A service security level determination method, device, system and storage medium
By processing the voiceprint features recorded by the microphone using a voiceprint processing model, the problem of verification accuracy caused by microphone recording deviation is solved, and accurate identity verification is achieved without changing the microphone.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- AGRICULTURAL BANK OF CHINA
- Filing Date
- 2023-04-14
- Publication Date
- 2026-07-03
AI Technical Summary
Voiceprint deviations recorded by the microphone reduce verification accuracy, and replacing the microphone is costly.
The voiceprint processing model is used to process the voiceprint features recorded by the target microphone into simulated voiceprint features, and then match them with the original voiceprint features recorded by the preset high-fidelity microphone to determine the business security level.
Accurate identity verification can be achieved without replacing the microphone, saving costs and avoiding reduced verification accuracy due to microphone quality issues.
Smart Images
Figure CN116543772B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of voiceprint recognition technology, and in particular to a method, apparatus, system, and storage medium for determining business security levels. Background Technology
[0002] Voiceprints are the vocal characteristics contained in speech that can represent and identify a speaker. Voiceprints are not only specific but also relatively stable; after adulthood, a person's voice can remain relatively stable for a long period of time.
[0003] Theoretically, voiceprints are like fingerprints; very few two people have the same voiceprint characteristics. In certain specific applications, such as large transactions at a bank counter, customers need to use biometric information for verification in addition to entering a password, and voiceprints are one important verification method.
[0004] The accuracy of voiceprint verification depends on the quality of the microphone. However, with frequent use, microphones may develop quality problems, such as distortion, which will cause deviations in the voiceprint. These deviations may reduce the accuracy of the verification, but replacing the microphone directly would be too costly. Summary of the Invention
[0005] This invention provides a method, apparatus, system, and storage medium for determining business security levels, in order to solve the problem of reduced verification accuracy due to deviations in the voiceprints recorded by microphones.
[0006] In a first aspect, the present invention provides a method for determining a business security level, comprising:
[0007] Determine the actual voiceprint characteristics of the current customer who is using the target microphone to conduct business;
[0008] Using the voiceprint processing model corresponding to the target microphone, the actual voiceprint features are processed to obtain simulated voiceprint features. The voiceprint processing model is determined based on sample voiceprint pairs, which include a first sample voiceprint collected using the target microphone and a second sample voiceprint collected using a preset high-fidelity microphone with higher fidelity than the target microphone.
[0009] Determine whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features, and determine the security level of the current customer's business based on the matching results. The original voiceprint features are the voiceprint features of the target customer determined using the preset high-fidelity microphone.
[0010] Secondly, the present invention provides an apparatus for determining a business security level, comprising:
[0011] The actual voiceprint feature determination module is used to determine the actual voiceprint features of the current customer who is currently using the target microphone to conduct business.
[0012] The simulated voiceprint feature determination module is used to process the actual voiceprint features using the voiceprint processing model corresponding to the target microphone to obtain simulated voiceprint features. The voiceprint processing model is determined based on sample voiceprint pairs, which include a first sample voiceprint collected using the target microphone and a second sample voiceprint collected using a preset high-fidelity microphone with a higher fidelity than the target microphone.
[0013] The security level determination module is used to determine whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features, and to determine the security level of the current customer's business based on the matching results. The original voiceprint features are the voiceprint features of the target customer determined using the preset high-fidelity microphone.
[0014] Thirdly, the present invention provides a business processing system, which includes:
[0015] At least one microphone, wherein the microphone is used to acquire the actual voiceprint characteristics of the current customer;
[0016] At least one processor, wherein the processor is used to process the actual voiceprint features; and a memory communicatively connected to the at least one processor;
[0017] The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to perform the method for determining the business security level of the first aspect described above.
[0018] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a processor to execute the method for determining the business security level described in the first aspect.
