Biological characteristic comprehensive verification processing method

Abstract

The invention relates to the field of biological characteristic comprehensive verification processing, in particular to a biological characteristic comprehensive verification processing method, which comprises the following steps: performing type collection processing by using real-time biological characteristic acquisition data to obtain a biological characteristic acquisition data type; establishing multi-level data features of the biological feature acquisition data according to the type of the biological feature acquisition data; a biological characteristic comprehensive verification processing result is obtained according to multi-level data characteristics of the biological characteristic acquisition data, a bilateral verification target is set for time change and data change, finally, cross parallel verification processing of the verification target is carried out, stable and efficient output of the verification processing result is ensured, and step correction iteration exists in the scheme, so that the verification accuracy is improved. After the self-circulation process is deployed, manual error correction processing is reduced, and the implementation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of biometric integrated verification processing, and in particular to a biometric integrated verification processing method. Background Art

[0002] Biometrics refer to the physiological attributes inherent in an individual, and can be divided into two categories: congenital physical characteristics and acquired behavioral characteristics based on their formation process. Typical biometrics include but are not limited to fingerprints, faces, irises, vein distribution, voiceprints, behavioral patterns, and genetic genes. Biometric recognition technology is a technical means of identity authentication based on individual biometric information. This technology uses automated equipment to accurately measure the individual's biometrics and matches the collected feature data with the pre-stored feature templates in the database to achieve accurate identity recognition. Therefore, the means of collecting and verifying biometric data is crucial, but in traditional solutions, the post-collection preprocessing of different biometrics is performed independently, which will cause a burden on the operation of the integrated biometric recognition system, thereby affecting subsequent further identification. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a biometric comprehensive verification processing method, which combines the biometric data with the collection time, extracts key features for analysis and verification, and achieves accurate and stable output of the final result.

[0004] To achieve the above object, the present invention provides a biometric comprehensive verification processing method, which is characterized by comprising: S1. Using real-time biometric feature collection data to perform type classification processing to obtain biometric feature collection data type; S2. Establishing multi-level data features of biometric feature collection data according to the biometric feature collection data type; S3. Obtain a biometric comprehensive verification processing result according to the multi-level data features of the biometric collection data.

[0005] Preferably, the biometric feature collection data type obtained by performing type classification processing using real-time biometric feature collection data includes: S1-1, obtain real-time biometric collection data; S1-2, using the real-time biometric feature collection data to establish a collection time tag corresponding to the collection time; S1-3, determining whether the real-time biometric feature collection data is image data, if so, obtaining an image pixel matrix as a data feature according to the image data corresponding to the real-time biometric feature collection data, otherwise obtaining a digital signal sequence as a data feature according to the digital signal data corresponding to the real-time biometric feature collection data; S1-4. Use the collection time tag and data features as the biometric collection data type.

[0006] Furthermore, establishing multi-level data features of biometric collection data according to the biometric collection data type includes: S2-1, using the collection time label corresponding to the biometric collection data type to establish the time trend characteristics of the biometric collection data; S2-2, using the data features corresponding to the biometric feature collection data type to establish the target data features of the biometric feature collection data; S2-3. Utilize the time trend characteristics of the biometric collection data and the target data characteristics to obtain multi-level data characteristics of the biometric collection data.

[0007] Furthermore, establishing the time trend characteristics of the biometric collection data using the collection time tag corresponding to the biometric collection data type includes: S2-1-1, using the collection time label corresponding to the biometric collection data type as the time trend starting time t; S2-1-2, respectively obtain the time t+1 corresponding to the starting time t of the time trend as the first verification time and the time t+2 as the second verification time; S2-1-3, determine whether the data type corresponding to the book feature of the biometric feature collection data is image data, if so, execute S2-1-4, otherwise, directly execute S2-1-6; S2-1-4, determine whether the image data at the time trend starting moment t and the image data at the time of one verification are in a stable state of image data, if so, execute S2-1-5, otherwise, update the time interval between the time trend starting moment t and the time trend starting moment t, and return to S2-1-2; S2-1-5, determine whether the image data at the starting time t of the time trend and the image data at the second verification time are in a stable state of image data, if so, use the starting time t of the time trend, the first verification time and the second verification time as the second verification time, otherwise, update the time interval between the starting time t of the time trend and the starting time t of the time trend, and return to S2-1-2; S2-1-6, determine whether the digital signal data at the starting time t of the time trend and the digital signal data at the time of one verification are in a stable state of digital signal data, if so, execute S2-1-6, otherwise, update the time interval between the starting time t of the time trend and the starting time t of the time trend, and return to S2-1-2; S2-1-7, determine whether the digital signal data at the starting time t of the time trend and the digital signal data at the second verification time are in a stable state of digital signal data, if so, use the starting time t of the time trend, the first verification time and the second verification time as the second verification time, otherwise, update the time interval between the starting time t of the time trend and the starting time t of the time trend, and return to S2-1-2; The stable state of the image data is that the data content and data capacity at adjacent moments are consistent, and the stable state of the digital signal data is that the signal frequency at adjacent moments is consistent.

