as the first biometric type.

[0012] Preferably, in the biometric selection module, determining the biometric type to be verified according to the current user recognition data and obtaining the first biometric type specifically includes: When the amount of predicted feature data of the first biometric type is less than the preset single decision parameter threshold, substitute the current user posture feature vector 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:

[0013] Wherein, is the unit vector of the nth biometric type, is the current user posture feature vector, is the decision coefficient of the biometric data amount of the nth type, and D is the fusion decision parameter threshold; identify the combination with the least number of identified biometric types, and use the corresponding biometric type as the first biometric.

[0014] The third aspect of the present application provides a device for a multi-biometric integrated user identity recognition method. The device includes a processor and a memory: The memory is used to store program codes and transmit the program codes to the processor; The processor is used to execute a multi-biometric integrated user identity recognition method according to any one of the first aspects of the present invention according to the instructions in the program codes.

[0015] The fourth aspect of the present application provides a computer-readable storage medium, which is used to store program codes, and the program codes are used to execute a multi-biometric integrated user identity recognition method according to any one of the first aspects of the present invention.

[0016] From the above technical solutions, it can be seen that the present invention has the following advantages: By receiving a user identity recognition instruction, obtaining current user recognition data; determining the biometric type to be verified according to the current user recognition data, and the obtained first biometric type is the biometric type with the highest efficiency for identifying the current user's identity; extracting biometric data from the current user recognition data based on the first biometric type to obtain the first biometric; identifying the user identity according to the first biometric, without the user having to repeat the attempt, and the best device can be called to quickly extract sufficient biometric data for identity comparison, completing the user identity recognition, improving the efficiency of user identity recognition, and optimizing the user's consumption experience. Description of the Drawings

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a flowchart of a user identity recognition method integrating multiple biometrics.

[0019] Figure 2 It is a structural diagram of a user identity recognition system integrating multiple biometrics. Detailed implementation manners

[0020] To make the objectives, features, and advantages of the present invention more obvious and understandable, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described below are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0021] The present invention provides a user identity recognition method integrating multiple biometrics, which is used to solve the problem that the biometrics that can be recognized by consumer devices in the prior art are single, resulting in low efficiency of user identity recognition and affecting the user consumption experience.

[0022] Please refer to Figure 1 , Figure 1 It is the first flowchart of a user identity recognition method integrating multiple biometrics provided by an embodiment of the present invention.

[0023] S100, receive a user identity recognition instruction, and obtain current user recognition data; determine the biometric type to be verified according to the current user recognition data to obtain the first biometric type; It should be noted that the user identity recognition device in this embodiment integrates various types of biometric recognition components internally, and can recognize and extract various biometric data in the data. For example, biometric features such as face, fingerprint, and palmprint need to be recognized and extracted from the user recognition data of image type; when receiving a user identity recognition instruction, the user whose identity is to be recognized currently enables the user identity recognition device. However, due to the integration of multiple biometrics in this device and the need to select the biometric feature that the current user intends to verify or is most suitable for the current user to verify, the best biometric feature type corresponding to the current user recognition data is determined. For example, when the current user opens the palm and triggers the data acquisition component of the user identity recognition device with a finger, the current user recognition data obtained by the device at this time is an image containing the finger, palm, and even the user's face. The user's intention is to recognize the fingerprint type of biometric feature. At this time, the biometric feature type to be verified can be determined as fingerprint, and the fingerprint biometric feature type is set as the first biometric feature type; and there may also be a situation where the user originally wanted to recognize the fingerprint, but there are stains on the finger, and it may be difficult to extract the fingerprint biometric feature that can be used to recognize the user's identity. Then, at this time, according to the image of the current user recognition data, the palmprint can be used as the first biometric feature type, or other biometric feature types in the integrated identity recognition device, such as voiceprint, face, iris, hand shape, gait, handwriting, skin infrared reflection, etc. can be set; A Linux system underlying main control board can be adopted in the user identity recognition device, which is used to control the acquisition, storage, comparison and verification of biometric features and various card swiping 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 an embedded program, and the program functions include functions closely related to consumer interface charging such as "transaction query, transaction parameters, user management, data management, system management, network management, device self-check, information query".

