Business processing method and device, equipment and medium

Abstract

The invention relates to a business processing method and device, equipment and a medium, and relates to the technical field of Internet and artificial intelligence. The method comprises the following steps: according to a transaction behavior mode associated with a client and an object feature associated with a login object of the client, identifying whether a service operation currently executed by the client triggers a set risk control strategy; if yes, key features are extracted from service information associated with the service operation; wherein the key feature comprises at least one of a field value, a service type and a service purpose of a specified service field; determining a target identity authentication process from a plurality of identity authentication processes based on the key features and the transaction behavior mode; and executing the target identity authentication process on the client to obtain an authentication result, and determining whether to allow the client to execute the service operation based on the authentication result. Therefore, high-risk business operation executed by a non-user himself / herself can be effectively blocked in time, and financial security is guaranteed.

Description

Technical Field

[0001] The present disclosure relates to the fields of Internet and artificial intelligence technology, and in particular to business processing methods, devices, equipment and media. Background Art

[0002] With the rise of digital financial business models and the rapid development of mobile banking, more and more users, with the help of financial technology, use terminals (such as smartphones, tablets, etc.) to handle banking-related services, such as transfers and loans.

[0003] However, in actual business scenarios, when users conduct banking business at the terminal, the business operations they perform may be high-risk operations. At this time, for the purpose of risk prevention, it is very important to conduct security verification of users to ensure financial security. Summary of the invention

[0004] The present disclosure provides a business processing method, apparatus, device and medium to solve one of the technical problems in the related art at least to a certain extent. The technical solution of the present disclosure is as follows:

[0005] According to a first aspect of an embodiment of the present disclosure, a service processing method is provided, including:

[0006] Identify whether a business operation currently executed by the client triggers a set risk control strategy based on a transaction behavior pattern associated with the client and an object feature associated with a login object of the client;

[0007] In the case where the business operation triggers the set risk control strategy, extracting key features from business information associated with the business operation; wherein the key features include at least one of a field value of a specified business field, a business type, and a business purpose;

[0008] Determining a target identity authentication process from a plurality of identity authentication processes based on the key features and the transaction behavior pattern;

[0009] The target identity authentication process is executed on the client to obtain an authentication result, and based on the authentication result, it is determined whether the client is allowed to execute the business operation.

[0010] According to a second aspect of an embodiment of the present disclosure, a service processing device is provided, including:

[0011] An identification module, used to identify whether a business operation currently executed by the client triggers a set risk control strategy based on a transaction behavior pattern associated with the client and an object feature associated with a login object of the client;

[0012] An extraction module, configured to extract key features from business information associated with the business operation when the business operation triggers the set risk control strategy; wherein the key features include at least one of a field value of a specified business field, a business type, and a business purpose;

[0013] A determination module, configured to determine a target identity authentication process from a plurality of identity authentication processes based on the key features and the transaction behavior pattern;

[0014] The execution module is used to execute the target identity authentication process on the client, obtain an authentication result, and determine whether to allow the client to execute the business operation based on the authentication result.

[0015] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the business processing method proposed in the above-mentioned first aspect of the present disclosure.

[0016] According to the fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the business processing method proposed in the first aspect of the present disclosure.

[0017] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, including: a computer program, which implements the business processing method as described in the above embodiment of the present disclosure when executed by a processor.

[0018] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0019] When a client performs a high-risk business operation, it can be achieved that key features are extracted from all business information associated with the high-risk business operation, and based on the key features and the transaction behavior pattern associated with the client, the target identity authentication process to be executed is determined from multiple identity authentication processes, and then the target identity authentication process is executed on the client to confirm whether the high-risk business operation is a business operation performed by the client's login object. This can achieve timely and effective blocking of high-risk business operations performed by non-users themselves, thereby ensuring financial security.

[0020] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0022] Figure 1 It is a flowchart of the business processing method shown in the first embodiment of the present disclosure.

[0023] Figure 2 It is a flowchart of a business processing method shown in the second embodiment of the present disclosure.

[0024] Figure 3 It is a flowchart of a business processing method shown in the third embodiment of the present disclosure.

[0025] Figure 4 It is a flowchart of a business processing method shown in the fourth embodiment of the present disclosure.

[0026] Figure 5 It is a flowchart of a business processing method shown in the fifth embodiment of the present disclosure.

[0027] Figure 6 It is a flowchart of a business processing method shown in the sixth embodiment of the present disclosure.

[0028] Figure 7 It is a schematic diagram of the device switching login process shown in an embodiment of the present disclosure.

[0029] Figure 8 It is a schematic diagram of the transfer process shown in the embodiment of the present disclosure.

[0030] Fig. 9 It is a structural diagram of a business processing device shown in the seventh embodiment of the present disclosure.

[0031] Fig.10 It is a schematic structural diagram of an electronic device shown in an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0034] It should be noted that the acquisition, storage, use, and processing of data in the technical solution disclosed in this disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0035] It should also be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0036] It should also be noted that in the embodiments of the present disclosure, certain software, components, models and other existing solutions in the industry may be mentioned, which should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present disclosure, but it does not mean that the applicant has or will necessarily use the solution.

[0037] With the rapid development of mobile banking, the financial industry has become a hard-hit area for network security issues. Mobile financial security issues need to be addressed urgently, and users' demand for security and convenience is growing.

[0038] In the related technologies, in order to ensure the security of logging into mobile banking with a different device, the following solutions are mainly used:

[0039] The first one adopts the concept of strongly bound devices. Users must bind a commonly used device to perform high-risk financial operations, such as large-value transfer operations, loan operations, etc. At this time, the user's login operations and other business operations on the strongly bound device are considered normal. If the user needs to change the device to log in, the user needs to unbind the original device.

[0040] This solution has certain defects. For example, many users do not know that they need to unbind the original device in advance. After the user's original device is lost or sold second-hand, the user finds that they cannot log in. At this time, the user needs to go to the branch counter to unbind the original device before logging in on the new device.

[0041] The second method is to conduct security verification on users when logging in with a different device, such as face recognition verification with liveness detection, SMS verification code plus login password, etc. However, the recognition success rate of face recognition cannot reach 100%, and there is a possibility that users can use pre-recorded videos to pass the test. In addition, some users' original face images have not been updated for a long time, or the images are blurred and cannot be successfully compared. At this time, users can also be given the option to verify their bank card passwords, but bank card password verification occurs before the user logs in, and requires comprehensive identity verification, so users need to enter more elements, and the user experience is average.

[0042] It should be noted that business operations such as large-value transfers and loans are also high-risk operations. When a user is detected performing a high-risk business operation, if the user changes the device to log in, the user's IP address changes, or the user's longitude and latitude change, a security verification method can be added to ensure financial security.

[0043] The above-mentioned method of binding mobile banking with commonly used devices requires that when a user changes the device to log in, the user needs to unbind the original device and then log in with the new device. However, most users are not aware that they need to unbind the original device when logging in with a different device. Some users lose their original devices or trade them in second-hand, and then find that they cannot log in with the new device. They need to go to the branch counter to unbind the device, which brings great inconvenience to the users.

[0044] In any embodiment of the present disclosure, in order to solve the problem of having to go to a branch counter to unbind when logging in to a different device, a random two of multiple security verification methods plus a fixed combination can be used to perform security verification for logging in to a different device. This solution can ensure the security of logging in to a different device and also brings convenience to users.

[0045] In any embodiment of the present disclosure, in order to solve the security problem of changing device login, when a high-risk user changes device login, security verification methods such as video customer service, voiceprint authentication, AI (Artificial Intelligence) customer service, and manual customer service can be added. For example, when a user changes device to log in to mobile banking, or when a user performs high-risk operations such as large transfers and loans, if the user is identified as a high-risk user, two random security verification methods such as face recognition, voiceprint, video customer service, SMS verification code, and bank card password can be used to verify whether the user is operating in person.

[0046] In summary, in order to solve at least one of the above problems, the present disclosure proposes a business processing method, device, equipment and medium. Before describing the embodiments of the present disclosure in detail, for the sake of easy understanding, the commonly used technical terms are first introduced:

[0047] IP address: refers to the Internet Protocol Address. The IP address is a unique identifier for each device on the Internet (such as computers, mobile phones, etc.) and is used to locate the device on the network.

[0048] Video customer service: It is mainly used in remote business processing, video face-to-face signing and other financial, financial, insurance, medical, education and other industries. It can provide vivid images, increase appeal and persuasiveness, and give users an immersive and comfortable experience. It can also interact with users at any time. The information generated in this series of processes can be automatically recorded. Video customer service combines the risk control needs of the financial industry. When high-risk users perform high-risk operations such as changing devices to log in or transferring large amounts, they can verify the identity of the user, eliminating the need for offline outlets, and bringing users a safe and convenient experience.

[0049] Liveness detection: facial recognition is performed through the front camera of the terminal, combined with liveness detection face scanning technology to confirm whether the client's login object is a real person. When logging in to the mobile financial APP (Application) or handling loan business, the liveness detection SDK (Software Development Kit) collects human actions such as blinking and opening the mouth, and compares the face image with the pre-collected face features. When the comparison score exceeds the preset score threshold, it means that the face comparison is successful. In this way, the user's identity can be identified, and random actions can also prevent users from using a pre-recorded video to fool around.

