CN113516167A

CN113516167A - Biological feature recognition method and device

Info

Publication number: CN113516167A
Application number: CN202110532532.XA
Authority: CN
Inventors: 唐绮雯; 黄维登; 程亮; 宁博
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2021-05-17
Filing date: 2021-05-17
Publication date: 2021-10-19

Abstract

The embodiment of the application provides a biological feature recognition method and a biological feature recognition device, which can be used in the technical field of artificial intelligence, and the method comprises the following steps: inputting environmental characteristic data corresponding to a target user initiating a biological characteristic identification request into a preset multi-algorithm decision model, and selecting one of a plurality of preset biological characteristic identification algorithms as a target biological characteristic identification algorithm corresponding to the target user according to the output of the multi-algorithm decision model; and acquiring a target biological characteristic recognition result corresponding to the biological image data of the target user based on the target biological characteristic recognition algorithm. The method and the device can effectively improve the automation degree and the intelligent degree of selecting the target biological feature recognition algorithm from the multiple biological recognition algorithms, further effectively improve the reliability and the accuracy of biological feature recognition based on the target biological feature recognition algorithm, and effectively improve the efficiency of biological feature recognition.

Description

Biological feature recognition method and device

Technical Field

The application relates to the technical field of biological identification, in particular to the technical field of artificial intelligence, and specifically relates to a biological feature identification method and device.

Background

The biometric identification technology is widely applied to the fields of product service, customer marketing, operation management and risk control of commercial banks, such as scenes of face-brushing payment, counter-face person verification, fingerprint/biometric access control/attendance checking and the like.

At present, a traditional biological recognition system uses a single algorithm model and is simultaneously applied to various different scenes, so that the application performance of the model performance is better in a single scene, but the performance is sharply reduced in other complex scenes. Therefore, each large-financial institution is not limited to use of a biometric algorithm of a single manufacturer, but uses a novel mode of fusing multiple algorithms, but the biometric algorithms of different manufacturers in different versions are good and bad in specific scene application, so that the current biometric multi-algorithm selection is manually adjusted based on expert rules, and the optimal algorithm application cannot be automatically selected by fusing scene characteristics.

Disclosure of Invention

Aiming at the problems in the prior art, the application provides a biological feature recognition method and device, which can effectively improve the automation degree and the intelligent degree of selecting a target biological feature recognition algorithm from multiple biological recognition algorithms, further effectively improve the reliability and the accuracy of biological feature recognition based on the target biological feature recognition algorithm, and effectively improve the efficiency of biological feature recognition.

In order to solve the technical problem, the application provides the following technical scheme:

in a first aspect, the present application provides a biometric identification method, including:

inputting environmental characteristic data corresponding to a target user initiating a biological characteristic identification request into a preset multi-algorithm decision model, and selecting one of a plurality of preset biological characteristic identification algorithms as a target biological characteristic identification algorithm corresponding to the target user according to the output of the multi-algorithm decision model;

and acquiring a target biological characteristic recognition result corresponding to the biological image data of the target user based on the target biological characteristic recognition algorithm.

Further, the environmental characteristic data includes: customer portrait data, business requirement data, and algorithmic capability data;

correspondingly, before the inputting the environmental characteristic data corresponding to the target user initiating the biometric identification request into the preset multi-algorithm decision model, the method further comprises:

receiving a biological characteristic identification request and corresponding biological acquisition data of a target user, wherein the biological characteristic identification request contains a unique identifier of the target user;

and acquiring client portrait data corresponding to the target user based on the unique identifier of the target user, and calling pre-stored service requirement data and algorithm capacity data.

Further, the inputting environmental feature data corresponding to a target user who initiates a biometric identification request into a preset multi-algorithm decision model, and selecting one of a plurality of preset biometric identification algorithms according to an output of the multi-algorithm decision model as a target biometric identification algorithm corresponding to the target user includes:

acquiring a target algorithm identifier output by the multi-algorithm decision model according to the client portrait data, the service requirement data and the algorithm capacity data corresponding to the target user;

and determining the biological characteristic recognition algorithm corresponding to the target algorithm identification from the one-to-one correspondence between the pre-stored algorithm identifications and the biological characteristic recognition algorithms, and determining the biological characteristic recognition algorithm as the target biological characteristic recognition algorithm corresponding to the target user.

Further, the environmental characteristic data further includes: the client portrait data, the service requirement data and the algorithm capability data respectively correspond to weights;

correspondingly, the obtaining of the target algorithm identifier output by the multi-algorithm decision model according to the client portrait data, the service requirement data and the algorithm capability data corresponding to the target user includes:

and inputting the client portrait data, the service requirement data and the algorithm capacity data corresponding to the target user and the weights corresponding to the client portrait data, the service requirement data and the algorithm capacity data corresponding to the target user into the multi-algorithm decision model so that the multi-algorithm decision model outputs a target algorithm identifier.

Further, still include:

acquiring a training data set, wherein the training data set comprises historical environment characteristic data of a plurality of users and labels corresponding to the historical environment characteristic data of each user, and the labels are one of algorithm identifications corresponding to preset biological characteristic recognition algorithms one by one;

and training the training data set by a deep learning network algorithm to obtain a multi-algorithm decision model for selecting each biological characteristic recognition algorithm and outputting a corresponding algorithm identifier.

Further, the historical environmental characteristic data comprises: client representation data, business requirement data and algorithm capability data, the historical environmental characteristic data further comprising: client representation data, business requirement data, and algorithmic capability data.

Further, after the receiving the biometric identification request and the corresponding biometric acquisition data of the target user, the method includes:

if the biological collected data of the target user is image data, judging whether the image data meets the preset biological characteristic image quality requirement, and if so, preprocessing the biological collected data of the target user to obtain the biological image data of the target user.

if the biological acquisition data of the target user is video data, performing frame extraction processing on the video data based on a preset frame extraction rule to obtain a plurality of image data corresponding to the target user;

and judging whether image data meeting the preset biological characteristic image quality requirement exists in each image data, if so, preprocessing the image data meeting the biological characteristic image quality requirement to obtain the biological image data of the target user.

Further, still include:

acquiring a biological characteristic processing type corresponding to the biological characteristic identification request;

and processing a target biological characteristic recognition result corresponding to the biological image data of the target user based on the biological characteristic processing type, and outputting a corresponding processing result.

Further, the biometric processing types include: registering the biological characteristics;

the corresponding processing of the target biological feature recognition result corresponding to the biological image data of the target user based on the biological feature processing type includes:

and storing a target biological characteristic recognition result corresponding to the biological image data of the target user into at least one biological characteristic recognition result corresponding to the identification of the target user so as to complete biological characteristic registration aiming at the target biological characteristic recognition result.