[0024] S200, extract biometric data from the current user recognition data based on the first biometric feature type to obtain a first biometric feature; recognize the user identity according to the first biometric feature.

[0025] It should be noted that in the foregoing steps, the first biometric type to be recognized and extracted subsequently is determined based on the current user recognition data, but the biometric is not extracted. In this step, the corresponding biometric recognition component is called according to the first biometric type to extract the first biometric in the current user recognition data; that is, the foregoing step S100 is equivalent to the preprocessing of the current user recognition data, and the first biometric extracted is the most effective biometric type for identity recognition in the current user recognition data. For example, when the user intends to recognize the fingerprint biometric, but there are stains on the finger and it is difficult to complete the identity recognition. A single device needs to repeatedly perform fingerprint recognition until the user wipes the finger clean and collects enough fingerprint biometric data. After preprocessing through the foregoing steps and selecting the first biometric type in the integrated device, there is no need for the user to repeat the attempt, and the best device is called to quickly extract enough biometric data for identity comparison to complete the user identity recognition.

[0026] In this embodiment, by receiving a user identity recognition instruction, the current user recognition data is obtained; the biometric type to be verified is determined according to the current user recognition data, and the obtained first biometric type is the biometric type with the highest identity recognition efficiency for the current user; based on the first biometric type, biometric data extraction is performed on the current user recognition data to obtain the first biometric; the user identity is recognized according to the first biometric. Without the user repeating the attempt, the best device can be called to quickly extract enough biometric data for identity comparison to complete the user identity recognition, improving the efficiency of user identity recognition and optimizing the user's consumption experience.

[0027] The above is the detailed description of the first embodiment of a multi-biometric integrated user identity recognition method provided by this application. The following is the detailed description of the second embodiment of a multi-biometric integrated user identity recognition method provided by this application.

[0028] In this embodiment, a multi-biometric integrated user identity recognition method is further provided. In the foregoing step S100, before receiving the user identity recognition instruction, it further includes: Obtain multiple groups of user recognition sample data, respectively extract biometric data of each type, and recognize the user posture characteristics in each group of user recognition sample data; calculate the data volume of biometric data of each type in each group of user recognition sample data, and establish the association relationship between the data volume of biometric data of each type and the user posture characteristics of the corresponding group. It should be noted that the user identification data when the user performs identity identification in different postures each time is used as a sample to form multiple groups of user identification sample data. The posture in each group of sample data can be the posture of the user stretching fingers, palms, or face, etc. When enabling all types of biometric recognition components inside the user identity recognition device for the sample data, all types of biometric data are extracted, and for the user postures in the user identification sample data, the user posture features therein are recognized. The user posture features are given directionality based on the user's limbs and actions. A vectorized regression neural network model can be pre-trained. After inputting the identification data detected by an image or other device, the user posture feature vector can be directly obtained. At the same time, unit vectors are also set for different biometric types. That is, when the component of the user posture feature vector in the direction of the unit vector of a certain biometric type reflects the amount of biometric data contained in the user posture, the larger the component, the more the feature data amount. According to the biometric data and user posture features of various types in multiple groups of user identification sample data, the correlation relationship between the data amount of biometric data of each type and the user posture features of the corresponding group is calculated to obtain the unit vector of biometric data of each type.

[0029] In step S100, determining the biometric type to be verified according to the current user identification data to obtain the first biometric type specifically includes: Recognize the user posture of the current user identification data to obtain the current user posture feature vector. According to the current user posture feature vector, predict the user posture type with the largest feature data amount and set it as the first biometric type; It should be noted that after extracting the current user posture feature vector in the current user identification data and calculating the components of the current user posture feature vector in the unit vectors of various types of biometrics, the biometric type with the largest component value is used as the first biometric type. Predicting that the biometric data amount contained in this biometric type is the largest can perform user identity recognition most efficiently.