[0050] Biometrics: To facilitate users to quickly log into the device, biometrics can be used to quickly log into the application while ensuring security. Biometrics include user's biological information such as fingerprints, faces and voiceprints, which are used to identify the user.

[0051] Voiceprint features: Voiceprint recognition technology is a type of biometric recognition technology. The sound wave spectrum that carries speech information is a biometric feature composed of more than 100 feature dimensions such as wavelength frequency and intensity. It has the characteristics of stability, measurability, and uniqueness. Voiceprint features can be used to detect the identity of the speaker. Compared with other biometric features, voiceprint features can be used for emotion recognition and determine the user's true intentions. For example, based on big data analysis, voiceprint features of various emotions can be determined, including fear, hesitation, and other emotions.

[0052] The following describes the service processing method, apparatus, device, and medium of the embodiments of the present disclosure with reference to the accompanying drawings.

[0053] Figure 1 It is a flowchart of the business processing method shown in the first embodiment of the present disclosure.

[0054] The business processing method of the embodiment of the present disclosure can be applied to the service end (or server, cloud end).

[0055] like Figure 1 As shown, the service processing method may include the following steps S11 to S14.

[0056] In step S11, whether the business operation currently executed by the client triggers the setting of the risk control strategy is identified based on the transaction behavior pattern associated with the client and the object characteristics associated with the login object of the client.

[0057] The client refers to a software program that runs on an electronic device and provides services to users. The electronic device can be any device with computing capabilities, such as a personal computer, a mobile terminal, etc. The mobile terminal can be a mobile phone, a tablet computer, a personal digital assistant, a wearable device, and other hardware devices with various operating systems, touch screens, and / or display screens.

[0058] Among them, business operations include but are not limited to: transfer operations, loan operations, etc.

[0059] The transaction behavior pattern is obtained by classifying the transaction behavior information associated with the client, wherein the transaction behavior information includes the relevant data generated by the client's login object (i.e., the logged-in user) when conducting transactions, which is used to reveal the transaction behavior pattern, habits, and possible abnormal behavior of the login object. Exemplarily, the transaction behavior information includes, but is not limited to: the transaction amount and transaction time of each transaction, transaction frequency, transaction type (such as transfer, payment, recharge, withdrawal, etc.), transaction object (with which accounts or entities the transaction is conducted, including the payee account, merchant information, etc.), etc.

[0060] Among them, transaction behavior patterns include but are not limited to: frequent large-value transfers, multiple transactions in a short period of time, etc.

[0061] Among them, object characteristics are used to characterize the identity information, behavior patterns, preferences, reputation level, credit status and possible risks of the client's login object.

[0062] Herein, setting a risk control strategy refers to a pre-set risk control strategy. Exemplarily, the set risk control strategy may be an anti-fraud strategy.

[0063] In the embodiment of the present disclosure, when the client performs a business operation, the server can obtain the transaction behavior pattern associated with the client and the object characteristics associated with the client's login object, and based on the transaction behavior pattern and object characteristics, identify whether the business operation currently performed by the client triggers the set risk control strategy.

[0064] If the business operation currently performed by the client does not trigger the set risk control strategy, the client can be allowed to continue to perform the business operation. If the business operation currently performed by the client triggers the set risk control strategy, in order to ensure financial security, subsequent steps can be further performed.

[0065] In step S12, when a business operation triggers the setting of a risk control strategy, key features are extracted from business information associated with the business operation.

[0066] The key feature includes at least one of a field value of a specified business field, a business type, and a business purpose.

[0067] The designated business field refers to a pre-set business field (or transaction field). For example, the designated business field may be a transaction amount or a transaction time.

[0068] Among them, business types include but are not limited to: transfer, loan, withdrawal, etc.

[0069] The business purpose includes but is not limited to: purchasing goods, paying fees, etc. In the embodiment of the present disclosure, when the business operation currently executed by the client triggers the setting of the risk control strategy, the server can further extract key features (such as the field value of the specified business field, the business type and the business purpose) from all business information associated with the business operation executed by the client.

[0070] Exemplarily, when the business operation is a transfer operation, the designated business field may be the transfer amount, and the server may extract the client's transfer amount field value (i.e., the specific amount), business type, and business purpose; when the business operation is a loan operation, the designated business field may be the loan amount, and the server may extract the client's loan amount field value, business type, and business purpose.

[0071] In step S13, a target identity authentication process is determined from a plurality of identity authentication processes based on key features and transaction behavior patterns.

[0072] Among them, a variety of identity authentication processes are pre-configured, including but not limited to: voiceprint authentication process, AI customer service authentication process, manual customer service authentication process, video customer service authentication process, etc.

[0073] In the disclosed embodiment, key features and transaction behavior patterns may be integrated to determine a target identity authentication process to be executed from a variety of identity authentication processes.

[0074] In step S14, a target identity authentication process is performed on the client to obtain an authentication result, and based on the authentication result, it is determined whether the client is allowed to perform a business operation.

[0075] In the disclosed embodiment, the server may perform a target identity authentication process on the client, obtain an authentication result, and determine whether to allow the client to continue to perform the above-mentioned business operation based on the authentication result.

[0076] As an example, when the authentication result indicates that the client's login object has passed the identity authentication, the server can allow the client to continue to perform business operations; when the authentication result indicates that the client's login user has not passed the identity authentication, the server can refuse the client to continue to perform business operations, that is, terminate the business operation.

[0077] The business processing method of the disclosed embodiment can extract key features from all business information associated with the high-risk business operation when the client executes the high-risk business operation, and based on the key features and the transaction behavior pattern associated with the client, determine the target identity authentication process to be executed from multiple identity authentication processes, and then execute the target identity authentication process on the client to confirm whether the high-risk business operation is a business operation performed by the client's login object himself, so as to timely and effectively block high-risk business operations performed by non-users themselves and ensure financial security.

[0078] The present disclosure provides another service processing method. Figure 2 It is a flowchart of a business processing method shown in the second embodiment of the present disclosure.

[0079] It should be noted that the business processing method can be executed alone, or it can be executed in combination with any embodiment of the present disclosure or a possible implementation method in the embodiment, or it can be executed in combination with any technical solution in the related technology, and the embodiments of the present disclosure are not limited to this.

[0080] like Figure 2 As shown, the business processing method may include the following steps S21 to S27.

[0081] In step S21, the transaction behavior information of the client within a set period of time is obtained.

[0082] The set period is a pre-set period, the end time of the set period may be the current time, and the time difference between the end time and the start time of the set period is pre-set. For example, the set period may be a recent time period.

[0083] Among them, transaction behavior information includes relevant data generated by the client's login object (i.e., the logged-in user) when conducting transactions within a set period of time, which is used to reveal the transaction behavior patterns, habits, and possible abnormal behaviors of the login object. Exemplarily, transaction behavior information includes but is not limited to: the transaction amount and transaction time of each transaction, transaction frequency, transaction type (such as transfer, payment, recharge, withdrawal, etc.), transaction object (with which accounts or entities the transaction is conducted, including the payee account, merchant information, etc.), etc.

[0084] In step S22, the transaction behavior information is classified to determine the transaction behavior pattern of the client.

[0085] Among them, transaction behavior patterns include but are not limited to: frequent large-value transfers, multiple transactions in a short period of time, etc.

[0086] As an example, transaction behavior information can be classified based on the classification algorithm in AI technology to obtain the client's transaction behavior pattern.

[0087] In step S23, object features associated with the login object of the client are acquired, and business features are extracted from all business information associated with the business operation.

[0088] Among them, object characteristics are used to characterize the identity information, behavior patterns, preferences, credit status and possible risks of the client's login object.

[0089] In an embodiment of the present disclosure, object features associated with login information of a client may be acquired.

[0090] In any embodiment of the present disclosure, the object features can be obtained by following steps A to C:

[0091] Step A: Get the device information of the device where the client is located.

[0092] The device information includes but is not limited to: device number, device IP address, etc.

[0093] Step B: Obtain object information and context information of the client's login object.

[0094] The object information includes, but is not limited to, basic information such as the age, gender, occupation, and education level of the login object.

[0095] The context information is used to characterize the environmental perception characteristics of the login object, including but not limited to: the current situation information (such as time and location) of the login object, device information, network status, geographic location, etc.

[0096] Step C: Using feature extraction technology, extract features from the above device information, object information and context information to obtain object features.

[0097] In summary, by constructing rich object features, we can more accurately portray user portraits, thereby timely identifying potential risks (such as fraud risks) when user behavior deviates from normal patterns, effectively curbing the occurrence of fraud, and further ensuring financial security.

[0098] In the disclosed embodiment, feature extraction may also be performed on all business information associated with the business operation based on a feature extraction algorithm to obtain business features.

[0099] Exemplarily, the business operation currently executed by the client is taken as a transfer operation for exemplary description, and the business characteristics include but are not limited to: payee information, transferor information, etc.

[0100] In step S24, based on the transaction behavior pattern, object characteristics and business characteristics, it is identified whether the business operation currently executed by the client triggers the setting of risk control strategy.