Further, the biometric processing types include: one-to-one identification;

and performing one-to-one identification on a target biological characteristic identification result corresponding to the biological image data of the target user and a pre-stored biological characteristic identification result corresponding to the identifier of the target user to obtain a corresponding one-to-one identification result.

Further, the biometric processing types include: one-to-many recognition;

and performing one-to-many recognition on a target biological characteristic recognition result corresponding to the biological image data of the target user and a plurality of pre-stored biological characteristic recognition results corresponding to the identification of the target user to obtain a corresponding one-to-many recognition result.

In a second aspect, the present application provides a biometric identification apparatus comprising:

the decision module is used for inputting the environmental characteristic data corresponding to the target user initiating the biological characteristic identification request into a preset multi-algorithm decision model and selecting one of a plurality of preset biological characteristic identification algorithms as the target biological characteristic identification algorithm corresponding to the target user according to the output of the multi-algorithm decision model;

and the identification module is used for acquiring a target biological characteristic identification result corresponding to the biological image data of the target user based on the target biological characteristic identification algorithm.

In a third aspect, the present application provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the biometric identification method when executing the program.

In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the biometric identification method.

According to the technical scheme, the biometric feature identification method and device provided by the application comprise the following steps: inputting environmental characteristic data corresponding to a target user initiating a biological characteristic identification request into a preset multi-algorithm decision model, and selecting one of a plurality of preset biological characteristic identification algorithms as a target biological characteristic identification algorithm corresponding to the target user according to the output of the multi-algorithm decision model; acquiring a target biological characteristic recognition result corresponding to the biological image data of the target user based on the target biological characteristic recognition algorithm; the method comprises the steps that environmental characteristic data corresponding to a target user initiating a biological characteristic identification request are input into a preset multi-algorithm decision model, one of a plurality of preset biological characteristic identification algorithms is selected as a target biological characteristic identification algorithm corresponding to the target user according to the output of the multi-algorithm decision model, the biological identification multi-algorithm dynamic decision fusing scene characteristics can be effectively realized, manual participation is not needed, the automation degree and the intelligent degree of selecting the target biological characteristic identification algorithm from the multi-biological identification algorithms can be effectively improved, the reliability and the accuracy of biological characteristic identification based on the target biological characteristic identification algorithm can be effectively improved, and the biological characteristic identification efficiency can be effectively improved; meanwhile, the defect that the traditional biological recognition system can only use a single algorithm for recognition is overcome, an intelligent decision solution is provided for simultaneous decision of a plurality of algorithms, and the generalization capability of the system is greatly improved; the cost of manual adjustment in the application of multiple algorithms in a new biological recognition system can be effectively reduced, the risks of easy error, influence on recognition passing rate and the like caused by adjustment are greatly reduced, and the intelligent level of the biological recognition system is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a first flowchart of a biometric identification method in an embodiment of the present application.

Fig. 2 is a second flowchart of the biometric identification method in the embodiment of the present application.

Fig. 3 is a third flowchart of the biometric identification method in the embodiment of the present application.

Fig. 4 is a fourth flowchart of the biometric identification method in the embodiment of the present application.

Fig. 5 is a fifth flowchart of a biometric identification method in the embodiment of the present application.

Fig. 6 is a sixth flowchart of the biometric identification method in the embodiment of the present application.

Fig. 7 is a seventh flowchart of the biometric identification method in the embodiment of the present application.

Fig. 8 is an eighth flowchart illustrating a biometric identification method according to an embodiment of the present application.

Fig. 9 is a ninth flowchart illustrating a biometric identification method according to an embodiment of the present application.

Fig. 10 is a tenth flowchart illustrating a biometric authentication method according to an embodiment of the present application.

Fig. 11 is an eleventh flowchart of a biometric identification method in the embodiment of the present application.

Fig. 12 is a schematic structural diagram of a biometric device in the embodiment of the present application.

Fig. 13 is a schematic structural diagram of a multi-algorithm intelligent decision-making biometric recognition system in the present application example.

Fig. 14 is a schematic structural diagram of a biometric acquisition module in a multi-algorithm intelligent decision-making biometric identification system in the present application example.

Fig. 15 is a schematic structural diagram of a data transmission module in the multi-algorithm intelligent decision-making biometric identification system in the present application example.

Fig. 16 is a schematic structural diagram of a biometric multi-algorithm intelligent decision module in a biometric system for multi-algorithm intelligent decision in the present application example.

Fig. 17 is a flowchart of the execution of the biometric main control module provided in the present application example.

Fig. 18 is a flowchart illustrating an upload execution of a data transfer module according to this embodiment.

Fig. 19 is a flowchart illustrating the issuing execution of the data transmission module according to the present application example.

Fig. 20 is a flowchart of the execution of the biometric multi-algorithm intelligent decision module provided in the present application example.

Fig. 21 is a schematic structural diagram of an electronic device in the embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the biometric identification method and apparatus disclosed in the present application can be used in the field of artificial intelligence technology, and can also be used in any field other than the field of artificial intelligence technology.

Aiming at the problems that the existing multi-biometric identification algorithm selection depends on manual work, the reliability is poor, the efficiency is low and the like, the application provides a biometric identification method, environmental feature data corresponding to a target user initiating a biometric identification request are input into a preset multi-algorithm decision model, and one of a plurality of preset biometric identification algorithms is selected as the target biometric identification algorithm corresponding to the target user according to the output of the multi-algorithm decision model; acquiring a target biological feature recognition result corresponding to biological image data of the target user based on the target biological feature recognition algorithm, inputting environmental feature data corresponding to the target user initiating a biological feature recognition request into a preset multi-algorithm decision model, and selecting one of a plurality of preset biological feature recognition algorithms as the target biological feature recognition algorithm corresponding to the target user according to the output of the multi-algorithm decision model, so that the biological recognition multi-algorithm dynamic decision fusing scene characteristics can be effectively realized, manual participation is not required, the defect that a traditional biological recognition system can only use a single algorithm for recognition is overcome, an intelligent decision solution is provided for simultaneous decision of a plurality of algorithms, and the generalization capability of the system is greatly improved; the cost of manual adjustment in the application of multiple algorithms in a new biological recognition system can be effectively reduced, the risks of easy error, influence on recognition passing rate and the like caused by adjustment are greatly reduced, and the intelligent level of the biological recognition system is improved.

