WO2023130606A1 - 生物识别算法配置方法及生物识别系统 - Google Patents

生物识别算法配置方法及生物识别系统 Download PDF

Info

Publication number
WO2023130606A1
WO2023130606A1 PCT/CN2022/087030 CN2022087030W WO2023130606A1 WO 2023130606 A1 WO2023130606 A1 WO 2023130606A1 CN 2022087030 W CN2022087030 W CN 2022087030W WO 2023130606 A1 WO2023130606 A1 WO 2023130606A1
Authority
WO
WIPO (PCT)
Prior art keywords
biometric
algorithm
identification
algorithms
target
Prior art date
Application number
PCT/CN2022/087030
Other languages
English (en)
French (fr)
Inventor
郭东丹
王晓亮
魏丽芹
王淋
智学
Original Assignee
中国民航信息网络股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中国民航信息网络股份有限公司 filed Critical 中国民航信息网络股份有限公司
Publication of WO2023130606A1 publication Critical patent/WO2023130606A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
    • G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition

Definitions

  • the invention belongs to the technical field of computers, and in particular relates to a biometric identification algorithm configuration method and a biometric identification system.
  • Biometrics is the close combination of computer and optics, acoustics, biosensors and biostatistics principles, using the inherent physiological characteristics of the human body (such as fingerprints, faces, irises, etc.) and behavioral characteristics (such as handwriting, voice, gait, etc.) ) for personal identification.
  • Biometric recognition algorithms include face recognition algorithms, iris recognition algorithms, etc.
  • biometric algorithms are used for biometric identification of passengers in order to identify the identity of passengers.
  • configuration of corresponding biometric algorithms for different airports or different business systems of the same airport requires technical personnel to complete.
  • the algorithm configuration process has high technical threshold and takes a long time, which makes it unable to meet the flexible configuration requirements.
  • the present application provides a biometric algorithm configuration method and a biometric system, which can flexibly configure a biometric algorithm for a business system.
  • An embodiment of the present application provides a biometric algorithm configuration method, the method is applied to a biometric system, and the biometric system is packaged with multiple biometric algorithms, and the method includes:
  • biometric system is used to provide biometric services for the business system;
  • the desired biometric algorithm is configured for the service system to be configured, so that when the service system to be configured sends a biometric request to the biometric system, the biometric system uses the Expect biometric algorithms for biometric identification.
  • the embodiment of the present application also provides a biometric system, the system includes: an algorithm encapsulation module and a biosystem algorithm configuration module; the biometric system is used to provide biometric services for business systems;
  • the algorithm encapsulation module is used for encapsulating a plurality of biometric identification algorithms
  • the biometric system algorithm configuration module is configured to select a desired biometric algorithm from a plurality of biometric algorithms encapsulated by the biometric system, and configure the desired biometric algorithm for the business system to be configured determined from at least one business system.
  • An identification algorithm so that when the service system to be configured sends a biometric identification request to the biometric identification system, the biometric identification system uses the desired biometric identification algorithm to perform biometric identification.
  • the embodiment of the present application also provides a biometric algorithm configuration device, including: a processor, a memory, and a system bus;
  • the processor and the memory are connected through the system bus;
  • the memory is used to store one or more programs, and the one or more programs include instructions that, when executed by the processor, cause the processor to perform a biological process as described in any one of the above. Identify algorithm configuration methods.
  • the embodiment of the present application also provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are run on a terminal device, the terminal device is made to execute the A biometric algorithm configuration method described above.
  • the embodiments of the present application provide a biometric algorithm configuration method and a biometric system.
  • the biometric algorithm configuration method is applied to a biometric system, and the biometric system is packaged with multiple biometric algorithms for providing biometric services for business systems.
  • a biometric algorithm for a business system first determine the business system to be configured from at least one business system.
  • the desired biometric algorithm is selected from the multiple biometric algorithms encapsulated by the biometric system, and the desired biometric algorithm is configured in the biometric system for the business system to be configured so that when the business system to be configured sends a biometric request to the biometric system , the biometric system utilizes a desired biometric algorithm for biometric identification.
  • the desired biometric corresponding to the business system to be configured can be directly selected from the multiple biometric algorithms encapsulated.
  • recognition algorithm Determine the corresponding relationship between the business system to be configured and the expected biometric algorithm in the biometric system, that is, the configuration process is completed, the configuration process is simple and flexible, and the purpose of flexibly configuring the corresponding biometric algorithm for the same business system or different business systems is realized. .
  • FIG. 1 is a schematic diagram of an exemplary application scenario provided by an embodiment of the present application
  • FIG. 2 is a flowchart of a biometric algorithm configuration method provided in an embodiment of the present application
  • FIG. 3 is a schematic diagram of establishing a biometric information database provided by an embodiment of the present application.
  • FIG. 4 is a flow chart of providing biometric services by a biometric system provided in an embodiment of the present application
  • FIG. 5 is a schematic structural diagram of a biometric identification system provided in an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of another biometric identification system provided by the embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • Biometrics is the close combination of computer and optics, acoustics, biosensors and biostatistics principles, using the inherent physiological characteristics of the human body (such as fingerprints, faces, irises, etc.) and behavioral characteristics (such as handwriting, voice, gait, etc.) ) for personal identification.
  • Biometric recognition algorithms include face recognition algorithms, iris recognition algorithms, etc.
  • the airport uses biometric algorithms to establish a biometric information database to create a unique passenger identity for each passenger.
  • different airports or different business systems of the same airport are equipped with biometric algorithms, and the configured biometric algorithms are used for biometric identification of passengers in order to identify the identity of passengers.
  • the process of configuring biometric algorithms for different airports or different business systems of the same airport has a high technical threshold, which cannot meet the flexible configuration requirements.
  • FIG. 1 is a schematic diagram of an exemplary application scenario provided by an embodiment of the present application.
  • the biometric algorithm configuration method is applied to a biometric system, and the biometric system is packaged with multiple biometric algorithms, including biometric algorithm 1, biometric algorithm 2, and biometric algorithm 3.
  • the biometric system is used to provide biometric services for business systems.
  • the biometric identification system can be installed on the terminal equipment.
  • the business system includes the check-in business system and the boarding business system, determine the business system to be configured as the check-in business system from the check-in business system and the boarding business system. Select the desired biometric algorithm as the biometric algorithm 2 from the plurality of biometric algorithms encapsulated by the biometric system.
  • biometric identification algorithm 2 is configured for the check-in service system, so that when the check-in service system sends a biometric identification request to the biometric identification system, the biometric identification system uses the biometric identification algorithm 2 to perform biometric identification.
  • the desired biometric algorithm corresponding to the boarding business system can also be selected from the multiple biometric algorithms encapsulated by the biometric system, such as biometric algorithm 1, and set as the boarding business system System Configuration Biometric Algorithm 1.
  • FIG. 1 is only an example in which the embodiments of the present application can be implemented.
  • the scope of applicability of the embodiments of the present application is not limited by any aspect of this framework.
  • this figure is a flowchart of a biometric algorithm configuration method provided by an embodiment of the present application, and the method is executed by a biometric system.
  • the method may include S201-S203:
  • S201 Determine a service system to be configured from at least one service system.
  • an embodiment of the present application provides a biometric identification system.
  • the biometric system provides biometric services for the business system, that is, when the business system sends a biometric request to the biometric system, the biometric system uses the biometric algorithm for biometric recognition, and then returns the biometric result to the business system.
  • the biometric identification system is packaged with multiple biometric identification algorithms, which can provide a unified protocol for the business system.
  • the business system to be configured can be determined from at least one business system, and the biometric system selected from multiple biometric algorithms can be configured for the business system to be configured in the biometric system. recognition algorithm.
  • the business system includes three business systems: check-in business system, boarding business system, and security check business system. Determine the business system to be configured from the three business systems.
  • a biometric recognition algorithm is selected from multiple packaged biometric recognition algorithms to configure the check-in business system.
  • the business system to be configured also has a boarding business system, re-execute S202-S203, and also configure a corresponding biometric algorithm for the boarding business system.
  • S202 Select a desired biometric recognition algorithm from multiple biometric recognition algorithms encapsulated by the biometric recognition system; the biometric recognition system is used to provide biometric recognition services for business systems.
  • the desired biometric algorithm After determining the business system to be configured, it is necessary to select the desired biometric algorithm from the encapsulated multiple biometric algorithms to configure the business system to be configured. It can be understood that the expected biometric algorithm configured for the service system to be configured can be selected from multiple biometric algorithms according to requirements. For example, the multiple biometric algorithms encapsulated by the biometric system are biometric algorithm 1, biometric algorithm 2, and biometric algorithm 3, and the selected desired biometric algorithm is biometric algorithm 1.
  • the multiple biometric identification algorithms include multiple basic biometric identification algorithms and biometric identification fusion algorithms.
  • the basic biometric recognition algorithms are different face recognition algorithms, fingerprint recognition algorithms or iris recognition algorithms, etc.
  • the basic biometric recognition algorithm includes face recognition algorithm 1, face recognition algorithm 2, fingerprint recognition algorithm 1, fingerprint recognition algorithm 2, iris recognition algorithm 1, iris recognition algorithm 2, and the like.
  • the biometric fusion algorithm is obtained by performing algorithm fusion of multiple basic biometric algorithms or multiple basic biometric algorithms.
  • the biometric fusion algorithm can be used as a special algorithm.
  • the biometric fusion algorithm is multiple basic biometric algorithms, when the biometric fusion algorithm performs biometric identification, it needs to use multiple basic biometric algorithms to perform biometric identification respectively.
  • the biometric fusion algorithm is face recognition algorithm 1 and face recognition algorithm 2
  • face recognition algorithm 1 and face recognition algorithm 2 it is necessary to use face recognition algorithm 1 and face recognition algorithm 2 to perform face recognition once to obtain the corresponding recognition results, and then select the optimal The recognition result is taken as the final recognition result.
  • algorithm fusion refers to the fusion of underlying algorithms, such as a new biometric recognition algorithm obtained by improving the recognition algorithm of face recognition algorithm 1 and iris recognition algorithm 1.
  • any biometric algorithm and biometric fusion algorithm currently supported by the biometric system can be selected. If a biometric fusion algorithm is configured for the business system to be configured, it means that when providing biometric services for the business system to be configured, multiple basic biometric algorithms of the system will be integrated for comprehensive calculation to provide the optimal recognition result.
  • biometric system can be expanded according to requirements.
  • the new biometric identification algorithm is packaged into the biometric identification system.
  • S203 In the biometric system, configure a desired biometric algorithm for the service system to be configured, so that when the service system to be configured sends a biometric request to the biometric system, the biometric system uses the desired biometric algorithm for biometric recognition.
  • the business system to be configured After determining the business system to be configured and the corresponding expected biometric algorithm, you can configure the expected biometric algorithm for the business system to be configured in the biometric system, so that when the business system to be configured sends a biometric request to the biometric system, the biometric The system performs biometric identification using a desired biometric algorithm.
  • the service system to be configured is the check-in service system, and the corresponding desired biometric identification algorithm is biometric identification algorithm 1. Then in the biometric system, configure the biometric algorithm 1 for the check-in business system, so that when the check-in business system sends a biometric request to the biometric system, the biometric system uses the biometric algorithm 1 to perform biometric identification, and then sends the biometric identification result Return to the check-in business system.
  • the relevant information of the biometric recognition algorithm includes the basic information of the biometric recognition algorithm, the version information of the biometric recognition algorithm, and the default recognition threshold of the biometric recognition algorithm.
  • the embodiment of the present application provides a biometric identification algorithm configuration method and a biometric identification system.
  • the biometric identification algorithm configuration method is applied to a biometric identification system.
  • the biometric identification system is packaged with multiple biometric identification algorithms for The business system provides biometric services.
  • When configuring a biometric algorithm for a business system first determine the business system to be configured from at least one business system.
  • the desired biometric algorithm is selected from the multiple biometric algorithms encapsulated by the biometric system, and the desired biometric algorithm is configured in the biometric system for the business system to be configured so that when the business system to be configured sends a biometric request to the biometric system , the biometric system utilizes a desired biometric algorithm for biometric identification.
  • the desired biometric corresponding to the business system to be configured can be directly selected from the multiple biometric algorithms encapsulated.
  • recognition algorithm Determine the corresponding relationship between the business system to be configured and the expected biometric algorithm in the biometric system, that is, the configuration process is completed, the configuration process is simple and flexible, and the purpose of flexibly configuring the corresponding biometric algorithm for the same business system or different business systems is realized. .
  • each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.
  • computer program code for carrying out the operations of the present disclosure may be written in one or more programming languages, or combinations thereof, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, also includes conventional procedural programming languages—such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through an Internet service provider). Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider such as AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • the business system is a check-in business system or a boarding business system in the airport. If the business system needs to replace the biometric algorithm, because different biometric algorithms usually use different interfaces and protocols, relevant technical personnel need to change the interface and protocol before using the replaced biometric algorithm, which makes the replacement of the biometric algorithm inefficient. And the technical threshold is high.
  • the embodiment of the present application provides a process of switching biometric algorithms based on the biometric system, including:
  • A1 Determine the business system whose algorithm is to be switched; the business system whose algorithm is to be switched is currently configured with the first biometric algorithm.
  • the business system whose algorithm is to be switched is the business system that needs to switch the configured biometric algorithm.
  • the business system whose algorithm is to be switched is currently configured with a first biometric algorithm, and the first biometric algorithm needs to be switched to configure a new biometric algorithm for the business system whose algorithm is to be switched.
  • A2 Select the second biometric algorithm from multiple biometric algorithms encapsulated by the biometric system.
  • the second biometric algorithm is selected from multiple biometric algorithms encapsulated by the biometric system, and the new biometric algorithm to be configured for the business system whose algorithm is to be switched is the second biometric algorithm.
  • A3 In the biometric system, switch the first biometric algorithm currently configured by the algorithm-to-be-switched business system to the second biometric algorithm, so that when the algorithm-to-be-switched business system sends a biometric request to the biometric system, the biometric system uses The second biometric identification algorithm performs biometric identification.
  • biometric identification algorithm 1 the first biometric identification algorithm configured for the check-in service system in the biometric identification system
  • biometric identification algorithm 2 the selected second biometric identification algorithm
  • the biometric system provided by the embodiment of the present application encapsulates multiple biometric algorithms, and provides a unified protocol for the business system.
  • the biometric algorithm service makes it possible to replace the biometric algorithm configured by the same business system. Even simpler, just re-select the configurable biometric algorithm in the biometric system.
  • biometric identification algorithms can be flexibly configured for the same business system or different business systems.
  • the biometric algorithm compare the biometric data of the user (or passenger) collected on-site with the biometric reference data in the biometric information database to obtain the similarity between the two, and then compare the similarity with the preset recognition threshold Compare to get biometric results.
  • the recognition threshold is the similarity threshold.
  • the recognition threshold is a critical value for judging whether two face photos are of the same person.
  • the similarity takes a value from 0 to 1, for example, the recognition threshold/similarity threshold is 0.85.
  • the recognition threshold is 0.85, the two photos are considered to be of the same person. At this time, the biometric identification result is passed.
  • the embodiment of the present application also provides another biometric algorithm configuration method, which, in addition to the above S201-S203, also includes:
  • the identification threshold of the desired biometric algorithm is configured for the service system to be configured.
  • the biometric system can not only flexibly configure and switch the biometric algorithm used by each business system, but also flexibly adjust the misrecognition of biometrics by configuring and switching the recognition threshold of the biometric algorithm in the biometric system.
  • the rate can reduce the cost of accessing biometric services for business systems.
  • FIG. 3 is a schematic diagram of establishing a biometric information database provided by an embodiment of the present application.
  • the embodiment of the present application provides a specific implementation of establishing a biometric information database, including the following steps:
  • B1 Obtain the biometric reference data and authorization data of different users collected by the target business system, and store the biometric reference data, authorization data and target business system information; the target business system is any one of at least one business system.
  • the business systems existing in the airport can be collected by the collection device, for example, the airport's security inspection business system, check-in business system, boarding business system or other business systems. Determine any one of the business systems as the target business system.
  • the check-in service system collects the biometric reference data and authorization data of user A, and the biometric reference data and authorization data of user B.
  • the boarding business system collects the biometric reference data and authorization data of user A, the biometric reference data and authorization data of user B, and the biometric reference data and authorization data of user C.
  • target business systems collect biometric reference data and authorization data through their respective internal biometric data collection systems.
  • the biometric reference data includes biometric reference data and identity information reference data.
  • the biometric reference data is used as a reference when used for biometric identification.
  • the biometric identification algorithm is a face recognition algorithm
  • the biometric reference data is a photo of a human face.
  • the biometric reference data is the user's fingerprint information.
  • the biometric recognition algorithm is an iris recognition algorithm
  • the biometric reference data is iris information of the user.
  • the identity information reference data is the user's identity information, such as the information on the user's ID card.
  • the authorization data is the applicable scenario/business system, validity period, etc. of the biometric reference data.
  • biometric reference data and authorization data After the biometric reference data and authorization data are collected, the collected data needs to be processed. Data processing includes data analysis and elimination of invalid data. Furthermore, the processed biometric reference data and authorization data are stored. Specifically, the data-processed authorization data and the data-processed identity information reference data are stored in a structured manner, that is, stored in a database. The biometric reference data after data processing is stored unstructured, that is, saved on the file server. It can be understood that the biometric information database established in the biometric system includes a database for structured data storage and a file server for unstructured data storage.
  • the target business system information also needs to be stored in a structured manner, that is, stored in a database. That is, when a certain set of biometric reference data and authorization data is collected by the target business system, the information of the target business system that collects the biometric reference data and authorization data is stored. For example, if user A's biometric reference data and authorization data are collected by the check-in service system, when storing user A's biometric reference data and authorization data, the corresponding check-in service system information is saved.
  • the biometric algorithm information configured for each business system should also be stored in the database, that is, structured storage.
  • the target biometric algorithm uses the target biometric algorithm to calculate the tag feature value corresponding to the biometric reference data of each user collected by the target business system, and store the tag feature value;
  • the target biometric algorithm is any one of multiple biometric algorithms.
  • biometric reference data of user A and user B collected by the check-in service system and the biometric reference data of user A, user B, and biometric reference data of user C collected by the boarding service system Identify reference data.
  • the biometric algorithms supported by the biometric system are biometric algorithm 1 and biometric algorithm 2.
  • the biometric algorithm 1 is used to calculate the tag feature value of the biometric reference data of user A collected by the check-in business system, the tag feature value of the biometric reference data of user B collected by the check-in business system, and the tag feature value of the biometric reference data of user B collected by the check-in business system.
  • the tag feature value of the user's biometric reference data, the tag feature value of the B user's biometric reference data collected by the boarding service system, and the tag feature value of the C user's biometric reference data collected by the boarding service system use the biometric algorithm 2 to calculate the tag feature value of the biometric reference data of user A collected by the check-in business system, the tag feature value of the biometric reference data of user B collected by the check-in business system, and the tag feature value of the biometric reference data collected by the boarding business system.
  • the tag feature value of the user's biometric reference data, the tag feature value of the B user's biometric reference data collected by the boarding service system, and the tag feature value of the C user's biometric reference data collected by the boarding service system use the biometric algorithm 2 to calculate the tag feature value of the biometric reference data of user A collected by the check-in business system, the tag feature value of the biometric reference data of user B collected by the check-in business system, and the tag feature value of the biometric reference data collected by
  • caching can also be used to load data in the database into the memory in advance to improve access speed.
  • biometric algorithm when there is a newly supported biometric algorithm in the biometric system, it is encapsulated in the biometric system, and the newly added biometric algorithm is used for all biometric reference data (such as face photos) in the biometric information database.
  • the algorithm calculates the tag feature value, and saves the tag feature value calculated by the newly added biometric algorithm into the database.
  • FIG. 4 is a flowchart of a biometric system providing biometric services provided by an embodiment of the present application; the method also includes:
  • S401 Receive the biometric identification request and the data to be identified sent by the target business system; the data to be identified includes the target business system information and the biometric information to be identified.
  • the target business system is a business system that sends a biometric identification request to the biometric identification system.
  • the target business system is the check-in business system, and the check-in business system will call the biometric service of the biometric system when it needs to use the biometric technology to handle the identification business.
  • Data to be identified includes target business system information and biological information to be identified.
  • the target business system information is the check-in business system information, which is used to inform the biometric system that the business system sending the biometric request is the check-in business system.
  • the biological information to be identified is the face photo information, fingerprint information or iris information of the user to be identified.
  • the biometric information to be identified is the face photo information, which is used for biometric comparison and identification of the user to be identified.
  • the biometric information to be identified also includes service-specific additional parameters for verifying user information, such as the current airport where the user is located, the user's flight number, and the user's flight date.
  • S402 Determine the target biometric algorithm configured by the biometric system for the target service system according to the target service system information.
  • the biometric recognition algorithm pre-configured for the target business system in the biometric system can be determined, that is, the biometric recognition algorithm configured for the target business system in S201-S203.
  • S403 Process the biological information to be identified by using an object biometric identification algorithm to obtain a biometric identification result.
  • the embodiment of the present application provides a specific implementation manner for processing the biological information to be recognized by using the object biometric recognition algorithm in S403, and obtaining the biometric recognition result, including:
  • C1 Use the object biometrics algorithm to calculate the eigenvalues to be compared of the biometrics to be identified.
  • the object biometric algorithm is used to calculate the feature value to be compared of the biological information to be identified, and the feature value to be compared is used for comparison with the tag feature value stored in the biometric information database.
  • the subject's biometric identification algorithm is a biometric fusion algorithm and the biometric fusion algorithm is a plurality of basic biometric identification algorithms
  • the subject's biometric identification algorithm is used to calculate the eigenvalues to be compared of the biological information to be identified, including: using multiple basic biometric identification algorithms respectively
  • Each basic biological algorithm in calculates the eigenvalues to be compared of the biological information to be identified, and obtains a plurality of eigenvalues to be compared.
  • the biometric fusion algorithm includes biometric algorithm 1 and biometric algorithm 2.
  • the biometrics algorithm 1 and the biometrics algorithm 2 are used to calculate the eigenvalues of the biological information to be identified respectively, and two eigenvalues to be compared are obtained. The two eigenvalues are compared with the tag eigenvalues stored in the biometric information database to select the optimal recognition result.
  • C2 Determine the recognition threshold of the object's biometric algorithm based on the object's business system information.
  • the biometric system configures the object biometric algorithm for the object business system, it also configures the recognition threshold of the object biometric algorithm, and obtains the recognition threshold configured for the object biometric algorithm in the biometric system.
  • C3 According to the target business system information, determine the tag feature value corresponding to the biometric reference data of each user collected under the target business system and calculated by the target biometric algorithm.
  • the target business system information is the check-in business system
  • the target biometric algorithm is biometric algorithm 1
  • the eigenvalues are object label eigenvalues.
  • C4 Calculate the similarity between the feature value to be compared and the feature value of each object label, and obtain the highest similarity.
  • the highest similarity is used to determine whether the user to be identified is identified.
  • the object's biometric identification algorithm is a biometric fusion algorithm and the biometric fusion algorithm is multiple basic biometric identification algorithms
  • calculate the similarity between the feature value to be compared and the feature value of each object label to obtain the highest similarity including:
  • C41 Determine each feature value to be compared among the plurality of feature values to be compared as a target feature value to be compared.
  • C42 Calculate the similarity between the target feature value to be compared and the feature value of each object label, and obtain multiple similarities under the target feature value to be compared.
  • C43 Obtain the highest similarity from the similarities under each feature value to be compared.
  • C5 Compare the highest similarity with the recognition threshold of the object biometric algorithm to obtain the biometric result.
  • the biometrics recognition result is obtained as the recognition pass. Otherwise, the recognition fails.
  • the user information corresponding to the biometric information to be identified is determined, the user information corresponding to the biometric information to be identified is desensitized, and the desensitized user information is returned to the target business system.
  • the result of biometric identification is identification failure, the passenger cannot be identified according to the face photo passed in by the business system, and an error message is returned, prompting the target business system to fail to identify.
  • the identification failure for example, the user has not collected biometric reference data and authorized data. Or, the biometric reference data collected by the user is not authorized to be used by the target business system. Or, due to problems such as light and angle, the biological information to be identified collected by the user at the scene is quite different from the previously collected biometric reference data, resulting in the similarity calculated by the biometric algorithm not reaching the recognition threshold.
  • the face of each user collected in the boarding business system and the check-in business system is processed with reference to the photos and authorization data, and through face recognition algorithm 1, face recognition algorithm 2, and face recognition algorithm 3
  • face recognition algorithm 1 face recognition algorithm 2
  • face recognition algorithm 3 face recognition algorithm 3
  • the face reference photo is stored on the file server in an unstructured storage form
  • the authorization data, identity information reference data, and tag feature values are stored in the database in a structured form.
  • the biometric system encapsulates face recognition algorithm 1, face recognition algorithm 2, face recognition algorithm 3 and biometric fusion algorithm.
  • the business system of the airport includes the boarding business system and the check-in business system. These two business systems will call the biometric identification service of the biometric identification system.
  • the biometric recognition algorithm configured and used for the boarding business system is face recognition algorithm 1
  • the recognition threshold is 0.8
  • the biometric recognition algorithm used in the configuration of the check-in business system is face recognition algorithm 2, and the recognition threshold is 0.83.
  • the types of biometric recognition algorithms supported by the biometric recognition system can be expanded according to requirements, and new biometric recognition algorithms can be configured in the biometric recognition system.
  • the biometric system is used to provide biometric services for the boarding business system and the check-in business system. If the boarding business system and the check-in business system want to use the face recognition service to check-in and check-in for passengers, they need to call the biometric service of this system.
  • the boarding business system and the check-in business system will initiate a biometric request.
  • the boarding business system calls the biometric service, it will carry the following data to be identified: boarding business system information, facial photo information (that is, passenger photos taken at the boarding gate), and additional business-specific parameters, such as the current airport, Flight number, flight date, etc.
  • the check-in business system calls the biometric service, it will carry the following data to be identified: check-in business system information, facial photo information (that is, passenger photos taken at check-in), and additional business-specific parameters, such as the current airport.
  • the obtained biometric recognition algorithm configured for the boarding business system is face recognition algorithm 1, and the recognition threshold is 0.85.
  • the recognition threshold is 0.83.
  • this application provides a unified calling method, which is convenient for business systems to flexibly select biometric recognition algorithms. If you modify the biometric algorithm to be used by the business system in the biometric system, you only need to modify the algorithm configuration information, and no other modifications are required.
  • the boarding business system uses face recognition algorithm 1
  • the similarity of the most similar faces obtained is 0.86
  • the check-in business system uses face recognition algorithm 2
  • the similarity of the most similar faces obtained is 0.82. Since the similarity 0.86 is greater than the recognition threshold configured for the boarding business system, the recognition is successful, and the recognized passenger information is returned.
  • the biometric system returns the identified passenger information to the boarding business system, and the boarding business system performs subsequent business operations based on the obtained passenger information. If sensitive information of passengers is involved, it needs to be desensitized and returned to the boarding business system, and the desensitized passenger information should be provided to the business system according to the principle of minimization, for example, only the passenger's name is provided.
  • the similarity 0.82 is less than the algorithm threshold 0.83 configured by the check-in business system. Determine that the recognition result is recognition failure, and return an error message, prompting that the check-in business system has not recognized the passenger.
  • the bio-fusion algorithm includes face recognition algorithm 1, face recognition algorithm 2, and face recognition algorithm 3.
  • the biometric system will comprehensively use the face recognition algorithm 1, face recognition algorithm 2, and face recognition algorithm 3 supported by the system to compare and recognize, and calculate the optimal recognition result.
  • the embodiment of the present application also provides a biometric system, which will be described below with reference to the accompanying drawings.
  • a biometric system which will be described below with reference to the accompanying drawings.
  • FIG. 5 is a schematic structural diagram of a biometric identification system provided by an embodiment of the present application.
  • the biometric system 1 includes: an algorithm encapsulation module 101 and a biological system algorithm configuration module 102; the biometric system 1 is used to provide biometric services for business systems;
  • the algorithm encapsulation module 101 is used for encapsulating a plurality of biometric identification algorithms
  • the biometric system algorithm configuration module 102 is configured to select a desired biometric algorithm from a plurality of biometric algorithms packaged in the biometric system 1, and configure the biometric algorithm for the business system to be configured determined from at least one business system.
  • the desired biometric identification algorithm so that when the service system to be configured sends a biometric identification request to the biometric identification system 1, the biometric identification system 1 performs biometric identification using the expected biometric identification algorithm.
  • At least one business system is, for example, a check-in business system, a boarding business system, and a security check business system.
  • the biological system algorithm configuration module 102 is further configured to configure the expected biological identification algorithm for the service system to be configured after configuring the desired biometric algorithm for the service system to be configured.
  • the recognition threshold of the recognition algorithm is further configured to configure the expected biological identification algorithm for the service system to be configured after configuring the desired biometric algorithm for the service system to be configured.
  • the biological system algorithm configuration module 102 is also used to determine the business system whose algorithm is to be switched; the business system whose algorithm is to be switched is currently configured with a first biometric algorithm; 1. Select the second biometric algorithm from the multiple biometric algorithms packaged; in the biometric system 1, switch the first biometric algorithm currently configured by the business system whose algorithm is to be switched to the second biometric identification algorithm, so that when the algorithm is to be switched and the business system sends a biometric identification request to the biometric identification system 1, the biometric identification system 1 uses the second biometric identification algorithm to perform biometric identification.