[0008] Furthermore, using the data features corresponding to the biometric feature collection data type to establish target data features of the biometric feature collection data includes: S2-2-1, determine whether the data feature corresponding to the data type of the biometric feature collection data is image data, if so, use the data feature corresponding to the data type of the biometric feature collection data to establish the overall feature vector of the image data, and execute S2-2-2, otherwise, establish a digital signal sequence cycle according to the data feature corresponding to the data type of the biometric feature collection data, and directly execute S2-2-3; S2-2-2, obtaining the main feature area of ​​the data feature corresponding to the biometric feature collection data type as the basic target data feature; S2-2-3, obtaining the average amplitude of the corresponding digital signal sequence according to the digital signal sequence period as the basic target data feature; S2-2-4, determine whether the data feature corresponding to the biometric feature collection data type is image data, if so, use the overall feature vector of the image data and the basic target data feature as the target data feature of the biometric feature collection data, otherwise, use the digital signal sequence period and the basic target data feature as the target data feature of the biometric feature collection data; Wherein, the main feature area is a biological feature area of ​​the image data.

[0009] Furthermore, the multi-level data features of the biometric collection data are obtained by using the time trend features of the biometric collection data and the target data features, including: S2-3-1. Use the temporal trend characteristics of the biometric collection data and the target data characteristics to establish the numerical trend characteristics of the biometric collection data; S2-3-2, using the time trend characteristics of the biometric collection data and the target data characteristics to establish the time series trend characteristics of the biometric collection data; S2-3-3. Use the numerical trend characteristics and temporal trend characteristics of the biometric collection data as multi-level data characteristics of the biometric collection data.

[0010] Furthermore, using the temporal trend feature of the biometric collection data and the target data feature to establish the numerical trend feature of the biometric collection data includes: S2-3-1-1, determine whether the biometric data is image data, if so, obtain the basic target data features of the corresponding target data features according to the time trend features to obtain the primary verification feature area and the secondary verification feature area, and execute S2-3-1-2, otherwise, obtain the basic target data features of the corresponding target data features according to the time trend features to obtain the primary verification average amplitude and the secondary verification average amplitude, and directly execute S2-3-1-5; S2-3-1-2, obtaining the change rate of the repeated area ratio between the first verification feature area and the second verification feature area as the verification feature area change rate; S2-3-1-3, respectively obtaining the average value of the change rate of the repeated area ratio between the first verification feature area and the basic target data feature and the change rate of the repeated area ratio between the second verification feature area and the basic target data feature as the relative change rate of the feature area; S2-3-1-4, determine whether the change rate of the verification feature area is less than the relative change rate of the feature area, if so, use the first verification feature area and the second verification feature area as the numerical trend feature of the biometric feature collection data, otherwise, return to S2-1-1; S2-3-1-5, obtaining the amplitude difference between the first verification average amplitude and the second verification average amplitude as the verification average amplitude change threshold; S2-3-1-6, respectively obtaining the average of the amplitude difference between the first verification average amplitude and the basic target data feature and the amplitude difference between the second verification average amplitude and the basic target data feature as the average amplitude relative change threshold; S2-3-1-7. Determine whether the verification average amplitude change threshold is less than the average amplitude relative change threshold. If so, use the first verification average amplitude and the second verification average amplitude as the numerical trend characteristics of the biometric collection data. Otherwise, return to S2-1-1.