[0030] In step S100, determining the biometric type to be verified according to the current user identification data to obtain the first biometric type specifically includes: When the predicted feature data amount of the first biometric type is less than the preset single decision parameter threshold, substitute the current user posture feature vector into the biometric fusion prediction model to obtain multiple groups of biometric type combinations that satisfy the biometric fusion prediction model. The biometric fusion prediction model is specifically:

[0031] Among them, is the unit vector of the nth biometric type, is the current user posture feature vector, is the decision coefficient of the biometric data volume of the nth type, and D is the fusion decision parameter threshold; identify the combination with the smallest number of biometric types, and use the corresponding biometric type as the first biometric.

[0032] It should be noted that in a multi-biometric integrated identity recognition device, if a single biometric cannot meet the user identity recognition, a multi-biometric fusion recognition method can be adopted; when the predicted feature data volume of the first biometric type is less than the preset single decision parameter threshold, it can be regarded as the biometric with the largest predicted biometric data volume currently, and the user identity recognition cannot be completed. Therefore, multiple biometrics need to be combined to achieve identity recognition, and the single decision parameter threshold is set according to the requirements of biometric recognition; after substituting the current user posture feature vector into the biometric fusion prediction model, it is possible to predict the effect of user identity recognition by using multiple biometrics to extract biometric features from the current user recognition data and then performing decision-level fusion. In the biometric fusion prediction model, the fusion decision parameter threshold D is used to judge whether this combination can complete the user's identity recognition; decision-level fusion is to make a final judgment by fusing the decision results of different features. For example, fingerprint and iris can be used for recognition respectively, and their decision results can be fused to obtain a more reliable recognition result. Since the amount of features required for each biometric to complete its corresponding recognition is different, the corresponding biometric data volume decision coefficient is constructed according to the ratio of the feature amounts required for different biometrics; When calculating the component of the current user posture feature vector on the unit vector of the nth biometric type if a certain biometric data cannot be extracted from the current user recognition data at all, this component will be zero or negative, but it can still form a biometric type combination. When identifying the combination with the smallest number of biometric types, this biometric type will inevitably be excluded. The biometric types of the combination that can achieve user identity recognition through decision fusion and require the fewest biometric types are used as the first biometric, so as to call the corresponding biometric recognition components with the least number later to improve the efficiency of user identity recognition; the first biometric in this step must include the biometric type with the largest contained biometric data volume.

[0033] Since there are two ends, the operation end and the consumption end, in consumer devices, dual-screen different displays can be adopted on the user identity recognition device, that is, the two display screens display different interface contents according to requirements, involving different human-computer interaction operations and display contents on different display ends. In addition to improving the intuitive feeling at the functional level, it also better reflects the data delivery content, function setting menu, application and conversion of picture and video stream display technologies; An operator display linkage board is set at the operation end, which is used for the operator to quickly control the built-in button input, control the display of the main display screen, and realize dual-screen real-time interaction with the underlying main control board of the Linux system, as well as the setting of various charging parameters, the feedback of charging status, and the quick modification of various charging modes. The main control module implements an embedded program, and the program functions include menu functions closely related to the operator control such as "consumption mode, charging statistics, device testing, receipt printing, button control"; the main display screen is connected to the operator display linkage board and the button board, and is used to display the current communication status, consumption status (consumption mode, consumption amount, success and failure status of transactions), recent transaction flow, etc. of the device in real time, so that the operator can quickly modify the consumption mode, consumption amount and transaction error correction, view transaction statistics, control the external USB receipt printer, etc. through the built-in or external keyboard; the customer display screen, by connecting to the underlying main control board of the Linux system and the touch screen, is used to display the consumption status in various modes (input consumption, fixed-amount consumption, account consumption, variety consumption, frequency consumption, transaction error correction, cash recharge, code scanning recharge, etc.) and the setting of consumption mode, and the human-computer interaction display and touch confirmation when the consumer uses various identities (face, palmprint, fingerprint, card, two-dimensional code), such as displaying transaction user information (for example: photo, name, job number, consumption amount, account balance, etc.), real-time display of IPC video stream, user data management of the charging system, network parameter setting for communication with the background, device operation status display, etc.

