Data processing method and apparatus, and computer device, storage medium and product

Abstract

Provided in the present application are a data processing method and apparatus, and a computer device, a storage medium and a product. The method comprises: acquiring biological recognition data which is collected for a preset object in a service scenario; performing identity recognition processing on the preset object on the basis of the biological recognition data, so as to obtain a recognition result for the preset object; and acquiring a first credit index corresponding to the preset object in the service scenario, and performing grade adjustment processing on the first credit index according to the recognition result, so as to obtain a second credit index, wherein the second credit index is different from the first credit index, and in the service scenario, a risk control policy associated with the second credit index is different from a risk control policy associated with the first credit index. The present application makes it possible to perform grade adjustment on a credit index of a user in a service scenario, so as to flexibly adjust a risk control policy for the user in the service scenario.

Description

Data processing method, device, computer equipment, storage medium and product

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on June 13, 2023, with application number 2023107006506 and application name “Data processing methods, devices, computer equipment, storage media and products”, all contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of computer technology, and in particular to a data processing method, a data processing apparatus, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0003] In various business scenarios such as payment scenarios, access control scenarios, and gaming scenarios, there are often a large number of business demands (for example, the demand for asset payment in payment scenarios, and the demand for door opening in access control scenarios, etc.). A large number of business demands are accompanied by a large amount of data interaction. Therefore, in order to avoid abnormal data interactions such as malicious transactions by users, corresponding risk control strategies need to be set in the business scenarios.

[0004] Currently, adjustments to risk control strategies in business scenarios generally require manual application, and one needs to find the corresponding application method before initiating an application for a risk control strategy, which is not flexible enough.

[0005] Summary of the Invention

[0006] The embodiments of the present application propose a data processing method, apparatus, computer equipment, storage medium and product, which can adjust the level of a user's credit indicators in a business scenario, thereby flexibly adjusting the user's risk control strategy in the business scenario.

[0007] In one aspect, an embodiment of the present application provides a data processing method, the method comprising:

[0008] Obtain biometric data collected from preset objects in business scenarios;

[0009] Perform identity recognition processing on a preset object based on the biometric data to obtain an identification result of the preset object;

[0010] Obtaining a first credit indicator corresponding to a preset object in a business scenario, and adjusting the first credit indicator based on the identification result to obtain a second credit indicator;

[0011] Among them, the second credit indicator is different from the first credit indicator; in the business scenario, the risk control strategy associated with the second credit indicator is different from the risk control strategy associated with the first credit indicator.

[0012] In one aspect, an embodiment of the present application provides a data processing device, comprising:

[0013] An acquisition unit, configured to acquire biometric data collected from a preset object in a business scenario;

[0014] A processing unit, configured to perform identity recognition processing on a preset object based on the biometric recognition data to obtain an identification result of the preset object;

[0015] The processing unit is further configured to obtain a first credit indicator corresponding to a preset object in a business scenario, and to perform a level adjustment process on the first credit indicator based on the recognition result to obtain a second credit indicator;

[0016] Among them, the second credit indicator is different from the first credit indicator; in the business scenario, the risk control strategy associated with the second credit indicator is different from the risk control strategy associated with the first credit indicator.

[0017] On the one hand, an embodiment of the present application provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the above-mentioned data processing method.

[0018] On the one hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is read and executed by a processor of a computer device, the computer device executes the above-mentioned data processing method.

[0019] In one aspect, embodiments of the present application provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the above-described data processing method.

[0020] In an embodiment of the present application, biometric data collected for a preset object in a business scenario is obtained, so that the preset object can be identified based on the biometric data to obtain an identification result of the preset object. Since the identification requirements are often closely related to the specific business scenario, the present application can identify the current user according to the user's biometric data in a specific business scenario (such as a payment scenario, an access control scenario, a game scenario, etc.), which can improve the adaptability of the scene of the identification; obtain a first credit indicator corresponding to the preset object in the business scenario, and adjust the level of the first credit indicator according to the identification result to obtain a second credit indicator; wherein the second credit indicator is different from the first credit indicator, and the risk control strategy associated with the second credit indicator is different from the risk control strategy associated with the first credit indicator. It can be seen from this that the present application can identify the user in the business scenario and flexibly adjust the user's credit indicator according to the identification result, so that as the user's credit indicator changes (i.e., from the first credit indicator to the second credit indicator), the risk control strategy for the user also changes accordingly. Therefore, the present application can flexibly adjust the corresponding risk control strategy based on the indicator adjustment method in a specific business scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] FIG1 is a schematic diagram of the architecture of a data processing system provided in an embodiment of the present application;

[0022] FIG2 is a schematic diagram of the architecture of a data processing scenario provided in an embodiment of the present application;

[0023] FIG3 is a flow chart of a data processing method provided in an embodiment of the application;

[0024] FIG4 is a flow chart of another data processing method provided in an embodiment of the application;

[0025] FIG5a is a schematic diagram of an interface for level adjustment processing provided in an embodiment of the present application;

[0026] FIG5 b is a schematic diagram of an interface for another level adjustment process provided in an embodiment of the present application;

[0027] FIG6 is a flow chart of a data processing scenario provided in an embodiment of the present application;

[0028] FIG7 a is a flow chart of a palm-swipe payment scenario provided in an embodiment of the present application;

[0029] FIG7 b is a flow chart of another palm-swipe payment scenario provided by an embodiment of the present application;

[0030] FIG8 is a schematic structural diagram of a data processing device provided in an embodiment of the present application;

[0031] FIG9 is a schematic structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] This application provides a data processing solution that is applicable to business scenarios such as payment scenarios, access control scenarios, and gaming scenarios. It can identify users in these business scenarios and flexibly adjust the user's security credit level (i.e., credit index) based on the identification results to change the user's risk control strategy in the corresponding business scenario, thereby meeting more business needs in the business scenario. Specifically, the principles of this data processing solution are as follows:

[0033] (1) When a need for identity recognition of a preset object is detected in a business scenario (for example, when a preset object is required to perform face-swiping payment in a payment scenario, or when a preset object is required to verify identity in an access control scenario), the biometric data collected for the preset object is obtained. The business scenario here can be any of the payment scenario, the identity verification scenario (such as the access control scenario), and the game scenario. The preset object is any object (usually a human object) that needs to be verified or recognized; the biometric recognition data here is data that can be used to reflect the identity of the preset object, such as palm data, fingerprint data, face data, pupil data, etc.

[0034] (2) Performing identity recognition processing on a preset object based on the biometric data to obtain an identification result of the preset object. The identification result here is used to reflect whether the identity recognition of the preset object is successful. Therefore, the identification result includes identification success and identification failure. The so-called identification success refers to the successful identification of the preset object, and the identification failure refers to the failure of the identification of the preset object.

[0035] (3) Obtaining a first credit indicator corresponding to a preset object in a business scenario, and adjusting the first credit indicator based on the identification result to obtain a second credit indicator; wherein the risk control strategy associated with the second credit indicator is different from the risk control strategy associated with the first credit indicator. It should be understood that a preset object refers to an object that has pre-registered its identity in a business scenario. Therefore, after the preset object is registered in the business scenario, a corresponding first credit indicator can be assigned to the preset object. Then, the first credit indicator can be adjusted based on the identification result obtained after the preset object is identified in the real-time business scenario to adjust the risk control strategy of the preset object.

[0036] It can be seen from this that the present application can perform identity identification processing for users (i.e., preset objects) with identity identification needs in business scenarios, so that the credit indicators of the user can be flexibly adjusted according to the identification results obtained by the identity identification processing; since different credit indicators can be associated with different risk control strategies in business scenarios, as the user's credit indicators change (i.e., from the first credit indicator to the second credit indicator), the risk control strategy for the user will also change accordingly, that is, the present application can flexibly adjust the corresponding risk control strategy based on the indicator adjustment method in a specific business scenario, and can flexibly adjust the risk control strategy of the user for the same user, and the risk control management method is more flexible.