[0011] Furthermore, using the time trend feature of the biometric collection data and the target data feature to establish the time series trend feature of the biometric collection data includes: S2-3-2-1, determine whether the time trend feature of the biometric collection data corresponds to the same time interval, if so, retain the current time trend feature as the temporal trend feature of the biometric collection data, otherwise, execute S2-3-2-2; S2-3-2-2. Determine whether the target data feature corresponding to the biometric collection data is consistent. If so, update the time interval using the target data feature corresponding time interval and return to S2-1-2. Otherwise, obtain the average value of the target data feature corresponding time interval of the biometric collection data, update the time interval and return to S2-1-2.

[0012] Furthermore, obtaining a biometric comprehensive verification processing result according to the multi-level data features of the biometric collection data includes: S3-1, respectively obtaining the multi-level data features of the biometric feature collection data and corresponding numerical trend features to establish a first cross-validation data feature and a second cross-validation data feature; S3-2, respectively obtaining the multi-level data features of the biometric feature collection data and corresponding time series trend features to establish a first cross-validation time feature and a second cross-validation time feature; S3-3, determining whether the first cross-validation data feature corresponds to the first cross-validation time feature, if so, executing S3-4, otherwise, the biometric feature comprehensive verification processing result is abnormal, and outputting the first cross-validation data feature and the first cross-validation time; S3-4. Determine whether the second cross-validation data feature corresponds to the second cross-validation moment feature. If so, use the first cross-validation moment feature and the second cross-validation moment to perform a review process to obtain a biometric comprehensive verification result. Otherwise, the biometric comprehensive verification result is abnormal, and output the second cross-validation data feature and the second cross-validation moment.

[0013] Further, the biometric comprehensive verification processing result obtained by performing a review process using the first cross-validation moment feature and the second cross-validation moment includes: S3-4-1, obtaining the difference between the basic target data feature corresponding to the first cross-validation moment feature and the basic target data feature corresponding to the multi-level data feature as a first verification difference; S3-4-2, obtaining the difference between the basic target data feature corresponding to the second cross-validation moment feature and the basic target data feature corresponding to the multi-level data feature as the second verification difference; S3-4-3, determine whether the relative change rate of the first recheck difference and the relative change rate of the second recheck difference meet the change rate threshold, if so, the biometric comprehensive verification processing result is normal, otherwise, the biometric comprehensive verification processing result is abnormal; Among them, the relative change rate is the ratio of the verified difference to the basic target data feature, and the change rate threshold is 5%.

[0014] Compared with the closest prior art, the present invention has the following beneficial effects: Biometric features can be quickly distinguished according to the collection method, and approximate feature extraction under the same scheme steps is guaranteed as much as possible for different types of feature data, reducing the complexity of scheme operation and alleviating the system operation burden in actual application deployment. At the same time, combined with time characteristics such as data collection time, bilateral verification targets are set for time changes and data changes, and finally cross-parallel verification processing is performed on the verification targets to ensure stable and efficient output of verification processing results. There are step correction iterations within the scheme, and its self-circulating process reduces manual error correction after deployment, thereby improving implementation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a biometric comprehensive verification processing method provided by the present invention. DETAILED DESCRIPTION

[0016] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Embodiment 1:

[0019] The present invention provides a biometric comprehensive verification processing method, such as Figure 1 As shown, including: S1. Using real-time biometric feature collection data to perform type classification processing to obtain biometric feature collection data type; S2. Establishing multi-level data features of biometric feature collection data according to the biometric feature collection data type; S3. Obtain a biometric comprehensive verification processing result according to the multi-level data features of the biometric collection data.

[0020] S1 specifically includes: S1-1, obtain real-time biometric collection data; S1-2, using the real-time biometric feature collection data to establish a collection time tag corresponding to the collection time; S1-3, determining whether the real-time biometric feature collection data is image data, if so, obtaining an image pixel matrix as a data feature according to the image data corresponding to the real-time biometric feature collection data, otherwise obtaining a digital signal sequence as a data feature according to the digital signal data corresponding to the real-time biometric feature collection data; S1-4. Use the collection time tag and data features as the biometric collection data type.