[0019] The present invention provides a scheme for determining the security level of a business transaction. This scheme determines the actual voiceprint characteristics of a current customer using a target microphone to conduct business. It then processes these actual voiceprint characteristics using a voiceprint processing model corresponding to the target microphone to obtain simulated voiceprint characteristics. The voiceprint processing model is determined based on sample voiceprint pairs, which include a first sample voiceprint collected using the target microphone and a second sample voiceprint collected using a preset high-fidelity microphone with higher fidelity than the target microphone. The scheme determines whether the actual voiceprint characteristics and the simulated voiceprint characteristics match the original voiceprint characteristics, and determines the security level of the current customer's business transaction based on the matching results. The original voiceprint characteristics are those of the target customer determined using the preset high-fidelity microphone. By adopting the above technical solution, when microphones experience quality problems such as distortion, the actual voiceprint features of the current customer can be processed into simulated voiceprint features using a voiceprint processing model. Then, based on the matching result between the simulated voiceprint features and the original voiceprint features determined by the preset high-fidelity microphone, the security level of the current customer's business can be determined. This eliminates the need to replace the microphone, enabling accurate verification of the current customer's identity, saving investment costs, and avoiding situations where microphone quality problems reduce the accuracy of identity verification.
[0020] It should be understood that the description in this section is not intended to identify key or essential features of the invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 This is a flowchart of a method for determining a business security level according to Embodiment 1 of the present invention;
[0023] Figure 2 This is a flowchart of a method for determining a business security level according to Embodiment 2 of the present invention;
[0024] Figure 3 This is a schematic diagram of a device for determining a business security level according to Embodiment 3 of the present invention;
[0025] Figure 4 This is a schematic diagram of the structure of a business processing system provided in Embodiment 4 of the present invention. Detailed Implementation
[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. In the description of this invention, unless otherwise stated, "a plurality of" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist; for example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.
[0028] Example 1
[0029] Figure 1 The flowchart below provides a method for determining a business security level according to Embodiment 1 of the present invention. This embodiment is applicable to situations where a business security level needs to be determined. The method can be executed by a business security level determination device, which can be implemented in hardware and / or software. The business security level determination device can be configured in a business processing system, which includes at least one microphone for acquiring the actual voiceprint characteristics of the customer currently processing the business. The business processing system can be composed of two or more physical entities.
[0030] like Figure 1 As shown in Embodiment 1 of the present invention, a method for determining a business security level specifically includes the following steps:
[0031] S101. Determine the actual voiceprint characteristics of the current customer who is currently using the target microphone to conduct business.
[0032] In this embodiment, the audio of the current customer conducting business can be collected using a target microphone, and the audio can be processed using a preset method, such as a preset feature extraction model, to determine the voiceprint features of the audio, i.e., the actual voiceprint features. The target microphone can be understood as a microphone currently being used by the current customer conducting business that has quality problems, such as a microphone with distortion issues. Whether the microphone has technical problems can be determined through testing or other methods. The current customer can be understood as the customer currently conducting business.
[0033] S102. Using the voiceprint processing model corresponding to the target microphone, the actual voiceprint features are processed to obtain simulated voiceprint features. The voiceprint processing model is determined based on sample voiceprint pairs. The sample voiceprint pairs include a first sample voiceprint collected using the target microphone and a second sample voiceprint collected using a preset high-fidelity microphone with higher fidelity than the target microphone.
[0034] In this embodiment, since there can be multiple microphones with quality problems, and the causes and characteristics of each problematic microphone's failure may differ, a voiceprint processing model corresponding to each problematic microphone can be pre-determined. The parameters of these voiceprint processing models are typically different. The voiceprint processing model corresponding to the target microphone can be used to process the actual voiceprint features to simulate the voiceprint features of a customer using a normal microphone; these voiceprint features are the simulated voiceprint features. The voiceprint processing model may include a mapping relationship between sample voiceprints (features) collected by the target microphone and sample voiceprints (features) collected by a preset high-fidelity microphone. This mapping relationship can be a mapping function, etc., and its form is not limited. The preset high-fidelity microphone can be understood as a microphone that functions normally and has a higher fidelity than the target microphone.
[0035] S103. Determine whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features, and determine the security level of the current customer's business based on the matching results, wherein the original voiceprint features are the voiceprint features of the target customer determined using the preset high-fidelity microphone.
[0036] In this embodiment, the target customer's audio can be pre-recorded using a preset high-fidelity microphone, and the corresponding voiceprint features, i.e., the original voiceprint features, can be determined. When the current customer comes to conduct business, the actual voiceprint features and simulated voiceprint features are matched with the original voiceprint features respectively. The security level of the current business can be determined based on the matching results. The higher the matching degree between the actual and simulated voiceprint features and the original voiceprint features, the greater the possibility that the current customer and the target customer are the same person, and the higher the security level of the current customer's business. Here, the target customer can be understood as the customer corresponding to the secure identity during identity verification.