  • FIG. 6 is a schematic structural diagram of another biometric identification system provided by an embodiment of the present application. As shown in Figure 6, in a possible implementation, the system further includes: a biometric reference data acquisition module, a data processing module and a data storage module;
  • the biometric reference data acquisition module is used to acquire the biometric reference data and authorization data of different users collected by the target business system;
  • the target business system is any one of at least one of the business systems;
  • target business systems collect biometric reference data and authorization data through their respective internal biometric data collection systems.
  • the data processing module is configured to use a target biometric algorithm to calculate the tag feature value corresponding to the biometric reference data of each user collected by the target business system;
  • the target biometric algorithm is a plurality of biometric algorithms any of
  • the data storage module is configured to store the biometric reference data, the authorization data and target service system information, and store the tag characteristic value.
  • the system further includes: a biometric service module;
  • the biometric service module includes: a receiving module, a determining module, and an identifying module;
  • the receiving module is used to receive the biological identification request and the data to be identified sent by the target business system; the data to be identified includes the target business system information and the biological information to be identified;
  • the determining module is configured to determine the object biometric algorithm configured by the biometric system 1 for the object service system according to the object service system information;
  • the identification module is configured to process the biological information to be identified by using the object biological identification algorithm to obtain a biological identification result.
  • the identification module includes: a first calculation submodule, a first determination submodule, a second determination submodule, a second calculation submodule, and a comparison submodule;
  • the first calculation submodule is used to calculate the feature value to be compared of the biological information to be identified by using the object biometric identification algorithm
  • the first determining submodule is configured to determine the identification threshold of the object's biometric identification algorithm according to the object's business system information
  • the second determining submodule is configured to determine, according to the target business system information, the tag feature value corresponding to the biometric reference data of each user collected under the target business system; the target tag feature value;
  • the second calculation submodule is used to calculate the similarity between the feature value to be compared and each of the object label feature values, and obtain the highest similarity;
  • the comparison submodule is used to compare the highest similarity with the recognition threshold of the object biometric recognition algorithm to obtain a biometric recognition result.
  • the plurality of biometric recognition algorithms include a plurality of basic biometric recognition algorithms and biometric fusion algorithms;
  • the basic biometric algorithm is obtained through algorithm fusion;
  • the first computing submodule is specifically configured to adopt multiple basic Each basic biological algorithm in the biometric recognition algorithm calculates the eigenvalues to be compared of the biological information to be identified, and obtains a plurality of eigenvalues to be compared;
  • the second calculation sub-module is specifically used to combine the multiple basic biometric algorithms to be compared when the target biometric algorithm is the biometric fusion algorithm and the biometric fusion algorithm is a plurality of basic biometric algorithms.
  • Each eigenvalue to be compared in the eigenvalues is determined as a target eigenvalue to be compared; the similarity between the target eigenvalues to be compared and each of the object label eigenvalues is calculated, and a plurality of eigenvalues under the target eigenvalues to be compared are obtained. Similarity: Obtain the highest similarity from the similarities under each of the feature values to be compared.
  • the biometric service module further includes a desensitization processing module
  • the desensitization processing module is used to determine the user information corresponding to the biometric information to be identified when the biometric identification result is passed; perform desensitization processing on the user information corresponding to the biometric information to be identified, and desensitize The processed user information is returned to the target service system.
  • the embodiment of the present application provides a biometric identification system.
  • the biometric identification system is packaged with multiple biometric identification algorithms for providing biometric identification services for business systems.
  • When configuring a biometric algorithm for a business system first determine the business system to be configured from at least one business system.
  • the desired biometric algorithm is selected from the multiple biometric algorithms encapsulated by the biometric system, and the desired biometric algorithm is configured in the biometric system for the business system to be configured so that when the business system to be configured sends a biometric request to the biometric system , the biometric system utilizes a desired biometric algorithm for biometric identification.
  • the desired biometric corresponding to the business system to be configured can be directly selected from the multiple biometric algorithms encapsulated.
  • Identification algorithm determine the corresponding relationship between the business system to be configured and the expected biometric algorithm in the biometric system, that is, the configuration process is completed, the configuration process is simple and flexible, and the corresponding biometrics can be flexibly configured for the same business system or different business systems purpose of the algorithm.
  • the embodiment of the present application also provides an application program vulnerability detection device, including: a processor, a memory, and a system bus;
  • the processor and the memory are connected through the system bus;
  • the memory is used to store one or more programs, and the one or more programs include instructions, and when the instructions are executed by the processor, the processor executes the application program vulnerability detection method described in the foregoing embodiments .
  • FIG. 7 shows a schematic structural diagram of an electronic device 700 suitable for implementing the embodiments of the present disclosure.
  • the terminal equipment in the embodiment of the present disclosure may include but not limited to such as mobile phone, notebook computer, digital broadcast receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable multimedia player), vehicle terminal (such as mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers and the like.
  • the electronic device shown in FIG. 7 is only an example, and should not limit the functions and application scope of the embodiments of the present disclosure.
  • an electronic device 700 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) Various appropriate actions and processes are executed by programs in the memory (RAM) 703 . In the RAM 703, various programs and data necessary for the operation of the electronic device 700 are also stored.
  • the processing device 701, ROM 702, and RAM 703 are connected to each other through a bus 704.
  • An input/output (I/O) interface 705 is also connected to the bus 704 .
  • the following devices can be connected to the I/O interface 705: input devices 704 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speaker, vibration an output device 707 such as a computer; a storage device 704 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 709.
  • the communication means 709 may allow the electronic device 700 to communicate with other devices wirelessly or by wire to exchange data. While FIG. 7 shows electronic device 700 having various means, it should be understood that implementing or having all of the means shown is not a requirement. More or fewer means may alternatively be implemented or provided.
  • the embodiment of the present application also provides a computer-readable storage medium, which is characterized in that instructions are stored in the computer-readable storage medium, and when the instructions are run on a terminal device, the terminal device is made to perform the aforementioned implementation.
  • the application vulnerability detection method described in the example is characterized in that instructions are stored in the computer-readable storage medium, and when the instructions are run on a terminal device, the terminal device is made to perform the aforementioned implementation.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the Android application package APK file of the application program to be detected.
  • the APK file is unpacked, and the intermediate state code file, resource file, and configuration file of the APK file are obtained.
  • the configuration file is parsed to obtain the attribute value of the target element included in the application to be detected. Decompile the APK file to obtain the source code of the APK file, and extract the keywords contained in the source code.
  • the target feature information is any one or more of the intermediate state code file, the resource file, the attribute value of the target element contained in the application to be detected, and the keyword contained in the source code. If the target characteristic information matching the vulnerability characteristic information is detected, the target characteristic information matching the vulnerability characteristic information is determined as a vulnerability item existing in the application program to be detected.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device, or may exist independently without being incorporated into the electronic device.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two.
  • a computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted by any appropriate medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
  • embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer readable medium, where the computer program includes program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from a network via communication means 709, or from storage means 706, or from ROM 702.
  • the processing device 701 When the computer program is executed by the processing device 701, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.
  • biometric algorithm configuration method including:
  • the method is applied to a biometric system, and the biometric system is packaged with a plurality of biometric algorithms, and the method includes:
  • biometric system is used to provide biometric services for the business system;
  • the desired biometric algorithm is configured for the service system to be configured, so that when the service system to be configured sends a biometric request to the biometric system, the biometric system uses the Expect biometric algorithms for biometric identification.
  • the method further includes:
  • the method also includes:
  • the biometric identification system uses the second biometric identification algorithm to perform biometric identification.
  • the method also includes:
  • the target business system is at least one of the business systems any of
  • the target biometric algorithm is used to calculate the tag feature value corresponding to the biometric reference data of each user collected by the target business system, and the tag feature value is stored; the target biometric algorithm is a plurality of the biometrics any of the algorithms.
  • the method also includes:
  • the data to be identified includes the target business system information and the biological information to be identified;
  • the biometric information to be identified is processed by using the object biometric identification algorithm to obtain a biometric identification result.
  • the processing of the biological information to be identified by using the object biometric algorithm to obtain a biometric result includes:
  • the target business system information determine that the tag feature value corresponding to the biometric reference data of each user collected under the target business system and calculated by using the target biometric algorithm is the target tag feature value;
  • the multiple biometric algorithms include multiple basic biometric algorithms and biometric fusion algorithms;
  • the biometric fusion algorithm is a plurality of basic biometric algorithms or is performed by multiple basic biometric algorithms. Algorithm fusion obtained;
  • the object biometric identification algorithm is the biometric identification fusion algorithm and the biometric identification fusion algorithm is a plurality of the basic biometric identification algorithms
  • the calculation of the biological information to be identified by using the object biometric identification algorithm Compare eigenvalues, including:
  • the object biometric algorithm is the biometric fusion algorithm and the biometric fusion algorithm is a plurality of basic biometric algorithms
  • the calculation of the feature value to be compared and each of the object tag feature values Similarity, to obtain the highest similarity including:
  • the highest similarity is obtained from the similarities under each of the feature values to be compared.
  • the method also includes:
  • the [system embodiment] provides the system of the method embodiment, including:
  • An algorithm encapsulation module and a biological system algorithm configuration module is used to provide biometric services for business systems;
  • the algorithm encapsulation module is used for encapsulating a plurality of biometric identification algorithms
  • the biometric system algorithm configuration module is configured to select a desired biometric algorithm from a plurality of biometric algorithms encapsulated by the biometric system, and configure the desired biometric algorithm for the business system to be configured determined from at least one business system.
  • An identification algorithm so that when the service system to be configured sends a biometric identification request to the biometric identification system, the biometric identification system uses the desired biometric identification algorithm to perform biometric identification.
  • the biological system algorithm configuration module is further configured to configure the identification threshold of the expected biometric algorithm for the service system to be configured after the desired biometric algorithm is configured for the service system to be configured.
  • the biological system algorithm configuration module is also used to determine the business system whose algorithm is to be switched; the business system whose algorithm is to be switched is currently configured with a first biometric algorithm; multiple biometrics packaged from the biometric system Select the second biometric algorithm in the algorithm; in the biometric system, switch the first biometric algorithm currently configured in the business system whose algorithm is to be switched to the second biometric algorithm, so that the algorithm is to be switched
  • the biometric identification system uses the second biometric identification algorithm to perform biometric identification.
  • the system further includes: a biometric reference data acquisition module, a data processing module and a data storage module;
  • the biometric reference data acquisition module is used to acquire the biometric reference data and authorization data of different users collected by the target business system;
  • the target business system is any one of at least one of the business systems;
  • the data processing module is configured to use a target biometric algorithm to calculate the tag feature value corresponding to the biometric reference data of each user collected by the target business system;
  • the target biometric algorithm is a plurality of biometric algorithms any of
  • the data storage module is configured to store the biometric reference data, the authorization data and target service system information, and store the tag characteristic value.
  • the system further includes: a biometric service module;
  • the biometric service module includes: a receiving module, a determining module, and an identifying module;
  • the receiving module is used to receive the biological identification request and the data to be identified sent by the target business system; the data to be identified includes the target business system information and the biological information to be identified;
  • the determining module is configured to determine the object biometric algorithm configured by the biometric system for the object service system according to the object service system information;
  • the identification module is configured to process the biological information to be identified by using the object biological identification algorithm to obtain a biological identification result.
  • the identification module includes: a first calculation submodule, a first determination submodule, a second determination submodule, a second calculation submodule and a comparison submodule;
  • the first calculation submodule is used to calculate the feature value to be compared of the biological information to be identified by using the object biometric identification algorithm
  • the first determining submodule is used to determine the identification threshold of the object biometric algorithm according to the object business system information
  • the second determining submodule is configured to determine, according to the target business system information, the tag feature value corresponding to the biometric reference data of each user collected under the target business system; the target tag feature value;
  • the second calculation submodule is used to calculate the similarity between the feature value to be compared and each of the object label feature values, and obtain the highest similarity;
  • the comparison submodule is used to compare the highest similarity with the recognition threshold of the object biometric recognition algorithm to obtain a biometric recognition result.
  • the multiple biometric algorithms include multiple basic biometric algorithms and biometric fusion algorithms;
  • the biometric fusion algorithm is a plurality of basic biometric algorithms or is performed by multiple basic biometric algorithms. Algorithm fusion obtained;
  • the first computing submodule is specifically configured to adopt multiple basic Each basic biological algorithm in the biometric recognition algorithm calculates the eigenvalues to be compared of the biological information to be identified, and obtains a plurality of eigenvalues to be compared;
  • the second calculation sub-module is specifically used to combine the multiple basic biometric algorithms to be compared when the target biometric algorithm is the biometric fusion algorithm and the biometric fusion algorithm is a plurality of basic biometric algorithms.
  • Each eigenvalue to be compared in the eigenvalues is determined as a target eigenvalue to be compared; the similarity between the target eigenvalues to be compared and each of the object label eigenvalues is calculated, and a plurality of eigenvalues under the target eigenvalues to be compared are obtained. Similarity: Obtain the highest similarity from the similarities under each of the feature values to be compared.
  • the biometric service module also includes a desensitization processing module
  • the desensitization processing module is used to determine the user information corresponding to the biometric information to be identified when the biometric identification result is passed; perform desensitization processing on the user information corresponding to the biometric information to be identified, and desensitize The processed user information is returned to the target service system.
  • [device embodiment] provides the device of the method embodiment, including: a processor, a memory, and a system bus;
  • the processor and the memory are connected through the system bus;
  • the memory is used to store one or more programs, and the one or more programs include instructions, and the instructions, when executed by the processor, cause the processor to execute the biometric algorithm configuration method.
  • [storage medium embodiment] provides the computer-readable storage medium of the method embodiment, the computer-readable storage medium stores instructions, and when the instructions are run on the terminal device , causing the terminal device to execute the biometric algorithm configuration method.
  • modules described in the embodiments of the present disclosure may be implemented by software or by hardware. Wherein, the name of the module does not constitute a limitation of the unit itself under certain circumstances.