[0037] The following is an introduction to the relevant technical terms involved in the embodiments of this application:

[0038] 1. Business scenarios and preset objects:

[0039] A business scenario is a scenario that provides business services and supports biometric identification (or identity recognition) of pre-set objects. The pre-set objects here refer to any object in the business scenario, or a specified object in the business scenario (such as an object requiring payment in a payment scenario). For example, if the business service is a payment service, the business scenario is a payment scenario, in which the identity of the payment object is allowed. If the business service is an identity verification service, the business scenario is an access control scenario, in which the identity of the identity verification object is allowed. If the business service is a gaming service, the business scenario can be a gaming scenario, in which the identity of the gaming object is allowed.

[0040] 2. Biometric Data

[0041] Biometric data refers to data used to identify or biometrically identify a user (i.e., a pre-defined subject). Identity identification includes at least palm recognition, fingerprint recognition, facial recognition, and pupil recognition. This biometric data may include, but is not limited to, palm data, fingerprint data, facial data, and pupil data. Specifically, palm recognition is a technology that identifies a user based on palm data; fingerprint recognition is a technology that identifies a user based on fingerprint data; facial recognition is a technology that identifies a user based on facial data; and pupil recognition is a technology that identifies a user based on pupil data.

[0042] This application mainly involves performing identity recognition processing on a preset object based on palm recognition technology to obtain an identification result of the preset object, and the identification result may include recognition success and recognition failure. Specifically, the palm recognition technology can be applied to various business scenarios such as payment scenarios, access control scenarios, game scenarios, etc. For example, in a payment scenario, the palm data of a preset object can be collected, and the identity of the preset object can be recognized based on the palm data. If the recognition is successful, subsequent payment processing and other operations can be performed; for example, in an access control scenario, the palm data of a preset object can be collected, and the identity of the preset object can be recognized based on the palm data. If the recognition is successful, subsequent operations such as opening the door can be performed.

[0043] 3. First and Second Credit Indicators:

[0044] The so-called credit index can be an indicator assigned to different objects in the same business scenario based on preset management rules. For example, the credit index corresponding to the user can be obtained only after analyzing the user's identity information and operation data in the business scenario through management rules. Optionally, the credit index is an indicator used to identify the security credit level of the user (i.e., the preset object) in the business scenario; the so-called security credit level, as the name suggests, refers to the level of security credit possessed by the object in the business scenario, which is used to characterize the object's security credit. The data form of the security credit level can be: Chinese, English, character string, etc. Specifically, the data form of the security credit level indicated by the corresponding credit indicators in different business scenarios can be the same or different. It should also be noted that the types and numbers of security credit levels specified in different business scenarios can be the same or different, and their specific numbers and types can vary based on different management rules; for example, there are 4 types of security credit levels in the payment scenario; and there are 3 types of security credit levels in the access control scenario. For example, in a payment scenario, the security credit level indicated by the corresponding credit indicator can be expressed as: primary, intermediate, advanced, and very advanced; in another example, in an access control scenario, the security credit level indicated by the corresponding credit indicator can be expressed as: 80%, 90%, and 100%; in another example, in a gaming scenario, the security credit level indicated by the corresponding credit indicator can be expressed as: level 1, level 2, level 3, and so on. In this application, the first credit indicator and the second credit indicator are different. For example, the security credit level indicated by the first credit indicator (e.g., advanced) can be higher than the security credit level indicated by the second credit indicator (e.g., intermediate); in another example, the security credit level indicated by the first credit indicator (e.g., advanced) can be lower than the security credit level indicated by the second credit indicator (e.g., very advanced).

[0045] 4. Risk Control Strategy

[0046] Risk control strategies, or risk management strategies, are strategies that employ various measures and methods to eliminate or reduce the likelihood of risk events. Specifically, different business scenarios require different risk control strategies. For example, in payment scenarios, risk control strategies might include strategies to control risks such as payment limits and payment frequency; in authentication scenarios, risk control strategies might include strategies to control risks such as identity tampering and information theft.

[0047] In this application, the risk control strategy in the business scenario is dynamically adjusted as the credit indicator of the preset object changes. Specifically, the risk control strategy associated with the second credit indicator is different from the risk control strategy associated with the first credit indicator. For example, in a payment scenario, the credit indicator of the preset object is the first credit indicator (for example, the security credit level indicated by the first credit indicator can be intermediate), then the risk control strategy associated with the first credit indicator can include a maximum payment amount of 1000 for an order; when the credit indicator of the preset object is adjusted to the second credit indicator (for example, the security credit level indicated by the second credit indicator can be advanced), then the risk control strategy associated with the second credit indicator can include a maximum payment amount of 2000 for an order.

[0048] 5. Cloud Technology

[0049] In this application, the aforementioned data processing scheme primarily includes the following processes: obtaining biometric data collected from a pre-set subject in a business scenario, performing identity recognition processing on the pre-set subject based on the biometric data, and adjusting the first credit indicator's rating based on the recognition results. These processes often involve extensive data computation and data storage services, requiring significant computer operating costs. Therefore, the data computation and data storage services involved in this application can all be implemented using cloud storage technology within cloud technology. Specifically, the blockchain is stored in the cloud using cloud storage technology. When transaction data generated during transactions within the business system needs to be stored on the blockchain, this transaction data can be uploaded to the blockchain in the cloud using cloud storage technology. Furthermore, when this transaction data needs to be read, it can be read from the blockchain in the cloud at any time. This reduces the storage requirements for computer equipment and expands the application scope of the blockchain.

[0050] Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, and application technology based on the cloud computing business model. It can form a resource pool that can be used flexibly and conveniently on demand. Cloud computing technology will become a key support. Cloud technology can include cloud storage technology. Cloud storage is a new concept that extends and develops from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as a storage system) uses cluster applications, grid technology, and distributed storage file systems to bring together a large number of different types of storage devices on the network through application software or application interfaces to work together and provide external data storage and service access capabilities.

[0051] 6. Artificial Intelligence

[0052] Artificial Intelligence (AI) is the theory, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. AI technology is an interdisciplinary discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Foundational AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, large-scale model training, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0053] The data processing solutions provided in the embodiments of the present application mainly involve the combination of machine learning technologies in the field of artificial intelligence. For example, a feature extraction model can be trained based on machine learning technology, and the trained feature extraction model (such as a first feature extraction model and a second feature extraction model) can be used to perform feature extraction processing on the biometric data of a preset object to obtain the biometric characteristics of the preset object. Subsequently, the identity of the preset object can be identified based on the biometric characteristics of the preset object. Among them, machine learning (ML) is a multi-disciplinary interdisciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their own performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all fields of artificial intelligence. Machine learning and deep learning generally include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and learning by formulas.

[0054] 7. Blockchain

[0055] Blockchain is a new application model for computer technologies such as distributed data storage, peer-to-peer (P2P) transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database consisting of a series of data blocks (also called blocks) linked together using cryptographic methods. Each block contains information about a batch of online transactions, which is used to verify the validity of that information (to prevent counterfeiting) and generate the next block. Blockchain uses cryptography to ensure that data cannot be tampered with or forged.

[0056] In this application, the data processing process involves a variety of data, such as biometric data, identification results, first credit indicators, second credit indicators, and risk control strategies. Optionally, this application can send this data to a blockchain for storage. The blockchain's immutability and traceability can prevent data tampering or leakage, thereby improving the security and reliability of the data processing process.

[0057] It should be noted that in this application, the relevant data involved in the data processing process, for example: biometric data, recognition results, first credit indicators, second credit indicators, risk control strategies, etc. When the above embodiments of this application are applied to specific products or technologies, user permission or consent must be obtained, and the relevant data collection, use and processing processes must comply with relevant national and regional laws, regulations and standards, and comply with the principles of legality, legitimacy and necessity, and do not involve obtaining data types prohibited or restricted by laws and regulations. In some optional embodiments, the relevant data involved in the embodiments of this application are obtained after the object has been individually authorized. In addition, when obtaining the individual authorization of the object, the purpose of the relevant data involved is indicated to the object.

[0058] The data processing system proposed in the embodiment of the present application is described in detail below with reference to FIG1 and FIG2 .

[0059] Please refer to Figure 1, which is a schematic diagram of the architecture of a data processing system provided in an embodiment of the present application. The data processing system architecture includes a server 104 and a terminal device cluster, wherein the terminal device cluster includes multiple terminal devices such as terminal device 101, terminal device 102, and terminal device 103. Any terminal device in the terminal device cluster can be directly or indirectly connected to server 104 via wired or wireless communication.

