Abnormal account determination method and device, program product and storage medium

Abstract

The embodiment of the invention provides an abnormal account determination method and device, a program product and a storage medium, and the method comprises the steps: obtaining target voice data and voice data of N accounts in a process of voice communication with a target voice account of a target account, the target voice data being the voice data of the N accounts when the target voice account is connected, and the voice data of the N accounts being the voice data of the N accounts; voice data is obtained through the target voice account, and the voice data is obtained through the voice account when the voice account corresponding to the account is connected; based on the account tags of the N accounts, calculating the voice feature matching degree between the voice data of the M accounts and the target voice data according to a preset tag sequence, M being a natural number less than or equal to N; and when the voice feature matching degree is greater than a preset threshold value, determining that the target voice data is abnormal, and determining the target account as an abnormal account. The problem that whether the account is abnormal or not cannot be efficiently determined in the prior art is solved, and the effect of efficiently determining the account abnormality is achieved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and more specifically, to a method and device for determining an abnormal account, a program product, and a storage medium. Background Art

[0002] In financial services, especially in the credit industry, customer identity confirmation is a key link to ensure business compliance and operational security. When a customer fails to repay a loan on time, the financial institution will contact the customer by telephone to remind and negotiate repayment. However, in recent years, with the rise of anti-collection companies, the credit industry faces new challenges, namely that customers may entrust business personnel in these companies to answer collection calls, and these business personnel often use professional strategies and rhetoric to evade repayment responsibilities or demand more favorable repayment terms. In this case, the traditional strong identity determination method usually involves collecting and verifying the customer's specific biometric information, such as voiceprints, fingerprints or facial recognition, to determine whether the account is abnormal by confirming a specific personal identity. This process often requires customers to actively register before using the service. With the development of technologies such as artificial intelligence and speech synthesis, fraud and impersonation technologies are also iteratively updated. The strong identity determination method lacks a certain generalization ability and there is a problem of being unable to efficiently determine whether the account is abnormal. Summary of the invention

[0003] The embodiments of the present application provide a method and device for determining an abnormal account, a program product, and a storage medium to solve the problem that related technologies cannot efficiently determine whether an account is abnormal.

[0004] According to one embodiment of the present application, a method for determining an abnormal account is provided, comprising: in a voice call with a target voice account of a target account, obtaining target voice data and voice data of N accounts, wherein the target voice data is sound data obtained through the target voice account when the target voice account is connected, and the voice data is sound data obtained through the voice account when the voice account corresponding to the account is connected; based on the account tags of the N accounts, and in accordance with a preset tag order, calculating the voice feature matching degree between the voice data of the M accounts and the target voice data, wherein the M is a natural number less than or equal to the N; when the voice feature matching degree is greater than a preset threshold, determining that the target voice data is abnormal, and determining the target account as an abnormal account.

[0005] In an exemplary embodiment, during a voice call with a target voice account of a target account, target voice data and voice data of N accounts are obtained, including: during the voice call with the target voice account, voice with voice quality greater than a preset quality threshold is intercepted to obtain the target voice data; based on the account tags of the N accounts, the N voice data are obtained, wherein the account tags are used to indicate abnormal conditions of the accounts, and the voice data include abnormal voice data of the abnormal accounts.

[0006] In an exemplary embodiment, based on the account tags of the N accounts, the N voice data are obtained, including: obtaining first voice data information of the first account and second voice data information of the second account from a registration table, wherein the account tag of the first account is an abnormal tag, the first account is the abnormal account, and the first voice data information is used to describe information of the abnormal voice data, and the account tag of the second account is a normal tag, the second account is a normal account, and the second voice data information is used to describe information of normal voice data; based on the storage information of the abnormal voice data in the first voice data information, obtaining the first voice data of the first account from a voiceprint database, wherein the first voice data is the abnormal voice data; based on the storage information of the normal voice data in the second voice data information, obtaining the second voice data of the second account from the voiceprint database, wherein the second voice data is the normal voice data.