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Collating Specific Patterns (AREA)

Abstract

本申请公开了生物识别算法配置方法及生物识别系统，生物识别算法配置方法应用于生物识别系统中，生物识别系统封装有多个生物识别算法，用于为业务系统提供生物识别服务。从至少一个业务系统中确定待配置业务系统，从生物识别系统封装的多个生物识别算法中选择期望生物识别算法，在生物识别系统中为待配置业务系统配置期望生物识别算法，以便待配置业务系统向生物识别系统发送生物识别请求时，生物识别系统利用期望生物识别算法进行生物识别。如此，使得在生物识别系统中，可直接从其封装的多个生物识别算法中选择期望的生物识别算法，并进行业务系统算法配置即可，实现了为同一业务系统或不同业务系统灵活配置对应的生物识别算法的目的。

Description

生物识别算法配置方法及生物识别系统
本申请要求于2022年1月10日提交中国国家知识产权局、申请号为202210022407.9、发明名称为“生物识别算法配置方法及生物识别系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明属于计算机技术领域，具体涉及一种生物识别算法配置方法及生物识别系统。
背景技术
生物识别为通过计算机与光学、声学、生物传感器和生物统计学原理等手段密切结合，利用人体固有的生理特性(如指纹、脸像、虹膜等)和行为特征(如笔迹、声音、步态等)来进行个人身份的鉴定。生物识别算法包括人脸识别算法、虹膜识别算法等。
目前，不同机场或同一机场不同业务系统配置有生物识别算法，配置的生物识别算法用于对旅客进行生物识别，以便识别出旅客的身份。当前为不同机场或同一机场不同业务系统配置对应的生物识别算法需要技术人员完成，算法配置过程技术门槛高、时间长，导致不能满足灵活性配置需求。
发明内容
为了解决上述技术问题，本申请提供了生物识别算法配置方法及生物识别系统，能够为业务系统灵活配置生物识别算法。
为了实现上述目的，本申请实施例提供的技术方案如下：
本申请实施例提供一种生物识别算法配置方法，所述方法应用于生物识别系统，所述生物识别系统封装有多个生物识别算法，所述方法包括：
从至少一个业务系统中确定待配置业务系统；
从所述生物识别系统封装的多个生物识别算法中选择期望生物识别算法；所述生物识别系统用于为所述业务系统提供生物识别服务；
在所述生物识别系统中，为所述待配置业务系统配置所述期望生物识别算法，以便所述待配置业务系统向所述生物识别系统发送生物识别请求时，所述生物识别系统利用所述期望生物识别算法进行生物识别。
本申请实施例还提供了一种生物识别系统，所述系统包括：算法封装模块和生物系统算法配置模块；所述生物识别系统用于为业务系统提供生物识别服务；
所述算法封装模块，用于封装多个生物识别算法；
所述生物系统算法配置模块，用于从所述生物识别系统封装的多个生物识别算法中选择期望生物识别算法，为从至少一个业务系统中确定的所述待配置业务系统配置所述期望生物识别算法，以便所述待配置业务系统向所述生物识别系统发送生物识别请求时，所述生物识别系统利用所述期望生物识别算法进行生物识别。
本申请实施例还提供了一种生物识别算法配置设备，包括：处理器、存储器、系统总线；
所述处理器以及所述存储器通过所述系统总线相连；
所述存储器用于存储一个或多个程序，所述一个或多个程序包括指令，所述指令当被所述处理器执行时使所述处理器执行如上述任一项所述的一种生物识别算法配置方法。
本申请实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，当所述指令在终端设备上运行时，使得所述终端设备执行如上述任一项所述的一种生物识别算法配置方法。
通过上述技术方案可知，本申请具有以下有益效果：
本申请实施例提供了生物识别算法配置方法及生物识别系统，该生物识别算法配置方法应用于生物识别系统中，生物识别系统封装有多个生物识别算法，用于为业务系统提供生物识别服务。为业务系统配置生物识别算法时，先从至少一个业务系统中确定待配置业务系统。进而，从生物识别系统封装的多个生物识别算法中选择期望生物识别算法，在生物识别系统中为待配置业务系统配置期望生物识别算法，以便待配置业务系统向生物识别系统发送生物识别请求时，生物识别系统利用期望生物识别算法进 行生物识别。如此，由于本申请实施例中的生物识别系统中已经封装有多个生物识别算法，使得基于生物识别系统，可直接从其封装的多个生物识别算法中选择和待配置业务系统对应的期望生物识别算法。在生物识别系统中确定待配置业务系统和期望生物识别算法的对应关系，即完成了配置过程，配置过程简单且灵活，实现了为同一业务系统或不同业务系统灵活配置对应的生物识别算法的目的。
附图说明
附图用来提供对本发明的进一步理解，并且构成说明书的一部分，与本发明实施例一起用于解释本发明，并不构成对本发明的限制。在附图中：
图1为本申请实施例提供的一种示例性应用场景的示意图；
图2为本申请实施例提供的一种生物识别算法配置方法的流程图；
图3为本申请实施例提供的一种建立生物特征信息数据库的示意图；
图4为本申请实施例提供的一种生物识别系统提供生物识别服务的流程图；
图5为本申请实施例提供的一种生物识别系统的结构示意图；
图6为本申请实施例提供的另一种生物识别系统的结构示意图；
图7为本申请实施例提供的一种电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。为了便于理解和解释本申请实施例提供的技术方案，下面先对本申请实施例的背景技术进行说明。
【方法实施例】
生物识别为通过计算机与光学、声学、生物传感器和生物统计学原理等手段密切结合，利用人体固有的生理特性(如指纹、脸像、虹膜等)和行为特征(如笔迹、声音、步态等)来进行个人身份的鉴定。生物识别算法包括人脸识别算法、虹膜识别算法等。
为了推动民航高质量发展，机场采用生物识别算法建立生物特征信息数据库，为每一位旅客建立旅客唯一身份标识。利用旅客的唯一身份标识，在值机、安检、登机、贵宾服务等机场各个环节对旅客进行生物识别，提高旅客的出行效率。目前，不同机场或同一机场不同业务系统配置有生物识别算法，配置的生物识别算法用于对旅客进行生物识别，以便识别出旅客的身份。当前为不同机场或同一机场不同业务系统配置生物识别算法的过程技术门槛高、导致不能满足灵活性配置需求。
基于此，本申请实施例提供了一种生物识别算法配置方法及生物识别系统，为了便于理解本申请实施例提供的生物识别算法配置方法，下面结合图1对其示例性应用场景进行说明。图1为本申请实施例提供的一种示例性应用场景的示意图。
在实际应用中，该生物识别算法配置方法应用于生物识别系统中，生物识别系统封装有多个生物识别算法，包括生物识别算法1、生物识别算法2和生物识别算法3。生物识别系统用于为业务系统提供生物识别服务。具体实施时，生物识别系统可安装于终端设备上。
若业务系统包括值机业务系统和登机业务系统，从值机业务系统和登机业务系统中确定待配置业务系统为值机业务系统。从生物识别系统封装的多个生物识别算法中选择期望生物识别算法为生物识别算法2。
进一步，为值机业务系统配置生物识别算法2，以便值机业务系统向生物识别系统发送生物识别请求时，生物识别系统利用生物识别算法2进行生物识别。
另外，待配置业务系统为登机业务系统时，也可从生物识别系统封装的多个生物识别算法中选择登机业务系统对应的期望生物识别算法，如生物识别算法1，并为登机业务系统配置生物识别算法1。
本领域技术人员可以理解，图1所示的框架示意图仅是本申请的实施方式可以在其中得以实现的一个示例。本申请实施方式的适用范围不受到该框架任何方面的限制。
基于上述说明，下面将结合附图对本申请提供的生物识别算法配置方法进行详细说明。
参见图2，该图为本申请实施例提供的生物识别算法配置方法的流程图，该方法由生物识别系统执行。如图2所示，方法可以包括S201-S203：
S201：从至少一个业务系统中确定待配置业务系统。
通常，机场中针对不同场景设置有不同的业务系统，例如值机业务系统、登机业务系统和安检业务系统等。在这些业务系统中，需要通过生物识别算法来识别旅客的身份，例如，采用人脸识别、虹膜识别等识别旅客的身份。
为了满足能够灵活为同一业务系统或不同业务系统配置生物识别算法，本申请实施例提供了一种生物识别系统。生物识别系统为业务系统提供生物识别服务，即当业务系统向生物识别系统发送生物识别请求时，生物识别系统利用生物识别算法进行生物识别，再将生物识别结果返回至业务系统。
在本申请实施例中，生物识别系统封装有多个生物识别算法，能够为业务系统提供统一协议。
需要说明的是，当为机场的业务系统配置生物识别算法时，可从至少一个业务系统中确定待配置业务系统，在生物识别系统中为待配置业务系统配置从多个生物识别算法选择的生物识别算法。例如，业务系统包括值机业务系统、登机业务系统和安检业务系统等三个业务系统。从三个业务系统中确定待配置业务系统。例如待配置业务系统为值机业务系统，则从封装的多个生物识别算法选择一个生物识别算法，为值机业务系统进行配置。若待配置业务系统还有登机业务系统，则重新执行S202-S203，也为登机业务系统配置对应的生物识别算法。
S202：从生物识别系统封装的多个生物识别算法中选择期望生物识别算法；生物识别系统用于为业务系统提供生物识别服务。
确定待配置业务系统后，需要从封装多个生物识别算法选择期望生物识别算法，为待配置业务系统进行配置。可以理解的是，可以根据需求从多个生物识别算法选择为待配置业务系统配置的期望生物识别算法。例如，生物识别系统封装的多个生物识别算法为生物识别算法1、生物识别算法2和生物识别算法3，选择的期望生物识别算法为生物识别算法1。
需要说明的是，多个生物识别算法包括多个基础生物识别算法和生物识别融合算法。其中，基础生物识别算法为不同的人脸识别算法、指纹识别算法或 虹膜识别算法等。例如，基础生物识别算法包括人脸识别算法1、人脸识别算法2、指纹识别算法1、指纹识别算法2、虹膜识别算法1和虹膜识别算法2等。
生物识别融合算法为多个基础生物识别算法或者由多个基础生物识别算法进行算法融合获得。生物识别融合算法可作为一种特殊算法。当生物识别融合算法为多个基础生物识别算法时，生物识别融合算法进行生物识别时，需要利用多个基础生物识别算法分别进行一次生物识别。例如，当生物识别融合算法为人脸识别算法1和人脸识别算法2时，需要采用人脸识别算法1和人脸识别算法2分别进行一次人脸识别，得到对应的识别结果，再选择最优的识别结果作为最终识别结果。另外，算法融合指的是底层算法融合，例如将人脸识别算法1和虹膜识别算法1进行识别算法上的改进后得到的新的生物识别算法。
在实际应用中，为待配置业务系统配置期望生物识别算法的时候，可以选择生物识别系统中目前已支持的任何一种生物识别算法以及生物识别融合算法。如果为待配置业务系统配置生物识别融合算法，则表示为待配置业务系统提供生物识别服务的时候，会融合系统多个基础生物识别算法进行综合计算，提供最优的识别结果。
还需要说明的是，生物识别系统支持的算法类型可以根据需求进行扩展。当获取新的生物识别算法且生物识别系统支持该新的生物识别算法时，将新的生物识别算法封装到生物识别系统中。
S203：在生物识别系统中，为待配置业务系统配置期望生物识别算法，以便待配置业务系统向生物识别系统发送生物识别请求时，生物识别系统利用期望生物识别算法进行生物识别。
确定待配置业务系统和对应的期望生物识别算法后，便可在生物识别系统中，为待配置业务系统配置期望生物识别算法，以便待配置业务系统向生物识别系统发送生物识别请求时，生物识别系统利用期望生物识别算法进行生物识别。
例如，待配置业务系统为值机业务系统，对应的期望生物识别算法为生物识别算法1。则在生物识别系统中，为值机业务系统配置生物识别算法1，以便值机业务系统向生物识别系统发送生物识别请求时，生物识别系统利用生物识别算法1进行生物识别，再把生物识别结果返回至值机业务系统。
另外，在生物识别系统中，还需要管理生物识别算法的相关信息。其中，生物识别算法的相关信息包括生物识别算法的基本信息、生物识别算法的版本信息和生物识别算法的默认识别阈值。
基于S201-S203的内容，本申请实施例提供了生物识别算法配置方法及生物识别系统，该生物识别算法配置方法应用于生物识别系统中，生物识别系统封装有多个生物识别算法，用于为业务系统提供生物识别服务。为业务系统配置生物识别算法时，先从至少一个业务系统中确定待配置业务系统。进而，从生物识别系统封装的多个生物识别算法中选择期望生物识别算法，在生物识别系统中为待配置业务系统配置期望生物识别算法，以便待配置业务系统向生物识别系统发送生物识别请求时，生物识别系统利用期望生物识别算法进行生物识别。如此，由于本申请实施例中的生物识别系统中已经封装有多个生物识别算法，使得基于生物识别系统，可直接从其封装的多个生物识别算法中选择和待配置业务系统对应的期望生物识别算法。在生物识别系统中确定待配置业务系统和期望生物识别算法的对应关系，即完成了配置过程，配置过程简单且灵活，实现了为同一业务系统或不同业务系统灵活配置对应的生物识别算法的目的。
需要说明的是，附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
需要注意，本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
需要注意，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这 些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。
需要注意，可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
由于目前不同机场或同一机场的不同业务系统对旅客进行生物识别时，采用固定的生物识别算法进行识别。其中，业务系统为机场中的值机业务系统或登机业务系统等。若业务系统需要更换生物识别算法，由于不同的生物识别算法通常所采用的接口和协议不同，需要相关技术人员更改接口和协议之后才能使用更换后的生物识别算法，使得更换生物识别算法的效率低且技术门槛高。
基于此，在一种可能的实现方式中，本申请实施例基于生物识别系统提供了一种切换生物识别算法的过程，包括：
A1：确定算法待切换业务系统；算法待切换业务系统当前配置有第一生物识别算法。
其中，算法待切换业务系统即为需要切换已配置的生物识别算法的业务系统。该算法待切换业务系统当前配置有第一生物识别算法，需要将第一生物识别算法进行切换，以为算法待切换业务系统配置新的生物识别算法。
A2：从生物识别系统封装的多个生物识别算法中选择第二生物识别算法。
从生物识别系统封装的多个生物识别算法中选择第二生物识别算法，要为算法待切换业务系统配置的新的生物识别算法即为第二生物识别算法。
A3：在生物识别系统中，将算法待切换业务系统当前配置的第一生物识别算法切换为第二生物识别算法，以便算法待切换业务系统向生物识别系统发送生物识别请求时，生物识别系统利用第二生物识别算法进行生物识别。
确定算法待切换业务系统和第二生物识别算法后，将算法待切换业务系统当前配置的第一生物识别算法切换为第二生物识别算法。
例如，若在生物识别系统中为值机业务系统配置的第一生物识别算法为生物识别算法1，且选择的第二生物识别算法为生物识别算法2。将生物识别系统中为值机业务系统当前配置的生物识别算法1更换为生物识别算法2。
基于A1-A3的内容可知，本申请实施例提供的生物识别系统封装了多个生物识别算法，为业务系统提供统一协议的生物识别算法服务，使得更换同一业务系统配置的生物识别算法的更换过程更加简单，只需在生物识别系统中重新选择可配置的生物识别算法即可。
另外，通过本申请实施例提供的生物识别系统，可灵活为同一业务系统或不同业务系统配置对应的生物识别算法。通过生物识别算法，对现场采集的用户(或旅客)的生物特征数据和生物特征信息数据库中的生物特征参照数据进行比对以得到两者的相似度，再将相似度和预设的识别阈值进行比较来获取生物识别结果。其中，识别阈值即为相似度阈值。例如，当生物特征数据为人脸识别照片时，可以认为识别阈值为用于判定两张人脸照片是否为同一个人的临界值。一般，相似度取值为0到1，例如识别阈值/相似度阈值为0.85。对于同一算法而言，两张照片相似度越高，认为两张照片越相似，若达到识别阈值0.85，认为两张照片为同一人的照片。此时，生物识别结果为通过。