[0037] The method for determining the business security level provided in this embodiment of the invention determines the actual voiceprint characteristics of the current customer currently using a target microphone to conduct business, processes the actual voiceprint characteristics using the voiceprint processing model corresponding to the target microphone to obtain simulated voiceprint characteristics, wherein the voiceprint processing model is determined based on sample voiceprint pairs, the sample voiceprint pairs including a first sample voiceprint collected using the target microphone and a second sample voiceprint collected using a preset high-fidelity microphone with higher fidelity than the target microphone, determines whether the actual voiceprint characteristics and the simulated voiceprint characteristics match the original voiceprint characteristics respectively, and determines the security level of the current customer conducting business based on the matching results, wherein the original voiceprint characteristics are the voiceprint characteristics of the target customer determined using the preset high-fidelity microphone. The technical solution of this invention addresses the issue that when a microphone experiences quality problems such as distortion, a voiceprint processing model can be used to process the actual voiceprint features of the current customer into simulated voiceprint features. Then, based on the matching result between the simulated voiceprint features and the original voiceprint features determined by a preset high-fidelity microphone, the security level of the current customer's business can be determined. This allows for accurate verification of the current customer's identity without replacing the microphone, saving investment costs and avoiding situations where microphone quality problems reduce the accuracy of identity verification.
[0038] Example 2
[0039] Figure 2 This is a flowchart of a method for determining a business security level according to Embodiment 2 of the present invention. The technical solution of the present invention is further optimized based on the above optional technical solutions, and provides a specific way to determine the business security level.
[0040] Optionally, determining whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features includes: determining the deviation information between the actual voiceprint features and the simulated voiceprint features and the original voiceprint features, wherein the deviation information includes the deviation position and the deviation magnitude; and determining whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features based on the deviation position and the deviation magnitude. The advantage of this configuration is that, based on the specific position and magnitude of the deviation, it is possible to accurately determine whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features.
[0041] Optionally, determining the security level of the current customer's transaction based on the matching result includes: if the matching result shows that both the actual voiceprint feature and the simulated voiceprint feature match the original voiceprint feature, then the security level of the current customer's transaction is determined to be high; if the matching result shows that only one of the actual voiceprint feature and the simulated voiceprint feature matches the original voiceprint feature, then the security level of the current customer's transaction is determined to be medium; if the matching result shows that neither the actual voiceprint feature nor the simulated voiceprint feature matches the original voiceprint feature, then the security level of the current customer's transaction is determined to be low. The advantage of this setting is that, based on whether the actual voiceprint feature and the simulated voiceprint feature match the original voiceprint feature, the possibility that the current customer and the target customer are the same person can be accurately determined.
[0042] like Figure 2 As shown in Embodiment 2 of the present invention, a method for determining a business security level specifically includes the following steps:
[0043] S201. Determine the actual voiceprint characteristics of the current customer who is currently using the target microphone to conduct business.
[0044] S202. Using the voiceprint processing model corresponding to the target microphone, process the actual voiceprint features to obtain simulated voiceprint features.
[0045] S203. Determine the deviation information between the actual voiceprint features and the simulated voiceprint features and the original voiceprint features.
[0046] The deviation information includes the deviation location and the deviation magnitude.
[0047] Specifically, the deviation location can be understood as the position where the actual voiceprint features and simulated voiceprint features deviate from the original voiceprint features, such as which characters or words have deviations in pronunciation or intonation. The deviation magnitude can be understood as the size of the deviation. Since everyone's habitual intonation and pronunciation of words are usually consistent, the deviation location and magnitude can be used to determine the probability that the current customer and the target customer are the same person.
[0048] S204. Based on the deviation position and the deviation amplitude, determine whether the actual voiceprint feature and the simulated voiceprint feature match the original voiceprint feature. If the matching result is that both the actual voiceprint feature and the simulated voiceprint feature match the original voiceprint feature, then proceed to step 205. If the matching result is that only one of the actual voiceprint feature and the simulated voiceprint feature matches the original voiceprint feature, then proceed to step 206. If the matching result is that neither the actual voiceprint feature nor the simulated voiceprint feature matches the original voiceprint feature, then proceed to step 207.