[0007] In an exemplary embodiment, based on the account labels of the N accounts above, and according to the preset label order, the voice feature matching degree between the voice data of the M accounts above and the target voice data is calculated, including: calculating the feature matching degree between the voice features of the first voice data of the first account among the M accounts and the voice features of the target voice data to obtain the first voice feature matching degree, wherein the account label of the first account is an abnormal label, the first voice data is abnormal voice data, and the voice feature matching degree includes the first voice feature matching degree; when the first voice feature matching degree is less than the preset threshold, calculating the feature matching degree between the voice features of the second voice data of the second account among the M accounts and the voice features of the target voice data to obtain the second voice feature matching degree, wherein the account label of the second account is a normal label, the second voice data is normal voice data, and the voice feature matching degree includes the second voice feature matching degree.

[0008] In an exemplary embodiment, when the voice feature matching degree is greater than a preset threshold, it is determined that the target voice data is abnormal, and the target account is determined as an abnormal account, including: when the first voice feature matching degree is greater than the preset threshold, it is determined that the target voice data is abnormal, and the target account is determined as the abnormal account; or, when the first voice feature matching degree is less than or equal to the preset threshold, and the second voice feature matching degree is greater than the preset threshold, it is determined that the target voice data is abnormal, and the target account is determined as the abnormal account.

[0009] In an exemplary embodiment, when the voice feature matching degree is greater than a preset threshold, it is determined that the target voice data is abnormal, and after the target account is determined as an abnormal account, the method further includes: storing the target voice data in an abnormal voiceprint database; and recording the target voice data information of the target voice data in an abnormal registration table.

[0010] According to one embodiment of the present application, a device for determining an abnormal account includes: a first acquisition module, which is used to obtain target voice data and voice data of N accounts during a voice call with a target voice account of a target account, wherein the target voice data is the sound data obtained through the target voice account when the target voice account is connected, and the voice data is the sound data obtained through the voice account when the voice account corresponding to the account is connected; a first calculation module, which is used to calculate the voice feature matching degree between the voice data of the M accounts and the target voice data based on the account tags of the N accounts and in a preset tag order, wherein the M is a natural number less than or equal to the N; a first determination module, which is used to determine that the target voice data is abnormal when the voice feature matching degree is greater than a preset threshold, and determine the target account as an abnormal account.

[0011] In an exemplary embodiment, the above-mentioned first acquisition module includes: a first interception sub-module, used to intercept voice with voice quality greater than a preset quality threshold during the voice call with the above-mentioned target voice account, to obtain the above-mentioned target voice data; a first acquisition sub-module, used to obtain N of the above-mentioned voice data based on the account tags of the above-mentioned N accounts, wherein the above-mentioned account tags are used to indicate the abnormal situation of the above-mentioned accounts, and the above-mentioned voice data include abnormal voice data of the above-mentioned abnormal accounts.

[0012] In an exemplary embodiment, the first acquisition submodule includes: a first acquisition unit, used to acquire first voice data information of the first account and second voice data information of the second account from a registration table, wherein the account label of the first account is an abnormal label, the first account is the abnormal account, and the first voice data information is used to describe information of the abnormal voice data; the account label of the second account is a normal label, the second account is a normal account, and the second voice data information is used to describe information of normal voice data; a second acquisition unit, used to acquire the first voice data of the first account from a voiceprint database based on storage information of the abnormal voice data in the first voice data information, wherein the first voice data is the abnormal voice data; a third acquisition unit, used to acquire the second voice data of the second account from the voiceprint database based on storage information of the normal voice data in the second voice data information, wherein the second voice data is the normal voice data.

[0013] In an exemplary embodiment, the first calculation module includes: a first calculation submodule, which is used to calculate the feature matching degree between the voice features of the first voice data of the first account among the M accounts and the voice features of the target voice data, to obtain the first voice feature matching degree, wherein the account label of the first account is an abnormal label, the first voice data is abnormal voice data, and the voice feature matching degree includes the first voice feature matching degree; a second calculation submodule, which is used to calculate the feature matching degree between the voice features of the second voice data of the second account among the M accounts and the voice features of the target voice data when the first voice feature matching degree is less than the preset threshold, to obtain the second voice feature matching degree, wherein the account label of the second account is a normal label, the second voice data is normal voice data, and the voice feature matching degree includes the second voice feature matching degree.