基于此，为了灵活设置生物识别算法的识别阈值，以灵活调整生物识别的误识率。在一种可能的实现方式中，本申请实施例还提供了另一种生物识别算法配置方法，除了上述的S201-S203，还包括：
在生物识别系统中，为待配置业务系统配置期望生物识别算法之后，为待配置业务系统配置期望生物识别算法的识别阈值。
也就是说，利用生物识别系统，不仅可以为各业务系统灵活配置并切换使用的生物识别算法，还能通过在生物识别系统中配置和切换生物识别算法的识别阈值来灵活调整生物识别的误识率，能够降低为业务系统接入生物识别服务 的成本。
为了提供生物识别服务，需要预先进行数据准备，建立生物特征信息数据库。基于此，参见图3，图3为本申请实施例提供的一种建立生物特征信息数据库的示意图。在一种可能的实现方式中，本申请实施例提供了建立生物特征信息数据库的具体实现方式，包括以下步骤：
B1：获取目标业务系统采集的不同用户的生物识别参照数据和授权数据，将生物识别参照数据、授权数据和目标业务系统信息进行存储；目标业务系统为至少一个业务系统中的任一个。
采集不同用户(即旅客)的生物识别参照数据和授权数据的渠道有很多。机场中存在的业务系统可以通过采集设备进行采集，例如，机场的安检业务系统、值机业务系统、登机业务系统或者其他业务系统。确定业务系统中的任一个为目标业务系统。获取至少一个业务系统中的任一个业务系统采集的不同用户的生物识别参照数据和授权数据。例如，值机业务系统采集了A用户的生物识别参照数据和授权数据、B用户的生物识别参照数据和授权数据。登机业务系统采集了A用户的生物识别参照数据和授权数据、B用户的生物识别参照数据和授权数据、C用户的生物识别参照数据和授权数据。在实际应用中，目标业务系统通过各自内部的生物识别数据采集系统采集生物识别参照数据和授权数据。
其中，生物识别参照数据包括生物特征参照数据和身份信息参照数据。生物识别参照数据用于生物识别时作为参照。当生物识别算法为人脸识别算法时，生物特征参照数据为人脸照片。当生物识别算法为指纹识别算法时，生物特征参照数据为用户的指纹信息。当生物识别算法为虹膜识别算法时，生物特征参照数据为用户的虹膜信息。身份信息参照数据为用户的身份信息，如用户的身份证上的信息。为了确保数据隐私和数据安全，采集生物识别参照数据时需要充分告知用户采集的数据范围，并由用户授权采集的数据的使用场景和使用期限。基于此，授权数据为生物识别参照数据适用的场景/业务系统、有效期等。
另外，采集到生物识别参照数据和授权数据后，需要对采集的数据进行处理。数据处理包括数据解析和剔除无效数据。进而，对数据处理后的生物识别 参照数据和授权数据进行存储。具体地，将数据处理后的授权数据和数据处理后的身份信息参照数据进行结构化存储，即存储于数据库中。将数据处理后的生物特征参照数据进行非结构化存储，即保存在文件服务器上。可以理解的是，在生物识别系统中建立的生物特征信息数据库包括结构化存储数据的数据库，也包括非结构化存储数据的文件服务器。
此外，目标业务系统信息也需要进行结构化存储，即存储在数据库中。即当某组生物识别参照数据和授权数据是由目标业务系统采集的，则将采集生物识别参照数据和授权数据的目标业务系统信息进行存储。例如，A用户的生物识别参照数据和授权数据为值机业务系统采集的，则在存储A用户的生物识别参照数据和授权数据时，保存对应的值机业务系统信息。另外，各个业务系统被配置的生物识别算法信息(包括生物识别算法和生物识别算法对应的识别阈值)也要存储在数据库中，即结构化存储。
B2：采用目标生物识别算法计算目标业务系统采集的各个用户的生物识别参照数据对应的标签特征值，将标签特征值进行存储；目标生物识别算法为多个生物识别算法中的任一个。
在不同业务系统下采集到各个用户的生物识别参照数据后，用生物识别系统支持的多个生物识别算法分别计算采集到的所有生物识别参照数据对应的标签特征值，获取任一生物识别参照数据对应的标签特征值，再将计算得到的所有标签特征值进行结构化存储，即存储于数据库中。标签特征值用于生物识别使用。
例如，值机业务系统采集的A用户的生物识别参照数据、B用户的生物识别参照数据，登机业务系统采集了A用户的生物识别参照数据、B用户的生物识别参照数据、C用户的生物识别参照数据。生物识别系统支持的生物识别算法为生物识别算法1和生物识别算法2。则采用生物识别算法1计算值机业务系统采集的A用户的生物识别参照数据的标签特征值、值机业务系统采集的B用户的生物识别参照数据的标签特征值、登机业务系统采集的A用户的生物识别参照数据的标签特征值、登机业务系统采集的B用户的生物识别参照数据的标签特征值、登机业务系统采集的C用户的生物识别参照数据的标签特征值。再用生物识别算法2计算值机业务系统采集的A用户的生物识别参照数据的标签 特征值、值机业务系统采集的B用户的生物识别参照数据的标签特征值、登机业务系统采集的A用户的生物识别参照数据的标签特征值、登机业务系统采集的B用户的生物识别参照数据的标签特征值、登机业务系统采集的C用户的生物识别参照数据的标签特征值。
在本申请实施例中，还可采用缓存提前将数据库中数据加载到内存，提高访问速度。
另外，当生物识别系统中有新增支持的生物识别算法时，在生物识别系统中进行封装，并对生物特征信息数据库中所有的生物识别参照数据(例如人脸照片)使用新增的生物识别算法计算标签特征值，并将利用新增的生物识别算法计算得到的标签特征值保存入库。
在建立生物特征信息数据库，以及为业务系统配置完成对应的生物识别算法后，便可利用生物识别系统为业务系统提供生物识别服务。参见图4，图4为本申请实施例提供的一种生物识别系统提供生物识别服务的流程图；方法还包括：
S401：接收对象业务系统发送的生物识别请求和待识别数据；待识别数据包括对象业务系统信息和待识别生物信息。
其中，对象业务系统为向生物识别系统发送生物识别请求的业务系统。例如，对象业务系统为值机业务系统，值机业务系统在需要使用生物识别技术办理识别业务的时候，会调用生物识别系统的生物识别服务。
对象业务系统调用生物识别系统的生物识别服务的时候会携带待识别数据。待识别数据包括对象业务系统信息和待识别生物信息。其中，当对象业务系统为值机业务系统时，对象业务系统信息为值机业务系统信息，用于告知生物识别系统发送生物识别请求的业务系统为值机业务系统。
待识别生物信息为待识别用户的人脸照片信息、指纹信息或虹膜信息等。当对象业务系统使用的是人脸照片采集设备采集用户的人脸照片时，待识别生物信息为人脸照片信息，用于进行生物识别比对，识别待识别用户。此外，待识别生物信息还包括业务特有附加参数，用于对用户信息进行验证，例如用户所处当前机场、用户的航班号、用户的航班日期等。
S402：根据对象业务系统信息确定生物识别系统为对象业务系统配置的对象生物识别算法。
确定对象业务系统信息后，便可确定在生物识别系统中预先为该对象业务系统配置的生物识别算法，即在S201-S203中为该对象业务系统配置的生物识别算法。
S403：采用对象生物识别算法对待识别生物信息进行处理，获取生物识别结果。
具体实施时，在一种可能的实现方式中，本申请实施例提供了一种S403中采用对象生物识别算法对待识别生物信息进行处理，获取生物识别结果的具体实施方式，包括：
C1：采用对象生物识别算法计算待识别生物信息的待对比特征值。
获取待识别生物信息后，采用对象生物识别算法计算待识别生物信息的待对比特征值，待对比特征值用于和生物特征信息数据库中存储的标签特征值进行比对。
当对象生物识别算法为生物识别融合算法且生物识别融合算法为多个基础生物识别算法时，采用对象生物识别算法计算待识别生物信息的待对比特征值，包括：分别采用多个基础生物识别算法中的每个基础生物算法计算待识别生物信息的待对比特征值，获取多个待对比特征值。
例如，生物识别融合算法包括生物识别算法1和生物识别算法2。则采用生物识别算法1和生物识别算法2分别计算待识别生物信息的特征值，获得2个待对比特征值。利用2个特征值分别和生物特征信息数据库中存储的标签特征值进行比对，选择最优识别结果。
C2：根据对象业务系统信息确定对象生物识别算法的识别阈值。
生物识别系统在为对象业务系统配置对象生物识别算法时，还配置了对象生物识别算法的识别阈值，获取生物识别系统中为对象生物识别算法配置的识别阈值。
C3：根据对象业务系统信息，确定在对象业务系统下采集的并用对象生物识别算法计算得到的各个用户的生物识别参照数据对应的标签特征值为对象标签特征值。
例如，对象业务系统信息为值机业务系统，对象生物识别算法为生物识别算法1，确定在值机业务系统下采集的并由生物识别算法1计算得到的各个用户的生物识别参照数据对应的标签特征值为对象标签特征值。
C4：计算待对比特征值和各个对象标签特征值的相似度，获取最高相似度。
其中，最高相似度用于确定待识别用户是否识别通过。
当对象生物识别算法为生物识别融合算法且生物识别融合算法为多个基础生物识别算法时，计算待对比特征值和各个对象标签特征值的相似度，获取最高相似度，包括：
C41：将多个待对比特征值中的每个待对比特征值确定为目标待对比特征值。
C42：计算目标待对比特征值和各个对象标签特征值的相似度，获取目标待对比特征值下的多个相似度。
C43：从各个待对比特征值下的相似度中获取最高相似度。
即，当待对比特征值为多个且对象标签特征值为多个时，需要先确定一个待对比特征值作为目标待对比特征值，计算该待对比特征值和每个对象标签特征值的相似度，获取该待对比特征值下的多个相似度。再从多个待对比特征值确定另一个待对比特征值作为目标待对比特征值，计算该待对比特征值下的多个相似度。遍历完所有待对比特征值后，从获得的所有的相似度中选取最高相似度。
另外，也可获取目标待对比特征值下的多个相似度后，选择目标待对比特征值下的最高相似度，再将多个目标待对比特征值下的最高相似度进行比较，选取最高相似度。
C5：将最高相似度和对象生物识别算法的识别阈值相比较，获取生物识别结果。
当最高相似度高于对象生物识别算法的识别阈值后，获取生物识别结果为识别通过。否则，为识别失败。
一方面，当生物识别结果为识别通过时，确定待识别生物信息对应的用户信息，对待识别生物信息对应的用户信息进行脱敏处理，将脱敏处理后的用户 信息返回至对象业务系统。另一方面，当生物识别结果为识别失败时，根据业务系统传入的人脸照片没有识别出旅客，返回错误信息，提示对象业务系统识别失败。其中，识别失败有多种原因，例如该用户没有进行生物识别参照数据和授权数据采集。或者，该用户采集的生物识别参照数据没有授权对象业务系统使用。或者，由于光线、角度等问题，该用户在现场采集的待识别生物信息，与先前采集的生物识别参照数据差异较大，导致生物识别算法计算出的相似度没有达到识别阈值。
【应用场景实施例】
为了便于理解本申请实施例提供的建立生物特征信息数据库、生物识别算法配置、生物识别系统提供生物识别服务的过程，下面以一具体示例进行说明。
首先，将在登机业务系统和值机业务系统分别采集到的各个用户的人脸参照照片和授权数据进行数据处理，并通过人脸识别算法1、人脸识别算法2、人脸识别算法3分别生成不同业务系统采集的各个用户的人脸参照照片的标签特征值。其中，人脸参照照片以非结构化存储形式保存在文件服务器上；授权数据、身份信息参照数据、标签特征值以结构化形式保存在数据库中。为了确保数据隐私和数据安全，在采集用户的人脸参照照片时，需要充分告知用户采集的数据范围，并由用户授权明确人脸参照照片的使用业务系统和使用期限，即授权数据。
其次，生物识别系统封装了人脸识别算法1、人脸识别算法2、人脸识别算法3和生物识别融合算法。机场的业务系统包括登机业务系统、值机业务系统，这两个业务系统会调用生物识别系统的生物识别服务。根据业务需求，为登机业务系统配置使用的生物识别算法为人脸识别算法1，识别阈值为0.8。值机业务系统配置使用的生物识别算法为人脸识别算法2，识别阈值为0.83。另外，生物识别系统支持的生物识别算法类型可以根据需求进行扩展，在生物识别系统中配置增加的新的生物识别算法即可。
最后，利用生物识别系统为登机业务系统和值机业务系统提供生物识别服务。登机业务系统和值机业务系统如果要使用人脸识别服务为旅客办理登机和值机业务，则需要调用本系统的生物识别服务。登机业务系统和值机业务系统会发起生物识别请求。登机业务系统调用生物识别服务的时候会携带如下待识 别数据：登机业务系统信息、人脸照片信息(即在登机口拍摄到的旅客照片)，以及业务特有附加参数，比如当前机场、航班号、航班日期等。值机业务系统调用生物识别服务的时候会携带如下待识别数据：值机业务系统信息、人脸照片信息(即在值机拍摄的旅客照片)，以及业务特有附加参数，比如当前机场等。
如果是登机业务系统调用生物识别服务，则获取到的为登机业务系统配置的生物识别算法为人脸识别算法1，识别阈值为0.85。如果是值机业务系统调用生物识别服务，则获取到的为值机业务系统配置的生物识别算法为人脸识别算法2，识别阈值为0.83。进而，使用人脸识别算法1对登机业务系统发送的人脸照片信息进行人脸识别，使用人脸识别算法2对值机业务系统发送的人脸照片信息人脸识别。对于不同的生物识别算法，本申请提供统一的调用方式，方便业务系统灵活选择生物识别算法。若在生物识别系统中修改业务系统要使用的生物识别算法，只需修改算法配置信息即可，无需做其他修改。
若登机业务系统使用人脸识别算法1，获取到的最相似人脸的相似度为0.86；值机业务系统使用人脸识别算法2，获取到的最相似人脸的相似度为0.82。由于相似度0.86大于为登机业务系统配置的识别阈值，则识别成功，返回识别到的旅客信息。生物识别系统将识别出的旅客信息返回登机业务系统，登机业务系统根据获取的旅客信息进行后续的业务操作。如果涉及到旅客的敏感信息，需要脱敏返回给登机业务系统，且按照最小化原则将脱敏后的旅客信息提供给业务系统，例如只提供旅客姓名。而相似度0.82小于值机业务系统配置的算法阈值0.83。确定识别结果为识别失败，返回错误信息，提示值机业务系统没有识别出旅客。
如果业务系统配置了生物融合算法进行人脸识别，生物融合算法包括人脸识别算法1、人脸识别算法2、人脸识别算法3。生物识别系统会综合使用系统支持的人脸识别算法1、人脸识别算法2、人脸识别算法3进行比对识别，计算出最优的识别结果。
【系统实施例】
基于上述方法实施例提供的生物识别算法配置方法，本申请实施例还提供了一种生物识别系统，下面将结合附图对该生物识别系统进行说明，该系统的技术详情请参见上述方法实施例。
参见图5，图5为本申请实施例提供的一种生物识别系统的结构示意图。如图5所示，该生物识别系统1包括：算法封装模块101和生物系统算法配置模块102；所述生物识别系统1用于为业务系统提供生物识别服务；
所述算法封装模块101，用于封装多个生物识别算法；
所述生物系统算法配置模块102，用于从所述生物识别系统1封装的多个生物识别算法中选择期望生物识别算法，为从至少一个业务系统中确定的所述待配置业务系统配置所述期望生物识别算法，以便所述待配置业务系统向所述生物识别系统1发送生物识别请求时，所述生物识别系统1利用所述期望生物识别算法进行生物识别。
其中，至少一个业务系统例如为值机业务系统、登机业务系统和安检业务系统。
在一种可能的实现方式中，所述生物系统算法配置模块102，还用于在为所述待配置业务系统配置所述期望生物识别算法之后，为所述待配置业务系统配置所述期望生物识别算法的识别阈值。
在一种可能的实现方式中，所述生物系统算法配置模块102，还用于确定算法待切换业务系统；所述算法待切换业务系统当前配置有第一生物识别算法；从所述生物识别系统1封装的多个生物识别算法中选择第二生物识别算法；在所述生物识别系统1中，将所述算法待切换业务系统当前配置的所述第一生物识别算法切换为所述第二生物识别算法，以便所述算法待切换业务系统向所述生物识别系统1发送生物识别请求时，所述生物识别系统1利用所述第二生物识别算法进行生物识别。
参见图6，图6为本申请实施例提供的另一种生物识别系统的结构示意图。如图6所示，在一种可能的实现方式中，所述系统还包括：生物识别参照数据采集模块、数据处理模块和数据存储模块；
所述生物识别参照数据采集模块，用于获取目标业务系统采集的不同用户的生物识别参照数据和授权数据；所述目标业务系统为至少一个所述业务系统 中的任一个；
在实际应用中，目标业务系统通过各自内部的生物识别数据采集系统采集生物识别参照数据和授权数据。