[0049] Specifically, the location and magnitude of the deviation between the actual and original voiceprint features can be determined. If the deviation magnitude is large and / or the deviation location is unusual, it can be determined that the actual and original voiceprint features do not match; otherwise, it can be determined that they match. Similarly, the location and magnitude of the deviation between the simulated and original voiceprint features can also be determined. If the deviation magnitude is large and / or the deviation location is unusual, it can be determined that the simulated and original voiceprint features do not match; otherwise, it can be determined that they match.
[0050] Optionally, determining whether the actual voiceprint feature and the simulated voiceprint feature match the original voiceprint feature based on the deviation position and the deviation amplitude includes: if the deviation position of the actual voiceprint feature belongs to a first preset position and / or the deviation amplitude of the actual voiceprint feature is greater than a first preset amplitude, then it is determined that the actual voiceprint feature does not match the original voiceprint feature; if the deviation position of the simulated voiceprint feature belongs to a second preset position and / or the deviation amplitude of the simulated voiceprint feature is greater than a second preset amplitude, then it is determined that the simulated voiceprint feature does not match the original voiceprint feature, wherein the first preset position is different from the second preset position, and the first preset amplitude is different from the second preset amplitude. The advantage of this setting is that, through the preset position and preset amplitude, voiceprint features that match and do not match the original voiceprint feature can be distinguished.
[0051] For example, if the first preset position is 'a', the first preset amplitude is Δr1, the second preset position is 'b', and the second preset amplitude is Δr2, then when the deviation position of the actual voiceprint feature is 'a' and / or the deviation amplitude is greater than Δr1, it can be determined that the actual voiceprint feature does not match the original voiceprint feature; otherwise, it can be determined that they match. When the deviation position of the simulated voiceprint feature is 'b' and / or the deviation amplitude is greater than Δr2, it can be determined that the simulated voiceprint feature does not match the original voiceprint feature; otherwise, it can be determined that they match.
[0052] S205. Determine that the security level of the current customer's business is high.
[0053] Specifically, when both the actual voiceprint features and the simulated voiceprint features match the original voiceprint features, it can be determined that there is a high probability that the current customer and the target customer are the same person, and the security level of the current customer's business transactions can be determined to be high.
[0054] S206. Determine that the security level of the current customer's business is medium.
[0055] Specifically, if only one of the actual voiceprint feature and the simulated voiceprint feature matches the original voiceprint feature, it can be determined that the probability of the current customer and the target customer being the same person is moderate, and the security level of the current customer's business can be determined to be medium.
[0056] S207. Determine that the security level of the current customer's business is low.
[0057] Specifically, when both the actual voiceprint characteristics and the simulated voiceprint characteristics do not match the original voiceprint characteristics, it can be determined that the possibility of the current customer and the target customer being the same person is small, and the security level of the current customer's business can be determined to be low.
[0058] Optionally, when a customer conducts business, different security levels correspond to different identity verification methods. The advantage of this setup is that the customer's identity is verified specifically based on the security level, ensuring the customer's asset security.
[0059] For example, if the security level is determined to be high, the customer's identity can be confirmed directly after the customer's password verification is successful. If the security level is determined to be medium, the customer's identity can be confirmed after both password verification and handwriting verification are successful. If the security level is determined to be low, the customer's identity can be confirmed after password verification, handwriting verification, and facial verification are all successful.
[0060] The business security level determination method provided in this invention utilizes a voiceprint processing model to correct the sound recorded by a problematic microphone. Based on the specific location and magnitude of the deviation between the corrected voiceprint and the original voiceprint features, the actual and simulated voiceprint features can be accurately determined, and their matching with the original voiceprint features can be verified. Furthermore, based on the matching of the actual and simulated voiceprint features with the original voiceprint features, the possibility that the current customer and the target customer are the same person and the security level of the current customer's business transactions can be accurately determined, thus ensuring the customer's property security and the accuracy of identity verification.
[0061] Optionally, before determining the actual voiceprint characteristics of the current customer using the target microphone to conduct business, the method further includes: collecting a first voiceprint for each preset microphone and collecting a second voiceprint using a preset high-fidelity microphone; determining the voiceprint deviation between each first voiceprint and the second voiceprint, and filtering out target voiceprint deviations greater than a preset deviation threshold from a plurality of voiceprint deviations; determining corresponding sample voiceprint pairs based on the target voiceprint deviation, and identifying the preset microphone associated with the sample voiceprint pair as the target microphone. The advantage of this setup is that by determining the voiceprint deviation between the first and second voiceprints collected using the preset high-fidelity microphone, problematic microphones can be filtered out from a plurality of preset microphones.