[0014] In an exemplary embodiment, the first determination module includes: a first determination submodule, used to determine that the target voice data is abnormal when the first voice feature matching degree is greater than the preset threshold, and determine the target account as the abnormal account; or, a second determination submodule, used to determine that the target voice data is abnormal when the first voice feature matching degree is less than or equal to the preset threshold, and the second voice feature matching degree is greater than the preset threshold, and determine the target account as the abnormal account.

[0015] In an exemplary embodiment, the device further includes: a first storage module for storing the target voice data into an abnormal voiceprint database; and a first recording module for recording the target voice data information of the target voice data into an abnormal registration table.

[0016] According to another embodiment of the present application, a computer program product is provided, including a computer program, wherein the computer program is configured for a processor to execute the steps of any of the above method embodiments.

[0017] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to enable a processor to execute the steps in any of the above method embodiments.

[0018] According to another embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor is configured to execute the computer program to perform the steps in any one of the method embodiments.

[0019] Through this application, the target voice data of the target voice account and the voice data of N accounts are obtained, and based on the account labels of the N accounts, the voice feature matching degree between the voice data of the M accounts and the target voice data is calculated in a preset label order. When the voice feature matching degree is greater than a preset threshold, it is determined that the target voice data is abnormal, and the target account is determined as an abnormal account. Since the present application can calculate the voice feature matching degree based on the account label in a preset label order, it is possible to analyze specific types of accounts in a targeted manner, thereby improving the targetedness and efficiency of detection. At the same time, by setting a preset threshold, it is possible to automatically determine whether the target voice data is abnormal, reducing manual intervention and improving the speed and accuracy of detection. Therefore, the problem of not being able to efficiently determine whether an account is abnormal in the related art is solved, and the effect of efficiently determining account abnormalities is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a hardware structure block diagram of a mobile terminal of a method for determining an abnormal account in an embodiment of the present application;

[0021] Figure 2 is a flow chart of a method for determining an abnormal account according to an embodiment of the present application;

[0022] Figure 3 It is a schematic diagram of a method for determining an abnormal account in a specific embodiment of the present application;

[0023] Figure 4This is a process of determining an abnormal account in a specific embodiment of the present application Figure 1 ;

[0024] Figure 5 This is a process of determining an abnormal account in a specific embodiment of the present application Figure 2 ;

[0025] Figure 6 It is a structural block diagram of a device for determining an abnormal account according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0028] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal of a method for determining an abnormal account in an embodiment of the present application. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0029] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as a computer program corresponding to a method for determining an abnormal account in an embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0030] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] In this embodiment, a method for determining abnormal accounts is provided. Figure 2 is a flow chart of a method for determining an abnormal account according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:

[0032] Step S202, during a voice call with a target voice account of a target account, obtaining target voice data and voice data of N accounts, wherein the target voice data is sound data obtained through the target voice account when the target voice account is connected, and the voice data is sound data obtained through the voice account when the voice account corresponding to the account is connected;

[0033] Optionally, the party having the voice call with the voice account of the target account includes but is not limited to manual customer service and intelligent customer service of the financial institution.

[0034] Optionally, the target account is an account of the opening bank. The target voice account is a phone number bound to the target account. The voice accounts of the N accounts are different from the target voice account of the target account.

[0035] Step S204, based on the account tags of the N accounts, and in a preset tag order, calculating the voice feature matching degree between the voice data of the M accounts and the target voice data, wherein the M is a natural number less than or equal to the N;

[0036] Optionally, the account tag is used to indicate whether the target account is an abnormal account.

[0037] Step S206: When the voice feature matching degree is greater than a preset threshold, it is determined that the target voice data is abnormal, and the target account is determined as an abnormal account.

[0038] Optionally, the abnormal account indicates that the object having a voice call with the customer service through the target voice account of the target account is the same object as the object having a voice call with the customer service through the voice account of another account.

[0039] In this embodiment, the execution subject of the above steps can be a terminal, a server, a specific processor set in the terminal or server, or a processor or processing device set relatively independently from the terminal or server, but is not limited to this, such as an abnormal account identification system.

[0040] Alternatively, if Figure 3 As shown, Figure 3 It is a schematic diagram of a method for determining an abnormal account in a specific embodiment of the present application. The communication platform module provides basic call services and collects voices. The user center module obtains the target voice data and the voice data of N accounts from the communication platform module through the business application module based on the voice-related interface, and calls the abnormal voice recognition and voice basic services in the voice service module based on the account labels of N accounts, and calculates the voice feature matching degree between the voice data of M accounts and the target voice data according to the preset label order, thereby determining the abnormal situation of the target account and marking the target account label. The business application module displays the determined target account label from the user center module to the customer service for viewing based on the voice-related interface.