[0060] Each terminal device in the terminal device cluster can be a mobile phone, a tablet computer, a laptop computer, a PDA, a mobile internet device (MID), a vehicle-mounted device, an aircraft, a wearable device (smart devices such as smart watches, smart bracelets, pedometers, etc.), a virtual reality device (such as VR (Virtual Reality) device, AR (Augmented Reality) device), etc. It can be understood that the type of each terminal device in the terminal device cluster can be the same or different. For example, terminal device 101 can be a mobile phone, and terminal device 102 can also be a mobile phone. For another example, terminal device 101 can be a tablet computer, and terminal device 103 can be a vehicle-mounted device. This application does not limit the number and type of terminal devices in the terminal device cluster.

[0061] Server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0062] Next, taking any terminal device (e.g., terminal device 101) in the data processing system as an example, the interaction process between the terminal device 101 and the server 104 is described accordingly:

[0063] ① The terminal device 101 responds to the identity recognition request of the preset subject and then obtains the biometric data collected for the preset subject in the business scenario. Specifically, in the payment scenario, the identity recognition request can be a payment request submitted by the preset subject; in the access control scenario, the identity recognition request can be a verification request submitted by the preset subject.

[0064] ② The terminal device 101 sends the acquired biometric data to the server 104. After receiving the biometric data of the preset object, the server 104 can perform identity recognition processing on the preset object based on the biometric data to obtain an identification result of the preset object.

[0065] ③ The server 104 may obtain a first credit indicator corresponding to a preset object in a business scenario, and perform a level adjustment process on the first credit indicator according to the identification result to obtain a second credit indicator.

[0066] ④ Server 104 may send the second credit indicator to terminal device 101, where the risk control strategy associated with the second credit indicator is different from the risk control strategy associated with the first credit indicator. Subsequently, terminal device 101 may perform business management on the preset object based on the risk control strategy indicated by the second credit indicator in the business scenario.

[0067] It should be noted that the interactive process of the above-mentioned data processing is only for illustration and does not limit the specific execution process of the terminal device and the server. For example, obtaining the first credit indicator corresponding to the preset object in the business scenario can also be executed by any terminal device; for another example, the process of analyzing and processing the graph structure can also be executed by the server. Optionally, all processes involved in the above-mentioned data processing process of this application: the process of obtaining biometric data, the process of identity recognition processing of the preset object based on the biometric data, and the level adjustment processing of the first credit indicator according to the recognition result, etc. can be executed separately by any terminal device or server.

[0068] In one possible implementation, the data processing system provided by the embodiment of the present application can be deployed in a blockchain system. For example, the server 104 and each terminal device included in the terminal device cluster (such as terminal device 101, terminal device 102, and terminal device 103, etc.) can be regarded as a node device of the blockchain, together forming a blockchain network. Therefore, the data processing process of the embodiment of the present application involves: the process of obtaining biometric data, the process of performing identity recognition processing on a preset object based on the biometric data, and the process of adjusting the level of the first credit indicator based on the recognition result, etc., can all be executed on the blockchain. This can ensure the fairness and justice of the data processing process, make the data processing process traceable, and ensure data security during the data processing process, thereby improving the security and reliability of the entire data processing process.

[0069] The data processing system provided in this application can be applied to various business scenarios such as payment scenarios, identity verification scenarios, and gaming scenarios. Next, taking the palm swipe recognition scenario (such as payment scenarios and identity verification scenarios) as an example, the specific architecture involved in the palm swipe recognition scenario is elaborated in detail.

[0070] Please refer to Figure 2, which is a schematic diagram of the architecture of a palm-swipe recognition scenario provided in an embodiment of the present application. As shown in Figure 2, the palm-swipe recognition scenario involves: palm-swipe device A, palm-swipe device B, palm-swipe device C, and a back-end server. Optionally, palm-swipe device A can be terminal device 101 in the data processing system shown in Figure 1, and palm-swipe device B can be terminal device 102 in the data processing system shown in Figure 1, palm-swipe device C can be terminal device 103 in the data processing system shown in Figure 1, and the back-end server can be server 104 in the data processing system shown in Figure 1. Among them, the palm-swiping device A, palm-swiping device B, and palm-swiping device C respectively run the palm-swiping client (APP). The business scenarios applicable to different palm-swiping devices can be the same or different. For example, palm-swiping device A is applicable to the authentication scenario, and palm-swiping device B is applicable to the small payment scenario (payment amount within 10,000), and palm-swiping device B is applicable to the large payment scenario (payment amount greater than 10,000). The back-end server is used to provide back-end services for the above-mentioned palm-swiping devices (palm-swiping device A, palm-swiping device B, palm-swiping device C). Next, the palm-swiping device (for example, palm-swiping device A) and the back-end server are introduced in detail:

[0071] 1. Palm scanning device A.

[0072] The palm-swiping device A is equipped with: an acquisition device and a palm-swiping client / APP (Application). The acquisition device can be, for example, a 3D camera (a traditional camera with added hardware and software for detecting living things, including a depth camera and an infrared camera, to ensure information security). The 3D camera mainly includes: a color sensor (RGB sensor) and an infrared sensor (IR sensor); the palm-swiping client is equipped with: a palm recognition module, a scene configuration module, and a payment application module. The following describes each module in the palm-swiping device.

[0073] ①RGB Sensor and IR Sensor: Collectively referred to as acquisition devices, they are used to collect bio-streaming data of a preset object. The RGB Sensor captures color images, while the IR Sensor captures infrared images. Bio-streaming data of the preset object can be generated based on the color images captured by the RGB Sensor and the infrared images captured by the IR Sensor.

[0074] ② Palm Recognition Module: This module is used to receive biometric streaming data collected by the acquisition device (RGB sensor and IR sensor) and process the biometric streaming data to obtain biometric identification data. Data processing can include optimization processing and biopsy processing. Optimization processing involves selecting the optimal image from multiple biometric images included in the biometric streaming data according to preset selection criteria (e.g., clarity, image contrast, image brightness, etc.). Biopsy processing involves determining whether a preset object is alive.

[0075] ③ Scenario Configuration Module: This module is used to obtain the factory information of the palm-swiping device and generate the scenario configuration information of palm-swiping device A based on the factory information. The scenario configuration information of palm-swiping device A is then sent to the back-end server for recording and storage. The scenario configuration information of palm-swiping device A may include, but is not limited to: device identification (MCH_ID), SN (Serial Number, string serial number), the security verification level of the business scenario in which the palm-swiping device is located, on_auto_type (used to indicate whether it is unmanned self-service, i.e., unsupervised scenario), and app_type (business scenario, such as pay, identify).

[0076] ④ Payment application module: used to determine the business scenario of the current palm-swiping device based on the scenario configuration information of the current palm-swiping device, and start the corresponding business service. Specifically, based on the scenario configuration information, different business scenarios will start different business services. For example, if the business scenario is a payment scenario, then when the user's palm-swiping recognition is passed, the business service started by the payment application module is: return the payment code. For example, if the business scenario is an access control scenario, then when the user's palm-swiping recognition is passed, the business service started by the payment application module is: return the door opening instruction information (OPENID), etc. Optionally, when the user is subject to risk control, that is, when the current user has not been authenticated to a security credit level that meets the current business scenario, a prompt message will be displayed. The prompt message is used to prompt the current user that the business conditions are not met, and guide the user to scan the code with a mobile phone or upgrade the level in other business scenarios that can be upgraded after authentication and try again.

[0077] 2. Backend server:

[0078] The back-end server is used to provide back-end services for the palm-swiping device A. The back-end services may include: palm-swiping recognition service, scene management service, credit rating management service, payment service, etc.

[0079] ① Palm swiping recognition service: Receive biometric data (such as palm data) collected by the collection device in the palm swiping device, and perform feature extraction on the palm data to perform identity recognition processing on the preset object. Among them, the feature extraction here may include: palm print feature extraction and palm vein feature extraction, so that the palm print features and palm vein features of the preset object can be obtained, and the preset object can be subsequently identified based on the palm print features and palm vein features. The dual-factor features (palm print feature extraction and palm vein features) used in this application are richer and more accurate than single-factor features, which can improve the accuracy of identity recognition and ensure the security and reliability of the data processing process.