[0062] Specifically, voiceprints can be collected using a preset microphone and a preset high-fidelity microphone. Among multiple preset microphones, the microphone with the largest voiceprint deviation from that collected by the preset high-fidelity microphone is identified, i.e., the microphone with a target voiceprint deviation greater than a preset deviation threshold. This microphone is the problematic microphone, or the target microphone. The sample voiceprint pair includes the voiceprint corresponding to the target microphone and the voiceprint corresponding to the preset high-fidelity microphone.
[0063] Optionally, based on the above-mentioned optional embodiments, the method further includes: training a preset machine learning model using the sample voiceprint pairs and a loss function to obtain a voiceprint processing model. The advantage of this approach is that by training the preset machine learning model using sample voiceprint pairs and a loss function, a highly accurate voiceprint processing model can be obtained.
[0064] Specifically, a preset machine learning model can be trained using sample voiceprint pairs. The completion of training is determined by the value of the loss function; a smaller loss function value indicates a suitable voiceprint processing model. This machine learning model can handle various data formats in dynamic, high-volume, and complex data environments. It possesses generalization capabilities and can accurately simulate the voiceprint corresponding to a normal microphone based on actual voiceprint characteristics.
[0065] Example 3
[0066] Figure 3 This is a schematic diagram of a device for determining the business security level according to Embodiment 3 of the present invention. Figure 3 As shown, the device includes: an actual voiceprint feature determination module 301, a simulated voiceprint feature determination module 302, and a security level determination module 303, wherein:
[0067] The actual voiceprint feature determination module is used to determine the actual voiceprint features of the current customer who is currently using the target microphone to conduct business.
[0068] The simulated voiceprint feature determination module is used to process the actual voiceprint features using the voiceprint processing model corresponding to the target microphone to obtain simulated voiceprint features. The voiceprint processing model is determined based on sample voiceprint pairs, which include a first sample voiceprint collected using the target microphone and a second sample voiceprint collected using a preset high-fidelity microphone with a higher fidelity than the target microphone.
[0069] The security level determination module is used to determine whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features, and to determine the security level of the current customer's business based on the matching results. The original voiceprint features are the voiceprint features of the target customer determined using the preset high-fidelity microphone.
[0070] The business security level determination device provided in this embodiment of the invention can process the actual voiceprint features of the current customer into simulated voiceprint features using a voiceprint processing model when the microphone has quality problems such as distortion. Then, based on the matching result of the simulated voiceprint features and the original voiceprint features determined according to the preset high-fidelity microphone, the security level of the current customer's business can be determined. It can accurately verify the identity of the current customer without replacing the microphone, saving investment costs and avoiding the situation where the accuracy of identity verification is reduced due to microphone quality problems.
[0071] Optional, the security level determination module includes:
[0072] A deviation information determination unit is used to determine the deviation information between the actual voiceprint feature and the simulated voiceprint feature and the original voiceprint feature, respectively, wherein the deviation information includes the deviation position and the deviation magnitude;
[0073] The matching judgment unit is used to determine whether the actual voiceprint feature and the simulated voiceprint feature match the original voiceprint feature based on the deviation position and the deviation amplitude.
[0074] Optionally, determining whether the actual voiceprint feature and the simulated voiceprint feature match the original voiceprint feature based on the deviation position and the deviation amplitude includes: if the deviation position of the actual voiceprint feature belongs to a first preset position and / or the deviation amplitude of the actual voiceprint feature is greater than a first preset amplitude, then it is determined that the actual voiceprint feature does not match the original voiceprint feature; if the deviation position of the simulated voiceprint feature belongs to a second preset position and / or the deviation amplitude of the simulated voiceprint feature is greater than a second preset amplitude, then it is determined that the simulated voiceprint feature does not match the original voiceprint feature, wherein the first preset position is different from the second preset position, and the first preset amplitude is different from the second preset amplitude.
[0075] Optional, the security level determination module includes:
[0076] The first level determination unit is used to determine the security level of the current customer's business as high if the matching result returned by the matching judgment unit is that both the actual voiceprint feature and the simulated voiceprint feature match the original voiceprint feature.