[0101] Herein, setting a risk control strategy refers to a pre-set risk control strategy. Exemplarily, the set risk control strategy may be an anti-fraud strategy.

[0102] In the disclosed embodiment, the server may identify whether the business operation currently executed by the client triggers the set risk control strategy by combining the transaction behavior pattern, object characteristics and business characteristics of the client.

[0103] As a possible implementation method, the server may be provided with a designated list (or blacklist), wherein the designated list includes the name of at least one user whose credibility is below a threshold. In the present disclosure, when the business operation is a transfer operation, it may be determined whether the name of the payee in the business feature is in the designated list. If so, it is determined that the business operation currently executed by the client triggers the setting of a risk control strategy.

[0104] As another possible implementation, when the transaction behavior pattern is frequent transfers or multiple transactions in a short period of time, it can be determined that the business operation currently executed by the client triggers the setting of a risk control strategy.

[0105] As another possible implementation, when the object feature indicates that the device IP address of the login object has changed, it can be determined that the business operation currently executed by the client triggers the setting of the risk control policy.

[0106] As another possible implementation, when the object feature indicates a short-term change in the longitude and latitude of the login object, it can be determined that the business operation currently executed by the client triggers the setting of a risk control policy.

[0107] As another possible implementation, when the object characteristics indicate that the login object is a high-risk and easily deceived person (for example, the login object is over 55 years old and the gender is a specified gender), it can be determined that the business operation currently executed by the client triggers the setting of a risk control policy.

[0108] It should be understood that other algorithms may also be used to identify whether the business operation currently performed by the client triggers the setting of a risk control strategy based on transaction behavior patterns, object characteristics, and business characteristics, and the embodiments of the present disclosure are not limited to this.

[0109] In step S25, when a business operation triggers the setting of a risk control policy, key features are extracted from business information associated with the business operation.

[0110] The key feature includes at least one of a field value of a specified business field, a business type, and a business purpose.

[0111] In step S26, a target identity authentication process is determined from a plurality of identity authentication processes based on the key features and transaction behavior patterns.

[0112] For explanations of steps S25 to S26, reference may be made to the relevant descriptions in any embodiment of the present disclosure and will not be repeated here.

[0113] In any embodiment of the present disclosure, the target identity authentication process can be determined by following steps E to G:

[0114] Step E: Determine a candidate identity authentication process that matches the key feature from among multiple identity authentication processes.

[0115] Among them, different identity authentication processes are adapted to different field values ​​with different value ranges, that is, each identity authentication process has a corresponding value range. In addition, different identity authentication processes may be adapted to different business types and business purposes.

[0116] In the present disclosure, a candidate identity authentication process adapted to the key feature can be determined from a variety of identity authentication processes according to the key feature associated with the business operation currently executed by the client.

[0117] Taking the example of a key feature including a field value of a specified business field, the value range of multiple identity authentication processes can be queried based on the field value of the specified business field to determine a target identity authentication process from the multiple identity authentication processes; wherein the field value of the specified business field is within the value range of the target identity authentication process.

[0118] Step F: Determine the risk level of the client's business operations based on the transaction behavior pattern.

[0119] Exemplarily, the correspondence between different transaction behavior patterns and risk levels may be preconfigured, so that in the present disclosure, the above correspondence may be queried according to the transaction behavior pattern associated with the client to determine the risk level of the client performing the business operation.

[0120] As an example, when the transaction behavior pattern is frequent large-value transfers or multiple transactions in a short period of time, the risk level is relatively high; when the transaction behavior pattern is stable transaction frequency, stable transaction amount or transactions with compliant transaction partners, the risk level is relatively low.

[0121] Step G: Determine a target authentication process from the candidate authentication processes based on the risk level.

[0122] Exemplarily, the correspondence between different risk levels and identity authentication processes can be pre-configured, so that in the present disclosure, the above correspondence can be queried according to the risk level of the business operation executed by the client to determine the target identity authentication process to be executed from the candidate identity authentication processes.

[0123] As an example, when the risk level is relatively low (for example, the risk level is lower than the first set level), the target identity authentication process may include a voiceprint authentication process; when the risk level is relatively high (for example, the risk level is higher than the second set level, where the second set level is higher than the first set level), the target identity authentication process may include a video customer service authentication process; when the risk level is between the first set level and the second set level, the target identity authentication process may include an AI customer service authentication process and / or a manual customer service authentication process.

[0124] Therefore, based on the key features, multiple identity authentication processes are preliminarily screened, and based on the risk level of the business operations performed by the client, the target identity authentication process is further screened from the preliminary screening results. This can take into account both screening efficiency and screening quality to meet identity authentication needs in different scenarios.

[0125] In any embodiment of the present disclosure, the target identity authentication process can be determined by following steps H to I:

[0126] Step H: Determine the risk level of the client's business operations based on key characteristics and transaction behavior patterns.

[0127] As an example, the following steps H_1 to H_4 may be used to calculate the risk level of the business operation performed by the client:

[0128] Step H_1: Determine the first risk score of the client in multiple business dimensions based on the key features.

[0129] Among them, business dimensions include but are not limited to: business field dimension, business type dimension, business purpose dimension, etc.

[0130] For example, the first risk score of the client in the business field dimension can be determined according to the field value of the specified transaction field (such as the transaction amount) in the key feature. The first risk score is positively correlated with the field value of the specified transaction field (such as the transaction amount), that is, the larger the field value, the higher the first risk score.

[0131] By setting risk assessment standards, the client's first risk score in the business type dimension is evaluated according to the business type in the key characteristics. For example, for business types such as cross-border payment and large transfer, the first risk score is higher, and for business types such as small transfer and intra-city payment, the first risk score is lower.

[0132] According to the business purpose in the key feature, a first risk score of the client in the business purpose dimension is determined; wherein the first risk score is used to indicate the legality and compliance of the business operation. For example, in the case where the business operation involves illegal activities or business purposes that violate regulatory requirements, the first risk score is higher.

[0133] Step H_2: Determine the second risk score of the client in the transaction dimension based on the transaction behavior pattern.

[0134] For example, when the transaction behavior pattern is frequent large-value transfers or multiple transactions in a short period of time, the second risk score is relatively high; when the transaction behavior pattern is stable transaction frequency, stable transaction amount or transactions with compliant transaction partners, the second risk score is relatively low.

[0135] Step H_3: Determine a target risk score for the client to perform the business operation based on the first risk scores of the multiple business dimensions and the second risk scores of the transaction dimension.

[0136] Exemplarily, a weighted sum of the first risk scores of multiple business dimensions and the second risk scores of the transaction dimension may be performed to obtain a target risk score.

[0137] Step H_4: Determine the risk level of the client's business operation based on the target risk score.

[0138] Among them, the risk level is positively correlated with the target risk score.

[0139] In summary, it is possible to comprehensively evaluate the risk level of the client's business operations by scoring the client's risk in multiple dimensions, which can improve the accuracy, rationality and reliability of the evaluation results.

[0140] Step I: Determine the target authentication process from multiple authentication processes based on the risk level.

[0141] Exemplarily, the correspondence between different risk levels and identity authentication processes can be pre-configured, so that in the present disclosure, the above correspondence can be queried according to the risk level of the business operation executed by the client to determine the target identity authentication process to be executed from multiple identity authentication processes.

[0142] Therefore, by comprehensively evaluating the risk level of the client's business operations based on key features and transaction behavior patterns, the rationality and reliability of the risk level assessment can be improved. Furthermore, based on a reasonable risk level, the target identity authentication process to be executed can be determined from a variety of identity authentication processes, which can improve the rationality and pertinence of the target identity authentication process screening.

[0143] In step S27, a target identity authentication process is performed on the client to obtain an authentication result, and based on the authentication result, it is determined whether the client is allowed to perform the service operation.

[0144] For explanations of steps S25 to S27, reference may be made to the relevant descriptions in any embodiment of the present disclosure and will not be repeated here.

[0145] The business processing method of the disclosed embodiment comprehensively considers the client's short-term transaction behavior pattern, the object features associated with the client's login object, and the business features obtained by feature extraction of business information associated with the business operation to identify whether the business operation currently executed by the client triggers the set risk control strategy, which can improve the accuracy and reliability of the identification results, and further ensure financial security.

[0146] The present disclosure provides another service processing method. Figure 3 It is a flowchart of a business processing method shown in the third embodiment of the present disclosure.

[0147] It should be noted that the business processing method can be executed alone, or it can be executed in combination with any embodiment of the present disclosure or a possible implementation method in the embodiment, or it can be executed in combination with any technical solution in the related technology, and the embodiments of the present disclosure are not limited to this.

[0148] like Figure 3 As shown, the business processing method may include the following steps S31 to S38.

[0149] In step S31, based on the transaction behavior pattern associated with the client and the object characteristics associated with the login object of the client, it is identified whether the business operation currently executed by the client triggers the setting of the risk control strategy.

[0150] In step S32, when a business operation triggers the setting of a risk control strategy, key features are extracted from business information associated with the business operation.

[0151] The key feature includes at least one of a field value of a specified business field, a business type, and a business purpose.