[0080] ② Scenario management and control service: used to identify the security credit level required for each business scenario and record the business scenario to which each palm-swiping device belongs. Among them, business scenarios may include: payment scenarios, identity verification scenarios (such as access control scenarios), and game scenarios. For example, the business scenario to which palm-swiping device A belongs is the identity verification scenario, and the security credit level required for the identity verification scenario is level 1; for another example, the business scenario to which palm-swiping device B belongs is the small-value payment scenario, and the security credit level required for the small-value payment scenario is level 2; for another example, the business scenario to which palm-swiping device C belongs is the large-value payment scenario, and the security credit level required for the large-value payment scenario is level 3.

[0081] ③ Credit Rating Management Service: This service records the current user's credit index (or security credit rating), assigns a unique risk control strategy, and provides guidance when the security credit rating indicated by the user's current credit index does not meet the scenario requirements. Each credit index is associated with a risk control strategy, and different risk control strategies are applicable to different business scenarios.

[0082] ④ Payment service: After the preset object is identified and the identification result is obtained, if the identification result is successful, the payment service can be called to complete the subsequent asset transfer processing (such as transferring the assets owned by the preset object to the account of the recipient).

[0083] In an embodiment of the present application, identity identification processing can be performed on users (i.e., preset objects) with identity identification needs in business scenarios, so that the credit indicators of the user can be flexibly adjusted according to the identification results obtained by the identity identification processing; since different credit indicators can be associated with different risk control strategies in business scenarios, as the user's credit indicators change (i.e., from the first credit indicator to the second credit indicator), the risk control strategy for the user also changes accordingly, that is, the present application can flexibly adjust the corresponding risk control strategy based on the indicator adjustment method in a specific business scenario, and can flexibly adjust the risk control strategy of the user for the same user, and the risk control management method is more flexible.

[0084] It can be understood that the system architecture diagram described in the embodiment of the present application is intended to more clearly illustrate the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided by the embodiment of the present application. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution provided by the embodiment of the present application is also applicable to similar technical problems.

[0085] Next, the data processing method proposed in the embodiment of the present application is described in detail.

[0086] Please refer to Figure 3, which is a flow chart of a data processing method provided in an embodiment of the present application. The data processing method can be executed by a computer device, which can be a terminal device or a server in the data processing system shown in Figure 1. The data processing method mainly includes but is not limited to the following steps S301 to S303:

[0087] S301: Obtain biometric data collected for a preset object in a business scenario.

[0088] In one possible implementation, biometric data may be data collected in real time in a business scenario. Specifically, in response to an identity recognition request submitted by a preset object in a business scenario, the identity recognition request is used to request identity recognition of the preset object; then, identity recognition technology (such as palm recognition technology, fingerprint recognition technology, face recognition technology, or pupil recognition technology, etc.) may be used to collect data from the preset object to obtain the biometric data of the preset object. Specifically, the types of biometric data collected using different types of identity recognition technologies are different. For example, the biometric data obtained using palm recognition technology is palm data; similarly, the biometric data obtained using fingerprint recognition technology is fingerprint data; the biometric data obtained using face recognition technology is face data, and so on. Under this implementation, biometric data is data collected in real time in a business scenario, and the real-time collected data is conducive to more accurate identity recognition processing of the preset object.

[0089] In another possible implementation, the biometric data may be historically collected data retrieved from a database. Specifically, the biometric data of a preset subject is retrieved from the database. This biometric data is pre-collected in a business scenario. In this implementation, the computer device can conveniently retrieve historical data collected for the preset subject from the database. Historical data here refers to data collected at a historical time. Historical time is based on the current system time and refers to time that has elapsed before the current system time.

[0090] The following takes real-time data collection as an example to explain the biometric data collection process in detail:

[0091] In one possible implementation, a computer device acquires biometric data collected for a preset object in a business scenario, which may include the following steps: ① Calling a collection device to collect biometric streaming data of the preset object, where the biometric streaming data includes multiple biometric images collected from the preset object, wherein the biometric streaming data may include, but is not limited to, video, image, audio, and other data. Specifically, the biometric streaming data of the preset object may be multiple biometric images collected by the collection device within a preset time period (e.g., half a minute, one minute), and the types of biometric images collected in different scenarios are different. For example, in a palm recognition scenario, the biometric image collected by the collection device is a palm image; in another example, in a fingerprint recognition scenario, the biometric image collected by the collection device is a fingerprint image; and in another example, in a face recognition scenario, the biometric image collected by the collection device is a face image.

[0092] ② Select and process multiple biometric images according to preset selection conditions to obtain biometric data of a preset subject. Here, the preset selection conditions include any one or more of image size (e.g., image length and width), shooting angle (e.g., 90 degrees, 45 degrees), image contrast, image brightness, and clarity. Optionally, if multiple biometric images are selected according to the preset selection conditions, a further selection process may be performed from the multiple biometric images. This further selection process may include random selection, selection based on acquisition time, and other selection methods. For example, if three biometric images are selected according to the preset selection conditions: img1, img2, and img3, and the acquisition times of these three biometric images are in the order of img1 > img2 > img3, then img1 may be used as the final selected biometric data. Optionally, after the biometric images are selected according to the preset selection conditions, the selected biometric images may be further processed (e.g., image enhancement), and the processed biometric images may be used as the biometric data of the preset subject.

[0093] According to the above method, the collected biological streaming media data is optimally processed to obtain the biometric data used for identity recognition, which can make the biometric data more accurate and reliable.

[0094] S302: Perform identity recognition processing on a preset object based on the biometric recognition data to obtain a recognition result of the preset object.

[0095] Specifically, the essence of performing identity recognition processing on a preset object is to identify the identity of the preset object. Generally speaking, a biometric feature is a feature that can uniquely identify the identity of a user. Therefore, when the present application performs identity recognition processing on a preset object based on the biometric data of the preset object, it specifically includes: obtaining the type of biometric data, and adopting an adaptive identity recognition technology to perform identity recognition according to different types of biometric data (wherein one type of biometric data is adapted to one identity recognition technology), so that the user's identity can be identified and authenticated. For example, if the biometric data is palm data, then palm recognition technology can be used to perform palm recognition processing on the palm data; for another example, if the biometric data is fingerprint data, then fingerprint recognition technology can be used to perform fingerprint recognition processing on the fingerprint data; for another example, if the biometric data is face data, then face recognition technology can be used to perform face recognition processing on the face data.

[0096] The specific process of how to perform identity recognition processing on the preset object is described in detail below.

[0097] In one possible implementation, a computer device performs identity recognition processing on a preset subject based on biometric data to obtain an identification result for the preset subject. The steps may include: 1. Performing feature extraction processing on the biometric data to obtain biometric features of the preset subject. For example, if the biometric data is palm data, the biometric features obtained through feature extraction may be palm features; if the biometric data is fingerprint data, the biometric features obtained through feature extraction may be fingerprint features; and if the biometric data is facial data, the biometric features obtained through feature extraction may be facial features. 2. Obtaining registration data for the preset subject. The registration data is generated after the preset subject successfully registers its identity in a business scenario and includes registration features. It should be noted that if the preset subject registers its identity based on palm registration, the registration features of the preset subject include palm features; similarly, if the preset subject registers its identity based on facial registration, the registration features of the preset subject include facial features. 3. Performing identity recognition processing on the preset subject based on the biometric features and the registration features of the preset subject to obtain an identification result for the preset subject. The identification result may include either a successful or failed identification. Specifically, feature matching can be performed on the biometric features and the registered features to identify the preset object. Specifically, the feature similarity between the biometric features and the registered features of the preset object can be calculated. If the feature similarity is greater than or equal to the similarity threshold, it can be determined that the identity recognition of the preset object has passed, that is, the recognition result is determined to be a successful recognition; if the feature similarity is less than the similarity threshold, it can be determined that the identity recognition of the preset object has failed, that is, the recognition result is determined to be a failed recognition.