[0041] Through the above steps, the target voice data of the target voice account and the voice data of N accounts are obtained, and based on the account labels of the N accounts, the voice feature matching degree between the voice data of the M accounts and the target voice data is calculated in a preset label order. When the voice feature matching degree is greater than the preset threshold, it is determined that the target voice data is abnormal, and the target account is determined as an abnormal account. Since the present application can calculate the voice feature matching degree based on the account label in a preset label order, it is possible to analyze specific types of accounts in a targeted manner, thereby improving the targetedness and efficiency of detection. At the same time, by setting a preset threshold, it is possible to automatically determine whether the target voice data is abnormal, thereby reducing manual intervention and improving the speed and accuracy of detection. Therefore, the problem of not being able to efficiently determine whether an account is abnormal in the related art is solved, and the effect of efficiently determining account abnormalities is achieved.

[0042] In an exemplary embodiment, during a voice call with a target voice account of a target account, target voice data and voice data of N accounts are obtained, including: during the voice call with the target voice account, voice with voice quality greater than a preset quality threshold is intercepted to obtain the target voice data; based on the account tags of the N accounts, the N voice data are obtained, wherein the account tags are used to indicate abnormal conditions of the accounts, and the voice data include abnormal voice data of the abnormal accounts.

[0043] Optionally, the indicators for evaluating voice quality include, but are not limited to, signal strength, clarity, volume level, and other indicators. Only when the voice quality is higher than a preset quality threshold will the voice be intercepted and saved to ensure that the voice data has sufficient clarity and integrity. The preset quality threshold can be dynamically adjusted based on the application scenario or voice scenario. For example, if the environment is noisy and the voice is unclear, the preset quality threshold can be lowered.

[0044] This embodiment only captures voice data with voice quality greater than a preset quality threshold, thereby excluding voice segments that may affect the analysis results due to signal interference, noise or other quality issues. This ensures that the voice data used for analysis is clear and reliable, thereby achieving the purpose of improving the accuracy of anomaly detection.

[0045] This embodiment achieves the purpose of targeted anomaly detection by acquiring voice data of N accounts based on account tags and paying special attention to abnormal voice data of abnormal accounts. At the same time, by calculating the voice feature matching degree in a preset tag sequence, the voice data of a large number of accounts can be automatically and quickly analyzed, achieving the purpose of significantly improving processing efficiency.

[0046] In an exemplary embodiment, based on the account tags of the N accounts, the N voice data are obtained, including: obtaining first voice data information of the first account and second voice data information of the second account from a registration table, wherein the account tag of the first account is an abnormal tag, the first account is the abnormal account, and the first voice data information is used to describe information of the abnormal voice data, and the account tag of the second account is a normal tag, the second account is a normal account, and the second voice data information is used to describe information of normal voice data; based on the storage information of the abnormal voice data in the first voice data information, obtaining the first voice data of the first account from a voiceprint database, wherein the first voice data is the abnormal voice data; based on the storage information of the normal voice data in the second voice data information, obtaining the second voice data of the second account from the voiceprint database, wherein the second voice data is the normal voice data.

[0047] Optionally, the financial institution first needs to establish a registry containing account tags, which are used to identify abnormal situations of accounts. For example, if an account is marked with an abnormal tag, it means that the account is suspected of anti-collection behavior.

[0048] Optionally, for an account marked as abnormal (first account), the first voice data information associated with the account will be obtained from the registry, and the first voice data information includes but is not limited to the storage information of the first voice data, the first account identifier, the voice account number, and the first voice data identifier. Similarly, for an account marked as normal (second account), the second voice data information will be obtained, and the second voice data information includes but is not limited to the storage information of the second voice data, the second account identifier, the voice account number, and the second voice data identifier.

[0049] Optionally, the storage information includes but is not limited to the path, name, and identifier of the recording file storing the voice data. Based on the path, name, and identifier of the recording file in the storage information, the voice data of the first account is retrieved from the voiceprint database. These data are abnormal voice data and may contain voice features of anti-collection behavior. Similarly, the voice data of the second account is also retrieved from the voiceprint database. These data are abnormal voice data.

