Dynamic password verification system and method based on biological characteristics of big data platform
The dynamic password verification system on a big data platform uses biometric analysis to generate secure authentication keys, addressing security and reliability issues in traditional methods by accurately verifying user identities and enhancing privacy protection.
Patent Information
- Application Number
- CN202411226481.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-12-13
AI Technical Summary
Traditional password-based and physical credential-based authentication methods are ineffective in providing high security and efficiency, and existing biometric recognition technologies fail to accurately identify users' voiceprint and lack robustness in verifying user identities, leading to security breaches and reduced reliability.
A dynamic password verification system using biometrics on a big data platform, comprising a user verification environment information acquisition module, a big data platform analysis module, a biometric information acquisition module, and a dynamic key generation module, which analyzes user verification environment information and voiceprint features to generate secure authentication keys.
Enhances identity authentication accuracy and efficiency while ensuring user privacy, preventing forgery attacks, and improving system anti-deception capabilities.
Smart Images
Figure CN119128846A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of identity authentication, and in particular to a dynamic password authentication system and method based on biometrics of a big data platform. Background Art
[0002] Traditional identity authentication methods, such as passwords and certificates, are easy to lose and forge, and are difficult to meet high security requirements. As the most common means of identity authentication, the security of passwords mainly depends on the complexity of passwords and the user's memory ability. However, users often choose simple passwords for easy memory, or use the same password on different platforms, which greatly increases the risk of password leakage. In addition, physical credentials such as certificates are also easy to be forged or misused, which greatly reduces the reliability of identity authentication.
[0003] Dynamic biometric recognition technology introduces the time dimension based on traditional static biometric recognition, analyzes the change pattern of biometrics over time, and thus improves the accuracy and security of recognition. This technology collects users' biometric data in real time through sensors, and uses algorithms to extract and match features, which can verify the authenticity of the user's identity in real time when the user authenticates the identity. Compared with static biometric recognition, dynamic biometric recognition technology can effectively prevent forgery attacks such as photos and videos, and improve the system's anti-deception capabilities.
[0004] In the prior art, in the dynamic password verification system based on biometrics, the verification security and efficiency are often low due to the inability to accurately identify the user's voiceprint audio and limited data analysis capabilities.
[0005] Therefore, there is an urgent need for a dynamic password verification system and method based on biometrics of a big data platform to solve the above problems. Summary of the invention
[0006] The purpose of the present invention is to provide a dynamic password verification system and method based on biometrics of a big data platform: to solve the security and reliability problems existing in traditional identity authentication methods, this method not only improves the accuracy and efficiency of identity authentication, but also provides a strong guarantee for user privacy protection.
[0007] The purpose of the present invention can be achieved through the following technical solutions: On the one hand, a dynamic password verification system based on biometrics of a big data platform, the system includes a user verification environment information acquisition module, a big data platform analysis module, a biometric information acquisition module, and a dynamic key generation module; The user verification environment information acquisition module is used to obtain user verification environment information, wherein the user verification environment information includes the user's IP address information, the user's node code information, the user's geographic location information, the user's verification behavior information, the verification frequency information and the verification time information, and sends the user verification environment information to the big data platform analysis module; The big data platform analysis module is used to receive user verification environment information, and generate a user verification environment safety index based on the user verification environment information, and determine whether the conditions for generating a user biometric information acquisition signal are met based on the user verification environment safety index. If so, generate a user biometric information acquisition signal and send it to the biometric information acquisition module; The biometric information acquisition module is used to receive a user biometric information acquisition signal, and acquire the user voiceprint information based on the user biometric information acquisition signal, wherein the voiceprint information includes the user voiceprint audio, and send the user voiceprint information to the dynamic key generation module; The dynamic key generation module is used to receive user voiceprint information, extract voiceprint feature vectors based on the user voiceprint information, determine the stable feature positions of the voiceprint feature vectors, generate a key corresponding to the user voiceprint information based on the stable feature positions, and complete verification based on the key.