Based on the above, the present application further provides a biometric identification apparatus for implementing the biometric identification method provided in one or more embodiments of the present application, where the biometric identification apparatus may be in communication connection with a technician and a client device held by a user by itself or through a third-party server, and the biometric identification apparatus may receive a biometric identification request or instruction sent by the technician and the user through the held client device, and then input environmental feature data corresponding to a target user who initiated the biometric identification request into a preset multi-algorithm decision model, and select one of a plurality of preset biometric identification algorithms as a target biometric identification algorithm corresponding to the target user according to an output of the multi-algorithm decision model; and acquiring a target biological feature recognition result corresponding to the biological image data of the target user based on the target biological feature recognition algorithm, and sending the target biological feature recognition result to a technician or the user through a held client device, or sending the target biological feature recognition result to other service systems of enterprises such as financial institutions for subsequent processing.

In one or more embodiments of the present application, the biometric apparatus may be a functional module provided in a service system of an enterprise such as a financial institution, or the biometric apparatus may be separately deployed as an apparatus such as a server that can perform information interaction with the service system.

The aforementioned biometric identification part of the biometric identification apparatus may be executed in the server as described above, or in another practical case, all operations may be performed in the client device. The selection may be specifically performed according to the processing capability of the client device, the limitation of the user usage scenario, and the like. This is not a limitation of the present application. If all operations are performed in the client device, the client device may further include a processor for performing a specific process of biometric identification.

It is understood that the client device for sending the request or the instruction to the biometric apparatus may be a device with image capturing function, or may be in communication connection with other image capturing devices to capture a biometric image or video of the user. Client devices may include smart phones, tablet electronic devices, network set-top boxes, portable computers, desktop computers, Personal Digital Assistants (PDAs), in-vehicle devices, smart wearable devices, and the like. Wherein, intelligence wearing equipment can include intelligent glasses, intelligent wrist-watch, intelligent bracelet etc..

The client device may have a communication module (i.e., a communication unit), and may be communicatively connected to a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, the server may also include a server on an intermediate platform, for example, a server on a third-party server platform that is communicatively linked to the task scheduling center server. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed apparatus.

The server and the client device may communicate using any suitable network protocol, including network protocols not yet developed at the filing date of this application. The network protocol may include, for example, a TCP/IP protocol, a UDP/IP protocol, an HTTP protocol, an HTTPS protocol, or the like. Of course, the network Protocol may also include, for example, an RPC Protocol (Remote Procedure Call Protocol), a REST Protocol (Representational State Transfer Protocol), and the like used above the above Protocol.

The following embodiments and application examples are specifically and individually described in detail.

In order to solve the problems of manual selection, poor reliability, low efficiency and the like of the conventional multi-biometric identification algorithm, the application provides an embodiment of a biometric identification method that can be executed by a biometric identification device, and referring to fig. 1, the biometric identification method specifically includes the following contents:

step 100: and inputting the environmental characteristic data corresponding to the target user initiating the biological characteristic identification request into a preset multi-algorithm decision model, and selecting one of a plurality of preset biological characteristic identification algorithms as the target biological characteristic identification algorithm corresponding to the target user according to the output of the multi-algorithm decision model.

In step 100, a biometric request may be sent to the biometric device by a technician or a financial user of the financial institution through a client device in his/her own, and it is understood that the biometric request mentioned in one or more embodiments of the present application refers to a physiological characteristic (fingerprint, iris, facial quality, etc.) or a behavioral characteristic (gait, etc.) inherent to a human body.

Step 200: and acquiring a target biological characteristic recognition result corresponding to the biological image data of the target user based on the target biological characteristic recognition algorithm.

It is understood that the multi-algorithm decision mentioned in one or more embodiments of the present application may also refer to an expert rule-based multi-algorithm decision mechanism or a voting-based multi-algorithm decision mechanism, but in a preferred embodiment of the present application, the execution manner of the step 100 is preferably selected to effectively improve the automation degree and the intelligence degree of the multi-algorithm decision and the biometric identification.

In step 200, the biometric features refer to feature data that can be acquired through images or videos, for example, the biometric image data may be face image data, iris image data, retina image data, facial image data, vein distribution map, palm three-dimensional image data, signature image data of the target user; and if the acquired data is video data, the target user corresponds to a plurality of biological image data obtained by extracting key frames of the video data.

As can be seen from the above description, in the biometric identification method provided in the embodiment of the present application, by inputting the environmental feature data corresponding to the target user who initiates the biometric identification request into the preset multi-algorithm decision model, and selecting one of the plurality of preset biometric algorithms as the target biometric identification algorithm corresponding to the target user according to the output of the multi-algorithm decision model, the biometric identification multi-algorithm dynamic decision combining the scene characteristics can be effectively implemented, without manual participation, the defect that the conventional biometric identification system can only use a single algorithm for identification is overcome, an intelligent decision solution is provided for the simultaneous decision of the plurality of algorithms, and the generalization capability of the system is greatly improved; the cost of manual adjustment in the application of multiple algorithms in a new biological recognition system can be effectively reduced, the risks of easy error, influence on recognition passing rate and the like caused by adjustment are greatly reduced, and the intelligent level of the biological recognition system is improved.

In order to effectively improve the efficiency and comprehensiveness of acquiring the environmental characteristic data, in an embodiment of the biometric method provided by the present application, the environmental characteristic data includes: customer portrait data, business requirement data, and algorithmic capability data; referring to fig. 2, before step 100 of the biometric identification method, the following contents are further included:

step 010: and receiving a biological characteristic identification request and corresponding biological acquisition data of the target user, wherein the biological characteristic identification request contains the unique identification of the target user.

Step 020: and acquiring client portrait data corresponding to the target user based on the unique identifier of the target user, and calling pre-stored service requirement data and algorithm capacity data.

As can be seen from the above description, according to the biometric feature recognition method provided in the embodiment of the present application, the client portrait data corresponding to the target user is obtained based on the unique identifier of the target user, and the pre-stored service requirement data and algorithm capability data are retrieved, so that efficiency and comprehensiveness of obtaining the environmental feature data can be effectively improved, and further, efficiency and accuracy of performing multi-algorithm decision by using the environmental feature data subsequently can be effectively improved.

In order to effectively improve the efficiency and accuracy of the multi-algorithm decision model application, in an embodiment of the biometric identification method provided in the present application, referring to fig. 3, the step 100 of the biometric identification method specifically includes the following steps:

step 110: and acquiring a target algorithm identifier output by the multi-algorithm decision model according to the client portrait data, the service requirement data and the algorithm capacity data corresponding to the target user.

Step 120: and determining the biological characteristic recognition algorithm corresponding to the target algorithm identification from the one-to-one correspondence between the pre-stored algorithm identifications and the biological characteristic recognition algorithms, and determining the biological characteristic recognition algorithm as the target biological characteristic recognition algorithm corresponding to the target user.