[0152] In step S33, based on the key features and transaction behavior patterns, a target identity authentication process is determined from multiple identity authentication processes, wherein the target identity authentication process is a voiceprint authentication process.

[0153] For explanations of steps S31 to S33, reference may be made to the relevant descriptions in any embodiment of the present disclosure and will not be repeated here.

[0154] In step S34, a voiceprint authentication process is performed on the client to obtain voice data sent by the client.

[0155] In the embodiment of the present disclosure, the server may perform a voiceprint authentication process on the client to obtain voice data (or audio data) sent by the client.

[0156] In step S35, a first voiceprint feature is extracted from the speech data, and emotion classification is performed on the first voiceprint feature to determine a first emotion category of the login object.

[0157] The first emotion category may include a positive emotion category (such as happiness, joy, etc.), a negative emotion category (anger, fear, tension, despair, etc.), and a neutral emotion category (such as neutrality).

[0158] In the embodiment of the present disclosure, the server can extract the voiceprint feature (referred to as the first voiceprint feature in the present disclosure) of the login object from the voice data based on the voiceprint recognition technology.

[0159] In an embodiment of the present disclosure, the server may also perform emotion classification on the first voiceprint feature based on the emotion classification technology in AI technology to obtain the emotion category of the login object (referred to as the first emotion category in the present disclosure).

[0160] In step S36, it is determined whether the first voiceprint feature matches the reference voiceprint feature associated with the client, and whether the first emotion category does not match the specified negative emotion category. If so, step S37 is executed, and if not, step S38 is executed.

[0161] The reference voiceprint feature refers to the voiceprint feature obtained by extracting features from audio data pre-recorded by the client's login object.

[0162] The designated negative emotion categories include, but are not limited to, tension, coercion and other negative emotion categories.

[0163] In the embodiment of the present disclosure, the server can determine whether the first voiceprint feature and the reference voiceprint feature associated with the client match, that is, determine whether the similarity between the first voiceprint feature and the reference voiceprint feature is higher than the set similarity threshold. If the similarity between the first voiceprint feature and the reference voiceprint feature is higher than the set similarity threshold, it is determined that the first voiceprint feature matches the reference voiceprint feature. If the similarity between the first voiceprint feature and the reference voiceprint feature is not higher than the set similarity threshold, it is determined that the first voiceprint feature does not match the reference voiceprint feature.

[0164] In the disclosed embodiment, the server may also determine whether the first emotion category does not match the specified negative emotion category, that is, determine whether the first emotion category is not included in the specified negative emotion category.

[0165] It should be noted that step S37 and step S38 are two parallel implementation methods. In actual application, only one needs to be executed.

[0166] In step S37, an authentication result is generated to indicate that the login object of the client has passed the voiceprint authentication, and the client is allowed to perform the service operation.

[0167] In an embodiment of the present disclosure, when the first voiceprint feature matches the reference voiceprint feature associated with the client, and the first emotion category does not match the specified negative emotion category, the server can generate an authentication result indicating that the client's login object has passed the voiceprint authentication and allow the client to continue to perform business operations.

[0168] In step S38, an authentication result is generated to indicate that the login object of the client has not passed the voiceprint authentication, and the client is denied from performing the service operation.

[0169] In an embodiment of the present disclosure, when the first voiceprint feature does not match the reference voiceprint feature associated with the client, and / or the first emotion category matches the negative emotion category, the server can generate an authentication result indicating that the client's login object has not passed the voiceprint authentication, and refuse the client to continue to perform business operations.

[0170] The business processing method of the disclosed embodiment executes a voiceprint authentication process on the client, and only when the first voiceprint feature in the voice data sent by the client matches the reference voiceprint feature associated with the client, and the emotion category of the first voiceprint feature does not match the specified negative emotion category, is it determined that the client's login object has passed the voiceprint authentication. This can ensure that the business operation is performed by the legitimate object of the client, enhance the security of identity authentication, and by identifying whether the login object has negative emotions such as tension and coercion, potential fraud can be discovered and prevented in a timely manner, thereby further ensuring financial security.

[0171] The present disclosure provides another service processing method. Figure 4 It is a flowchart of a business processing method shown in the fourth embodiment of the present disclosure.

[0172] It should be noted that the business processing method can be executed alone, or it can be executed in combination with any embodiment of the present disclosure or a possible implementation method in the embodiment, or it can be executed in combination with any technical solution in the related technology, and the embodiments of the present disclosure are not limited to this.

[0173] like Figure 4 As shown, the business processing method may include the following steps S401 to S412.

[0174] In step S401, it is identified whether the business operation currently executed by the client triggers the setting of the risk control strategy according to the transaction behavior pattern associated with the client and the object characteristics associated with the login object of the client.

[0175] In step S402, when a business operation triggers the setting of a risk control strategy, key features are extracted from business information associated with the business operation.

[0176] The key feature includes at least one of a field value of a specified business field, a business type, and a business purpose.

[0177] In step S403, based on key features and transaction behavior patterns, a target identity authentication process is determined from multiple identity authentication processes, wherein the target identity authentication process includes an AI customer service authentication process.

[0178] For explanations of steps S401 to S403, reference may be made to the relevant descriptions in any embodiment of the present disclosure, and will not be repeated here.

[0179] In step S404, AI customer service is used to perform an AI customer service authentication process on the client to obtain a first video stream of the interaction between the AI ​​customer service and the login object.

[0180] In an embodiment of the present disclosure, AI customer service can be used to execute an AI customer service authentication process on the client, so that the AI ​​customer service can interact (or interact) with the login object of the client, and obtain a video stream of the interaction between the AI ​​customer service and the login object (referred to as the first video stream in this disclosure).

[0181] In step S405, AI customer service is used to perform image recognition on the first video stream to obtain the first facial features, the first behavior pattern, and the second emotion category of the login object.

[0182] Among them, the first behavior pattern is used to indicate the hand movements, limb movements, body postures and other behaviors of the logged-in object, reflecting the activity type, intention, emotional state and other information of the logged-in object.

[0183] The second emotion category may include a positive emotion category (such as happiness, joy, etc.), a negative emotion category (anger, fear, tension, despair, etc.), and a neutral emotion category (such as neutrality).

[0184] In the disclosed embodiment, AI customer service can perform face detection on the video frames in the first video stream based on a face detection algorithm to obtain a face area, and then can perform feature extraction on the face area based on a face feature extraction algorithm to obtain the first facial feature of the login object.

[0185] The AI ​​customer service may track and analyze information such as the face position, posture, and action in multiple consecutive video frames in the first video stream to determine the first behavior pattern of the login object. Exemplarily, the AI ​​customer service may extract behavior features from multiple consecutive video frames, and classify the behavior features using a classification algorithm in machine learning or deep learning technology to obtain the first behavior pattern of the login object.

[0186] AI customer service can extract features from the multimodal information in the first video stream (including facial expressions, audio, body language, etc.) to obtain emotional features, and use an emotional classification model to classify the emotional features to obtain a second emotional category.

[0187] In step S406, AI customer service is used to perform voice recognition on the audio in the first video stream to obtain a second voiceprint feature of the login object.

[0188] In an embodiment of the present disclosure, AI customer service can extract the second voiceprint feature of the login object from the audio in the first video stream based on voiceprint recognition technology.

[0189] In step S407, it is determined whether the AI ​​customer service can identify the target recognition result based on the first facial feature, the first behavior pattern, the second voiceprint feature and the second emotion category. If so, steps S408 and S412 are executed; if not, steps S409 to S412 are executed.

[0190] The target recognition result is used to indicate whether the login object has passed the identity authentication.

[0191] In the embodiment of the present disclosure, the AI ​​customer service can integrate the first facial feature, the first behavior pattern, the second voiceprint feature and the second emotion category to identify whether the login object has passed the identity authentication. If the AI ​​customer service can obtain the target recognition result, steps S408 and S412 can be further executed. If the AI ​​customer service cannot obtain the target recognition result, steps S409 to S412 can be further executed.

[0192] In any embodiment of the present disclosure, the target recognition result can be obtained by following steps a to c:

[0193] Step a: Use AI customer service to identify whether the login object is a legitimate object bound to the client based on the first facial feature and the second voiceprint feature, and obtain an initial recognition result.

[0194] The initial recognition result is used to indicate whether the login object is the legitimate object of the client.

[0195] As an example, AI customer service can determine whether the first facial feature matches the reference facial feature associated with the client. If so, the AI ​​customer service can continue to determine whether the second voiceprint feature matches the reference voiceprint feature associated with the client. If so, an initial recognition result is generated that the login object is a legitimate object of the client.

[0196] If the first facial feature does not match the reference facial feature, and / or the second voiceprint feature does not match the reference voiceprint feature, an initial recognition result is generated indicating that the login object is not a legitimate object of the client.

[0197] Step b: Use AI customer service to determine the risk level of the business operation performed by the login object based on the first behavior pattern and the second emotion category.

[0198] As an example, AI customer service can analyze whether the first behavior pattern is consistent with the usual habits of the logged-in object, for example, whether the hand movements when performing business operations are abnormal, whether the body posture is tense, etc., and analyze whether the second emotion category matches the specified negative emotion category (such as tension, coercion, etc.). Combined with the changes in the first behavior pattern and the changes in the second emotion category, the risk level of the logged-in object performing business operations is evaluated in real time.