[0021] S2 specifically includes: S2-1, using the collection time label corresponding to the biometric collection data type to establish the time trend characteristics of the biometric collection data; S2-2, using the data features corresponding to the biometric feature collection data type to establish the target data features of the biometric feature collection data; S2-3. Utilize the time trend characteristics of the biometric collection data and the target data characteristics to obtain multi-level data characteristics of the biometric collection data.

[0022] S2-1 specifically includes: S2-1-1, using the collection time label corresponding to the biometric collection data type as the time trend starting time t; S2-1-2, respectively obtain the time t+1 corresponding to the starting time t of the time trend as the first verification time and the time t+2 as the second verification time; S2-1-3, determine whether the data type corresponding to the book feature of the biometric feature collection data is image data, if so, execute S2-1-4, otherwise, directly execute S2-1-6; S2-1-4, determine whether the image data at the time trend starting moment t and the image data at the time of one verification are in a stable state of image data, if so, execute S2-1-5, otherwise, update the time interval between the time trend starting moment t and the time trend starting moment t, and return to S2-1-2; S2-1-5, determine whether the image data at the starting time t of the time trend and the image data at the second verification time are in a stable state of image data, if so, use the starting time t of the time trend, the first verification time and the second verification time as the second verification time, otherwise, update the time interval between the starting time t of the time trend and the starting time t of the time trend, and return to S2-1-2; S2-1-6, determine whether the digital signal data at the starting time t of the time trend and the digital signal data at the time of one verification are in a stable state of digital signal data, if so, execute S2-1-6, otherwise, update the time interval between the starting time t of the time trend and the starting time t of the time trend, and return to S2-1-2; S2-1-7, determine whether the digital signal data at the starting time t of the time trend and the digital signal data at the second verification time are in a stable state of digital signal data, if so, use the starting time t of the time trend, the first verification time and the second verification time as the second verification time, otherwise, update the time interval between the starting time t of the time trend and the starting time t of the time trend, and return to S2-1-2; The stable state of the image data is that the data content and data capacity at adjacent moments are consistent, and the stable state of the digital signal data is that the signal frequency at adjacent moments is consistent.

[0023] S2-2 specifically includes: S2-2-1, determine whether the data feature corresponding to the data type of the biometric feature collection data is image data, if so, use the data feature corresponding to the data type of the biometric feature collection data to establish the overall feature vector of the image data, and execute S2-2-2, otherwise, establish a digital signal sequence cycle according to the data feature corresponding to the data type of the biometric feature collection data, and directly execute S2-2-3; S2-2-2, obtaining the main feature area of ​​the data feature corresponding to the biometric feature collection data type as the basic target data feature; S2-2-3, obtaining the average amplitude of the corresponding digital signal sequence according to the digital signal sequence period as the basic target data feature; S2-2-4, determine whether the data feature corresponding to the biometric feature collection data type is image data, if so, use the overall feature vector of the image data and the basic target data feature as the target data feature of the biometric feature collection data, otherwise, use the digital signal sequence period and the basic target data feature as the target data feature of the biometric feature collection data; Wherein, the main feature area is a biological feature area of ​​the image data.

[0024] S2-3 specifically includes: S2-3-1. Use the temporal trend characteristics of the biometric collection data and the target data characteristics to establish the numerical trend characteristics of the biometric collection data; S2-3-2, using the time trend characteristics of the biometric collection data and the target data characteristics to establish the time series trend characteristics of the biometric collection data; S2-3-3. Use the numerical trend characteristics and temporal trend characteristics of the biometric collection data as multi-level data characteristics of the biometric collection data.