[0098] Next, taking palm data as an example of biometric data, the specific process of performing feature extraction on palm data is described in detail. In one possible implementation, a computer device performs feature extraction on biometric data to obtain the biometric features of a preset object, which may include the following steps:

[0099] ① Performing palm vein feature extraction on the palm data to obtain the palm vein features of a preset object; and performing palm print feature extraction on the palm data to obtain the palm print features of the preset object. Specifically, a first feature extraction model can be used to extract the palm print features of the preset object, and a second feature extraction model can be used to extract the palm vein features of the preset object. The first feature extraction model and the second feature extraction model can be the same or different. For example, the first feature extraction model or the second feature extraction model can be a neural network model. The neural network model can include, but is not limited to: CNN (Convolutional neural networks) model, RNN (Recurrent neural networks) model, LSTM (Long Short Term Memory) model, GRU (Gated recurrent units) model, etc. The embodiment of the present application does not specifically limit the model structure of the neural network model.

[0100] ② Performing feature fusion processing on the palm print features and palm vein features to obtain the biometric features of the preset object; wherein the feature fusion processing includes at least any of the following: feature weighting processing, feature alignment processing, and feature calculation processing. For example, the palm print features and palm vein features can be weighted to obtain the biometric features of the preset object; for another example, the palm print features and palm vein features can be averaged to obtain the biometric features of the preset object; for another example, the palm print features and palm vein features can be aligned (for example, if the feature dimension of the palm print feature is k1×k2 and the feature dimension of the palm vein feature is k2×k3, the feature dimension of the palm vein feature can be aligned with the feature dimension of the palm print feature. Since the feature dimensions of the two are the same after the feature alignment processing, it can facilitate subsequent feature processing) to obtain the biometric features of the preset object.

[0101] According to the above method, when the biometric data of the preset subject is palm data, the dual-factor features of the palm print and palm vein (palm vein features and palm print features) can be extracted for identity recognition. The advantage of dual-factor features over single-factor features (palm vein features or palm print features) is that they provide higher accuracy and security in identity recognition. In addition, palm vein features are more difficult to identify and are not easily forged or simulated. Therefore, the extraction of dual-factor features can improve the accuracy and reliability of identity recognition of the preset subject.

[0102] S303: Obtain a first credit indicator corresponding to a preset object in a business scenario, and perform a grade adjustment process on the first credit indicator based on the identification result to obtain a second credit indicator; wherein, in the business scenario, the risk control strategy associated with the second credit indicator is different from the risk control strategy associated with the first credit indicator.

[0103] Specifically, in a business scenario, the risk control strategy for the same user can be dynamically adjusted as the credit indicator level is adjusted, that is, for the preset object, the risk control strategy associated with the second credit indicator is different from the risk control strategy associated with the first credit indicator. For example, the business scenario is a payment scenario. In this payment scenario, the risk control strategy associated with the security credit level (e.g., intermediate) indicated by the first credit indicator of the preset object can be: the strategy adopted when the maximum payment amount of any order paid by the preset object exceeds 1,000; the risk control strategy associated with the security credit level (e.g., advanced) indicated by the first credit indicator of the preset object can be: the strategy adopted when the maximum payment amount of any order paid by the preset object exceeds 2,000. That is to say, in the payment scenario, the risk control strategy is used to control the maximum amount paid by the user for a single order.

[0104] In one possible implementation, the computer device may adjust the first credit indicator based on the recognition result to obtain the second credit indicator, which may include: if the recognition result is successful, then upgrading the first credit indicator according to a first adjustment method to obtain the second credit indicator. The first adjustment method is used to indicate upgrading the security credit level indicated by the first credit indicator. If the security credit level is level 1, then the preset object may be adjusted from level 1 to level 2 according to the first adjustment method to obtain the second credit indicator of the preset object.

[0105] In another possible implementation, the computer device adjusts the first credit indicator based on the identification result to obtain a second credit indicator, which may also include: obtaining scenario configuration information for the business scenario, the scenario configuration information including the security verification level of the business scenario; if the security verification level of the business scenario meets the level adjustment conditions and the identification result is successful, then upgrading the first credit indicator according to the first adjustment method to obtain the second credit indicator. The security verification level can be used to indicate whether the business scenario is subject to object supervision. If the business scenario is subject to object supervision, the security verification level of the business scenario is the first level; if the business scenario is subject to object supervision, the security verification level of the business scenario is the second level.

[0106] The specific process of adjusting the grade of the first credit indicator is described in detail below.

[0107] 1. Adjust the grade of the first credit indicator based on the identification results.

[0108] In one possible implementation, the computer device adjusts the level of the first credit indicator based on the recognition result, which may include the following methods: ① If the recognition result is successful, the first credit indicator is upgraded according to the first adjustment method to obtain a second credit indicator, for example, upgrading the preset object from level 2 (first credit indicator) to level 3 (second credit indicator); ② If the recognition result is failed, the first credit indicator is downgraded according to the second adjustment method to obtain a third credit indicator, for example, downgrading the preset object from level 2 (first credit indicator) to level 1 (third credit indicator); ③ If the recognition result is failed, the first credit indicator is maintained, that is, the preset object is maintained at level 2 (first credit indicator). The first adjustment method and the second adjustment method are different; the differences here may include: different level adjustment ranges for the first credit indicator (i.e., the level adjustment range indicated by the first adjustment method is different from the level adjustment range indicated by the second adjustment method) and different level adjustment methods for the first credit indicator.

[0109] Specifically, if the security credit level indicated by the first credit indicator is intermediate, the adjustment range indicated by the first adjustment method may be to increase one level, and the credit indicator of the preset object may be increased from intermediate to advanced; if the security credit level indicated by the first credit indicator is intermediate, the adjustment range indicated by the second adjustment method may be to decrease one level, and the credit indicator of the preset object may be decreased from intermediate to primary. It should be noted that the adjustment range of the first adjustment method and the adjustment range of the second adjustment method may be the same or different. For example, the level adjustment process may include: when the level is increased, one level may be increased; when the level is decreased, one level may be decreased; for example, the level adjustment process may also include: when the level is increased, two levels may be increased; when the level is decreased, one level may be decreased. In this implementation method, the credit indicator may be adjusted according to the recognition result. If the recognition is successful, the security credit level of the credit indicator of the preset object may be increased; if the recognition fails, the security credit level of the credit indicator of the preset object may be decreased.

[0110] 2. Adjust the grade of the first credit indicator based on the business scenario and identification results.

[0111] In one possible implementation, the computer device may adjust the level of the first credit indicator based on the recognition result and the scenario configuration information of the business scenario, which may include the following methods:

[0112] ① If the security verification level of the business scenario meets the level adjustment conditions and the identification result is successful, the first credit indicator is upgraded according to the first adjustment method to obtain the second credit indicator. For example, if the business scenario is a scenario with object supervision (i.e., the security verification level of the business scenario is Level 1) and the identification result is successful, the preset object can be upgraded from Level 2 (first credit indicator) to Level 3 (second credit indicator).

[0113] ② If the security verification level of the business scenario does not meet the level adjustment conditions, or the identification result is an identification failure, the first credit indicator will be downgraded according to the second adjustment method to obtain the third credit indicator. For example, if the business scenario is a scenario where there is no object supervision (i.e., the security verification level of this business scenario is Level 2), or the identification result is an identification failure, the preset object can be downgraded from Level 2 (first credit indicator) to Level 1 (third credit indicator).

[0114] ③ If the security verification level of the business scenario meets the level adjustment conditions and the recognition result is recognition failure, the first credit indicator level will be maintained. For example, if the business scenario is a scenario with object supervision (i.e., the security verification level of the business scenario is level 1) and the recognition result is recognition success, the preset object level 2 (first credit indicator) can be maintained.

[0115] ④ If the security verification level of the business scenario does not meet the level adjustment conditions and the recognition result is successful, the first credit indicator level will be maintained. For example, if the business scenario is a scenario where there is no object supervision (i.e., the security verification level of this business scenario is Level 2) and the recognition result is successful, the preset object level 2 (first credit indicator) can be maintained.

[0116] In methods 1-4 above, the level adjustment condition may include the presence of an object for supervision. For example, if the business scenario's security verification level is level 1, then the level adjustment condition is met; if the business scenario's security verification level is level 2, then the level adjustment condition is not met. In other words, the level adjustment condition indicates that the level adjustment can only be performed in a scenario with object supervision.

[0117] 3. Adjust the level of the first credit indicator based on the business scenario, historical business data, and identification results.