所述数据处理模块，用于采用目标生物识别算法计算所述目标业务系统采集的各个用户的所述生物识别参照数据对应的标签特征值；所述目标生物识别算法为多个所述生物识别算法中的任一个；
所述数据存储模块，用于将所述生物识别参照数据、所述授权数据和目标业务系统信息进行存储，将所述标签特征值进行存储。
在一种可能的实现方式中，所述系统还包括：生物识别服务模块；所述生物识别服务模块包括：接收模块、确定模块和识别模块；
所述接收模块，用于接收对象业务系统发送的生物识别请求和待识别数据；所述待识别数据包括对象业务系统信息和待识别生物信息；
所述确定模块，用于根据所述对象业务系统信息确定所述生物识别系统1为所述对象业务系统配置的对象生物识别算法；
所述识别模块，用于采用所述对象生物识别算法对所述待识别生物信息进行处理，获取生物识别结果。
在一种可能的实现方式中，所述识别模块包括：第一计算子模块、第一确定子模块、第二确定子模块、第二计算子模块和比较子模块；
所述第一计算子模块，用于采用所述对象生物识别算法计算所述待识别生物信息的待对比特征值；
所述第一确定子模块，用于根据所述对象业务系统信息确定所述对象生物识别算法的识别阈值；
所述第二确定子模块，用于根据所述对象业务系统信息，确定在所述对象业务系统下采集的各个用户的生物识别参照数据对应的标签特征值为对象标签特征值；
所述第二计算子模块，用于计算所述待对比特征值和各个所述对象标签特征值的相似度，获取最高相似度；
所述比较子模块，用于将所述最高相似度和所述对象生物识别算法的识别阈值相比较，获取生物识别结果。
在一种可能的实现方式中，多个所述生物识别算法包括多个基础生物识别算法和生物识别融合算法；所述生物识别融合算法为多个所述基础生物识别算法或者由多个所述基础生物识别算法进行算法融合获得；
所述第一计算子模块，具体用于当所述对象生物识别算法为所述生物识别融合算法且所述生物识别融合算法为多个所述基础生物识别算法时，分别采用多个所述基础生物识别算法中的每个基础生物算法计算所述待识别生物信息的待对比特征值，获取多个待对比特征值；
所述第二计算子模块，具体用于当所述对象生物识别算法为所述生物识别融合算法且所述生物识别融合算法为多个所述基础生物识别算法时，将多个所述待对比特征值中的每个待对比特征值确定为目标待对比特征值；计算所述目标待对比特征值和各个所述对象标签特征值的相似度，获取所述目标待对比特征值下的多个相似度；从各个所述待对比特征值下的相似度中获取最高相似度。
在一种可能的实现方式中，所述生物识别服务模块还包括脱敏处理模块；
所述脱敏处理模块，用于当所述生物识别结果为识别通过时，确定所述待识别生物信息对应的用户信息；对所述待识别生物信息对应的用户信息进行脱敏处理，将脱敏处理后的用户信息返回至所述对象业务系统。
本申请实施例提供了生物识别系统，生物识别系统封装有多个生物识别算法，用于为业务系统提供生物识别服务。为业务系统配置生物识别算法时，先从至少一个业务系统中确定待配置业务系统。进而，从生物识别系统封装的多个生物识别算法中选择期望生物识别算法，在生物识别系统中为待配置业务系统配置期望生物识别算法，以便待配置业务系统向生物识别系统发送生物识别请求时，生物识别系统利用期望生物识别算法进行生物识别。如此，由于本申请实施例中的生物识别系统中已经封装有多个生物识别算法，使得基于生物识别系统，可直接从其封装的多个生物识别算法中选择和待配置业务系统对应的期望生物识别算法，在生物识别系统中确定待配置业务系统和期望生物识别算法的对应关系，即完成了配置过程，配置过程简单且灵活，实现了为同一业务系统或不同业务系统灵活配置对应的生物识别算法的目的。
【设备实施例】
本申请实施例还提供了一种应用程序漏洞检测设备，包括：处理器、存储器、系统总线；
所述处理器以及所述存储器通过所述系统总线相连；
所述存储器用于存储一个或多个程序，所述一个或多个程序包括指令，所述指令当被所述处理器执行时使所述处理器执行前述实施例所述的应用程序漏洞检测方法。
具体的，参考图7，其示出了适于用来实现本公开实施例的电子设备700的结构示意图。本公开实施例中的终端设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图7示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图7所示，电子设备700可以包括处理装置(例如中央处理器、图形处理器等)701，其可以根据存储在只读存储器(ROM)702中的程序或者从存储装置707加载到随机访问存储器(RAM)703中的程序而执行各种适当的动作和处理。在RAM 703中，还存储有电子设备700操作所需的各种程序和数据。处理装置701、ROM 702以及RAM 703通过总线704彼此相连。输入/输出(I/O)接口705也连接至总线704。
通常，以下装置可以连接至I/O接口705：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置704；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置707；包括例如磁带、硬盘等的存储装置704；以及通信装置709。通信装置709可以允许电子设备700与其他设备进行无线或有线通信以交换数据。虽然图7示出了具有各种装置的电子设备700，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
【存储介质实施例】
本申请实施例还提供了一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有指令，当所述指令在终端设备上运行时，使得所述终端设备执行前述实施例所述的应用程序漏洞检测方法。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：获取待检测应用程序的安卓应用程序包APK文件。对APK文件进行解包处理，获取APK文件的中间态代码文件、资源文件以及配置文件。解析配置文件，得到待检测应用程序包含的目标元素的属性值。对APK文件进行反编译，得到APK文件的源代码，提取源代码包含的关键词。将目标特征信息与漏洞特征信息进行匹配，目标特征信息为中间态代码文件、资源文件、待检测应用程序包含的目标元素的属性值以及源代码包含的关键词中的任意一项或多项。如果检测到与漏洞特征信息匹配的目标特征信息，将与漏洞特征信息匹配的目标特征信息确定为待检测应用程序存在的漏洞项。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置709从网络上被下载和安装，或者从存储装置706被安装，或者从ROM 702被安装。在该计算机程序被处理装置701执行时，执行本公开实施例的方法中限定的上述功能。
根据本公开的一个或多个实施例，【方法实施例】提供了一种生物识别算法配置方法，包括：
所述方法应用于生物识别系统，所述生物识别系统封装有多个生物识别算法，所述方法包括：
从至少一个业务系统中确定待配置业务系统；
从所述生物识别系统封装的多个生物识别算法中选择期望生物识别算法；所述生物识别系统用于为所述业务系统提供生物识别服务；
在所述生物识别系统中，为所述待配置业务系统配置所述期望生物识别算法，以便所述待配置业务系统向所述生物识别系统发送生物识别请求时，所述生物识别系统利用所述期望生物识别算法进行生物识别。
可选地，在所述在所述生物识别系统中，为所述待配置业务系统配置所述期望生物识别算法之后，所述方法还包括：
为所述待配置业务系统配置所述期望生物识别算法的识别阈值。
可选地，所述方法还包括：
确定算法待切换业务系统；所述算法待切换业务系统当前配置有第一生物识别算法；
从所述生物识别系统封装的多个生物识别算法中选择第二生物识别算法；
在所述生物识别系统中，将所述算法待切换业务系统当前配置的所述第一生物识别算法切换为所述第二生物识别算法，以便所述算法待切换业务系统向所述生物识别系统发送生物识别请求时，所述生物识别系统利用所述第二生物识别算法进行生物识别。
可选地，所述方法还包括：
获取目标业务系统采集的不同用户的生物识别参照数据和授权数据，将所述生物识别参照数据、所述授权数据和目标业务系统信息进行存储；所述目标业务系统为至少一个所述业务系统中的任一个；
采用目标生物识别算法计算所述目标业务系统采集的各个用户的所述生物识别参照数据对应的标签特征值，将所述标签特征值进行存储；所述目标生物识别算法为多个所述生物识别算法中的任一个。
可选地，所述方法还包括：
接收对象业务系统发送的生物识别请求和待识别数据；所述待识别数据包括对象业务系统信息和待识别生物信息；
根据所述对象业务系统信息确定所述生物识别系统为所述对象业务系统配置的对象生物识别算法；
采用所述对象生物识别算法对所述待识别生物信息进行处理，获取生物识别结果。
可选地，所述采用所述对象生物识别算法对所述待识别生物信息进行处理，获取生物识别结果，包括：
采用所述对象生物识别算法计算所述待识别生物信息的待对比特征值；
根据所述对象业务系统信息确定所述对象生物识别算法的识别阈值；
根据所述对象业务系统信息，确定在所述对象业务系统下采集的并用所述对象生物识别算法计算得到的各个用户的生物识别参照数据对应的标签特征值为对象标签特征值；
计算所述待对比特征值和各个所述对象标签特征值的相似度，获取最高相似度；
将所述最高相似度和所述对象生物识别算法的识别阈值相比较，获取生物识别结果。
可选地，多个所述生物识别算法包括多个基础生物识别算法和生物识别融合算法；所述生物识别融合算法为多个所述基础生物识别算法或者由多个所述基础生物识别算法进行算法融合获得；
当所述对象生物识别算法为所述生物识别融合算法且所述生物识别融合算法为多个所述基础生物识别算法时，所述采用所述对象生物识别算法计算所 述待识别生物信息的待对比特征值，包括：
分别采用多个所述基础生物识别算法中的每个基础生物算法计算所述待识别生物信息的待对比特征值，获取多个待对比特征值；
当所述对象生物识别算法为所述生物识别融合算法且所述生物识别融合算法为多个所述基础生物识别算法时，所述计算所述待对比特征值和各个所述对象标签特征值的相似度，获取最高相似度，包括：
将多个所述待对比特征值中的每个待对比特征值确定为目标待对比特征值；
计算所述目标待对比特征值和各个所述对象标签特征值的相似度，获取所述目标待对比特征值下的多个相似度；
从各个所述待对比特征值下的相似度中获取最高相似度。
可选地，所述方法还包括：
当所述生物识别结果为识别通过时，确定所述待识别生物信息对应的用户信息；
对所述待识别生物信息对应的用户信息进行脱敏处理，将脱敏处理后的用户信息返回至所述对象业务系统。
根据本公开的一个或多个实施例，【系统实施例】提供了方法实施例的系统，包括：
算法封装模块和生物系统算法配置模块；所述生物识别系统用于为业务系统提供生物识别服务；
所述算法封装模块，用于封装多个生物识别算法；
所述生物系统算法配置模块，用于从所述生物识别系统封装的多个生物识别算法中选择期望生物识别算法，为从至少一个业务系统中确定的所述待配置业务系统配置所述期望生物识别算法，以便所述待配置业务系统向所述生物识别系统发送生物识别请求时，所述生物识别系统利用所述期望生物识别算法进行生物识别。
可选地，所述生物系统算法配置模块，还用于在为所述待配置业务系统配置所述期望生物识别算法之后，为所述待配置业务系统配置所述期望生物识别算法的识别阈值。
可选地，所述生物系统算法配置模块，还用于确定算法待切换业务系统；所述算法待切换业务系统当前配置有第一生物识别算法；从所述生物识别系统封装的多个生物识别算法中选择第二生物识别算法；在所述生物识别系统中，将所述算法待切换业务系统当前配置的所述第一生物识别算法切换为所述第二生物识别算法，以便所述算法待切换业务系统向所述生物识别系统发送生物识别请求时，所述生物识别系统利用所述第二生物识别算法进行生物识别。
可选地，所述系统还包括：生物识别参照数据采集模块、数据处理模块和数据存储模块；
所述生物识别参照数据采集模块，用于获取目标业务系统采集的不同用户的生物识别参照数据和授权数据；所述目标业务系统为至少一个所述业务系统中的任一个；
所述数据处理模块，用于采用目标生物识别算法计算所述目标业务系统采集的各个用户的所述生物识别参照数据对应的标签特征值；所述目标生物识别算法为多个所述生物识别算法中的任一个；
所述数据存储模块，用于将所述生物识别参照数据、所述授权数据和目标业务系统信息进行存储，将所述标签特征值进行存储。
可选地，所述系统还包括：生物识别服务模块；所述生物识别服务模块包括：接收模块、确定模块和识别模块；
所述接收模块，用于接收对象业务系统发送的生物识别请求和待识别数据；所述待识别数据包括对象业务系统信息和待识别生物信息；
所述确定模块，用于根据所述对象业务系统信息确定所述生物识别系统为所述对象业务系统配置的对象生物识别算法；
所述识别模块，用于采用所述对象生物识别算法对所述待识别生物信息进行处理，获取生物识别结果。
可选地，所述识别模块包括：第一计算子模块、第一确定子模块、第二确定子模块、第二计算子模块和比较子模块；
所述第一计算子模块，用于采用所述对象生物识别算法计算所述待识别生物信息的待对比特征值；
所述第一确定子模块，用于根据所述对象业务系统信息确定所述对象生物 识别算法的识别阈值；
所述第二确定子模块，用于根据所述对象业务系统信息，确定在所述对象业务系统下采集的各个用户的生物识别参照数据对应的标签特征值为对象标签特征值；
所述第二计算子模块，用于计算所述待对比特征值和各个所述对象标签特征值的相似度，获取最高相似度；
所述比较子模块，用于将所述最高相似度和所述对象生物识别算法的识别阈值相比较，获取生物识别结果。
可选地，多个所述生物识别算法包括多个基础生物识别算法和生物识别融合算法；所述生物识别融合算法为多个所述基础生物识别算法或者由多个所述基础生物识别算法进行算法融合获得；
所述第一计算子模块，具体用于当所述对象生物识别算法为所述生物识别融合算法且所述生物识别融合算法为多个所述基础生物识别算法时，分别采用多个所述基础生物识别算法中的每个基础生物算法计算所述待识别生物信息的待对比特征值，获取多个待对比特征值；
所述第二计算子模块，具体用于当所述对象生物识别算法为所述生物识别融合算法且所述生物识别融合算法为多个所述基础生物识别算法时，将多个所述待对比特征值中的每个待对比特征值确定为目标待对比特征值；计算所述目标待对比特征值和各个所述对象标签特征值的相似度，获取所述目标待对比特征值下的多个相似度；从各个所述待对比特征值下的相似度中获取最高相似度。
可选地，所述生物识别服务模块还包括脱敏处理模块；
所述脱敏处理模块，用于当所述生物识别结果为识别通过时，确定所述待识别生物信息对应的用户信息；对所述待识别生物信息对应的用户信息进行脱敏处理，将脱敏处理后的用户信息返回至所述对象业务系统。
根据本公开的一个或多个实施例，【设备实施例】提供了方法实施例的设备，包括：处理器、存储器、系统总线；
所述处理器以及所述存储器通过所述系统总线相连；
所述存储器用于存储一个或多个程序，所述一个或多个程序包括指令，所 述指令当被所述处理器执行时使所述处理器执行所述的生物识别算法配置方法。
根据本公开的一个或多个实施例，【存储介质实施例】提供了方法实施例的计算机可读存储介质，所述计算机可读存储介质中存储有指令，当所述指令在终端设备上运行时，使得所述终端设备执行所述的生物识别算法配置方法。
需要注意，描述于本公开实施例中所涉及到的模块可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，模块的名称在某种情况下并不构成对该单元本身的限定。
需要注意，本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
需要说明的是，尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题，但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反，上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。
虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域 技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (18)