[0025] S2-3-1 specifically includes: S2-3-1-1, determine whether the biometric data is image data, if so, obtain the basic target data features of the corresponding target data features according to the time trend features to obtain the primary verification feature area and the secondary verification feature area, and execute S2-3-1-2, otherwise, obtain the basic target data features of the corresponding target data features according to the time trend features to obtain the primary verification average amplitude and the secondary verification average amplitude, and directly execute S2-3-1-5; S2-3-1-2, obtaining the change rate of the repeated area ratio between the first verification feature area and the second verification feature area as the verification feature area change rate; S2-3-1-3, respectively obtaining the average value of the change rate of the repeated area ratio between the first verification feature area and the basic target data feature and the change rate of the repeated area ratio between the second verification feature area and the basic target data feature as the relative change rate of the feature area; S2-3-1-4, determine whether the change rate of the verification feature area is less than the relative change rate of the feature area, if so, use the first verification feature area and the second verification feature area as the numerical trend feature of the biometric feature collection data, otherwise, return to S2-1-1; S2-3-1-5, obtaining the amplitude difference between the first verification average amplitude and the second verification average amplitude as the verification average amplitude change threshold; S2-3-1-6, respectively obtaining the average of the amplitude difference between the first verification average amplitude and the basic target data feature and the amplitude difference between the second verification average amplitude and the basic target data feature as the average amplitude relative change threshold; S2-3-1-7. Determine whether the verification average amplitude change threshold is less than the average amplitude relative change threshold. If so, use the first verification average amplitude and the second verification average amplitude as the numerical trend characteristics of the biometric collection data. Otherwise, return to S2-1-1.

[0026] S2-3-2 specifically includes: S2-3-2-1, determine whether the time trend feature of the biometric collection data corresponds to the same time interval, if so, retain the current time trend feature as the temporal trend feature of the biometric collection data, otherwise, execute S2-3-2-2; S2-3-2-2. Determine whether the target data feature corresponding to the biometric collection data is consistent. If so, update the time interval using the target data feature corresponding time interval and return to S2-1-2. Otherwise, obtain the average value of the target data feature corresponding time interval of the biometric collection data, update the time interval and return to S2-1-2.

[0027] S3 specifically includes: S3-1, respectively obtaining the multi-level data features of the biometric feature collection data and corresponding numerical trend features to establish a first cross-validation data feature and a second cross-validation data feature; S3-2, respectively obtaining the multi-level data features of the biometric feature collection data and corresponding time series trend features to establish a first cross-validation time feature and a second cross-validation time feature; S3-3, determining whether the first cross-validation data feature corresponds to the first cross-validation time feature, if so, executing S3-4, otherwise, the biometric feature comprehensive verification processing result is abnormal, and outputting the first cross-validation data feature and the first cross-validation time; S3-4. Determine whether the second cross-validation data feature corresponds to the second cross-validation moment feature. If so, use the first cross-validation moment feature and the second cross-validation moment to perform a review process to obtain a biometric comprehensive verification result. Otherwise, the biometric comprehensive verification result is abnormal, and output the second cross-validation data feature and the second cross-validation moment.

[0028] S3-4 specifically includes: S3-4-1, obtaining the difference between the basic target data feature corresponding to the first cross-validation moment feature and the basic target data feature corresponding to the multi-level data feature as a first verification difference; S3-4-2, obtaining the difference between the basic target data feature corresponding to the second cross-validation moment feature and the basic target data feature corresponding to the multi-level data feature as the second verification difference; S3-4-3, determine whether the relative change rate of the first recheck difference and the relative change rate of the second recheck difference meet the change rate threshold, if so, the biometric comprehensive verification processing result is normal, otherwise, the biometric comprehensive verification processing result is abnormal; Among them, the relative change rate is the ratio of the verified difference to the basic target data feature, and the change rate threshold is 5%.

[0029] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0030] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0031] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0032] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0033] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A biometric comprehensive verification processing method, characterized in that: include: S1. Using real-time biometric feature collection data to perform type classification processing to obtain biometric feature collection data type; S2. Establishing multi-level data features of biometric feature collection data according to the biometric feature collection data type; S3. Obtain a biometric comprehensive verification processing result according to the multi-level data features of the biometric collection data.

2. A biometric comprehensive verification processing method as claimed in claim 1, characterized in that: The biometric feature collection data type obtained by performing type classification processing using real-time biometric feature collection data includes: S1-1, obtain real-time biometric collection data; S1-2, using the real-time biometric feature collection data to establish a collection time tag corresponding to the collection time; S1-3, determining whether the real-time biometric feature collection data is image data, if so, obtaining an image pixel matrix as a data feature according to the image data corresponding to the real-time biometric feature collection data, otherwise obtaining a digital signal sequence as a data feature according to the digital signal data corresponding to the real-time biometric feature collection data; S1-4. Use the collection time tag and data features as the biometric collection data type.