[0118] In one possible implementation, if the security verification level of the business scenario does not meet the level adjustment conditions (i.e., the business scenario is a scenario where there is no object supervision), the historical business data of the preset object can be obtained, and the first credit indicator of the preset object can be adjusted in level according to the obtained historical business data and the identification result. Among them, the historical business data may at least include: the business data generated by the preset object in the business scenario during the historical time period, and the data generated by the preset object in other business scenarios (such as scenarios where there is object supervision) during the historical time period. For example, in a payment scenario, the historical business data may include the historical payment data generated by the preset object within a historical month (i.e., looking back one month from the current time point). The computer device may use the historical payment data of the preset object obtained as sample data, and train a level recognition model based on the sample data. The level recognition model can be used to identify the security credit level of the preset object in the business scenario. Here, the level recognition model can be a neural network model of any network structure, which is not limited in the embodiments of the present application. Subsequently, the preset object can be graded and identified based on the trained grade identification model. The grade identification here refers to identifying the security credit grade of the preset object. ① For example, if the security credit grade obtained by identification meets the credit grade threshold (for example, advanced) and the identification result is successful identification, the preset object can be graded and upgraded, that is, the preset object is upgraded from the first credit indicator to the second credit indicator; ② For another example, if the security credit grade obtained by identification meets the credit grade threshold (for example, advanced), or the identification result is identification failure, the preset object can be grade maintained; ③ For another example, if the security credit grade obtained by identification meets or does not meet the credit grade threshold and the identification result is identification failure, the preset object can be grade downgraded, that is, the preset object is reduced from the first credit indicator to the third credit indicator.

[0119] Specifically, historical payment data may include: payment time, payment quantity, payment amount and other data. In the process of training the grade recognition model based on the historical payment data, the computer device may specifically include: first, performing data analysis on the historical payment data of the preset object to extract payment features (such as whether the payment is on time, whether the payment frequency is frequent, and whether the payment amount is abnormal); then, training the grade recognition model according to the extracted payment features. In this way, the grade recognition model can be trained based on the user's historical payment data, and the trained grade recognition model can be used to evaluate the user's security credit level to meet the special business needs of business scenarios that are unsupervised for a long time and can be adjusted according to personal historical business data. Since the grade recognition model is trained based on the user's historical business data, the credibility of the security credit level identified by the grade recognition model is high, so that the user's credit index can be accurately and reliably adjusted.

[0120] In an embodiment of the present application, identity identification processing can be performed on users (i.e., preset objects) with identity identification needs in business scenarios, so that the credit indicators of the user can be flexibly adjusted according to the identification results obtained by the identity identification processing; since different credit indicators can be associated with different risk control strategies in business scenarios, as the user's credit indicators change (i.e., from the first credit indicator to the second credit indicator), the risk control strategy for the user also changes accordingly, that is, the present application can flexibly adjust the corresponding risk control strategy based on the indicator adjustment method in a specific business scenario, and can flexibly adjust the risk control strategy of the user for the same user, and the risk control management method is more flexible.

[0121] Please refer to Figure 4, which is a flow chart of another data processing method provided in an embodiment of the present application. The data processing method can be executed by a computer device, which can be a terminal device or a server in the data processing system shown in Figure 1. The data processing method mainly includes but is not limited to the following steps S401 to S404:

[0122] S401: Obtain biometric data collected for a preset object in a business scenario.

[0123] In one possible implementation, a computer device acquires biometric data collected for a preset subject in a business scenario, which may include the following steps: ① Invoking a collection device to collect biometric streaming data of the preset subject, where the biometric streaming data includes multiple biometric images collected from the preset subject. The biometric streaming data may include, but is not limited to, video, image, audio, and other data. Specifically, the biometric streaming data of the preset subject may be multiple biometric images collected by the collection device within a preset time period (e.g., half a minute, one minute). The types of biometric images collected in different scenarios vary. For example, in a palm recognition scenario, the biometric image collected by the collection device is a palm image; in a fingerprint recognition scenario, the biometric image collected by the collection device is a fingerprint image; and in a face recognition scenario, the biometric image collected by the collection device is a face image. ② Selecting and processing the multiple biometric images according to preset selection conditions to obtain the biometric data of the preset subject. The preset selection conditions herein include any one or more of image size (e.g., image length and width), shooting angle (e.g., 90 degrees, 45 degrees), image contrast, image brightness, and image clarity. Optionally, if multiple biometric images are selected according to the preset selection conditions, further selection processing can be performed from the multiple biometric images. The selection processing here can include: random selection, selection according to acquisition time, etc. For example, if three biometric images are selected according to the preset selection conditions: img1, img2, and img3, and the acquisition times of these three biometric images are: img1>img2>img3, then img1 can be used as the final selected biometric data. Optionally, after the biometric images are selected according to the preset selection conditions, image processing (such as image enhancement) can be further performed on the selected biometric images, and the processed biometric images can be used as the biometric data of the preset object.

[0124] According to the above method, the collected biological streaming media data is optimally processed to obtain the biometric data used for identity recognition, which can make the biometric data more accurate and reliable.

[0125] S402: performing identity recognition processing on a preset object based on the biometric recognition data to obtain a recognition result of the preset object.

[0126] Specifically, the essence of performing identity recognition processing on a preset object is to identify the identity of the preset object. Generally speaking, a biometric feature is a feature that can uniquely identify the identity of a user. Therefore, the present application can perform identity recognition processing on a preset object based on the biometric data of the preset object. Specifically, corresponding technologies can be adopted according to different types of biometric data to perform identity recognition, so that the user's identity can be identified and authenticated. For example, if the biometric data is palm data, palm recognition technology can be used to perform palm recognition processing on the palm data; for another example, if the biometric data is fingerprint data, fingerprint recognition technology can be used to perform fingerprint recognition processing on the fingerprint data; for another example, if the biometric data is face data, face recognition technology can be used to perform face recognition processing on the face data.

[0127] It should be noted that the execution operations corresponding to steps S401-S402 in the embodiment of the present application can be detailed in the execution operations corresponding to steps S301-S302 in the embodiment of Figure 3 above, and the embodiment of the present application will not be repeated here.

[0128] In one possible implementation, a computer device performs identity recognition processing on a preset object based on biometric data, and after obtaining the recognition result of the preset object, further includes the following steps: if the recognition result is successful, outputting a prompt interface, the prompt interface including a prompt area and an adjustment control, the prompt area being used to prompt the preset object whether to authorize the adjustment of the level of the first credit indicator, and the adjustment control being used to receive a confirmation operation for the adjustment of the level of the first credit indicator; in response to the authorization confirmation operation triggered by the preset object in the prompt area, triggering the execution of the steps of obtaining the first credit indicator corresponding to the preset object in the business scenario, and adjusting the level of the first credit indicator according to the recognition result. Specifically, when the recognition result is successful, in response to the authorization confirmation operation triggered for the first control in the prompt area, the level of the first credit indicator is adjusted to the second credit indicator; when the recognition result is unsuccessful, in response to the authorization confirmation operation triggered for the second control in the prompt area, the level of the first credit indicator is reduced to the third credit indicator; when the recognition result is successful or unsuccessful, in response to the authorization confirmation operation triggered for the third control in the prompt area, the level of the first credit indicator is maintained.

[0129] The interface process of how to adjust the level will be described below with reference to FIG. 5 a and FIG. 5 b .

[0130] Please refer to Figure 5a, which is a schematic diagram of an interface for a grade adjustment process provided in an embodiment of the present application. As shown in Figure 5a, prompt interface S501 is provided with a prompt area 5011, and prompt area 5011 displays a prompt message, which is used to prompt the preset object whether to authorize the grade adjustment process of the first credit indicator. The grade adjustment process includes: any one or more of: grade reduction process, grade increase process, and grade retention process; for example, prompt message 5012 may be: The current grade can be upgraded, please confirm whether to upgrade the grade. Prompt interface S501 is also provided with an adjustment control, which is used to receive a confirmation operation for the grade adjustment process of the first credit indicator. Among them, the adjustment controls include: a first control 5013, a second control 5014, and a third control 5015; and, the prompt interface S501 is also provided with a cancel control 5016, the first control 5013 is used to receive the confirmation operation of the level upgrade processing; the second control 5014 is used to receive the confirmation operation of the level reduction processing; the third control 5015 is used to receive the confirmation operation of the level reduction processing; and the cancel control 5016 is used to receive the cancellation operation of the level adjustment processing. For example, if the prompt information indicates that the first credit indicator is to be upgraded, the user can click the first control 5013 to upgrade the first credit indicator to the second credit indicator. At this time, since the level adjustment process is a level upgrade process, the status of the second control 5014 and the third control 5015 can be set to an unclickable state, that is, the second control 5014 and the third control 5015 cannot respond to the user's click operation (such as single click, double click, long press, etc.). In this case, the user is allowed to click the first control 5013 and the cancel control 5016, but the user is not allowed to click the second control 5014 and the third control 5015. Similarly, if the prompt information indicates that the first credit indicator is to be downgraded, in this case, the user is allowed to click the second control 5014 and the cancel control 5016, but the user is not allowed to click the first control 5013 and the third control 5015.