[0050] This embodiment achieves the purpose of improving the efficiency of abnormal account identification and anti-collection behavior identification capabilities by accurately distinguishing and analyzing the voice data of abnormal and normal accounts.

[0051] In an exemplary embodiment, based on the account labels of the N accounts above, and according to the preset label order, the voice feature matching degree between the voice data of the M accounts above and the target voice data is calculated, including: calculating the feature matching degree between the voice features of the first voice data of the first account among the M accounts and the voice features of the target voice data to obtain the first voice feature matching degree, wherein the account label of the first account is an abnormal label, the first voice data is abnormal voice data, and the voice feature matching degree includes the first voice feature matching degree; when the first voice feature matching degree is less than the preset threshold, calculating the feature matching degree between the voice features of the second voice data of the second account among the M accounts and the voice features of the target voice data to obtain the second voice feature matching degree, wherein the account label of the second account is a normal label, the second voice data is normal voice data, and the voice feature matching degree includes the second voice feature matching degree.

[0052] Optionally, when determining whether the target account is an abnormal account, the collection department of the consumer finance company will analyze the matching degree of the voice features. The specific process is as follows: First, the voice features of the target historical voice data and the voice features of the voice data in the current voice call are extracted respectively. The voice features include but are not limited to voiceprint features, speech speed features, pitch features, and the frequency of use of specific words. Through an artificial intelligence algorithm, such as a deep neural network or a recurrent neural network, the voice data is analyzed to extract the voice features of the first voice data, the voice features of the second voice data, and the voice features of the target voice data. The first voice feature matching degree and the second voice feature matching degree are calculated using a feature matching algorithm. The voice feature matching degree can be the Euclidean distance between the two feature vectors, the cosine similarity, or other applicable metrics. In order to improve the efficiency of abnormal account identification, the first voice feature matching degree between the abnormal voice data and the target voice data is first calculated. If the first voice feature matching degree is less than a preset threshold, the second voice feature matching degree between the normal voice data and the target voice data is further calculated.

[0053] In an exemplary embodiment, when the voice feature matching degree is greater than a preset threshold, it is determined that the target voice data is abnormal, and the target account is determined as an abnormal account, including: when the first voice feature matching degree is greater than the preset threshold, it is determined that the target voice data is abnormal, and the target account is determined as the abnormal account; or, when the first voice feature matching degree is less than or equal to the preset threshold, and the second voice feature matching degree is greater than the preset threshold, it is determined that the target voice data is abnormal, and the target account is determined as the abnormal account.

[0054] This embodiment further checks the matching degree of the second voice feature when the matching degree of the first voice feature does not exceed the threshold. This multi-level detection mechanism can ensure that anomalies can be accurately identified in different situations, and achieves efficient identification of whether there is an abnormal situation of multiple accounts with one person in the target account.

[0055] In an exemplary embodiment, when the voice feature matching degree is greater than a preset threshold, it is determined that the target voice data is abnormal, and after the target account is determined as an abnormal account, the method further includes: storing the target voice data in an abnormal voiceprint database; and recording the target voice data information of the target voice data in an abnormal registration table.

[0056] Optionally, the registry includes an abnormal account registry and a normal account registry. The voiceprint database includes an abnormal voiceprint database and a normal voiceprint database.

[0057] Optionally. Figure 4 As shown, Figure 4 This is a process of determining an abnormal account in a specific embodiment of the present application Figure 1 , S402, the voice service module counts abnormal language data through a scheduled task;

[0058] S404, the batch run results are output to the voiceprint database in the form of files;

[0059] S406, the user center module notifies the user through the interface to process abnormal voice data;

[0060] S408, the user records the abnormal voice data in the voiceprint database into the abnormal registration table;

[0061] S410, updating the label of the abnormal account.