As can be seen from the above description, the biometric characteristic recognition method provided in the embodiment of the present application can effectively improve the efficiency and accuracy of the multi-algorithm decision model application by obtaining the target algorithm identifier output by the multi-algorithm decision model according to the client portrait data, the service requirement data, and the algorithm capability data corresponding to the target user, and further can effectively improve the efficiency and accuracy of biometric characteristic recognition according to the target biometric characteristic recognition algorithm.

In order to further improve the reliability and accuracy of the multi-algorithm decision model application, in an embodiment of the biometric identification method provided by the present application, the environmental feature data further includes: the client portrait data, the service requirement data and the algorithm capability data respectively correspond to weights; referring to fig. 4, the step 110 of the biometric identification method specifically includes the following steps:

step 111: and inputting the client portrait data, the service requirement data and the algorithm capacity data corresponding to the target user and the weights corresponding to the client portrait data, the service requirement data and the algorithm capacity data corresponding to the target user into the multi-algorithm decision model so that the multi-algorithm decision model outputs a target algorithm identifier.

As can be seen from the above description, in the biometric feature recognition method provided in the embodiment of the present application, the client portrait data, the service requirement data, and the algorithm capability data corresponding to the target user, and the weights corresponding to the client portrait data, the service requirement data, and the algorithm capability data corresponding to the target user are input into the multi-algorithm decision model, so that the reliability and the accuracy of the application of the multi-algorithm decision model can be further improved, and further, the reliability and the accuracy of biometric feature recognition according to the target biometric feature recognition algorithm can be further improved.

In order to further improve the reliability and accuracy of the application of the multi-algorithm decision model, in an embodiment of the biometric identification method provided by the present application, referring to fig. 5, the following contents are further specifically included before step 100 or before step 010:

step 001: and acquiring a training data set, wherein the training data set comprises historical environment characteristic data of a plurality of users and labels corresponding to the historical environment characteristic data of each user, and the labels are one of algorithm identifications corresponding to preset biological characteristic recognition algorithms one to one.

Step 002: and training the training data set by a deep learning network algorithm to obtain a multi-algorithm decision model for selecting each biological characteristic recognition algorithm and outputting a corresponding algorithm identifier.

From the above description, it can be seen that the biometric feature recognition method provided in the embodiment of the present application can effectively improve the application reliability and accuracy of a multi-algorithm decision model by training the training data set with a deep learning network algorithm, and further can further improve the reliability and accuracy of biometric feature recognition according to a target biometric feature recognition algorithm.

In order to further train the reliability and accuracy of the application of the obtained multi-algorithm decision model, in an embodiment of the biometric identification method provided by the present application, the historical environmental feature data includes: client representation data, business requirement data and algorithm capability data, the historical environmental characteristic data further comprising: client representation data, business requirement data, and algorithmic capability data.

As can be seen from the above description, the biometric identification method provided in the embodiment of the present application includes: client representation data, business requirement data and algorithm capability data, the historical environmental characteristic data further comprising: the application reliability and accuracy of the multi-algorithm decision model obtained through further training can be further improved through the corresponding weights of the client portrait data, the service requirement data and the algorithm capability data, and further the reliability and accuracy of the biological feature recognition according to the target biological feature recognition algorithm can be further improved.

In order to effectively improve the application range of data acquisition, in an embodiment of the biometric method provided in the present application, referring to fig. 6, the following contents are further specifically included after step 010 in the biometric method:

step 011: if the biological collected data of the target user is image data, judging whether the image data meets the preset biological characteristic image quality requirement, and if so, preprocessing the biological collected data of the target user to obtain the biological image data of the target user.

As can be seen from the above description, the biometric identification method provided in the embodiments of the present application can effectively improve the application range of data acquisition by providing a processing manner of biometric image data, and can perform the reliability and accuracy of biometric identification according to the target biometric identification algorithm.

In order to effectively improve the application range of data acquisition, in an embodiment of the biometric method provided in the present application, referring to fig. 7, the following contents are further specifically included after step 010:

step 012: and if the biological acquisition data of the target user is video data, performing frame extraction processing on the video data based on a preset frame extraction rule to obtain a plurality of image data corresponding to the target user.

Step 013: and judging whether image data meeting the preset biological characteristic image quality requirement exists in each image data, if so, preprocessing the image data meeting the biological characteristic image quality requirement to obtain the biological image data of the target user.

As can be seen from the above description, the biometric identification method provided in the embodiment of the present application can effectively improve the application range of data acquisition by providing a processing manner of the biometric video data, and can perform the reliability and accuracy of biometric identification according to the target biometric identification algorithm.

In order to effectively improve the application range of data acquisition, in an embodiment of the biometric method provided in the present application, referring to fig. 8, the following contents are further specifically included after step 200 in the biometric method:

step 300: and acquiring a biological characteristic processing type corresponding to the biological characteristic identification request.

Step 400: and processing a target biological characteristic recognition result corresponding to the biological image data of the target user based on the biological characteristic processing type, and outputting a corresponding processing result.

As can be seen from the above description, the biometric identification method provided in the embodiment of the present application can improve the applicability of the biometric identification method by processing the target biometric identification result corresponding to the biometric image data of the target user based on the biometric processing type, and is particularly suitable for a financial institution to perform subsequent transaction processing after performing biometric identification on the user during a transaction of the user, and can effectively improve the security and reliability of the subsequent transaction processing.

In order to further improve the applicability and comprehensiveness of the biometric identification method, in one embodiment of the biometric identification method provided in the present application, the biometric processing types include: registering the biological characteristics; referring to fig. 9, the step 400 of the biometric identification method specifically includes the following steps:

step 411: and storing a target biological characteristic recognition result corresponding to the biological image data of the target user into at least one biological characteristic recognition result corresponding to the identification of the target user so as to complete biological characteristic registration aiming at the target biological characteristic recognition result.

Step 412: and outputting a processing result of performing biological characteristic registration on the target biological characteristic identification result.

As can be seen from the above description, the biometric identification method provided in the embodiment of the present application can further improve the universality and comprehensiveness of the biometric identification method by performing biometric registration on the corresponding target biometric identification result, and is particularly suitable for a biometric registration scenario.

In order to further improve the applicability and comprehensiveness of the biometric identification method, in one embodiment of the biometric identification method provided in the present application, the biometric processing types include: one-to-one identification (which may also be referred to as 1:1 identification); referring to fig. 10, the step 400 of the biometric identification method specifically includes the following steps:

step 421: and performing one-to-one identification on a target biological characteristic identification result corresponding to the biological image data of the target user and a pre-stored biological characteristic identification result corresponding to the identifier of the target user to obtain a corresponding one-to-one identification result.

Step 422: and outputting the one-to-one recognition result.