  1. 一种生物识别算法配置方法，其特征在于，所述方法应用于生物识别系统，所述生物识别系统封装有多个生物识别算法，所述方法包括：
    从至少一个业务系统中确定待配置业务系统；
    从所述生物识别系统封装的多个生物识别算法中选择期望生物识别算法；所述生物识别系统用于为所述业务系统提供生物识别服务；
    在所述生物识别系统中，为所述待配置业务系统配置所述期望生物识别算法，以便所述待配置业务系统向所述生物识别系统发送生物识别请求时，所述生物识别系统利用所述期望生物识别算法进行生物识别。
  2. 根据权利要求1所述的方法，其特征在于，在所述在所述生物识别系统中，为所述待配置业务系统配置所述期望生物识别算法之后，所述方法还包括：
    为所述待配置业务系统配置所述期望生物识别算法的识别阈值。
  3. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    确定算法待切换业务系统；所述算法待切换业务系统当前配置有第一生物识别算法；
    从所述生物识别系统封装的多个生物识别算法中选择第二生物识别算法；
    在所述生物识别系统中，将所述算法待切换业务系统当前配置的所述第一生物识别算法切换为所述第二生物识别算法，以便所述算法待切换业务系统向所述生物识别系统发送生物识别请求时，所述生物识别系统利用所述第二生物识别算法进行生物识别。
  4. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    获取目标业务系统采集的不同用户的生物识别参照数据和授权数据，将所述生物识别参照数据、所述授权数据和目标业务系统信息进行存储；所述目标业务系统为至少一个所述业务系统中的任一个；
    采用目标生物识别算法计算所述目标业务系统采集的各个用户的所述生物识别参照数据对应的标签特征值，将所述标签特征值进行存储；所述目标生物识别算法为多个所述生物识别算法中的任一个。
  5. 根据权利要求1-4任一项所述的方法，其特征在于，所述方法还包括：
    接收对象业务系统发送的生物识别请求和待识别数据；所述待识别数据包括对象业务系统信息和待识别生物信息；
    根据所述对象业务系统信息确定所述生物识别系统为所述对象业务系统配置的对象生物识别算法；
    采用所述对象生物识别算法对所述待识别生物信息进行处理，获取生物识别结果。
  6. 根据权利要求5所述的方法，其特征在于，所述采用所述对象生物识别算法对所述待识别生物信息进行处理，获取生物识别结果，包括：
    采用所述对象生物识别算法计算所述待识别生物信息的待对比特征值；
    根据所述对象业务系统信息确定所述对象生物识别算法的识别阈值；
    根据所述对象业务系统信息，确定在所述对象业务系统下采集的并用所述对象生物识别算法计算得到的各个用户的生物识别参照数据对应的标签特征值为对象标签特征值；
    计算所述待对比特征值和各个所述对象标签特征值的相似度，获取最高相似度；
    将所述最高相似度和所述对象生物识别算法的识别阈值相比较，获取生物识别结果。
  7. 根据权利要求6所述的方法，其特征在于，多个所述生物识别算法包括多个基础生物识别算法和生物识别融合算法；所述生物识别融合算法为多个所述基础生物识别算法或者由多个所述基础生物识别算法进行算法融合获得；
    当所述对象生物识别算法为所述生物识别融合算法且所述生物识别融合算法为多个所述基础生物识别算法时，所述采用所述对象生物识别算法计算所述待识别生物信息的待对比特征值，包括：
    分别采用多个所述基础生物识别算法中的每个基础生物算法计算所述待识别生物信息的待对比特征值，获取多个待对比特征值；
    当所述对象生物识别算法为所述生物识别融合算法且所述生物识别融合算法为多个所述基础生物识别算法时，所述计算所述待对比特征值和各个所述对象标签特征值的相似度，获取最高相似度，包括：
    将多个所述待对比特征值中的每个待对比特征值确定为目标待对比特征值；
    计算所述目标待对比特征值和各个所述对象标签特征值的相似度，获取所述目标待对比特征值下的多个相似度；
    从各个所述待对比特征值下的相似度中获取最高相似度。
  8. 根据权利要求5所述的方法，其特征在于，所述方法还包括：
    当所述生物识别结果为识别通过时，确定所述待识别生物信息对应的用户信息；
    对所述待识别生物信息对应的用户信息进行脱敏处理，将脱敏处理后的用户信息返回至所述对象业务系统。
  9. 一种生物识别系统，其特征在于，所述系统包括：算法封装模块和生物系统算法配置模块；所述生物识别系统用于为业务系统提供生物识别服务；
    所述算法封装模块，用于封装多个生物识别算法；
    所述生物系统算法配置模块，用于从所述生物识别系统封装的多个生物识别算法中选择期望生物识别算法，为从至少一个业务系统中确定的所述待配置业务系统配置所述期望生物识别算法，以便所述待配置业务系统向所述生物识别系统发送生物识别请求时，所述生物识别系统利用所述期望生物识别算法进行生物识别。
  10. 根据权利要求9所述的系统，其特征在于，所述生物系统算法配置模块，还用于在为所述待配置业务系统配置所述期望生物识别算法之后，为所述待配置业务系统配置所述期望生物识别算法的识别阈值。
  11. 根据权利要求9所述的系统，其特征在于，所述生物系统算法配置模块，还用于确定算法待切换业务系统；所述算法待切换业务系统当前配置有第一生物识别算法；从所述生物识别系统封装的多个生物识别算法中选择第二生物识别算法；在所述生物识别系统中，将所述算法待切换业 务系统当前配置的所述第一生物识别算法切换为所述第二生物识别算法，以便所述算法待切换业务系统向所述生物识别系统发送生物识别请求时，所述生物识别系统利用所述第二生物识别算法进行生物识别。
  12. 根据权利要求9所述的系统，其特征在于，所述系统还包括：生物识别参照数据采集模块、数据处理模块和数据存储模块；
    所述生物识别参照数据采集模块，用于获取目标业务系统采集的不同用户的生物识别参照数据和授权数据；所述目标业务系统为至少一个所述业务系统中的任一个；
    所述数据处理模块，用于采用目标生物识别算法计算所述目标业务系统采集的各个用户的所述生物识别参照数据对应的标签特征值；所述目标生物识别算法为多个所述生物识别算法中的任一个；
    所述数据存储模块，用于将所述生物识别参照数据、所述授权数据和目标业务系统信息进行存储，将所述标签特征值进行存储。
  13. 根据权利要求9-12任一项所述的系统，其特征在于，所述系统还包括：生物识别服务模块；所述生物识别服务模块包括：接收模块、确定模块和识别模块；
    所述接收模块，用于接收对象业务系统发送的生物识别请求和待识别数据；所述待识别数据包括对象业务系统信息和待识别生物信息；
    所述确定模块，用于根据所述对象业务系统信息确定所述生物识别系统为所述对象业务系统配置的对象生物识别算法；
    所述识别模块，用于采用所述对象生物识别算法对所述待识别生物信息进行处理，获取生物识别结果。
  14. 根据权利要求13所述的系统，其特征在于，所述识别模块包括：第一计算子模块、第一确定子模块、第二确定子模块、第二计算子模块和比较子模块；
    所述第一计算子模块，用于采用所述对象生物识别算法计算所述待识别生物信息的待对比特征值；
    所述第一确定子模块，用于根据所述对象业务系统信息确定所述对象生物识别算法的识别阈值；
    所述第二确定子模块，用于根据所述对象业务系统信息，确定在所述对象业务系统下采集的各个用户的生物识别参照数据对应的标签特征值为对象标签特征值；
    所述第二计算子模块，用于计算所述待对比特征值和各个所述对象标签特征值的相似度，获取最高相似度；
    所述比较子模块，用于将所述最高相似度和所述对象生物识别算法的识别阈值相比较，获取生物识别结果。
  15. 根据权利要求14所述的系统，其特征在于，多个所述生物识别算法包括多个基础生物识别算法和生物识别融合算法；所述生物识别融合算法为多个所述基础生物识别算法或者由多个所述基础生物识别算法进行算法融合获得；
    所述第一计算子模块，具体用于当所述对象生物识别算法为所述生物识别融合算法且所述生物识别融合算法为多个所述基础生物识别算法时，分别采用多个所述基础生物识别算法中的每个基础生物算法计算所述待识别生物信息的待对比特征值，获取多个待对比特征值；
    所述第二计算子模块，具体用于当所述对象生物识别算法为所述生物识别融合算法且所述生物识别融合算法为多个所述基础生物识别算法时，将多个所述待对比特征值中的每个待对比特征值确定为目标待对比特征值；计算所述目标待对比特征值和各个所述对象标签特征值的相似度，获取所述目标待对比特征值下的多个相似度；从各个所述待对比特征值下的相似度中获取最高相似度。
  16. 根据权利要求13所述的系统，其特征在于，所述生物识别服务模块还包括脱敏处理模块；
    所述脱敏处理模块，用于当所述生物识别结果为识别通过时，确定所述待识别生物信息对应的用户信息；对所述待识别生物信息对应的用户信息进行脱敏处理，将脱敏处理后的用户信息返回至所述对象业务系统。
  17. 一种生物识别算法配置设备，其特征在于，包括：处理器、存储器、系统总线；
    所述处理器以及所述存储器通过所述系统总线相连；
    所述存储器用于存储一个或多个程序，所述一个或多个程序包括指令，所述指令当被所述处理器执行时使所述处理器执行权利要求1-8任一项所述的一种生物识别算法配置方法。
  18. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有指令，当所述指令在终端设备上运行时，使得所述终端设备执行权利要求1-8任一项所述的一种生物识别算法配置方法。
PCT/CN2022/087030 2022-01-10 2022-04-15 生物识别算法配置方法及生物识别系统 WO2023130606A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210022407.9 2022-01-10
CN202210022407.9A CN114373112A (zh) 2022-01-10 2022-01-10 生物识别算法配置方法及生物识别系统