[0008] Furthermore, generating a user verification environment security index based on the user verification environment information specifically includes the following process: Determine whether the user's IP address information, the user's node code information, and the user's geographic location information are abnormal. If not, the user verification environment safety factor R is 1; if so, the user verification environment safety factor R is 0; Based on the user verification behavior information, the number of times S that the user clicks the verification operation screen during the verification request process is obtained. The verification operation screen includes the mobile user client screen, and the maximum number of times the user clicks the verification operation screen during the verification request process is obtained in the storage module of the big data platform analysis module. , calculate S The proportion ; Get user verification frequency based on verification frequency information , where the verification frequency The number of user verifications within a preset time; Get the time when the user sends the verification request based on the verification time information and the moment when the user completes the slider verification operation , and calculate the time To time The slider verification operation is an operation in which the user needs to touch and hold the slider on the verification operation screen with a finger and slide it to the correct position or complete the puzzle as required; Verify the user's environmental safety factor R, ratio , User verification frequency Substitute the time period T into the user verification environment safety index calculation formula to calculate the user verification environment safety index YZH, which is as follows: .
[0009] Furthermore, determining whether the user's IP address information, the user's node code information, and the user's geographic location information are abnormal specifically includes the following process: Compare the user's IP address information with the user's historical IP address information to determine whether the two are consistent. If so, the user's IP address information is normal, otherwise, the user's IP address information is abnormal; compare the user's node coding information with the registered node coding information to determine whether the user's node coding information is included in the registered node coding information. If so, the user's node coding information is normal, otherwise, it is abnormal; compare the user's geographic location information with the user's registered geographic location information to determine whether the two are consistent. If so, the user's geographic location information is normal, otherwise, it is abnormal; when the user's IP address information, the user's node coding information and the user's geographic location information are all normal, the user verification environment safety factor R is 1, and when at least one of the user's IP address information, the user's node coding information and the user's geographic location information is abnormal, the user verification environment safety factor R is 0.
[0010] Further, judging whether the condition for generating a user biometric information acquisition signal is met based on the user verification environment security index includes the following process: The storage module loads the user verification environment security index threshold based on the big data platform analysis module , where the user verification environment security index threshold Pre-set by the system and stored in the storage module; Determine whether the user verification environment safety index exceeds the user verification environment safety index threshold If so, the condition for generating a user biometric information acquisition signal is met; if not, the condition for generating a user biometric information acquisition signal is not met.
[0011] Furthermore, extracting a voiceprint feature vector based on the user's voiceprint information includes the following process: The voiceprint FBank features are extracted from the user's voiceprint audio through pre-emphasis, framing, windowing, short-time Fourier transform, and Mel filtering. The ResNet model is selected to train the voiceprint FBank features. The training sample set is the voiceprint FBank features. After the training with the training set is completed, the fully connected layer is removed and the voiceprint feature map is output. The feature vector that conforms to the normal distribution is selected from the voiceprint feature map and the features output by the fully connected layer, and the feature vector that conforms to the normal distribution is recorded as the voiceprint feature vector.
[0012] Furthermore, determining the stable feature position of the voiceprint feature vector specifically includes the following process: Prepare a sequence P marking the feature positions of the voiceprint; Initialize each value in P to 1; set up , ; For the The position where P[j]=1 in the voiceprint feature vector, If V[i][j] = V[i+1][j], then P[j]=1, otherwise, P[j]=0; Until all positions in all voiceprint vectors are traversed, the position where P[j]=1 is the selected stable feature position, P[j] represents the j-th position value in the voiceprint feature position vector, and V[i][j] represents the value of the j-th position in the i-th voiceprint vector.
[0013] Furthermore, generating a key corresponding to the user's voiceprint information based on the stable feature position specifically includes the following process: Extract b subsequences based on stable feature positions, where a subsequence is a continuous digital sequence; For a single subsequence Encode, where , and record the corresponding calibration part code for each subsequence ; Construct a polynomial such that the key output is bounded to the polynomial constant term ,item For the key: ; in, ,... , is the random coefficient, , Representative Model The remaining domain of Represents modulus. Its value is a prime number. , and Used in the key extraction phase.