As can be seen from the above description, the biometric identification method provided in the embodiment of the present application can further improve the universality and comprehensiveness of the biometric identification method by performing 1:1 identification on the corresponding target biometric identification result, and is particularly applicable to 1:1 identification scenes.

In order to further improve the applicability and comprehensiveness of the biometric identification method, in one embodiment of the biometric identification method provided in the present application, the biometric processing types include: one-to-many recognition (which may also be referred to as 1: n recognition); referring to fig. 11, the step 400 of the biometric identification method specifically includes the following steps:

step 431: and performing one-to-many recognition on a target biological characteristic recognition result corresponding to the biological image data of the target user and a plurality of pre-stored biological characteristic recognition results corresponding to the identification of the target user to obtain a corresponding one-to-many recognition result.

Step 432: and outputting the one-to-many recognition result.

As can be seen from the above description, the biometric identification method provided in the embodiment of the present application can further improve the universality and comprehensiveness of the biometric identification method by performing 1: n identification on the corresponding target biometric identification result, and is particularly applicable to 1: n identification scenes.

From the software level, in order to solve the problems of manual dependency, poor reliability, low efficiency, and the like of the existing multi-biometric identification algorithm selection, the present application provides an embodiment of a biometric identification apparatus for executing all or part of the contents of the biometric identification method, and referring to fig. 12, the biometric identification apparatus specifically includes the following contents:

the decision module 10 is configured to input environmental feature data corresponding to a target user who initiates a biometric identification request into a preset multi-algorithm decision model, and select one of a plurality of preset biometric identification algorithms according to an output of the multi-algorithm decision model as a target biometric identification algorithm corresponding to the target user.

In the decision module 10, the biometric identification request may be sent to the biometric identification device by a technician or a financial user of the financial institution through a client device in his/her own, and it is understood that the biometric identification request mentioned in one or more embodiments of the present application refers to a physiological characteristic (fingerprint, iris, facial features, etc.) or a behavior characteristic (gait, etc.) inherent to a human body.

And the identification module 20 is configured to obtain a target biometric identification result corresponding to the biometric image data of the target user based on the target biometric identification algorithm.

In the recognition module 20, the biometric features particularly refer to feature data that can be acquired through images or videos, for example, the biometric image data may be face image data, iris image data, retina image data, facial image data, vein distribution map, palm three-dimensional image data, signature image data of a target user; and if the acquired data is video data, the target user corresponds to a plurality of biological image data obtained by extracting key frames of the video data.

The embodiment of the biometric apparatus provided in the present application may be specifically used to execute the processing procedure of the embodiment of the biometric method in the foregoing embodiment, and the functions of the embodiment are not described herein again, and reference may be made to the detailed description of the embodiment of the method.

As can be seen from the above description, the biometric identification apparatus provided in the embodiment of the present application inputs the environmental feature data corresponding to the target user initiating the biometric identification request into the preset multi-algorithm decision model, and selects one of the plurality of preset biometric algorithms as the target biometric identification algorithm corresponding to the target user according to the output of the multi-algorithm decision model, so that the biometric identification multi-algorithm dynamic decision fusing the scene characteristics can be effectively implemented, manual participation is not required, the defect that the conventional biometric identification system can only use a single algorithm for identification is overcome, an intelligent decision solution is provided for the simultaneous decision of the plurality of algorithms, and the generalization capability of the system is greatly improved; the cost of manual adjustment in the application of multiple algorithms in a new biological recognition system can be effectively reduced, the risks of easy error, influence on recognition passing rate and the like caused by adjustment are greatly reduced, and the intelligent level of the biological recognition system is improved.

For further explanation, the present application provides a multi-algorithm intelligent decision biometric identification method implemented by a biometric identification system using multi-algorithm intelligent decision (i.e., a specific example of the foregoing biometric feature identification method). A biological recognition multi-algorithm intelligent decision model is constructed on the basis of an artificial intelligence technology deep neural network DNN, and the optimal algorithm dynamic switching of transaction dimensions is realized. Constructing model features by three dimensions of a client portrait, business characteristics and algorithm capacity; the sample data is from the service data of each scene of biological recognition, the marking mode uses a plurality of algorithms to vote through background batch operation, and the optimal algorithm evaluation is realized on the transaction by combining the customer portrait and the service requirement; the verification sample is also derived from biometric business data. The application example can well solve the problem of biological recognition multi-algorithm dynamic decision of fusion scene characteristics, realizes automatic selection of optimal algorithm recognition for each biological transaction, does not need manual participation, and supports the multi-algorithm intelligent application requirements on various large scenes in the financial field.

Aiming at the defects and shortcomings in the prior art, the application example provides a biological identification system and a biological identification method for multi-algorithm intelligent decision, a biological identification multi-algorithm intelligent decision model is constructed based on an artificial intelligence technology, the automatic selection of an optimal algorithm for each biological identification transaction is realized, and the problem of manual multi-algorithm adjustment based on expert rules at present is solved. The application example makes up the defect that the traditional biological recognition system can only use a single algorithm for recognition on one hand, provides an intelligent decision solution for simultaneous decision of a plurality of algorithms, and greatly improves the generalization capability of the system; on the other hand, the cost of manual adjustment when multiple algorithms are applied in a new biological identification system is reduced, the risks of easy error, influence on identification passing rate and the like caused by adjustment are greatly reduced, and the intelligent level of the biological identification system is improved.

The application example provides a biological recognition system and a method for multi-algorithm intelligent decision, and the biological recognition system for multi-algorithm intelligent decision comprises a biological recognition main control module, a biological characteristic acquisition module, a data transmission module and a biological recognition multi-algorithm intelligent decision module. When multi-algorithm biological identification transaction is carried out, a biological feature acquisition module drives a camera to acquire biological image or video unstructured data of a user, then the biological image or video unstructured data are uploaded to a biological identification multi-algorithm intelligent decision module through a data transmission module to carry out algorithm scheduling and decision, and after algorithm selection is completed, relevant biological feature registration, 1:1 identification and 1: and n, identifying at least one item in the algorithm, and issuing a processing result to the intelligent interaction equipment end after the algorithm processing is finished.

The biological characteristic acquisition module mainly completes the acquisition of non-mechanization data such as biological images or videos and the like and the data quality detection control function. The method comprises the steps that camera equipment deployed on an intelligent interaction equipment end is driven by an acquisition control unit to acquire biological images or video unstructured data of a user; the biological characteristic acquisition main control unit sends the acquired biological image or video unstructured data to the biomass quantity control unit. When the collected data is an image, directly judging whether the organisms in the image meet the use standard: if the interpupillary distance > of the human eyes is 60 pixels, whether motion blur exists or not, whether the images are too bright or too dark or not, whether no living things exist or not, and the like; when the collected data is a video, firstly, extracting a key frame from the video data, wherein the required duration of the video is less than 5 seconds, extracting 2 frames or s as the key frame for detection in order to improve the efficiency, and judging whether the biological characteristics in the image frame meet the use standard or not: for example, the interpupillary distance > is 60 pixels, whether the image has motion blur or not, the image is too bright, the image is too dark, and no biological features exist. If the request is satisfied, a biological characteristic data transmission processing request is initiated, so that the biological characteristic data acquisition process is completed.