[0077] The second-level determination unit is used to determine the security level of the current customer's business as medium if the matching result returned by the matching judgment unit is that only one of the actual voiceprint feature and the simulated voiceprint feature matches the original voiceprint feature.
[0078] The third-level determination unit is used to determine the security level of the current customer's business as low if the matching result returned by the matching judgment unit is that neither the actual voiceprint feature nor the simulated voiceprint feature matches the original voiceprint feature.
[0079] Optionally, the device may also include:
[0080] The voiceprint acquisition module is used to acquire a first voiceprint for each preset microphone and a second voiceprint using a preset high-fidelity microphone before determining the actual voiceprint characteristics of the current customer who is currently using the target microphone to conduct business.
[0081] The filtering module is used to determine the voiceprint deviation between each of the first voiceprint and the second voiceprint, and to filter out the target voiceprint deviation that is greater than a preset deviation threshold from the multiple voiceprint deviations.
[0082] The target microphone determination module is used to determine the corresponding sample voiceprint pair based on the target voiceprint deviation, and to determine the preset microphone associated with the sample voiceprint pair as the target microphone.
[0083] Optionally, the device may also include:
[0084] The model determination module is used to train a preset machine learning model using the sample voiceprint pairs and loss function to obtain a voiceprint processing model.
[0085] Optionally, when a customer conducts business, different security levels correspond to different authentication methods.
[0086] The business security level determination device provided in the embodiments of the present invention can execute the business security level determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0087] Example 4
[0088] Figure 4 This is a schematic diagram of the structure of a business processing system, such as... Figure 4 As shown, the business processing system includes at least one microphone 401 for acquiring the actual voiceprint characteristics of the current customer. The business processing system can be a digital computer of various forms. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.
[0089] like Figure 4 As shown, the business processing system also includes at least one processor 402 for processing actual voiceprint characteristics, and a memory 403, such as a read-only memory (ROM) or random access memory (RAM), communicatively connected to the at least one processor 402. The memory 403 stores computer programs executable by the at least one processor. The processor 402 can perform various appropriate actions and processes based on the computer programs stored in the ROM or loaded from memory units into the RAM. The RAM can also store various programs and data required for the operation of the business processing system. The processor, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.
[0090] Multiple components in a business processing system are connected to I / O interfaces, including: input units such as keyboards and mice; output units such as various types of displays and speakers; storage units such as disks and optical discs; and communication units such as network interface cards (NICs), modems, and wireless transceivers. The communication units allow the business processing system to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0091] A processor can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processors include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor performs the various methods and processes described above, such as methods for determining business security levels.
[0092] In some embodiments, the method for determining the business security level may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded into and / or installed into the business processing system via ROM and / or a communication unit. When the computer program is loaded into RAM and executed by a processor, one or more steps of the method for determining the business security level described above may be performed. Alternatively, in other embodiments, the processor may be configured to perform the method for determining the business security level by any other suitable means (e.g., by means of firmware).
[0093] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0094] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0095] The computer equipment provided above can be used to execute the method for determining the business security level provided in any of the above embodiments, and has corresponding functions and beneficial effects.
[0096] Example 5
[0097] In the context of this invention, the computer-readable storage medium may be a tangible medium, and the computer-executable instructions, when executed by a computer processor, are used to perform a method for determining a business security level, the method comprising:
[0098] Determine the actual voiceprint characteristics of the current customer who is using the target microphone to conduct business;
[0099] Using the voiceprint processing model corresponding to the target microphone, the actual voiceprint features are processed to obtain simulated voiceprint features. The voiceprint processing model is determined based on sample voiceprint pairs, which include a first sample voiceprint collected using the target microphone and a second sample voiceprint collected using a preset high-fidelity microphone with higher fidelity than the target microphone.
[0100] Determine whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features, and determine the security level of the current customer's business based on the matching results. The original voiceprint features are the voiceprint features of the target customer determined using the preset high-fidelity microphone.
[0101] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by, or in conjunction with, an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0102] The computer equipment provided above can be used to execute the method for determining the business security level provided in any of the above embodiments, and has corresponding functions and beneficial effects.
[0103] It is worth noting that in the embodiments of the above-mentioned business security level determination device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.