[0199] For example, when the first behavior pattern is inconsistent with the usual habits of the login object, and / or the second emotion category matches the specified negative emotion category, it can be determined that the risk level of the login object in performing business operations is relatively high, while when the first behavior pattern is consistent with the usual habits of the login object, and the second emotion category does not match the specified negative emotion category, it can be determined that the risk level of the login object in performing business operations is relatively low.

[0200] Step c: Use AI customer service to generate a target recognition result of whether the login object has passed the identity authentication based on the initial recognition result and risk level.

[0201] As an example, when the initial recognition result indicates that the login object is the legitimate object of the client and the risk level is relatively low, a target recognition result that the login object passes the identity authentication can be generated; and when the initial recognition result indicates that the login object is not the legitimate object of the client, and / or the risk level is relatively high, a target recognition result that the login object fails the identity authentication can be generated.

[0202] In summary, AI customer service combines the first facial feature, the first behavioral pattern, the second voiceprint feature, and the second emotion category to identify whether the login object has passed the identity authentication, which can improve the accuracy and reliability of the recognition results.

[0203] In step S408, based on the target recognition result fed back by the AI ​​customer service, an authentication result is generated to show whether the login object has passed the AI ​​customer service authentication.

[0204] In the disclosed embodiment, the server can generate an authentication result of whether the client's login object has passed the AI ​​customer service authentication based on the target recognition result fed back by the AI ​​customer service.

[0205] As an example, when the target recognition result indicates that the login object has passed the identity authentication, the server can generate an authentication result that the login object has passed the AI ​​customer service authentication; when the target recognition result indicates that the login object has not passed the identity authentication, the server can generate an authentication result that the login object has not passed the AI ​​customer service authentication.

[0206] In step S409, a first customer service representative to be scheduled is determined from among multiple manual customer service representatives.

[0207] In the disclosed embodiment, when the AI ​​customer service is unable to identify the target recognition result based on the first facial feature, the first behavior pattern, the second voiceprint feature and the second emotion category (that is, the AI ​​customer service is unable to identify whether the login object has passed the identity authentication, for example, the first facial feature fails to match multiple times, the second voiceprint feature fails to match multiple times, etc.), the server can further determine the first customer service to be scheduled from multiple manual customer services.

[0208] As an example, the server may determine the first customer service representative to be scheduled from among multiple customer service representatives based on their scheduling information and unprocessed task load. For example, the first customer service representative may be the customer service representative who is currently on duty and has the least task load.

[0209] In step S410, the first customer service is scheduled to execute the manual customer service authentication process in the target identity authentication process on the client, so as to interact with the login object through video through the first customer service to identify whether the login object has passed the identity authentication.

[0210] In the disclosed embodiment, the server may schedule the first customer service to execute a manual customer service authentication process on the client, so as to interact with the login object via video through the first customer service and manually identify whether the login object has passed the identity authentication.

[0211] In step S411, based on the first feedback information sent by the first customer service, an authentication result is generated to determine whether the login object has passed the manual customer service authentication.

[0212] The first feedback information is used to indicate whether the login object has passed the identity authentication.

[0213] As an example, when the first feedback information sent by the first customer service indicates that the login object has passed the identity authentication, the server can generate an authentication result that the login object has passed the manual customer service authentication; and when the first feedback information sent by the first customer service indicates that the login object has not passed the identity authentication, the server can generate an authentication result that the login object has not passed the manual customer service authentication.

[0214] In step S412, based on the authentication result, it is determined whether the client is allowed to perform the service operation.

[0215] As an example, when the authentication result indicates that the login object has passed the AI ​​customer service authentication, the server may allow the client to continue to perform business operations; when the authentication result indicates that the login object has not passed the AI ​​customer service authentication, the server may refuse the client to continue to perform business operations.

[0216] As another example, when the authentication result indicates that the login object has passed the manual customer service authentication, the server may allow the client to continue to perform business operations; when the authentication result indicates that the login object has not passed the manual customer service authentication, the server may refuse the client to continue to perform business operations.

[0217] The business processing method of the disclosed embodiment dispatches AI customer service to perform identity recognition on the client's login object, which can not only reduce the labor cost of manual customer service, but also improve recognition efficiency, as well as improve the accuracy and reliability of recognition results.

[0218] When AI customer service is unable to perform identity recognition, dispatching manual customer service to perform identity recognition on the client's login object can improve the effectiveness and comprehensiveness of identity recognition and further ensure financial security.

[0219] The present disclosure provides another service processing method. Figure 5It is a flowchart of a business processing method shown in the fifth embodiment of the present disclosure.

[0220] It should be noted that the business processing method can be executed alone, or it can be executed in combination with any embodiment of the present disclosure or a possible implementation method in the embodiment, or it can be executed in combination with any technical solution in the related technology, and the embodiments of the present disclosure are not limited to this.

[0221] like Figure 5 As shown, the business processing method may include the following steps S51 to S59.

[0222] In step S51, based on the transaction behavior pattern associated with the client and the object characteristics associated with the login object of the client, it is identified whether the business operation currently executed by the client triggers the setting of the risk control strategy.

[0223] In step S52, when a business operation triggers the setting of a risk control policy, key features are extracted from business information associated with the business operation.

[0224] The key feature includes at least one of a field value of a specified business field, a business type, and a business purpose.

[0225] In step S53, based on the key features and transaction behavior patterns, a target identity authentication process is determined from a plurality of identity authentication processes, wherein the target identity authentication process includes a video customer service authentication process.

[0226] For explanations of steps S51 to S53, reference may be made to the relevant descriptions in any embodiment of the present disclosure and will not be repeated here.

[0227] In step S54, based on the scheduling information and unprocessed task volume of multiple manual customer service staff, a second customer service staff to be scheduled is determined from the multiple manual customer service staff, and the second customer service staff is scheduled to execute the video customer service authentication process on the client to obtain a second video stream of the interaction between the second customer service staff and the login object.

[0228] In an embodiment of the present disclosure, the server can determine a second customer service representative to be scheduled from among multiple manual customer service representatives based on their scheduling information and unprocessed task volumes. For example, the second customer service representative can be the manual customer service representative who is currently on duty and has the least task volume.

[0229] In the disclosed embodiment, the server may also schedule the second customer service to execute a video customer service authentication process on the client to obtain a second video stream of the interaction between the second customer service and the login object.

[0230] In step S55, the second facial features, the second behavior pattern, the third emotion category and the third voiceprint features of the login object are identified from the second video stream.

[0231] It should be noted that the implementation principle of step S55 is similar to the implementation principle of steps S405 to S406, and will not be elaborated here.

[0232] In step S56, the identity of the login object is authenticated based on the second facial feature, the second behavior pattern, the third voiceprint feature and the third emotion category to obtain a preliminary authentication result.

[0233] The preliminary authentication result is used to indicate whether the login object has passed the preliminary identity authentication.

[0234] It should be noted that the method for obtaining the preliminary authentication result is similar to the method for obtaining the target recognition result, which will not be described in detail here.

[0235] In step S57, the preliminary authentication result is sent to the second customer service so that the second customer service can identify whether the login object has passed the identity authentication based on the initial authentication result and the interaction with the login object.

[0236] In the disclosed embodiment, the server may send the initial authentication result to the second customer service so that the second customer service can manually identify whether the login object has passed the identity authentication based on the initial authentication result and the interaction between the login object and the second customer service.

[0237] In step S58, based on the second feedback information sent by the second customer service, an authentication result is generated to determine whether the login object has passed the video customer service authentication.

[0238] The second feedback information is used to indicate whether the login object has passed the identity authentication.

[0239] In the disclosed embodiment, the server may generate an authentication result of whether the login object has passed the video customer service authentication based on the second feedback information fed back by the second customer service.

[0240] As an example, when the second feedback information sent by the second customer service indicates that the login object has passed the identity authentication, the server can generate an authentication result that the login object has passed the video customer service authentication; and when the second feedback information sent by the second customer service indicates that the login object has not passed the identity authentication, the server can generate an authentication result that the login object has not passed the video customer service authentication.

[0241] In step S59, based on the authentication result, it is determined whether the client is allowed to perform the service operation.

[0242] As an example, when the authentication result indicates that the login object has passed the video customer service authentication, the server may allow the client to continue to perform business operations; and when the authentication result indicates that the login object has not passed the video customer service authentication, the server may refuse the client to continue to perform business operations.

[0243] The business processing method of the disclosed embodiment can use AI technology to perform preliminary identity authentication on the second video stream of the interaction between the second customer service and the login object, and based on the preliminary authentication result of the AI ​​technology, assist the manual customer service to authenticate the login object, which can not only improve the accuracy of the recognition result, but also reduce the workload of the manual customer service.

[0244] The present disclosure provides another service processing method. Figure 6 It is a flowchart of a business processing method shown in the sixth embodiment of the present disclosure.

[0245] It should be noted that the business processing method can be executed alone, or it can be executed in combination with any embodiment of the present disclosure or a possible implementation method in the embodiment, or it can be executed in combination with any technical solution in the related technology, and the embodiments of the present disclosure are not limited to this.