[0062] The present invention will be described below in conjunction with specific embodiments:

[0063] This embodiment is explained by using the confirmation of the target account in a manual customer service or intelligent customer service scenario. Figure 5 This is a process of determining an abnormal account in a specific embodiment of the present application Figure 2 , including the following steps:

[0064] S502, start, the first subject calls in or the artificial or intelligent customer service of the financial institution calls out, enters the customer service workbench page, and the first subject makes a voice call with the artificial or intelligent customer service through the target voice bound to the target account;

[0065] S504, the user center module feeds back account information and account labels to the business application module, including but not limited to: target account identifier, target voice account number, and normal label;

[0066] S506, the customer service workstation displays to the manual customer service or the intelligent customer service that the target account is a normal account;

[0067] S508, after the voice call is connected, the first subject has a voice call with the manual or intelligent customer service through the target voice account;

[0068] S510, the communication platform module calls the call extraction interface, continuously evaluates the voice quality during the voice call, and checks indicators such as signal strength, clarity, and volume level. For example, the preset voice quality threshold is that the signal-to-noise ratio is greater than 70db. After the voice call starts, the detected signal-to-noise ratio is 75db. 5 seconds after the call starts, the signal-to-noise ratio stabilizes above 75db. From this point in time, the next 10 seconds of voice are intercepted, that is, from the 5th second to the 15th second. After intercepting 10 seconds of high-quality voice clips, it is determined as the target voice data. The target voice data is saved in the recording file under the path specified in the storage module;

[0069] S512, the business application module obtains the target voice data from the storage module based on the path and file name of the recording file returned by the communication platform module;

[0070] S514, the business application module sends the target voice account and target voice data of the target account to the user center module;

[0071] S516, the user center module obtains the target voice data information of the target account from the registration table according to the target voice account and the target account;

[0072] S518, based on the target voice data information, determine whether there is historical voice data of the target account in the voiceprint database, if yes, go to S520, otherwise go to S532 to register the voice call;

[0073] S520, based on the account tag of the account, obtain abnormal voice data information of the abnormal account from the abnormal registration table, and obtain abnormal voice data according to the storage information of the abnormal voice data in the abnormal voice data information. Obtain normal voice data information of the normal account from the normal registration table, and obtain normal voice data according to the storage information of the normal voice data in the normal voice data information;

[0074] S522, determine the voice feature matching degree between the target voice data and the abnormal voice data and the normal voice data. First, perform semantic filtering operation on the target voice data, and use audio processing algorithms (such as noise threshold, spectrum analysis) to identify and remove background noise therein, such as environmental sound, other people's voices, etc., to ensure that the extracted voice features only come from the first object. Similarly, semantic filtering is also performed on abnormal voice data and normal voice data to remove background noise. For example, there is a call record in the target voice data that contains noisy background sound of a coffee shop. Use a spectrum analysis algorithm to identify and filter out the background noise, and only retain the clear human voice part. Then, perform standardization operations on the above voice data and perform preprocessing, for example, adjust the volume and frequency response to unify the audio benchmark to ensure that the voiceprint feature comparison between different voice data is performed under the same conditions. Then, use a feature matching algorithm to calculate the voice feature matching degree, which can be the Euclidean distance, cosine similarity or other applicable metrics between two feature vectors. If the voice feature matching degree is less than the preset threshold, it is preliminarily determined that the voiceprint of the current call is inconsistent with the voiceprint features in the historical voice data;

[0075] S524, saving the calculated voice feature matching degree;

[0076] S526: If the voice feature match between the target voice data and the abnormal voice data is greater than a preset threshold, the target account is determined to be an abnormal account, and there are multiple accounts with one person; or if the voice feature match between the target voice data and the abnormal voice data is less than a preset threshold, and the voice feature match of the normal voice data is greater than a preset threshold, the target account is determined to be an abnormal account, and there are multiple accounts with one person. Feedback the abnormal situation of the target account to the business application module;

[0077] S528, the customer service workstation displays the abnormal situation of the target account to the human customer service or the intelligent customer service, and the human customer service or the intelligent customer service can adjust the call strategy accordingly, increase vigilance and perform additional verification steps;

[0078] S530, saving the abnormal situation of the target account in the record of the voice call, where the fields in the record include but are not limited to: identification information of the target account, voice account number, voice call record number, voice feature matching degree, abnormal label of the target account, and effective time of the abnormal label;

[0079] S532, the user center module determines that there is no historical voice data of the target account in the voiceprint database based on the registration table, and feeds back a voiceprint unregistered prompt to the manual customer through the business application module, and then asynchronously processes the registration process;

[0080] S534, the user center module calls the voiceprint service interface to trigger the voiceprint registration of the voice service module;

[0081] S536, the voice service module uses the user center voiceprint identification interface to obtain the target voice account number and target voice data of the target account for voiceprint registration;

[0082] S538, registration is successful, the user center module saves the voiceprint registration information to the target account's registry, the fields in the registry include but are not limited to: target account identification information, voice account number, voice call record number, recording file name, recording file path, first object identifier. After registration is completed, go to S522 and start executing abnormal confirmation;

[0083] S540, end.