[0014] Furthermore, in the key extraction phase, the user's voiceprint corresponding , and Is it consistent with the preset one? If so, the user identity is correct; if not, the user identity is illegal.
[0015] On the other hand, a dynamic password verification method based on biometrics of a big data platform includes: Obtain user verification environment information, wherein the user verification environment information includes the user's IP address information, the user's node code information, the user's geographic location information, the user's verification behavior information, the verification frequency information, and the verification time information, and send the user verification environment information to the big data platform analysis module; Generate a user verification environment security index based on the user verification environment information, and determine whether a condition for generating a user biometric information acquisition signal is met based on the user verification environment security index, and if so, generate a user biometric information acquisition signal; Acquiring user voiceprint information based on a user biometric information acquisition signal, wherein the voiceprint information includes user voiceprint audio; A voiceprint feature vector is extracted based on the user's voiceprint information, and a stable feature position of the voiceprint feature vector is determined. A key corresponding to the user's voiceprint information is generated based on the stable feature position, and verification is completed based on the key.
[0016] Compared with the existing solutions, the present invention achieves the following beneficial effects: The present invention solves the security and reliability problems of traditional identity authentication methods by introducing dynamic biometric recognition technology and the data processing capabilities of a big data platform. This method not only improves the accuracy and efficiency of identity authentication, but also provides a strong guarantee for user privacy protection. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0018] Figure 1 It is a system block diagram of a dynamic password verification system based on biometrics of a big data platform according to an embodiment of the present invention; Figure 2 This is a workflow diagram of a dynamic password verification system based on biometric features of a big data platform according to an embodiment of the present invention; Figure 3This is a workflow diagram of a dynamic password verification method based on biometrics of a big data platform according to an embodiment of the present invention. DETAILED DESCRIPTION
[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.
[0020] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, well-known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.
[0021] This embodiment provides a dynamic password verification system based on biometrics of a big data platform. Figure 1 is a system block diagram of a dynamic password verification system based on biometric features of a big data platform according to an embodiment of the present invention. Figure 1 As shown, the system includes a user verification environment information acquisition module, a big data platform analysis module, a biometric information acquisition module, and a dynamic key generation module; The user verification environment information acquisition module is used to obtain user verification environment information, wherein the user verification environment information includes the user's IP address information, the user's node code information, the user's geographic location information, the user's verification behavior information, the verification frequency information and the verification time information, and sends the user verification environment information to the big data platform analysis module; The big data platform analysis module is used to receive user verification environment information, and generate a user verification environment safety index based on the user verification environment information, and determine whether the conditions for generating a user biometric information acquisition signal are met based on the user verification environment safety index. If so, generate a user biometric information acquisition signal and send it to the biometric information acquisition module; The biometric information acquisition module is used to receive a user biometric information acquisition signal, and acquire the user voiceprint information based on the user biometric information acquisition signal, wherein the voiceprint information includes the user voiceprint audio, and send the user voiceprint information to the dynamic key generation module; The dynamic key generation module is used to receive user voiceprint information, extract voiceprint feature vectors based on the user voiceprint information, determine the stable feature positions of the voiceprint feature vectors, generate a key corresponding to the user voiceprint information based on the stable feature positions, and complete verification based on the key.
[0022] In summary, the present invention obtains user verification environment information, wherein the user verification environment information includes the user's IP address information, the user's node coding information, the user's geographic location information, the user's verification behavior information, the verification frequency information and the verification time information; generates a user verification environment security index based on the user verification environment information, determines whether the conditions for generating a user biometric information acquisition signal are met based on the user verification environment security index, and if so, generates a user biometric information acquisition signal; obtains user voiceprint information based on the user biometric information acquisition signal, wherein the voiceprint information includes the user voiceprint audio; extracts a voiceprint feature vector based on the user voiceprint information, and determines the stable feature position of the voiceprint feature vector, generates a key corresponding to the user voiceprint information based on the stable feature position, and completes verification based on the key. The present invention solves the security and reliability problems existing in traditional identity authentication methods by introducing dynamic biometric recognition technology and the data processing capabilities of a big data platform. This method not only improves the accuracy and efficiency of identity authentication, but also provides a strong guarantee for user privacy protection.