3. A biometric comprehensive verification processing method as claimed in claim 2, characterized in that: Establishing multi-level data features of biometric collection data according to the biometric collection data type includes: S2-1, using the collection time label corresponding to the biometric collection data type to establish the time trend characteristics of the biometric collection data; S2-2, using the data features corresponding to the biometric feature collection data type to establish the target data features of the biometric feature collection data; S2-3. Utilize the time trend characteristics of the biometric collection data and the target data characteristics to obtain multi-level data characteristics of the biometric collection data.

4. A biometric comprehensive verification processing method as claimed in claim 3, characterized in that: Using the biometric feature collection data type corresponding to the collection time tag to establish the time trend characteristics of the biometric feature collection data includes: S2-1-1, using the collection time label corresponding to the biometric collection data type as the time trend starting time t; S2-1-2, respectively obtain the time t+1 corresponding to the starting time t of the time trend as the first verification time and the time t+2 as the second verification time; S2-1-3, determine whether the data type corresponding to the book feature of the biometric feature collection data is image data, if so, execute S2-1-4, otherwise, directly execute S2-1-6; S2-1-4, determine whether the image data at the time trend starting moment t and the image data at the time of one verification are in a stable state of image data, if so, execute S2-1-5, otherwise, update the time interval between the time trend starting moment t and the time trend starting moment t, and return to S2-1-2; S2-1-5, determine whether the image data at the starting time t of the time trend and the image data at the second verification time are in a stable state of image data, if so, use the starting time t of the time trend, the first verification time and the second verification time as the second verification time, otherwise, update the time interval between the starting time t of the time trend and the starting time t of the time trend, and return to S2-1-2; S2-1-6, determine whether the digital signal data at the starting time t of the time trend and the digital signal data at the time of one verification are in a stable state of digital signal data, if so, execute S2-1-6, otherwise, update the time interval between the starting time t of the time trend and the starting time t of the time trend, and return to S2-1-2; S2-1-7, determine whether the digital signal data at the starting time t of the time trend and the digital signal data at the second verification time are in a stable state of digital signal data, if so, use the starting time t of the time trend, the first verification time and the second verification time as the second verification time, otherwise, update the time interval between the starting time t of the time trend and the starting time t of the time trend, and return to S2-1-2; The stable state of the image data is that the data content and data capacity at adjacent moments are consistent, and the stable state of the digital signal data is that the signal frequency at adjacent moments is consistent.

5. A biometric comprehensive verification processing method as claimed in claim 4, characterized in that: The target data features of the biometric collection data are established by using the data features corresponding to the biometric collection data types, including: S2-2-1, determine whether the data feature corresponding to the data type of the biometric feature collection data is image data, if so, use the data feature corresponding to the data type of the biometric feature collection data to establish the overall feature vector of the image data, and execute S2-2-2, otherwise, establish a digital signal sequence cycle according to the data feature corresponding to the data type of the biometric feature collection data, and directly execute S2-2-3; S2-2-2, obtaining the main feature area of ​​the data feature corresponding to the biometric feature collection data type as the basic target data feature; S2-2-3, obtaining the average amplitude of the corresponding digital signal sequence according to the digital signal sequence period as the basic target data feature; S2-2-4, determine whether the data feature corresponding to the biometric feature collection data type is image data, if so, use the overall feature vector of the image data and the basic target data feature as the target data feature of the biometric feature collection data, otherwise, use the digital signal sequence period and the basic target data feature as the target data feature of the biometric feature collection data; Wherein, the main feature area is a biological feature area of ​​the image data.

6. A biometric comprehensive verification processing method as claimed in claim 5, characterized in that: The multi-level data features of the biometric collection data obtained by using the time trend features of the biometric collection data and the target data features include: S2-3-1. Use the temporal trend characteristics of the biometric collection data and the target data characteristics to establish the numerical trend characteristics of the biometric collection data; S2-3-2, using the time trend characteristics of the biometric collection data and the target data characteristics to establish the time series trend characteristics of the biometric collection data; S2-3-3. Use the numerical trend characteristics and temporal trend characteristics of the biometric collection data as multi-level data characteristics of the biometric collection data.