[0246] like Figure 6 As shown, based on any of the above embodiments, before step S11, S21, S31, S401 or S51, the service processing method may further include the following steps S61 to S66.

[0247] In step S61, when it is monitored that the client performs a login operation, it is identified whether the login object of the client changes the login device according to the login information sent by the client.

[0248] In the embodiment of the present disclosure, when the server detects that the client is performing a login operation, it can identify whether the client's login object has changed the login device based on the login information sent by the client. If so, step S62 is executed. If not, the existing identity authentication process is used to perform login authentication on the client's login object. For example, any one of the quick login authentication methods, such as password login, gesture login, and biometric login, can be used to perform login authentication on the client's login object.

[0249] As an example, the login information may include an account name (or mobile phone number), a device number or a device IP address. The server can query the device number or device IP address bound to the account name based on the account name in the login information, and determine whether the device number bound to the account name matches the device number in the login information. If so, it is determined that the client's login object has not changed the login device. If not, it is determined that the client's login object has changed the login device.

[0250] Alternatively, the server can determine whether the device IP address bound to the account name matches the device IP address in the login information. If so, it is determined that the client's login object has not changed the login device. If not, it is determined that the client's login object has changed the login device.

[0251] In step S62, if yes, a liveness detection process is performed on the client to determine whether the login object passes the liveness detection. If yes, S64 is executed; if no, S63 is executed.

[0252] In an embodiment of the present disclosure, when the login object of the client changes the login device, the server can perform a liveness detection process on the client to determine whether the login object of the client passes the liveness detection.

[0253] In step S63, the voiceprint authentication process is executed on the client to determine whether the login object passes the voiceprint authentication. If so, step S64 is executed, and if not, step S66 is executed.

[0254] In the embodiment of the present disclosure, when the login object fails the liveness detection, the server may further perform a voiceprint authentication process on the client to determine whether the login object passes the voiceprint authentication. The implementation principle is similar to that of steps S34 to S38 and will not be repeated here.

[0255] In step S64, a login password authentication process or a SMS verification code authentication process is executed on the client to determine whether the login object is a legal object. If so, step S65 is executed, and if not, step S66 is executed.

[0256] In the disclosed embodiment, when the login object passes the voiceprint authentication, or the login object passes the liveness detection, the server may further execute the login password authentication process or the SMS verification code authentication process on the client to determine whether the login object is a legitimate object of the client, that is, to determine whether the login object is the login person himself.

[0257] In step S65, a first indication message indicating successful login is sent to the client.

[0258] In the embodiment of the present disclosure, when the login object is a legal object, the server may send a first indication message to the client to indicate that the client has successfully logged in.

[0259] In step S66, a second indication message indicating a login failure is sent to the client.

[0260] In an embodiment of the present disclosure, when the login object fails to pass the voiceprint authentication, or the login object is not a legitimate object of the client, the server may send a second indication message to the client to indicate that the client login has failed.

[0261] The business processing method of the disclosed embodiment adds a security verification method of voiceprint authentication when the user changes the device to log in, which can ensure that it is the user himself who is operating, thereby ensuring financial security.

[0262] In the event of a user login failure, an indication message is sent to the client indicating the login failure, which can terminate malicious login operations in a timely manner, thereby further improving financial security.

[0263] In any of the embodiments of the present disclosure, the present disclosure proposes an implementation scheme combining multiple security technologies, aiming to improve the security of mobile banking during the process of changing device login and business (such as transfer business, loan business). When high-risk business operations are detected, such as changing device login, or when the user's IP address, longitude and latitude change significantly, the business operations performed by the user (such as transfer operations, loan operations, etc.) can use video customer service authentication, voiceprint authentication, manual customer service authentication, AI customer service authentication, etc. to verify the user's true identity and detect whether the user is in a state of tension or panic, so as to ensure financial security.

[0264] Among them, mobile banking is an important part of financial services, and its security is directly related to the property safety of users. In order to cope with increasingly complex online fraud methods, banks need to adopt advanced technical means to ensure transaction security.

[0265] In order to solve the security problem of changing device login, this solution proposes to add random security verification methods such as voiceprint authentication when high-risk users change devices to log in. When users change devices to log in to mobile banking, or perform high-risk operations such as large transfers, if the user triggers the set risk control strategy (such as anti-fraud strategy), two random security verification methods such as face recognition, voiceprint, video customer service, SMS verification code, and bank card password are used to verify whether the user is the real person.

[0266] As an example, the device login process can be as follows: Figure 7 As shown, it mainly includes the following steps:

[0267] Step 1: The user enters the account and password on the new device.

[0268] Step 2: The system triggers the liveness detection process (or liveness detection face scanning process).

[0269] Step 3: After the user passes facial recognition, voiceprint verification is performed.

[0270] Step 4: After successful verification, the user completes the login and the system records the login information of the new device.

[0271] It should be noted that when the user logs in to the client and enters the mobile phone number, or automatically brings in the last mobile phone number and sends it to the server for login check, the server saves the user's last login device number, current login status and other data. The server checks whether the user's current login device has changed and whether the user is currently logged in. Based on the check results, the client goes through different login processes.

[0272] For example, when security is detected, the client can go through a quick login process, such as password login, gesture login, biometric login, etc. When a change in the login device is detected, or the IP address changes within a short period of time, or the user's longitude and latitude changes, the system requires facial recognition, and verifies the user through random actions such as blinking and smiling, rather than using a pre-recorded video to log in, and verifies the user's SMS verification code and login password, etc. Multiple security checks ensure the user's financial security.

[0273] However, due to the natural limitations of face scanning, the user's facial data may not be matched due to blurry photos or long time. In this case, the bank card password can be verified to replace the liveness detection face scanning process. However, before the user logs in, verifying the bank card password requires the user to enter more elements, including user information, card number and password, and there is a possibility that the data can be stolen.

[0274] In order to solve the above problems, this solution can use random voiceprint authentication to replace the verification method of the liveness detection face scanning process. For example, after the user logs in, the voiceprint can be set, and the user says a few random numbers when setting. Among them, based on the voiceprint features, the identity of the speaker is detected, and emotion recognition can be performed relative to other biometric features to determine the user's true intentions. In this disclosure, the user's voiceprint information and voiceprint features are stored, so that when the user changes the device to log in, if it is detected that the user has set the voiceprint, random voiceprint authentication can be used to replace the liveness detection face scanning verification method.

[0275] As an example, setting the risk control strategy as the anti-fraud strategy and the business operation currently performed by the client as the transfer operation are taken as an example. The anti-fraud technology for transfer mainly involves the anti-fraud system and video customer service. Among them, the anti-fraud system: monitors transaction behavior in real time and analyzes abnormal patterns, such as frequent large-value transfers, multiple transactions in a short period of time, etc. For example, machine learning algorithms can be used to model user transaction behaviors and identify abnormal transaction behavior patterns. Video customer service: When a suspicious transaction is detected, the system automatically triggers the video customer service to communicate with the user face to face. The user receives a video invitation and confirms the authenticity of the transaction through the video customer service.

[0276] The transfer process can be as follows: Figure 8 As shown, it mainly includes the following steps:

[0277] Step 1: The user initiates a transfer request.

[0278] Step 2: The system analyzes transaction behavior to determine whether anti-fraud strategies are triggered.

[0279] Step 3: If triggered, the system automatically contacts the user and authenticates the user through video customer service or voiceprint.

[0280] Step 4: After the user confirms the transaction, the system executes the transfer operation.

[0281] By combining technologies such as liveness detection, face scanning, voiceprint recognition, anti-fraud systems and video customer service, mobile banking can provide users with a safe and convenient environment for logging in and transferring money with a different device. This multi-dimensional security strategy can effectively reduce the risk of fraud, regularly conduct risk assessments on security strategies, and promptly update anti-fraud strategies to protect the property safety of users.

[0282] User identity is authenticated through video customer service. Traditional manual video customer service has certain limitations. Users have needs 24 hours a day, but customer service is not available at night or there are high labor costs. The addition of AI technology to video customer service can provide users with 7*24 hours of uninterrupted video customer service. Real-time video communication technology enables customer service personnel to communicate with users face to face, and the AI ​​auxiliary function provides decision support for customer service through intelligent analysis of user emotions, voice and behavior patterns, including but not limited to identity authentication, and analysis of user emotions to determine whether they are under tension or coercion.

[0283] The solution provided by the present disclosure aims to build a safer financial transaction environment through multi-dimensional security measures. For example, when a user performs operations such as transferring money, if the user has security risks (for example, abnormal behavior of the user is detected, such as frequent transfers, IP changes in a short period of time, longitude and latitude changes significantly, or triggers a blacklist, or is a high-risk and vulnerable group), voiceprint or video customer service verification is added to determine whether the operation is performed by the user himself, whether there is tension, coercion and other emotions, and the transfer can continue after the inspection, and risky behavior is intercepted, which can achieve timely blocking of high-risk operations, further ensure financial security, and provide a better user experience for financial security.

[0284] With the above Figures 1 to 8 Corresponding to the service processing method provided in the embodiment, the present disclosure also provides a service processing device. Figures 1 to 8 The business processing method provided in the embodiment corresponds to the business processing method, so the implementation method of the business processing method is also applicable to the business processing device provided in the embodiment of the present disclosure, and will not be described in detail in the embodiment of the present disclosure.