[0084] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0085] In this embodiment, a device for determining an abnormal account is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0086] Figure 6 is a structural block diagram of a device for determining an abnormal account according to an embodiment of the present application, such as Figure 6 As shown, the device comprises:

[0087] The first acquisition module 602 is used to acquire target voice data and voice data of N accounts during a voice call with a target voice account of a target account, wherein the target voice data is sound data acquired through the target voice account when the target voice account is connected, and the voice data is sound data acquired through the voice account when the voice account corresponding to the account is connected;

[0088] A first calculation module 604 is used to calculate the voice feature matching degree between the voice data of the M accounts and the target voice data based on the account tags of the N accounts and in a preset tag order, wherein the M is a natural number less than or equal to the N.

[0089] The first determination module 606 is used to determine that the target voice data is abnormal when the voice feature matching degree is greater than a preset threshold, and determine the target account as an abnormal account.

[0090] In an exemplary embodiment, the above-mentioned first acquisition module includes: a first interception sub-module, used to intercept voice with voice quality greater than a preset quality threshold during the voice call with the above-mentioned target voice account, to obtain the above-mentioned target voice data; a first acquisition sub-module, used to obtain N of the above-mentioned voice data based on the account tags of the above-mentioned N accounts, wherein the above-mentioned account tags are used to indicate the abnormal situation of the above-mentioned accounts, and the above-mentioned voice data include abnormal voice data of the above-mentioned abnormal accounts.

[0091] In an exemplary embodiment, the first acquisition submodule includes: a first acquisition unit, used to acquire first voice data information of the first account and second voice data information of the second account from a registration table, wherein the account label of the first account is an abnormal label, the first account is the abnormal account, and the first voice data information is used to describe information of the abnormal voice data; the account label of the second account is a normal label, the second account is a normal account, and the second voice data information is used to describe information of normal voice data; a second acquisition unit, used to acquire the first voice data of the first account from a voiceprint database based on storage information of the abnormal voice data in the first voice data information, wherein the first voice data is the abnormal voice data; a third acquisition unit, used to acquire the second voice data of the second account from the voiceprint database based on storage information of the normal voice data in the second voice data information, wherein the second voice data is the normal voice data.

[0092] In an exemplary embodiment, the above-mentioned first calculation module includes: a first calculation submodule, which is used to calculate the feature matching degree between the voice features of the first voice data of the first account among the M accounts and the voice features of the target voice data, so as to obtain the first voice feature matching degree, wherein the account label of the above-mentioned first account is an abnormal label, the above-mentioned first voice data is the above-mentioned abnormal voice data, and the above-mentioned voice feature matching degree includes the above-mentioned first voice feature matching degree; a second calculation submodule, which is used to calculate the feature matching degree between the voice features of the second voice data of the second account among the M accounts and the voice features of the target voice data when the first voice feature matching degree is less than the above-mentioned preset threshold, so as to obtain the second voice feature matching degree, wherein the account label of the above-mentioned second account is a normal label, the above-mentioned second voice data is normal voice data, and the above-mentioned voice feature matching degree includes the above-mentioned second voice feature matching degree.

[0093] In an exemplary embodiment, the first determination module includes: a first determination submodule, used to determine that the target voice data is abnormal when the first voice feature matching degree is greater than the preset threshold, and determine the target account as the abnormal account; or, a second determination submodule, used to determine that the target voice data is abnormal when the first voice feature matching degree is less than or equal to the preset threshold, and the second voice feature matching degree is greater than the preset threshold, and determine the target account as the abnormal account.

[0094] In an exemplary embodiment, the device further includes: a first storage module for storing the target voice data into an abnormal voiceprint database; and a first recording module for recording the target voice data information of the target voice data into an abnormal registration table.