[0131] Please refer to Figure 5b, which is a schematic diagram of another interface for grade adjustment processing provided in an embodiment of the present application. As shown in Figure 5b, prompt interface S502 is provided with a prompt area 5021. Prompt information is displayed in prompt area 5021. This prompt information is used to prompt the preset subject whether to authorize the grade adjustment processing of the first credit indicator. Grade adjustment processing includes any one or more of grade reduction processing, grade increase processing, and grade maintenance processing. For example, prompt information 5022 may be: Please confirm whether to adjust the grade. Prompt interface S502 is also provided with an adjustment control 5023 and a cancel control 5024. If the user clicks the cancel control 5024, it means that the user does not agree to the grade adjustment. If the user clicks the adjustment control 5023, prompt interface S503 may be displayed. Among them, prompt information 5031 is displayed in prompt interface S503. For example, prompt information 5031 may be: The current grade can be upgraded. Please confirm whether to upgrade the grade. In this case, the prompt interface S503 displays a first control 5032 and a cancel control 5033. If the user clicks the first control 5031, it means that the user agrees to the level adjustment and can upgrade the first credit indicator to the second credit indicator.

[0132] Based on the above description, after the user (preset object) is identified, a prompt interface can be output to allow the user to customize whether to adjust the level. This method can meet the special business needs of users who do not want to adjust the level, thereby improving the user experience in business scenarios.

[0133] S403: Obtain a first credit indicator corresponding to a preset object in a business scenario.

[0134] In one possible implementation, the first credit indicator refers to the credit indicator assigned to the preset object after the preset object completes identity registration in the business scenario; if the business scenario is a payment scenario; then before the computer device obtains the biometric data collected for the preset object in the business scenario, it also includes: responding to the identity registration request of the preset object in the payment scenario, obtaining the scene configuration information of the payment scene, the scene configuration information includes the security verification level of the payment scene; if the security verification level of the payment scene meets the level adjustment conditions, then in the payment scenario, the credit indicator is assigned to the preset object according to the security verification level of the payment scene; if the security verification level of the payment scene does not meet the level adjustment conditions, then in the payment scenario, the reference credit indicator is determined as the credit indicator assigned to the preset object.

[0135] Specifically, if the payment scenario is a scenario with object supervision (that is, the security verification level of the payment scenario is the first level, for example, the first level is advanced), then the security verification level (advanced) of the payment scenario can be used as the first credit indicator (advanced) of the preset object; if the payment scenario is a scenario without object supervision (that is, the security verification level of the payment scenario is the second level), then the first credit indicator of the user can be defaulted to primary (reference credit indicator). In this way, the corresponding credit indicator can be assigned to the preset object according to the security verification level of the business scenario during identity registration (that is, whether there is object supervision), so that the credit indicator of the preset object can be more in line with the scenario requirements.

[0136] S404: Acquire scenario configuration information of the business scenario, and perform level adjustment processing on the first credit indicator according to the scenario configuration information and the recognition result to obtain a second credit indicator.

[0137] In one possible implementation, a computer device adjusts the first credit indicator based on the scenario configuration information and the recognition result to obtain a second credit indicator. This may include: if the security verification level of the business scenario satisfies the level adjustment condition and the recognition result is successful, then upgrading the first credit indicator according to the first adjustment method to obtain the second credit indicator. The security verification level can be used to indicate whether the business scenario is subject to object supervision. If the business scenario is subject to object supervision, the security verification level of the business scenario is level 1; if the business scenario is subject to object supervision, the security verification level of the business scenario is level 2. The level adjustment condition may include the condition that an object is subject to object supervision. For example, if the security verification level of the business scenario is level 1, the business scenario satisfies the level adjustment condition; if the security verification level of the business scenario is level 2, the business scenario does not meet the level adjustment condition. For example, if the business scenario is subject to object supervision (i.e., the security verification level of the business scenario is level 1) and the recognition result is successful, the preset object may be upgraded from level 2 (first credit indicator) to level 3 (second credit indicator).

[0138] It should be understood that the data processing method provided in the embodiments of the present application is applicable to business scenarios such as payment scenarios, access control scenarios, game scenarios, etc., and can identify the identity of users in the above business scenarios and flexibly adjust the user's security credit level (i.e., credit index) according to the identification results to change the user's risk control strategy in the corresponding business scenario, thereby meeting more business needs in the business scenario.

[0139] The complete process of the data processing scenario is described in detail below with reference to FIG6 .

[0140] Please refer to Figure 6, which is a flow chart of a data processing scenario provided by an embodiment of the present application. As shown in Figure 6, the process of the data processing scenario mainly involves: palm-brush device A, palm-brush device B, palm-brush device C, and the back-end server in the data processing system shown in Figure 2. Among them, the process of the data processing scenario mainly includes but is not limited to the following steps S601 to S611. Specifically, the process of the data processing scenario mainly involves: scenario configuration process, identity registration process and palm-brush recognition process. The specific steps of the above three processes are explained in turn below.

[0141] 1. Scene configuration process (S601-S603).

[0142] S601: The palm-swiping device A submits a first scenario configuration request of the unattended scenario A to the backend server.

[0143] In a specific implementation, the business scenario A to which the palm-swiping device A belongs is a scenario without object supervision (i.e., unattended scenario A). This business scenario A is an authentication scenario. The palm-swiping device A can generate a first scenario configuration request for a preset object in business scenario A and send the first scenario configuration request to the backend server. The first scenario configuration request includes scenario configuration information for business scenario A. For example, the scenario configuration information may include, but is not limited to: the security verification level of business scenario A (used to indicate whether there is object supervision / whether there is human supervision).

[0144] Optionally, the backend server may respond to the first scenario configuration request and perform scenario configuration for business scenario B based on the scenario configuration information of business scenario A, obtaining a configuration result. The configuration result may include: configuration success or configuration failure. Subsequently, the backend server may return the configuration result to palm-brush device A (as shown in step S6011).

[0145] S602: The palm-swiping device B submits a second scenario configuration request for the attended scenario B to the backend server.

[0146] In a specific implementation, if business scenario B to which palm-swiping device B belongs is a scenario with object supervision (i.e., human-attended scenario B), and this business scenario is a small-amount payment scenario (i.e., the payment amount is less than a first payment threshold), palm-swiping device B may generate a second scenario configuration request for a preset object in business scenario B and send the second scenario configuration request to the backend server. The second scenario configuration request includes scenario configuration information for business scenario B. For example, the scenario configuration information may include, but is not limited to: the security verification level of business scenario B (used to indicate whether there is object supervision / whether there is human-attended).

[0147] Optionally, the backend server may respond to the second scenario configuration request and perform scenario configuration for business scenario B based on the scenario configuration information of business scenario B, obtaining a configuration result. The configuration result may include: configuration success or configuration failure. Subsequently, the backend server may return the configuration result to palm-brush device B (as shown in step S6021).

[0148] S603: The palm-swiping device C submits a third scenario configuration request of the attended scenario C to the backend server.

[0149] In a specific implementation, if the business scenario C to which the palm-swiping device C belongs is a scenario with object supervision (i.e., a person-attended scenario C), and the business scenario C is a large-value payment scenario (i.e., the payment amount is greater than or equal to the second payment threshold, and the second payment threshold is greater than the first payment threshold), the palm-swiping device C can generate a third scenario configuration request for a preset object in the business scenario C and send the third scenario configuration request to the backend server. The third scenario configuration request includes scenario configuration information for the business scenario C. For example, the scenario configuration information may include, but is not limited to: the security verification level of the business scenario C (used to indicate whether there is object supervision / whether there is a person on duty).