The data transmission module mainly completes uploading of the biological characteristic image or video unstructured data and issuing of the biological characteristic image or characteristic. The biological characteristic data transmission main control unit firstly performs data security check control, judges whether the uploaded data are biological image or video unstructured data, and uploads the biological characteristic data to a cloud database in an http or socket mode if the uploaded data are the biological image or video unstructured data; when data are downloaded, the issuing unit directly issues a picture or feature query application to the cloud database, and the data are issued to the intelligent interaction equipment terminal or the application server by the data issuing unit after corresponding results are queried, so that the transmission processing flow of the biological feature data is completed.

The biological recognition multi-algorithm intelligent decision module mainly completes the scheduling of biological recognition multi-algorithms, multi-algorithm intelligent selection, biological characteristic registration and biological characteristic recognition processing, and finally returns the related registration or recognition result to the intelligent equipment processing front end. Firstly, carrying out biological recognition multi-algorithm scheduling, retrieving the type and the number of server algorithm models, and sending a scheduling result to a multi-algorithm decision model for carrying out optimal algorithm selection. The application of the biological recognition algorithms of different versions of different manufacturers on specific scenes has advantages and disadvantages, and the prior biological recognition multi-algorithm selection is manually adjusted based on expert rules and cannot be optimally applied by combining scene characteristics. The main function of the biological recognition multi-algorithm decision model is to fuse scenes and application characteristics and realize optimal algorithm selection with channels and transactions as dimensions. The multi-algorithm decision model is trained by a deep learning network DNN, and model features are constructed mainly by 3 feature dimensions of customer figures, service requirements and algorithm capacity. The sample data is comprehensively derived from the biological scene service data, the data annotation is realized by background batch operation and automatic voting evaluation by using a plurality of algorithms, and the sample is verified to be derived from the biological identification service scene data. Before algorithm processing, whether the processed data is an image or not is judged, if the processed data is the image, the processed data is directly sent to a corresponding algorithm processing unit, and if the processed data is the video, the best biological characteristic data frame is extracted firstly and then sent to the corresponding algorithm processing unit. Sending the image data to a corresponding algorithm service processing unit for processing: and preprocessing data to be subjected to the biological feature registration algorithm processing to complete biological feature extraction and modeling, and then registering the user information and the biological features into a biological recognition system database. And performing image preprocessing on the request needing to be processed by the 1:1 biological recognition algorithm to finish biological feature extraction and modeling, then performing 1:1 comparison on the feature data and the biological features inquired in the database, and returning a comparison result to the request client. And after finishing the image preprocessing and the biological feature extraction and modeling, carrying out 1: N identification on the N biological features in the database, and returning an identification result to the request client. Wherein, N and N mentioned in one or more embodiments of the application are both positive integers.

Based on the above, the multi-algorithm intelligent decision-making biometric identification system is shown in fig. 13, and includes: the system comprises a biological identification main control module 1, a biological characteristic acquisition module 2, a data transmission module 3 and a biological identification multi-algorithm intelligent decision module 4. The biological recognition main control module 1, the biological feature acquisition module 2, the data transmission module 3 and the biological recognition multi-algorithm intelligent decision module 4 are in network communication in an HTTPS mode.

Referring to fig. 14, the biometric acquisition module 2 is used for overall control of a biometric data acquisition front end, and includes a biometric acquisition main control MCU unit 21, a biometric unstructured data acquisition control unit 22, and a biometric unstructured data quality control unit 23, where communication among the biometric acquisition main control MCU unit 21, the biometric unstructured data acquisition control unit 22, and the biometric unstructured data quality control unit 2 is completed through JavaScript instant messaging or java internal communication, and the front-end biometric acquisition main control module is mainly deployed at an intelligent interactive device terminal.

Referring to fig. 15, the data transmission module 3 is used for uploading and downloading the biometric data. The system comprises a biological characteristic unstructured data transmission main control unit 31, a data uploading unit 32 and a data issuing unit 33, wherein the units communicate with each other through JavaScript instant messaging or java internal communication, and are mainly deployed at an intelligent interaction equipment terminal.

Referring to fig. 16, the biometric multi-algorithm intelligent decision module 4 is configured to complete biometric multi-algorithm intelligent decision and algorithm processing functions. The system comprises a biological recognition algorithm main control unit 41 and a biological recognition algorithm intelligent decision unit 42; the biometric algorithm intelligent decision unit 42 comprises: a biometric multi-algorithm scheduling unit 421, a biometric multi-algorithm model decision unit 422, an algorithm a (biometric a algorithm subunit) 423, an algorithm B (biometric B algorithm subunit) 424, and an algorithm C (biometric C algorithm subunit) 425, wherein the algorithms A, B and C refer to different versions of biometric algorithm models of different manufacturers, respectively, and can be expanded horizontally and vertically, and are not limited to the 3 examples in fig. 16. The multi-algorithm intelligent decision module 4 further includes a biometric registration algorithm processing unit 43, a feature 1:1 recognition algorithm processing unit 44, and a feature 1: the n recognition algorithm processing units 45 are completed through java internal communication, and the modules are mainly deployed at a background server.

Referring to fig. 17, the execution flow of the biometric main control module in the present application example is as follows:

step S101: initiating a biological characteristic data acquisition request;

step S102: driving a front-end camera to acquire biological characteristic images or video data according to the data acquisition instruction;

step S103: sending the biological characteristic data to a quality judger;

step S104: judging whether the collected image is a biological characteristic image, and entering the step S107 when the collected image is the biological characteristic image, and entering the step S105 when the collected image is not the biological image;

step S105: when the step S104 judges that the collected data is not the biological characteristic image, judging whether the collected data is biological characteristic video data;

step S106: when the step S105 judges that the collected data is not the biological characteristic video data, the step S102 is returned to for re-collection; when the collected data is judged to be the biological characteristic video data in the step S105, extracting video key frames, entering the step S107, and detecting frame by frame;

step S107: judging the quality of the biological characteristic image, if the interpupillary distance of the human eyes is equal to 60 pixels, and if the conditions of motion blur, too bright image, too dark image, no living things and the like exist, returning to the step S102 for re-acquisition if the conditions exist;

step S108: initiating a request for uploading the biological characteristic data;

step S109: completing the collection of the biological characteristic data;

step S110: and ending the biological characteristic data acquisition process.