[0285] Fig. 9It is a structural diagram of a business processing device shown in the seventh embodiment of the present disclosure.

[0286] Reference Fig. 9 The business processing device 900 may include: an identification module 910, an extraction module 920, a determination module 930 and an execution module 940.

[0287] The identification module 910 is used to identify whether the business operation currently executed by the client triggers the set risk control strategy according to the transaction behavior pattern associated with the client and the object characteristics associated with the login object of the client;

[0288] An extraction module 920 is used to extract key features from business information associated with a business operation when a business operation triggers the setting of a risk control strategy; wherein the key features include at least one of a field value of a specified business field, a business type, and a business purpose;

[0289] A determination module 930, for determining a target identity authentication process from a plurality of identity authentication processes based on key features and transaction behavior patterns;

[0290] The execution module 940 is used to execute the target identity authentication process on the client, obtain the authentication result, and determine whether to allow the client to perform the business operation based on the authentication result.

[0291] In a possible implementation of the embodiment of the present disclosure, the determination module 930 is specifically used to: determine a candidate identity authentication process that is adapted to the key features from a variety of identity authentication processes; determine the risk level of the client performing business operations based on the transaction behavior pattern; and determine the target identity authentication process from the candidate identity authentication processes based on the risk level.

[0292] In a possible implementation of the embodiment of the present disclosure, the determination module 930 is specifically used to: determine the risk level of the client performing the business operation based on key features and transaction behavior patterns; and determine the target identity authentication process from multiple identity authentication processes based on the risk level.

[0293] In a possible implementation of the embodiment of the present disclosure, the determination module 930 is specifically used to: determine a first risk score of the client in multiple business dimensions based on key features; determine a second risk score of the client in the transaction dimension based on the transaction behavior pattern; determine a target risk score for the client to perform business operations based on the first risk scores of the multiple business dimensions and the second risk score of the transaction dimension; determine the risk level of the client to perform business operations based on the target risk score.

[0294] In a possible implementation of the embodiment of the present disclosure, the identification module 910 is specifically used to: obtain the transaction behavior information of the client within a set time period; classify the transaction behavior information to determine the transaction behavior pattern of the client; obtain object features associated with the client's login object, and extract business features from all business information associated with the business operation; based on the transaction behavior pattern, object features and business features, identify whether the business operation currently executed by the client triggers the set risk control strategy.

[0295] In a possible implementation of the embodiment of the present disclosure, the identification module 910 is specifically used to: obtain device information of the device where the client is located; obtain object information and context information of the client's login object; wherein the context information is used to characterize the environmental perception characteristics of the login object; perform feature extraction on the device information, object information and context information to obtain object features.

[0296] In a possible implementation of the embodiments of the present disclosure, the target identity authentication process is a voiceprint authentication process; the execution module 940 is specifically used to: execute the voiceprint authentication process on the client to obtain voice data sent by the client; extract a first voiceprint feature from the voice data, and perform emotion classification on the first voiceprint feature to determine a first emotion category of the login object; when the first voiceprint feature matches a reference voiceprint feature associated with the client, and the first emotion category does not match a specified negative emotion category, generate an authentication result indicating that the login object of the client has passed the voiceprint authentication; when the first voiceprint feature does not match the reference voiceprint feature, and / or the first emotion category matches a negative emotion category, generate an authentication result indicating that the login object of the client has not passed the voiceprint authentication.

[0297] In a possible implementation of the embodiments of the present disclosure, the target identity authentication process includes an artificial intelligence (AI) customer service authentication process; an execution module 940 is specifically used to: use AI customer service to execute the AI ​​customer service authentication process on the client to obtain a first video stream of interaction between the AI ​​customer service and the login object; use AI customer service to perform image recognition on the first video stream to obtain the first facial features, first behavior pattern, and second emotion category of the login object; use AI customer service to perform speech recognition on the audio in the first video stream to obtain the second voiceprint features of the login object; use AI customer service to identify whether the login object has passed the identity authentication based on the first facial features, first behavior pattern, second voiceprint features, and second emotion category to obtain a target recognition result; and generate an authentication result of whether the login object has passed the AI ​​customer service authentication based on the target recognition result fed back by the AI ​​customer service.

[0298] In a possible implementation of the embodiment of the present disclosure, the execution module 940 is specifically used to: use AI customer service to identify whether the login object is a legitimate object bound to the client based on the first facial feature and the second voiceprint feature, and obtain an initial recognition result; use AI customer service to determine the risk level of the login object performing business operations based on the first behavior pattern and the second emotion category; use AI customer service to generate a target recognition result of whether the login object has passed the identity authentication based on the initial recognition result and the risk level.

[0299] In a possible implementation of the embodiment of the present disclosure, the target identity authentication process also includes a manual customer service authentication process; the execution module 940 is also used to: when the AI ​​customer service is unable to identify whether the login object has passed the identity authentication based on the first facial feature, the first behavior pattern, the second voiceprint feature and the second emotion category, determine the first customer service to be scheduled from multiple manual customer services; schedule the first customer service to execute the manual customer service authentication process on the client, so as to interact with the login object through video through the first customer service to identify whether the login object has passed the identity authentication; and generate an authentication result of whether the login object has passed the manual customer service authentication based on the first feedback information sent by the first customer service.

[0300] In a possible implementation of the embodiment of the present disclosure, the target identity authentication process includes a video customer service authentication process; the execution module 940 is specifically used to: determine a second customer service to be scheduled from multiple manual customer services based on the scheduling information and unprocessed task volume of multiple manual customer services, and schedule the second customer service to execute the video customer service authentication process on the client to obtain a second video stream of the interaction between the second customer service and the login object; from the second video stream, identify the second facial features, second behavior patterns, third emotion categories and third voiceprint features of the login object; authenticate the login object based on the second facial features, second behavior patterns, third voiceprint features and third emotion categories to obtain a preliminary authentication result; send the preliminary authentication result to the second customer service, so that the second customer service can identify whether the login object has passed the identity authentication based on the initial authentication result and the interaction with the login object; generate an authentication result of whether the login object has passed the video customer service authentication based on the second feedback information sent by the second customer service.

[0301] In a possible implementation of the embodiment of the present disclosure, the service processing device 900 may further include:

[0302] A login authentication module is used to identify whether the client's login object has changed the login device based on the login information sent by the client when it is monitored that the client is performing a login operation; if so, a liveness detection process is performed on the client to determine whether the login object has passed the liveness detection; if the login object has not passed the liveness detection, a voiceprint authentication process is performed on the client to determine whether the login object has passed the voiceprint authentication; if the login object has passed the voiceprint authentication, or the login object has passed the liveness detection, a login password authentication process or a SMS verification code authentication process is performed on the client to determine whether the login object is a legal object of the client; if the login object is a legal object, a first indication message is sent to the client to indicate that the login is successful.

[0303] In a possible implementation of the embodiment of the present disclosure, the service processing device 900 may further include:

[0304] The sending module is used to send a second indication message indicating a login failure to the client when any of the following conditions is met: the login object fails to pass the voiceprint authentication; the login object is not a legal object.

[0305] The business processing device of the disclosed embodiment can extract key features from business information associated with the high-risk business operation when the client executes the high-risk business operation, and determine the target identity authentication process to be executed from multiple identity authentication processes based on the key features and the transaction behavior pattern associated with the client, and then execute the target identity authentication process on the client to confirm whether the high-risk business operation is a business operation performed by the client's login object himself, so as to timely and effectively block high-risk business operations performed by non-users themselves and ensure financial security.

[0306] In an exemplary embodiment, the present disclosure further proposes an electronic device, wherein the electronic device comprises: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the service processing method proposed in any of the aforementioned embodiments of the present disclosure.

[0307] As an example, Fig.10 is a schematic diagram of the structure of an electronic device 1000 shown in an exemplary embodiment of the present disclosure, such as Fig.10 As shown, the electronic device 1000 may further include:

[0308] The memory 1010 and the processor 1020, a bus 1030 connecting different components (including the memory 1010 and the processor 1020), the memory 1010 stores a computer program, and when the processor 1020 executes the program, the business processing method described in any embodiment of the present disclosure is implemented.

[0309] Bus 1030 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0310] The electronic device 1000 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by the electronic device 1000, including volatile and non-volatile media, removable and non-removable media.

[0311] The memory 1010 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 1040 and / or cache memory 1050. The server 1000 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 1060 may be used to read and write non-removable, non-volatile magnetic media ( Fig.10 not shown, usually called a "hard drive"). Although Fig.10 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 1030 via one or more data medium interfaces. The memory 1010 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present disclosure.

[0312] A program / utility 1080 having a set (at least one) of program modules 1070 may be stored, for example, in the memory 1010, such program modules 1070 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 1070 generally perform the functions and / or methods of the embodiments described in the present disclosure.