[0023] In some embodiments, generating a user verification environment security index based on user verification environment information specifically includes the following process: Determine whether the user's IP address information, the user's node code information, and the user's geographic location information are abnormal. If not, the user verification environment safety factor R is 1; if so, the user verification environment safety factor R is 0; Based on the user verification behavior information, the number of times S that the user clicks the verification operation screen during the verification request process is obtained. The verification operation screen includes the mobile user client screen, and the maximum number of times the user clicks the verification operation screen during the verification request process is obtained in the storage module of the big data platform analysis module. , calculate S The proportion ; Get user verification frequency based on verification frequency information , where the verification frequency The number of user verifications within a preset time; Get the time when the user sends the verification request based on the verification time information and the moment when the user completes the slider verification operation , and calculate the time To time The slider verification operation is an operation in which the user needs to touch and hold the slider on the verification operation screen with a finger and slide it to the correct position or complete the puzzle as required; Verify the user's environmental safety factor R, ratio , User verification frequency Substitute the time period T into the user verification environment safety index calculation formula to calculate the user verification environment safety index YZH, which is as follows: .
[0024] In some embodiments, determining whether the user's IP address information, the user's node code information, and the user's geographic location information are abnormal specifically includes the following process: Compare the user's IP address information with the user's historical IP address information to determine whether the two are consistent. If so, the user's IP address information is normal, otherwise, the user's IP address information is abnormal; compare the user's node coding information with the registered node coding information to determine whether the user's node coding information is included in the registered node coding information. If so, the user's node coding information is normal, otherwise, it is abnormal; compare the user's geographic location information with the user's registered geographic location information to determine whether the two are consistent. If so, the user's geographic location information is normal, otherwise, it is abnormal; when the user's IP address information, the user's node coding information and the user's geographic location information are all normal, the user verification environment safety factor R is 1, and when at least one of the user's IP address information, the user's node coding information and the user's geographic location information is abnormal, the user verification environment safety factor R is 0.
[0025] In some embodiments, judging whether the condition for generating a user biometric information acquisition signal is met based on the user verification environment security index includes the following process: The storage module loads the user verification environment security index threshold based on the big data platform analysis module , where the user verification environment security index threshold Pre-set by the system and stored in the storage module; Determine whether the user verification environment safety index exceeds the user verification environment safety index threshold If so, the condition for generating a user biometric information acquisition signal is met; if not, the condition for generating a user biometric information acquisition signal is not met.
[0026] In some embodiments, Figure 2 This is a workflow diagram of a dynamic password verification system based on biometric features of a big data platform according to an embodiment of the present invention. Figure 2As shown, extracting a voiceprint feature vector based on user voiceprint information includes the following steps: Step S201: extract voiceprint FBank features from the user's voiceprint audio through pre-emphasis, framing, windowing, short-time Fourier transform, and Mel filtering: Pre-emphasis: Pre-emphasis processing is to pass the speech signal through a high-pass filter to enhance the high-frequency part of the speech signal and compensate for the high-frequency part of the speech signal suppressed by the pronunciation system. The purpose of pre-emphasis is to make the signal spectrum flat for subsequent processing. The transfer function of pre-emphasis is usually expressed as: y(t) = x(t) -αx(t-1), where α is the pre-emphasis coefficient, which is generally between 0.9 and 1.0, and the commonly used value is 0.97.
[0027] Framing: Since speech signals are time-varying, they need to be divided into multiple short time frames for better analysis. Usually the frame length is 20-30ms and the frame shift is 10-15ms. Framing is achieved through a sliding window to ensure that adjacent frames overlap partially to maintain signal continuity.
[0028] Windowing: To reduce the discontinuity between frames, it is necessary to perform windowing on each frame after framing. Common window functions include rectangular window, Hamming window, and Hanning window. Windowing can make the two ends of the frame decay smoothly, thus obtaining a higher quality spectrum.