Referring to fig. 18, the upload execution flow of the data transmission module in the application example is as follows:

step S201: initiating a biological characteristic data uploading request;

step S202: performing security access control on the biological characteristic data;

step S203: judging whether the uploaded image data is biological characteristic image data or video data, if so, entering step S206 for processing, and if not, entering step S204 for processing;

step S204: rejecting the uploading request of the biological characteristic data;

step S205: ending the uploading process of the biological characteristic data;

step S206: when the biometric image or video data is judged to be uploaded in step S204, whether to upload the biometric registered image or video data is judged;

step S207: when it is judged in step S206 that the image data or the video data registered for the biometric feature is uploaded, the data is uploaded to the cloud database in https or socket;

step S208: initiating a biological recognition algorithm intelligent decision request;

step S209: finishing uploading the biological characteristic registration data;

step S210: ending the uploading process of the biological characteristic data;

step S211: when it is judged in step S206 that the biometric characteristic registration image or video data is not uploaded, it is judged whether to upload biometric 1:1 identification image data or video data;

step S212: when the step S211 judges that the image data or the video data identified by the living beings 1:1 are uploaded, the data are uploaded to a cloud database in an https or socket mode;

step S213: initiating a biological recognition algorithm intelligent decision and a 1:1 recognition algorithm processing request;

step S214: 1, organism: 1, completing data uploading;

step S215: ending the uploading process of the biological characteristic data;

step S216: when it is determined in step S211 that the biometric 1: 1-recognized image data or video data is not uploaded, it is determined whether the biometric 1: n identifying image data or video data;

step S217: when the step S216 judges that the biological 1: n identification image data or the video data is uploaded, the data is uploaded to a cloud database in an https or socket mode;

step S218: initiating a biological recognition algorithm intelligent decision and a 1: n recognition algorithm processing request;

step S219: 1, organism: n, completing data uploading;

step S220: ending the uploading process of the biological characteristic data;

step S221: determination by step S216 as not to upload organism 1: n, when image data or video data is identified, the uploading request of the biological characteristic data is refused;

step S222: and ending the uploading process of the biological characteristic data.

Referring to fig. 19, the issuing execution flow of the data transmission module in the application example is as follows:

step S301: initiating a biological characteristic data issuing request;

step S302: judging that the issued data is biological characteristic data or image data;

step S303: when the step 301 determines that the biometric data or the image data is not to be issued, the biometric data issue request is rejected;

step S304: ending the process of sending the biological characteristic data;

step S305: when the step S302 judges that the transmission is the biological characteristic data or the image data, whether the 1:1 identification characteristic data or the image data of the organism is transmitted is judged;

step S306: when the step S305 judges that the information is the 1:1 essential feature data or the image data of the creature, inquiring 1 biological feature data or image data from the cloud database according to the client information;

step S307: 1 biological feature or image is sent to a designated interactive device or an application server;

step S308: the sending request of the biological characteristic data is completed;

step S309: ending the process of sending the biological characteristic data;

step S310: when it is determined in step S305 that the identification feature data or the image data of the issued creature 1:1 is not issued, it is determined whether the identification feature data or the image data of the issued creature 1: n is issued;

step S311: the judgment in step S310 is that the issuing organism 1: when the feature data or the image data are identified, inquiring and acquiring N biological feature data or image data from a cloud database according to the client grouping information;

step S312: sending the N biological characteristics or images to a designated interactive device or an application server;

step S313: the sending request of the biological characteristic data is completed;

step S314: ending the process of sending the biological characteristic data;

step S315: if it is determined in step S310 that the transmission of the biometric characteristic data is not 1:n identification features or image data, the transmission of the biometric characteristic data is denied;

step S316: and ending the process of sending the biological characteristic data.

Referring to fig. 20, the execution flow of the biometric multi-algorithm intelligent decision module in the present application example is as follows:

step S401: initiating a biometric algorithm processing request;

step S402: selecting weights according to a customer representation calculation algorithm;

step S403: calculating algorithm selection weight according to scene service requirements;

step S404: calculating algorithm selection weight according to algorithm capacity;

step S405: carrying out biological recognition multi-algorithm scheduling;

step S406: calling a biological recognition multi-algorithm decision model;

step S407: combining the weights, and selecting the optimal processing algorithm of the transaction by a multi-algorithm decision model;

step S408: judging whether the processed data is an image, and if so, proceeding to step S413;

step S409: when it is determined in step S408 that the processed data is not an image, it is determined whether the processed data is a video;

step S410: when it is determined in step S410 that the processed data is video data, the optimum video frame is extracted from the video data, and the process proceeds to step S413;

step S411: when it is determined in step S409 that the processed data is not video data, the biometric authentication algorithm rejects the processing request;

step S412: ending the biometric identification algorithm processing flow;

step S413: judging whether a biological characteristic registration algorithm processing request is carried out or not;

step S414: when it is determined in step S413 that the request for processing the biometric registration algorithm is made, the request is sent to the biometric registration algorithm processing unit;

step S415: preprocessing the unstructured data of the biological image or the video by using an optimal calculation method selected by a decision model;

step S416: extracting and modeling biological characteristics by using an optimal calculation method selected by a decision model;

step S417: storing the biological characteristics to a cloud database;

step S418: returning a registration result to the request client;

step S419: the request is processed and completed by the biological characteristic registration algorithm;

step S420: ending the biometric identification algorithm processing flow;

step S421: when it is judged in step S413 that the biometric feature registration algorithm processing is not to be performed, it is judged whether or not the biometric 1:1 recognition algorithm processing request is to be performed;

step S422: when it is judged in step S421 that the request for the 1:1 biometric identification algorithm processing is to be made, the request is sent to the 1:1 biometric identification algorithm processing unit;

step S423: preprocessing the unstructured data of the biological image or the video by using an optimal calculation method selected by a decision model;

step S424: extracting and modeling biological characteristics by using an optimal calculation method selected by a decision model;

step S425: 1:1 comparison is carried out on the biological characteristics of 1 piece of the tea obtained by the cloud;

step S426: returning the comparison result to the requesting client

Step S427: biometric 1:1 recognition algorithm processing request completion

Step S428: ending the biometric identification algorithm processing flow;

step S429: when it is determined in step S421 that the biological 1:1 recognition algorithm processing request is not to be made, it is determined whether or not the biological 1: n recognition algorithm processing request is to be made;

step S430: when it is judged in step S429 that the request for the biometric 1: n recognition algorithm processing is made, the request is sent to the biometric 1: n recognition algorithm processing unit;

step S431: preprocessing the unstructured data of the biological image or the video by using an optimal calculation method selected by a decision model;

step S432: extracting and modeling biological characteristics by using an optimal calculation method selected by a decision model;

step S433: performing 1: N identification on the N biological characteristics acquired by the cloud, and returning the client information of top1 as an identification result;

step S434: returning the identification result to the request client;

step S435: 1, organism: n identifying the algorithm processing request completion;

step S436: ending the biometric identification algorithm processing flow;

step S437: when it is judged by the step S429 that the biometric 1: n recognition algorithm processing request is not made, the biometric recognition algorithm processing request is rejected;

step S438: the biometric algorithm process flow ends.