Publications (1)

Publication Number Publication Date
WO2023130606A1 true WO2023130606A1 (zh) 2023-07-13

Family

ID=81144173

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/087030 WO2023130606A1 (zh) 2022-01-10 2022-04-15 生物识别算法配置方法及生物识别系统

Country Status (2)

Country Link
CN (1) CN114373112A (zh)
WO (1) WO2023130606A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106055946A (zh) * 2016-05-18 2016-10-26 成都芯软科技发展有限公司 一种身份识别系统及方法
US10469487B1 (en) * 2016-05-31 2019-11-05 Wells Fargo Bank, N.A. Biometric electronic signature authenticated key exchange token
CN113378689A (zh) * 2021-06-07 2021-09-10 广发银行股份有限公司 一种生物识别系统及生物识别方法
CN113516167A (zh) * 2021-05-17 2021-10-19 中国工商银行股份有限公司 生物特征识别方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106055946A (zh) * 2016-05-18 2016-10-26 成都芯软科技发展有限公司 一种身份识别系统及方法
US10469487B1 (en) * 2016-05-31 2019-11-05 Wells Fargo Bank, N.A. Biometric electronic signature authenticated key exchange token
CN113516167A (zh) * 2021-05-17 2021-10-19 中国工商银行股份有限公司 生物特征识别方法及装置
CN113378689A (zh) * 2021-06-07 2021-09-10 广发银行股份有限公司 一种生物识别系统及生物识别方法

Also Published As

Publication number Publication date
CN114373112A (zh) 2022-04-19

Similar Documents

Publication Publication Date Title
US11019103B2 (en) Managing security agents in a distributed environment
CN111581291B (zh) 数据处理方法、装置、电子设备及可读介质
US11140261B1 (en) Systems and methods for authenticating a caller at a call center
JP2022532677A (ja) 身元検証及び管理システム
CN109416800B (zh) 一种移动终端的认证方法及移动终端
KR20160124833A (ko) 모바일 디바이스들을 위한 신뢰 브로커 인증 방법
CN112926059B (zh) 一种数据处理方法、装置、设备及存储介质
US20200412535A1 (en) Authentication information transmission method, apparatus, and storage medium
WO2023123754A1 (zh) 一种业务办理方法、装置、设备及介质
WO2023130606A1 (zh) 生物识别算法配置方法及生物识别系统
CN116110159B (zh) 基于cfca认证标准的用户认证方法、设备和介质
US20170289146A1 (en) Authentication method with enhanced security based on eye recognition and authentication system thereof
CN115987657B (zh) 云存储安全认证方法、装置、设备及存储介质
US20150220720A1 (en) Electronic device and method for controlling access to given area thereof
US20230224146A1 (en) Quorum-based authorization
US11418503B2 (en) Sensor-based authentication, notification, and assistance systems
CN111598544A (zh) 用于处理信息的方法和装置
CN117392596B (zh) 数据处理方法、电子设备和计算机可读介质
CN113641966B (zh) 一种应用集成方法、系统、设备及介质
US11869294B2 (en) Providing digital identifications generated for checkpoint validation based on biometric identification
WO2018133231A1 (zh) 智能处理应用事件的方法与装置
CN116132125B (zh) 云服务数据存储方法、装置、设备及存储介质
US20230245127A1 (en) Augmented user authentication
CN113468506B (zh) 设备激活的方法、装置、设备以及存储介质
US20230421608A1 (en) Using a requestor identity to enforce a security policy on a network connection that conforms to a shared-access communication protocol

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22918070

Country of ref document: EP

Kind code of ref document: A1