[0029] Feature extraction stage; Short-time Fourier transform (STFT): Perform a fast Fourier transform (FFT) on each frame of the windowed signal to obtain the spectrum of each frame. FFT can convert the signal from the time domain to the frequency domain, making it easier to analyze the frequency characteristics of the signal.
[0030] Compute the power spectrum: The power spectrum of the speech signal is obtained by taking the modulus square of the spectrum of each frame. The power spectrum reflects the energy distribution of the signal at different frequencies.
[0031] Apply a Mel filter bank: The Mel filter bank is a group of triangular filters evenly distributed on the Mel frequency scale. By passing the power spectrum through the Mel filter bank, the energy sum in each filter band can be obtained, that is, the Mel spectrum. The number of Mel filter banks is generally 22 to 40, and the specific number depends on actual needs.
[0032] Take the logarithm: Take the logarithm of each element in the Mel spectrum to get the logarithmic Mel spectrum. Logarithmic transformation can compress the dynamic range of the signal, making the difference in the low-frequency part more significant.
[0033] Discrete Cosine Transform (DCT): If you need to extract MFCC features, you need to perform discrete cosine transform (DCT) on the logarithmic Mel spectrum. DCT can convert the signal from the time domain to the frequency domain and extract the main features of the signal. However, for FBank features, DCT transformation is usually not performed, but the logarithmic Mel spectrum is directly used as the feature vector.
[0034] Step S202: Select the ResNet model to train the voiceprint FBank features, and the training sample set is the voiceprint FBank features; Step S203: After training with the training set is completed, the fully connected layer is removed and the voiceprint feature map is output. A feature vector that conforms to the normal distribution is selected from the features of the voiceprint feature map and the output of the fully connected layer, and the feature vector that conforms to the normal distribution is recorded as the voiceprint feature vector.
[0035] In some embodiments, determining the stable feature position of the voiceprint feature vector specifically includes the following process: Prepare a sequence P marking the feature positions of the voiceprint; Initialize each value in P to 1; set up , ; For the The position where P[j]=1 in the voiceprint feature vector, If V[i][j] = V[i+1][j], then P[j]=1, otherwise, P[j]=0; Until all positions in all voiceprint vectors are traversed, the position where P[j]=1 is the selected stable feature position, P[j] represents the j-th position value in the voiceprint feature position vector, and V[i][j] represents the value of the j-th position in the i-th voiceprint vector.
[0036] In some embodiments, generating a key corresponding to the user's voiceprint information based on the stable feature position specifically includes the following process: Extract b subsequences based on stable feature positions, where a subsequence is a continuous digital sequence; For a single subsequence Encode, where , and record the corresponding calibration part code for each subsequence ; Construct a polynomial such that the key output is bounded to the polynomial constant term ,item For the key: ; in, ,... , is the random coefficient, , Representative Model The remaining domain of Represents modulus. Its value is a prime number. , and Used in the key extraction phase.
[0037] It is worth noting that it is a common practice to encode a single subsequence and record the corresponding calibration part during the encryption process, especially when designing encryption algorithms that require high security and error detection capabilities. This method can be used to ensure the integrity and security of data during transmission or storage.
[0038] Define subsequences: First, determine the data blocks (i.e. subsequences) you need to encrypt. These data blocks can be byte sequences of any length.
[0039] Encrypt subsequences: Encrypt each subsequence using an encryption algorithm (such as AES, RSA, or simpler ones such as XOR encryption).
[0040] Generate the calibration section: Checksum: Calculate the checksum (such as CRC, MD5, SHA-256, etc.) of the encrypted subsequence and use it as the calibration part.
[0041] Key part: If the encryption algorithm requires a key, the key itself or parts of it can also be considered part of the calibration part, especially in the scenarios of key exchange or shared secrets.
[0042] Combine: Combine the encrypted subsequence with the calibration part. This can be done by simple concatenation (appending the calibration part to the encrypted subsequence) or by more complex data structures.
[0043] Transmission or storage: Send the combined data to a destination or store it.
[0044] Furthermore, in the key extraction phase, the user's voiceprint corresponding , and Is it consistent with the preset one? If so, the user identity is correct; if not, the user identity is illegal.