[0313] The electronic device 1000 may also communicate with one or more external devices 1090 (e.g., keyboard, pointing device, display 1091, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1000, and / or communicate with any device that enables the electronic device 1000 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed through an input / output (I / O) interface 1092. In addition, the electronic device 1000 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) through a network adapter 1093. As shown, the network adapter 1093 communicates with other modules of the electronic device 1000 through a bus 1030. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0314] The processor 1020 executes various functional applications and business processing by running the programs stored in the memory 1010 .

[0315] It should be noted that the implementation process and technical principles of the electronic device of this embodiment refer to the aforementioned explanation of the business processing method of any embodiment of the present disclosure, and will not be repeated here.

[0316] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory including instructions, and the above instructions can be executed by a processor of an electronic device to complete the method proposed in any of the above embodiments. Optionally, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0317] In an exemplary embodiment, a computer program product is also provided, including a computer program / instruction, wherein the computer program / instruction implements the method proposed in any of the above embodiments when executed by a processor.

[0318] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0319] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A business processing method, characterized in that: include: Identify whether a business operation currently executed by the client triggers a set risk control strategy based on a transaction behavior pattern associated with the client and an object feature associated with a login object of the client; In the case where the business operation triggers the set risk control strategy, extracting key features from business information associated with the business operation; wherein the key features include at least one of a field value of a specified business field, a business type, and a business purpose; Determining a target identity authentication process from a plurality of identity authentication processes based on the key features and the transaction behavior pattern; The target identity authentication process is executed on the client to obtain an authentication result, and based on the authentication result, it is determined whether the client is allowed to execute the business operation.

2. The method according to claim 1, characterized in that The determining a target identity authentication process from a plurality of identity authentication processes based on the key features and the transaction behavior pattern includes: Determining, from the multiple identity authentication processes, a candidate identity authentication process that is compatible with the key feature; Determining, based on the transaction behavior pattern, a risk level of the client executing the business operation; The target identity authentication process is determined from the candidate identity authentication processes according to the risk level.

3. The method according to claim 1, characterized in that The determining a target identity authentication process from a plurality of identity authentication processes based on the key features and the transaction behavior pattern includes: Determining, based on the key features and the transaction behavior pattern, a risk level of the client executing the business operation; The target identity authentication process is determined from the multiple identity authentication processes according to the risk level.

4. The method according to claim 3, characterized in that Determining the risk level of the client executing the business operation according to the key feature and the transaction behavior pattern includes: Determining, based on the key features, a first risk score of the client in multiple business dimensions; Determining a second risk score of the client in a transaction dimension according to the transaction behavior pattern; Determining a target risk score for the client to perform the business operation according to the first risk scores of the multiple business dimensions and the second risk score of the transaction dimension; A risk level of the client executing the business operation is determined according to the target risk score.

5. The method according to claim 1, characterized in that The step of identifying whether a business operation currently executed by the client triggers setting a risk control strategy according to a transaction behavior pattern associated with the client and an object feature associated with a login object of the client includes: Obtaining the transaction behavior information of the client within a set period of time; Classifying the transaction behavior information to determine the transaction behavior pattern of the client; Acquire object features associated with the login object of the client, and extract business features from all business information associated with the business operation; Based on the transaction behavior pattern, the object characteristics and the business characteristics, it is identified whether the business operation currently executed by the client triggers the set risk control strategy.

6. The method according to claim 5, characterized in that The acquiring of the object characteristics associated with the login object of the client includes: Obtain device information of the device where the client is located; Obtaining object information and context information of the login object of the client; wherein the context information is used to characterize the environmental perception characteristics of the login object; Feature extraction is performed on the device information, the object information and the context information to obtain the object feature.

7. The method according to claim 1, characterized in that The target identity authentication process is a voiceprint authentication process; The performing the target identity authentication process on the client to obtain an authentication result includes: Executing the voiceprint authentication process on the client to obtain voice data sent by the client; Extracting a first voiceprint feature from the voice data, and performing emotion classification on the first voiceprint feature to determine a first emotion category of the login object; If the first voiceprint feature matches a reference voiceprint feature associated with the client, and the first emotion category does not match a specified negative emotion category, generating an authentication result indicating that the login object of the client has passed the voiceprint authentication; When the first voiceprint feature does not match the reference voiceprint feature, and / or the first emotion category matches the negative emotion category, an authentication result is generated indicating that the login object of the client has failed the voiceprint authentication.

8. The method according to claim 1, characterized in that The target identity authentication process includes an artificial intelligence AI customer service authentication process; The performing the target identity authentication process on the client to obtain an authentication result includes: Using AI customer service to execute the AI ​​customer service authentication process on the client to obtain a first video stream of the interaction between the AI ​​customer service and the login object; Using the AI ​​customer service to perform image recognition on the first video stream to obtain a first facial feature, a first behavior pattern, and a second emotion category of the login object; Using the AI ​​customer service to perform voice recognition on the audio in the first video stream to obtain a second voiceprint feature of the login object; Using the AI ​​customer service to identify whether the login object has passed identity authentication according to the first facial feature, the first behavior pattern, the second voiceprint feature, and the second emotion category, and obtain a target recognition result; Based on the target recognition result fed back by the AI ​​customer service, an authentication result is generated to determine whether the login object has passed the AI ​​customer service authentication.

9. The method according to claim 8, characterized in that The AI ​​customer service is used to identify whether the login object has passed the identity authentication according to the first facial feature, the first behavior pattern, the second voiceprint feature and the second emotion category, and obtain a target recognition result, including: Using the AI ​​customer service to identify whether the login object is a legitimate object bound to the client according to the first facial feature and the second voiceprint feature, and obtaining an initial recognition result; Using the AI ​​customer service to determine the risk level of the login object performing the business operation according to the first behavior pattern and the second emotion category; The AI ​​customer service is used to generate a target recognition result of whether the login object has passed the identity authentication based on the initial recognition result and the risk level.

10. The method according to claim 8, characterized in that The target identity authentication process also includes a manual customer service authentication process; Executing the target identity authentication process on the client to obtain an authentication result, further comprising: When the AI ​​customer service cannot identify whether the login object has passed identity authentication based on the first facial feature, the first behavior pattern, the second voiceprint feature, and the second emotion category, determining a first customer service to be scheduled from multiple manual customer services; Dispatching the first customer service to execute the manual customer service authentication process on the client, so as to interact with the login object through video through the first customer service to identify whether the login object has passed the identity authentication; According to the first feedback information sent by the first customer service, an authentication result is generated to indicate whether the login object has passed the manual customer service authentication.

11. The method according to claim 1, characterized in that: The target identity authentication process includes a video customer service authentication process; The performing the target identity authentication process on the client to obtain an authentication result includes: Based on the scheduling information and unprocessed task volume of multiple manual customer service personnel, determine a second customer service to be scheduled from the multiple manual customer service personnel, and schedule the second customer service personnel to perform the video customer service authentication process on the client to obtain a second video stream of the interaction between the second customer service personnel and the login object; identifying, from the second video stream, a second facial feature, a second behavior pattern, a third emotion category, and a third voiceprint feature of the login object; Performing identity authentication on the login object according to the second facial feature, the second behavior pattern, the third voiceprint feature, and the third emotion category to obtain a preliminary authentication result; Sending the preliminary authentication result to the second customer service so that the second customer service can identify whether the login object has passed the identity authentication based on the preliminary authentication result and the interaction with the login object; According to the second feedback information sent by the second customer service, an authentication result is generated to determine whether the login object has passed the video customer service authentication.

12. The method according to any one of claims 1 to 11, characterized in that Before identifying whether a business operation currently executed by the client triggers setting a risk control strategy based on a transaction behavior pattern associated with the client and an object feature associated with a login object of the client, the method further includes: In the case of monitoring that the client performs a login operation, identifying whether the login object of the client changes the login device according to the login information sent by the client; If yes, executing a liveness detection process on the client to determine whether the login object passes the liveness detection; In the case that the login object fails the liveness detection, executing a voiceprint authentication process on the client to determine whether the login object passes the voiceprint authentication; When the login object passes the voiceprint authentication, or the login object passes the liveness detection, executing a login password authentication process or a short message verification code authentication process on the client to determine whether the login object is a legitimate object of the client; In a case where the login object is the legal object, a first indication message for indicating successful login is sent to the client.

13. The method according to claim 12, characterized in that The method further comprises: When any of the following conditions is met, a second indication message indicating a login failure is sent to the client: The login object fails to pass the voiceprint authentication; The login object is not the legal object.

14. A service processing device, characterized in that: include: An identification module, used to identify whether a business operation currently executed by the client triggers a set risk control strategy based on a transaction behavior pattern associated with the client and an object feature associated with a login object of the client; An extraction module, configured to extract key features from business information associated with the business operation when the business operation triggers the set risk control strategy; wherein the key features include at least one of a field value of a specified business field, a business type, and a business purpose; A determination module, configured to determine a target identity authentication process from a plurality of identity authentication processes based on the key features and the transaction behavior pattern; The execution module is used to execute the target identity authentication process on the client, obtain an authentication result, and determine whether to allow the client to execute the business operation based on the authentication result.

15. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the business processing method according to any one of claims 1 to 13.

16. A computer-readable storage medium, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the service processing method according to any one of claims 1 to 13.

17. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the service processing method according to any one of claims 1 to 13 is implemented.

Images