7. A biometric comprehensive verification processing method as claimed in claim 6, characterized in that: Using the temporal trend characteristics of the biometric collection data and the target data characteristics to establish the numerical trend characteristics of the biometric collection data includes: S2-3-1-1, determine whether the biometric data is image data, if so, obtain the basic target data features of the corresponding target data features according to the time trend features to obtain the primary verification feature area and the secondary verification feature area, and execute S2-3-1-2, otherwise, obtain the basic target data features of the corresponding target data features according to the time trend features to obtain the primary verification average amplitude and the secondary verification average amplitude, and directly execute S2-3-1-5; S2-3-1-2, obtaining the change rate of the repeated area ratio between the first verification feature area and the second verification feature area as the verification feature area change rate; S2-3-1-3, respectively obtaining the average value of the change rate of the repeated area ratio between the first verification feature area and the basic target data feature and the change rate of the repeated area ratio between the second verification feature area and the basic target data feature as the relative change rate of the feature area; S2-3-1-4, determine whether the change rate of the verification feature area is less than the relative change rate of the feature area, if so, use the first verification feature area and the second verification feature area as the numerical trend feature of the biometric feature collection data, otherwise, return to S2-1-1; S2-3-1-5, obtaining the amplitude difference between the first verification average amplitude and the second verification average amplitude as the verification average amplitude change threshold; S2-3-1-6, respectively obtaining the average of the amplitude difference between the first verification average amplitude and the basic target data feature and the amplitude difference between the second verification average amplitude and the basic target data feature as the average amplitude relative change threshold; S2-3-1-7. Determine whether the verification average amplitude change threshold is less than the average amplitude relative change threshold. If so, use the first verification average amplitude and the second verification average amplitude as the numerical trend characteristics of the biometric collection data. Otherwise, return to S2-1-1.

8. A biometric comprehensive verification processing method as claimed in claim 6, characterized in that: Using the time trend feature of the biometric collection data and the target data feature to establish the time series trend feature of the biometric collection data includes: S2-3-2-1, determine whether the time trend feature of the biometric collection data corresponds to the same time interval, if so, retain the current time trend feature as the temporal trend feature of the biometric collection data, otherwise, execute S2-3-2-2; S2-3-2-2. Determine whether the target data feature corresponding to the biometric collection data is consistent. If so, update the time interval using the target data feature corresponding time interval and return to S2-1-2. Otherwise, obtain the average value of the target data feature corresponding time interval of the biometric collection data, update the time interval and return to S2-1-2.

9. A biometric comprehensive verification processing method as claimed in claim 3, characterized in that: The biometric comprehensive verification processing result obtained according to the multi-level data features of the biometric collection data includes: S3-1, respectively obtaining the multi-level data features of the biometric feature collection data and corresponding numerical trend features to establish a first cross-validation data feature and a second cross-validation data feature; S3-2, respectively obtaining the multi-level data features of the biometric feature collection data and corresponding time series trend features to establish a first cross-validation time feature and a second cross-validation time feature; S3-3, determining whether the first cross-validation data feature corresponds to the first cross-validation time feature, if so, executing S3-4, otherwise, the biometric feature comprehensive verification processing result is abnormal, and outputting the first cross-validation data feature and the first cross-validation time; S3-4. Determine whether the second cross-validation data feature corresponds to the second cross-validation moment feature. If so, use the first cross-validation moment feature and the second cross-validation moment to perform a review process to obtain a biometric comprehensive verification result. Otherwise, the biometric comprehensive verification result is abnormal, and output the second cross-validation data feature and the second cross-validation moment.

10. A biometric comprehensive verification processing method as claimed in claim 9, characterized in that: The biometric comprehensive verification processing result obtained by performing a review process using the first cross-validation moment feature and the second cross-validation moment includes: S3-4-1, obtaining the difference between the basic target data feature corresponding to the first cross-validation moment feature and the basic target data feature corresponding to the multi-level data feature as a first verification difference; S3-4-2, obtaining the difference between the basic target data feature corresponding to the second cross-validation moment feature and the basic target data feature corresponding to the multi-level data feature as the second verification difference; S3-4-3, determine whether the relative change rate of the first recheck difference and the relative change rate of the second recheck difference meet the change rate threshold, if so, the biometric comprehensive verification processing result is normal, otherwise, the biometric comprehensive verification processing result is abnormal; Among them, the relative change rate is the ratio of the verified difference to the basic target data feature, and the change rate threshold is 5%.

Images