[0045] This embodiment also provides a dynamic password verification method based on biometrics of a big data platform. Figure 3 This is a workflow diagram of a dynamic password verification method based on biometrics of a big data platform according to an embodiment of the present invention. Figure 3 As shown, the method includes: Step S301: obtaining user verification environment information, wherein the user verification environment information includes the user's IP address information, the user's node code information, the user's geographic location information, the user's verification behavior information, the verification frequency information, and the verification time information; Step S302: Generate a user verification environment security index based on the user verification environment information, and determine whether the condition for generating a user biometric information acquisition signal is met based on the user verification environment security index. If so, generate a user biometric information acquisition signal; if not, do not generate a user biometric information acquisition signal; Step S303: acquiring user voiceprint information based on the user biometric information acquisition signal, wherein the voiceprint information includes the user voiceprint audio; Step S304: extracting a voiceprint feature vector based on the user's voiceprint information, determining a stable feature position of the voiceprint feature vector, generating a key corresponding to the user's voiceprint information based on the stable feature position, and completing verification based on the key.
[0046] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0047] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0048] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0049] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0050] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0051] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A dynamic password verification system based on biometrics of a big data platform, characterized in that: The system includes a user verification environment information acquisition module, a big data platform analysis module, a biometric information acquisition module, and a dynamic key generation module; The user verification environment information acquisition module is used to obtain user verification environment information, wherein the user verification environment information includes the user's IP address information, the user's node code information, the user's geographic location information, the user's verification behavior information, the verification frequency information and the verification time information, and sends the user verification environment information to the big data platform analysis module; The big data platform analysis module is used to receive user verification environment information, and generate a user verification environment safety index based on the user verification environment information, and determine whether the conditions for generating a user biometric information acquisition signal are met based on the user verification environment safety index. If so, generate a user biometric information acquisition signal and send it to the biometric information acquisition module; The biometric information acquisition module is used to receive a user biometric information acquisition signal, and acquire the user voiceprint information based on the user biometric information acquisition signal, wherein the voiceprint information includes the user voiceprint audio, and send the user voiceprint information to the dynamic key generation module; The dynamic key generation module is used to receive user voiceprint information, extract voiceprint feature vectors based on the user voiceprint information, determine the stable feature positions of the voiceprint feature vectors, generate a key corresponding to the user voiceprint information based on the stable feature positions, and complete verification based on the key.
2. According to claim 1, a dynamic password verification system based on biometrics of a big data platform is characterized in that: Generating a user verification environment security index based on user verification environment information specifically includes the following processes: Determine whether the user's IP address information, the user's node code information, and the user's geographic location information are abnormal. If not, the user verification environment safety factor R is 1; if so, the user verification environment safety factor R is 0; Based on the user verification behavior information, the number of times S that the user clicks the verification operation screen during the verification request process is obtained. The verification operation screen includes the mobile user client screen, and the maximum number of times the user clicks the verification operation screen during the verification request process is obtained in the storage module of the big data platform analysis module. , calculate S The proportion ; Get user verification frequency based on verification frequency information , where the verification frequency The number of user verifications within a preset time; Get the time when the user sends the verification request based on the verification time information and the moment when the user completes the slider verification operation , and calculate the time To time The slider verification operation is an operation in which the user needs to touch and hold the slider on the verification operation screen with a finger and slide it to the correct position or complete the puzzle as required; Verify the user's environmental safety factor R, ratio , User verification frequency Substitute the time period T into the user verification environment safety index calculation formula to calculate the user verification environment safety index YZH, which is as follows: 。 3. According to claim 2, a dynamic password verification system based on biometrics of a big data platform is characterized in that: Determining whether the user's IP address information, the user's node code information, and the user's geographic location information are abnormal specifically includes the following process: Compare the user's IP address information with the user's historical IP address information to determine whether the two are consistent. If so, the user's IP address information is normal, otherwise, the user's IP address information is abnormal; compare the user's node coding information with the registered node coding information to determine whether the user's node coding information is included in the registered node coding information. If so, the user's node coding information is normal, otherwise, it is abnormal; compare the user's geographical location information with the user's registered geographical location information to determine whether the two are consistent. If so, the user's geographical location information is normal, otherwise, it is abnormal; When the user's IP address information, the user's node coding information, and the user's geographic location information are all normal, the user verification environment safety factor R is 1. When at least one of the user's IP address information, the user's node coding information, and the user's geographic location information is abnormal, the user verification environment safety factor R is 0.