[0034] The user identity recognition device can also be set with a function communication board, which is used to control the device power supply, power on and off, and communication with external devices. This communication board integrates a charge and discharge circuit, a start control circuit, an RJ45 Ethernet communication interface, a USB input device, USB communication, an external USB receipt printer, an external electronic scale, etc.; a button control area is set at the operation area end, which is connected to the operator display linkage board and is used for the operator to quickly modify the consumption mode, consumption amount and transaction error correction, view transaction statistics, control the external USB receipt printer, etc., and control the input of various settings or display functions of the operator display linkage board.

[0035] The entire device mainly uses the underlying main control board of the Linux system and the operator display linkage board as the core control components of the device, and completes the linkage with other components through the built-in embedded program to meet the application requirements of different application scenarios.

[0036] The above is the detailed description of a multi-biometric integrated user identity recognition method provided in the first aspect of this application. Next is the detailed description of an embodiment of a multi-biometric integrated user identity recognition system provided in the second aspect of this application.

[0037] Please refer to Figure 2 , Figure 2It is a structural diagram of a multi-biometric integrated user identity recognition system. This embodiment provides a multi-biometric integrated user identity recognition system, including: A biometric selection module 10, configured to receive a user identity recognition instruction, obtain current user recognition data; determine a biometric type to be verified according to the current user recognition data, and obtain a first biometric type; A user identity recognition module 20, configured to extract biometric data from the current user recognition data based on the first biometric type to obtain a first biometric; recognize the user identity according to the first biometric.

[0038] In the biometric selection module 10, before receiving the user identity recognition instruction, it further includes: Obtain multiple groups of user recognition sample data, respectively extract biometric data of each type, and recognize the user posture features in each group of user recognition sample data; calculate the data volume of biometric data of each type in each group of user recognition sample data, and establish an association relationship between the data volume of biometric data of each type and the user posture features of the corresponding group.

[0039] In the biometric selection module 10, determining the biometric type to be verified according to the current user recognition data to obtain a first biometric type specifically includes: Recognize the user posture of the current user recognition data to obtain a current user posture feature vector, predict the user posture type with the largest feature data volume according to the current user posture feature vector, and set it as the first biometric type.

[0040] In the biometric selection module 10, determining the biometric type to be verified according to the current user recognition data to obtain a first biometric type specifically includes: When the predicted feature data volume of the first biometric type is less than the preset single decision parameter threshold, substitute the current user posture feature vector 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:

[0041] Wherein, Is the unit vector of the nth biometric type, Is the current user posture feature vector, Is the decision coefficient of the biometric data volume of the nth type, D is the fusion decision parameter threshold; recognize the combination with the least number of biometric types, and use the corresponding biometric type as the first biometric.

[0042] The third aspect of the present application further provides a multi-biometric integrated user identity recognition method and device, including 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 above multi-biometric integrated user identity recognition method according to the instructions in the program code.

[0043] The fourth aspect of the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code, and the program code is used to execute the above multi-biometric integrated user identity recognition method.

[0044] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0045] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, indirect couplings or communication connections of devices or units, and can be in electrical, mechanical, or other forms.

[0046] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0047] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0048] When the integrated unit is implemented in the form of 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. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0049] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of various embodiments of the present invention.

Claims

1. A user identification method integrating multiple biometric features, characterized in that include: Receive a user identity recognition instruction and obtain current user identification data; determine a biometric feature type to be verified based on the current user identification data to obtain a first biometric feature type; Extracting biometric data from current user identification data based on the first biometric type to obtain a first biometric feature; and identifying the user identity based on the first biometric feature.