[0095] An embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0096] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0097] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0098] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0099] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0100] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0101] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0102] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining abnormal accounts, characterized in that: include: During a voice call with a target voice account of a target account, target voice data and voice data of N accounts are obtained, wherein the target voice data is sound data obtained through the target voice account when the target voice account is connected, and the voice data is sound data obtained through the voice account when the voice account corresponding to the account is connected; Based on the account labels of the N accounts, and in a preset label order, calculating the voice feature matching degree between the voice data of the M accounts and the target voice data, wherein M is a natural number less than or equal to N; When the voice feature matching degree is greater than a preset threshold, it is determined that the target voice data is abnormal, and the target account is determined as an abnormal account.

2. The method according to claim 1, characterized in that During a voice call with a target voice account of a target account, the target voice data and the voice data of N accounts are obtained, including: During the voice call with the target voice account, intercepting voice with voice quality greater than a preset quality threshold to obtain the target voice data; Based on the account tags of the N accounts, N voice data are obtained, wherein the account tag is used to indicate an abnormal situation of the account, and the voice data includes abnormal voice data of the abnormal account.

3. The method according to claim 2, characterized in that Based on the account tags of the N accounts, obtaining the N voice data includes: Acquire first voice data information of a first account and second voice data information of a second account from a registry, wherein the account tag of the first account is an abnormal tag, the first account is the abnormal account, the first voice data information is used to describe information of the abnormal voice data, the account tag of the second account is a normal tag, the second account is a normal account, and the second voice data information is used to describe information of normal voice data; Based on the storage information of the abnormal voice data in the first voice data information, obtaining the first voice data of the first account from the voiceprint database, wherein the first voice data is the abnormal voice data; Based on the storage information of the normal voice data in the second voice data information, the second voice data of the second account is obtained from the voiceprint database, wherein the second voice data is the normal voice data.

4. The method according to claim 1, characterized in that: Based on the account labels of the N accounts, and in a preset label order, calculating the voice feature matching degree between the voice data of the M accounts and the target voice data, including: Calculate a feature matching degree between a voice feature of first voice data of a first account among the M accounts and a voice feature of the target voice data to obtain a first voice feature matching degree, wherein the account label of the first account is an abnormal label, the first voice data is abnormal voice data, and the voice feature matching degree includes the first voice feature matching degree; When the first voice feature matching degree is less than the preset threshold, the feature matching degree between the voice features of the second voice data of the second account among the M accounts and the voice features of the target voice data is calculated to obtain the second voice feature matching degree, wherein the account label of the second account is a normal label, the second voice data is normal voice data, and the voice feature matching degree includes the second voice feature matching degree.

5. The method according to claim 4, characterized in that When the voice feature matching degree is greater than a preset threshold, determining that the target voice data is abnormal, and determining the target account as an abnormal account includes: When the first voice feature matching degree is greater than the preset threshold, it is determined that the target voice data is abnormal, and the target account is determined as the abnormal account; or When the first voice feature matching degree is less than or equal to the preset threshold and the second voice feature matching degree is greater than the preset threshold, it is determined that the target voice data is abnormal and the target account is determined as the abnormal account.

6. The method according to claim 1, characterized in that When the voice feature matching degree is greater than a preset threshold, it is determined that the target voice data is abnormal, and after determining the target account as an abnormal account, the method further includes: storing the target voice data in an abnormal voiceprint database; The target voice data information of the target voice data is recorded in an abnormal registration table.

7. A device for determining an abnormal account, characterized in that: include: A first acquisition module is used to acquire target voice data and voice data of N accounts during a voice call with a target voice account of a target account, wherein the target voice data is sound data acquired through the target voice account when the target voice account is connected, and the voice data is sound data acquired through the voice account when the voice account corresponding to the account is connected; A first calculation module, configured to calculate, based on the account tags of the N accounts, the voice feature matching degree between the voice features of the M voice data and the target voice data in a preset tag order, wherein M is a natural number less than or equal to N; The first determination module is used to determine that there is an abnormality in the target voice data and determine that the target account is an abnormal account when the voice feature matching degree is greater than a preset threshold.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 6 when executed by a processor.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 6 are implemented.

Images