From the above description, the biological identification system with multi-algorithm intelligent decision and the biological identification method with multi-algorithm intelligent decision provided by the application example of the application example construct a biological identification multi-algorithm intelligent decision model through artificial intelligence technology and deep neural network DNN training, and realize automatic selection of an optimal algorithm for identification of each piece of biological identification transaction data. On one hand, the application example makes up the defect that the traditional biological recognition system can only use a single algorithm for recognition, provides an intelligent decision solution for simultaneous decision of a plurality of algorithms, and greatly improves the generalization capability of the system; on the other hand, the cost of manual adjustment when multiple algorithms are applied in a new biological identification system is reduced, the risks of easy error, influence on identification passing rate and the like caused by adjustment are greatly reduced, and the intelligent level of the biological identification system is improved.

In terms of hardware, in order to solve the problems of manual selection, poor reliability, low efficiency, and the like of the existing multi-biometric identification algorithm, the present application provides an embodiment of an electronic device for implementing all or part of the contents in the biometric identification method, where the electronic device specifically includes the following contents:

fig. 21 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present application. As shown in fig. 21, the electronic device 9600 can include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this fig. 21 is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.

In one embodiment, the biometric identification function may be integrated into the central processor. Wherein the central processor may be configured to control:

As can be seen from the above description, according to the electronic device provided in the embodiment of the present application, by inputting the environmental feature data corresponding to the target user initiating the biometric identification request into the preset multi-algorithm decision model, and selecting one of the multiple preset biometric algorithms as the target biometric identification algorithm corresponding to the target user according to the output of the multi-algorithm decision model, the biometric multi-algorithm dynamic decision fusing the scene characteristics can be effectively implemented, manual participation is not required, the defect that the conventional biometric identification system can only use a single algorithm for identification is overcome, an intelligent decision solution is provided for the simultaneous decision of multiple algorithms, and the generalization capability of the system is greatly improved; the cost of manual adjustment in the application of multiple algorithms in a new biological recognition system can be effectively reduced, the risks of easy error, influence on recognition passing rate and the like caused by adjustment are greatly reduced, and the intelligent level of the biological recognition system is improved.

In another embodiment, the biometric device may be configured separately from the central processor 9100, for example, the biometric device may be configured as a chip connected to the central processor 9100, and the biometric function may be implemented under the control of the central processor.

As shown in fig. 21, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 also does not necessarily include all of the components shown in fig. 21; in addition, the electronic device 9600 may further include components not shown in fig. 21, which can be referred to in the related art.

As shown in fig. 21, a central processor 9100, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device, which central processor 9100 receives input and controls the operation of the various components of the electronic device 9600.

The memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to realize information storage or processing, or the like.

The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. Power supply 9170 is used to provide power to electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.

The memory 9140 can be a solid state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 9140 could also be some other type of device. Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 being used for storing application programs and function programs or for executing a flow of operations of the electronic device 9600 by the central processor 9100.

The memory 9140 can also include a data store 9143, the data store 9143 being used to store data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers for the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, contact book applications, etc.).

The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.

Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing ordinary telecommunications functions. The audio processor 9130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100, thereby enabling recording locally through the microphone 9132 and enabling locally stored sounds to be played through the speaker 9131.

Embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps in the biometric identification method in the above embodiments, where the computer-readable storage medium stores thereon a computer program, and when the computer program is executed by a processor, the computer program implements all the steps of the biometric identification method in the above embodiments, where the execution subject is a server or a client, for example, the processor implements the following steps when executing the computer program:

As can be seen from the above description, the computer-readable storage medium provided in the embodiment of the present application inputs the environmental feature data corresponding to the target user initiating the biometric identification request into the preset multi-algorithm decision model, and selects one of the multiple preset biometric algorithms as the target biometric identification algorithm corresponding to the target user according to the output of the multi-algorithm decision model, so that the biometric multi-algorithm dynamic decision fusing the scene characteristics can be effectively implemented, manual participation is not required, the defect that the conventional biometric identification system can only use a single algorithm for identification is overcome, an intelligent decision solution is provided for the simultaneous decision of multiple algorithms, and the generalization capability of the system is greatly improved; the cost of manual adjustment in the application of multiple algorithms in a new biological recognition system can be effectively reduced, the risks of easy error, influence on recognition passing rate and the like caused by adjustment are greatly reduced, and the intelligent level of the biological recognition system is improved.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. A biometric identification method, comprising:

2. The biometric identification method according to claim 1, wherein the environmental feature data includes: customer portrait data, business requirement data, and algorithmic capability data;

3. The biometric recognition method according to claim 2, wherein inputting the environmental feature data corresponding to the target user who initiated the biometric recognition request into a preset multi-algorithm decision model, and selecting one of a plurality of preset biometric recognition algorithms as the target biometric recognition algorithm corresponding to the target user according to the output of the multi-algorithm decision model comprises:

4. The biometric identification method according to claim 3, wherein the environmental feature data further comprises: the client portrait data, the service requirement data and the algorithm capability data respectively correspond to weights;

5. The biometric identification method according to claim 1, further comprising:

6. The biometric identification method according to claim 5, wherein the historical environmental feature data comprises: client representation data, business requirement data and algorithm capability data, the historical environmental characteristic data further comprising: client representation data, business requirement data, and algorithmic capability data.

7. The biometric identification method of claim 2, wherein after receiving the biometric identification request and the corresponding biometric data of the target user, comprising:

8. The biometric identification method of claim 2, wherein after receiving the biometric identification request and the corresponding biometric data of the target user, comprising:

9. The biometric identification method according to any one of claims 1 to 8, further comprising:

10. The biometric identification method according to claim 9, wherein the biometric processing type includes: registering the biological characteristics;

11. The biometric identification method according to claim 9, wherein the biometric processing type includes: one-to-one identification;

12. The biometric identification method according to claim 9, wherein the biometric processing type includes: one-to-many recognition;

13. A biometric identification device, comprising:

14. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the biometric identification method of any one of claims 1 to 12 when executing the computer program.

15. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the biometric identification method according to any one of claims 1 to 12.