[0104] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.
Claims
1. A method of determining a service security level, characterized by, include: Determine the actual voiceprint characteristics of the current customer who is using the target microphone to conduct business; Using the voiceprint processing model corresponding to the target microphone, the actual voiceprint features are processed to obtain simulated voiceprint features. The voiceprint processing model is determined based on sample voiceprint pairs, which include a first sample voiceprint collected using the target microphone and a second sample voiceprint collected using a preset high-fidelity microphone with higher fidelity than the target microphone. The simulated voiceprint features are simulated voiceprint features of the current customer using a normal microphone. Determine whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features, and determine the security level of the current customer's business based on the matching results. The original voiceprint features are the voiceprint features of the target customer determined using the preset high-fidelity microphone.
2. The method according to claim 1, characterized in that, The step of determining whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features includes: The deviation information between the actual voiceprint features and the simulated voiceprint features and the original voiceprint features is determined, wherein the deviation information includes the deviation position and the deviation magnitude; Based on the deviation position and the deviation magnitude, determine whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features.
3. The method according to claim 2, characterized in that, The step of determining whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features based on the deviation position and the deviation magnitude includes: If the deviation position of the actual voiceprint feature belongs to the first preset position and / or the deviation amplitude of the actual voiceprint feature is greater than the first preset amplitude, then it is determined that the actual voiceprint feature does not match the original voiceprint feature. If the deviation position of the simulated voiceprint feature belongs to the second preset position and / or the deviation amplitude of the simulated voiceprint feature is greater than the second preset amplitude, then it is determined that the simulated voiceprint feature does not match the original voiceprint feature, wherein the first preset position is different from the second preset position, and the first preset amplitude is different from the second preset amplitude.
4. The method according to claim 1, characterized in that, Determining the security level of the current customer's transaction based on the matching results includes: If the matching result is that both the actual voiceprint feature and the simulated voiceprint feature match the original voiceprint feature, then the security level of the current customer's business is determined to be high. If the matching result is that only one of the actual voiceprint feature and the simulated voiceprint feature matches the original voiceprint feature, then the security level of the current customer's business is determined to be medium. If the matching result is that neither the actual voiceprint feature nor the simulated voiceprint feature matches the original voiceprint feature, then the security level of the current customer's business is determined to be low.
5. The method according to claim 1, characterized in that, Before determining the actual voiceprint characteristics of the current customer currently using the target microphone to conduct business, the method further includes: The first voiceprint is collected for each preset microphone, and the second voiceprint is collected using a preset high-fidelity microphone; For each voiceprint deviation between the first voiceprint and the second voiceprint, a target voiceprint deviation greater than a preset deviation threshold is selected from the multiple voiceprint deviations. The corresponding sample voiceprint pair is determined based on the target voiceprint deviation, and the preset microphone associated with the sample voiceprint pair is determined as the target microphone.
6. The method according to claim 5, characterized in that, Also includes: The preset machine learning model is trained using the sample voiceprint pairs and loss function to obtain the voiceprint processing model.
7. The method according to claim 1, characterized in that, in, When a customer conducts business, the authentication method varies depending on the security level.
8. A device for determining the security level of a business operation, characterized in that, include: The actual voiceprint feature determination module is used to determine the actual voiceprint features of the current customer who is currently using the target microphone to conduct business. The simulated voiceprint feature determination module is used to process the actual voiceprint features using the voiceprint processing model corresponding to the target microphone to obtain simulated voiceprint features. The voiceprint processing model is determined based on sample voiceprint pairs, which include a first sample voiceprint collected using the target microphone and a second sample voiceprint collected using a preset high-fidelity microphone with higher fidelity than the target microphone. The simulated voiceprint features are simulated voiceprint features of the current customer using a normal microphone. The security level determination module is used to determine whether the actual voiceprint features and the simulated voiceprint features match the original voiceprint features, and to determine the security level of the current customer's business based on the matching results. The original voiceprint features are the voiceprint features of the target customer determined using the preset high-fidelity microphone.
9. A business processing system, characterized in that, The business processing system includes: At least one microphone, wherein the microphone is used to acquire the actual voiceprint characteristics of the current customer; At least one processor, wherein the processor is used to process the actual voiceprint features; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the method for determining the business security level as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for determining the business security level as described in any one of claims 1-7.