2. The user identification method integrating multiple biometric features according to claim 1, characterized in that: The receiving of the user identification instruction also includes: Acquire multiple groups of user identification sample data, extract each type of biometric data respectively, and identify the user posture features in each group of user identification sample data; calculate the data volume of each type of biometric data in each group of user identification sample data, and establish a correlation relationship between the data volume of each type of biometric data and the user posture features of the corresponding group.

3. The user identification method integrating multiple biometric features according to claim 2, characterized in that: The step of determining the biometric feature type to be verified according to the current user identification data to obtain the first biometric feature type specifically includes: The user posture of the current user identification data is identified to obtain the current user posture feature vector, and the user posture type with the largest feature data amount is predicted according to the current user posture feature vector, and is set as the first biometric feature type.

4. The user identification method integrating multiple biometric features according to claim 2, characterized in that: The step of determining the biometric feature type to be verified according to the current user identification data to obtain the first biometric feature type specifically includes: When the amount of predicted feature data of the first biometric feature type is less than the preset single decision parameter threshold, the current user posture feature vector is substituted into the biometric feature fusion prediction model to obtain multiple groups of biometric feature type combinations that meet the biometric feature fusion prediction model, and the biometric feature fusion prediction model is specifically: in, is the unit vector of the nth biometric type, is the current user posture feature vector, is the decision coefficient of the amount of biometric data of the nth type, and D is the threshold of the fusion decision parameter; identify the combination with the least number of biometric types, and take the corresponding biometric type as the first biometric.

5. A user identification system integrating multiple biometric features, characterized in that: include: A biometric feature selection module, configured to receive a user identification instruction and obtain current user identification data; determine a biometric feature type to be verified based on the current user identification data and obtain a first biometric feature type; The user identity recognition module is used to extract biometric data from current user identification data based on a first biometric type to obtain a first biometric feature; and recognize the user identity based on the first biometric feature.

6. The user identification system integrating multiple biometric features according to claim 5, characterized in that: In the biometric feature selection module, before receiving the user identity recognition instruction, the module also includes: Acquire multiple groups of user identification sample data, extract each type of biometric data respectively, and identify the user posture features in each group of user identification sample data; calculate the data volume of each type of biometric data in each group of user identification sample data, and establish a correlation relationship between the data volume of each type of biometric data and the user posture features of the corresponding group.

7. The user identification system integrating multiple biometric features according to claim 6, characterized in that: In the biometric feature selection module, determining the biometric feature type to be verified according to the current user identification data to obtain the first biometric feature type specifically includes: The user posture of the current user identification data is identified to obtain the current user posture feature vector, and the user posture type with the largest feature data amount is predicted according to the current user posture feature vector, and is set as the first biometric feature type.

8. The user identification system integrating multiple biometric features according to claim 6, characterized in that: In the biometric feature selection module, determining the biometric feature type to be verified according to the current user identification data to obtain the first biometric feature type specifically includes: When the amount of predicted feature data of the first biometric feature type is less than the preset single decision parameter threshold, the current user posture feature vector is substituted into the biometric feature fusion prediction model to obtain multiple groups of biometric feature type combinations that meet the biometric feature fusion prediction model, and the biometric feature fusion prediction model is specifically: in, is the unit vector of the nth biometric type, is the current user posture feature vector, is the decision coefficient of the amount of biometric data of the nth type, and D is the threshold of the fusion decision parameter; identify the combination with the least number of biometric types, and take the corresponding biometric type as the first biometric.

9. A user identification device integrating multiple biometric features, characterized in that: The device comprises 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 identity recognition method integrating multiple biometric features as described in any one of claims 1 to 4 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and the program code is used to execute the user identity recognition method integrating multiple biometric features as described in any one of claims 1-4.

Images