4. According to claim 1, a dynamic password verification system based on biometrics of a big data platform is characterized in that: Judging whether the conditions for generating a user biometric information acquisition signal are met based on the user verification environment security index includes the following process: The storage module loads the user verification environment security index threshold based on the big data platform analysis module , where the user verification environment security index threshold Pre-set by the system and stored in the storage module; Determine whether the user verification environment safety index exceeds the user verification environment safety index threshold If so, the condition for generating a user biometric information acquisition signal is met; if not, the condition for generating a user biometric information acquisition signal is not met.
5. According to claim 1, a dynamic password verification system based on biometrics of a big data platform is characterized in that: Extracting voiceprint feature vectors based on user voiceprint information includes the following processes: The voiceprint FBank features are extracted from the user's voiceprint audio through pre-emphasis, framing, windowing, short-time Fourier transform, and Mel filtering. The ResNet model is selected to train the voiceprint FBank features. The training sample set is the voiceprint FBank features. After the training with the training set is completed, the fully connected layer is removed and the voiceprint feature map is output. The feature vector that conforms to the normal distribution is selected from the voiceprint feature map and the features output by the fully connected layer, and the feature vector that conforms to the normal distribution is recorded as the voiceprint feature vector.
6. A dynamic password verification system based on biometrics of a big data platform according to claim 5, characterized in that: Determining the stable feature position of the voiceprint feature vector specifically includes the following process: Prepare a sequence P marking the feature positions of the voiceprint; Initialize each value in P to 1; set up , ; For the The position where P[j]=1 in the voiceprint feature vector, If V[i][j] = V[i+1][j], then P[j]=1, otherwise, P[j]=0; Until all positions in all voiceprint vectors are traversed, the position where P[j]=1 is the selected stable feature position, P[j] represents the j-th position value in the voiceprint feature position vector, and V[i][j] represents the value of the j-th position in the i-th voiceprint vector.
7. A dynamic password verification system based on biometrics of a big data platform according to claim 6, characterized in that: Generating the key corresponding to the user's voiceprint information based on the stable feature position specifically includes the following process: Extract b subsequences based on stable feature positions, where a subsequence is a continuous digital sequence; For a single subsequence Encode, where , and record the corresponding calibration part code for each subsequence ; Construct a polynomial such that the key output is bounded to the polynomial constant term ,item For the key: ； in, ,... , is the random coefficient, , Representative Model The remaining domain of Represents modulus. Its value is a prime number. , and Used in the key extraction phase.
8. A dynamic password verification system based on biometrics of a big data platform according to claim 7, characterized in that: In the key extraction phase, determine the user's voiceprint corresponding to , and Is it consistent with the preset one? If so, the user identity is correct; if not, the user identity is illegal.
9. A dynamic password verification method based on biometrics of a big data platform, applicable to any one of the dynamic password verification systems based on biometrics of a big data platform in claims 1 to 8, characterized in that: Methods include: Obtaining user verification environment information, wherein the user verification environment information includes the user's IP address information, the user's node code information, the user's geographic location information, the user's verification behavior information, the verification frequency information, and the verification time information; Generate a user verification environment security index based on the user verification environment information, and determine whether a condition for generating a user biometric information acquisition signal is met based on the user verification environment security index, and if so, generate a user biometric information acquisition signal; Acquiring user voiceprint information based on a user biometric information acquisition signal, wherein the voiceprint information includes user voiceprint audio; A voiceprint feature vector is extracted based on the user's voiceprint information, and a stable feature position of the voiceprint feature vector is determined. A key corresponding to the user's voiceprint information is generated based on the stable feature position, and verification is completed based on the key.