[0150] Optionally, the backend server may respond to the third scenario configuration request and perform scenario configuration for business scenario C based on the scenario configuration information of business scenario C to obtain a configuration result. The configuration result may include: configuration success or configuration failure. Subsequently, the backend server may return the configuration result to palm-brush device C (as shown in step S6031).

[0151] 2. Identity registration process and palm recognition process (S604-S611).

[0152] S604: The palm-swiping device A obtains an identity registration request for palm-swiping authentication of a preset object.

[0153] In a specific implementation, the preset object can register its identity in business scenario A (i.e., the access control scenario for palm swiping authentication) to which palm-swiping device A belongs, and generate an identity registration request. The identity registration request may include the identity information of the preset object. For example, the identity information may include, but is not limited to, an identity identifier, ID, and other data used to uniquely identify the user. In this application, since it mainly involves palm swiping recognition, the identity information of the preset object may include the palm data of the preset object.

[0154] S605: The palm-swiping device A registers its identity with the backend server based on the identity registration request.

[0155] In a specific implementation, after receiving the identity registration request, the backend server may register the preset object according to the preset object's identity information. After the identity registration is completed, the backend server may assign a credit indicator (e.g., a first credit indicator) to the preset object in business scenario A to generate a registration result. The registration result may include: registration success or registration failure.

[0156] Optionally, the backend server may return the registration result to the palm-brush device A (as shown in step S6051 ), and the palm-brush device A may return the registration result to a preset object (as shown in step S6052 ).

[0157] S606: The palm-swiping device A obtains a palm-swiping authentication request from a preset object.

[0158] In specific implementation, the preset object needs to request to open the door in business scenario A (i.e., the access control scenario of palm swiping authentication), and can submit a palm swiping authentication request to the palm swiping device A. The palm swiping authentication request is used to request identity recognition of the preset object (such as palm recognition).

[0159] S607: The palm-swiping device A sends the palm-swiping authentication request to the back-end server.

[0160] In specific implementation, the palm-swiping device A responds to the palm-swiping authentication request, and calls the collection device in business scenario A to collect biometric data of the preset object, and sends the collected biometric data to the back-end server.

[0161] Optionally, the backend server performs identity recognition processing on the preset object based on the biometric data, obtains the recognition result of the preset object (recognition success or recognition failure), and returns the recognition result to the palm-swiping device A (as shown in step S6071). Subsequently, the palm-swiping device can return the recognition result to the preset object (as shown in step S6072).

[0162] S608: The palm-swiping device B obtains a palm-swiping payment request (small amount) from a preset object.

[0163] In specific implementation, the asset requested for processing in the palm-swipe payment request is a small-value asset, where the so-called small-value asset refers to an asset amount that is less than the first payment threshold.

[0164] S609: The palm-swiping device B requests the backend server to make a palm-swiping payment (small amount).

[0165] In specific implementation, the back-end server responds to the small-amount palm-swipe payment request of the preset object and performs palm-swipe recognition processing on the preset object. If the palm-swipe recognition of the preset object is passed, the payment service can be called to perform asset transfer processing (payment processing) to generate a payment result, which may include payment success or payment failure.

[0166] Optionally, the backend service may return the payment result to the palm-swiping device B (as shown in step S6091); the palm-swiping device B may return the payment result to a preset object (as shown in step S6092).

[0167] S610: The palm-swiping device C obtains a palm-swiping payment request (large amount) of a preset object.

[0168] In specific implementation, the asset requested for processing in the palm-swipe payment request is a large-value asset. The so-called large-value asset means that the amount of the asset is greater than or equal to the second payment threshold, and the second payment threshold is greater than the first payment threshold.

[0169] S611: The palm-swiping device C requests the backend server to make a palm-swiping payment (large amount).

[0170] In specific implementation, the back-end server responds to the large-amount palm-swipe payment request of the preset object and performs palm-swipe recognition processing on the preset object. If the palm-swipe recognition of the preset object is passed, the payment service can be called to perform asset transfer processing (payment processing) to generate a payment result, which may include payment success or payment failure.

[0171] Optionally, the backend service may return the payment result to the palm-swiping device C (as shown in step S6111 ); the palm-swiping device C may return the payment result to a preset object (as shown in step S6112 ).

[0172] The following uses the payment scenario as an example to explain the palm swiping recognition process in detail.

[0173] In one possible implementation, the business scenario is a payment scenario, and the risk control strategy in the payment scenario is used to indicate: one credit indicator corresponds to one payment amount; the computer device adjusts the level of the preset object from the first credit indicator according to the identification result, and after obtaining the second credit indicator, it also includes the following steps: detecting the amount of assets requested to be processed in the payment scenario; if the payment amount corresponding to the second credit indicator is greater than or equal to the amount of assets requested to be processed, calling the payment service to perform transfer processing on the assets corresponding to the asset amount; if the payment amount corresponding to the second credit indicator is less than the amount of assets requested to be processed, outputting a prompt message, and the prompt message is used to trigger the level adjustment processing of the second credit indicator of the preset object, so that the payment amount corresponding to the second credit indicator after the level adjustment processing is greater than or equal to the amount of assets requested to be processed.

[0174] Please refer to Figure 7a, which is a flow chart of a palm-swipe payment scenario provided by an embodiment of the present application. As shown in Figure 7a, a preset object can be palm-swipe identified in the payment scenario, and a palm-swipe device is called to collect the palm data of the preset object, the palm data is displayed in the palm-swipe identification interface, and the palm data is identified and processed. If the identification is successful, and the payment amount corresponding to the second credit indicator of the preset object is greater than or equal to the asset amount requested for processing in the current payment scenario, the payment processing interface is displayed, and the payment service is called to perform payment processing on the assets corresponding to the asset amount. Please refer to Figure 7b, which is a flow chart of another palm-swipe payment scenario provided by an embodiment of the present application. As shown in Figure 7b, a preset object can be palm-swipe identified in the payment scenario. If the payment amount corresponding to the second credit indicator of the preset object is less than the asset amount requested for processing in the current payment scenario, a prompt message is output, for example, the prompt message includes: Your security credit level does not meet the current payment conditions, please try again later! Subsequently, the second credit indicator can be upgraded in other authenticatable business scenarios before making a payment. In this way, the risk control strategy can be flexibly adjusted in the payment scenario based on the level of security credit indicated by the user's credit indicators, thereby ensuring the reliability and security of the relevant business processing process.

[0175] In the embodiments of this application, different palm-swipe devices need to be configured for different business scenarios, so that users can complete identity registration in the configured corresponding business scenarios (such as palm-swipe authentication scenarios, payment scenarios, etc.); subsequently, users can perform related business processing operations such as opening doors and making payments in the business scenarios. This application trusts users to register for their own scenarios while combining it with a continuously adjusted and refined risk control strategy to gradually verify and upgrade the user's palm-swipe authentication, thereby gradually improving the user experience in various business scenarios while ensuring security.

[0176] The above details the method of the embodiment of the present application. In order to facilitate the better implementation of the above scheme of the embodiment of the present application, the device of the embodiment of the present application is provided below accordingly. Next, combined with the data processing scheme provided in the above embodiment of the present application, the relevant devices of the embodiment of the present application are introduced accordingly.

[0177] Please refer to Figure 8, which is a structural diagram of a data processing device provided in an embodiment of the present application. As shown in Figure 8, the data processing device 800 can be applied to the computer device (such as a terminal device or a server) mentioned in the aforementioned embodiment. Specifically, the data processing device 800 can be a computer program (including program code) running in a computer device, for example, the data processing device 800 is an application software; the data processing device 800 can be used to execute the corresponding steps in the data processing method provided in an embodiment of the present application. In specific implementation, the data processing device 800 can specifically include:

[0178] An acquisition unit 801 is configured to acquire biometric data collected from a preset object in a business scenario;

[0179] The processing unit 802 is configured to perform identity recognition processing on a preset object based on the biometric recognition data to obtain a recognition result of the preset object;

[0180] The processing unit 802 is further configured to obtain a first credit indicator corresponding to a preset object in a business scenario, and perform a level adjustment process on the first credit indicator according to the recognition result to obtain a second credit indicator;

[0181] Among them, the second credit indicator is different from the first credit indicator; in the business scenario, the risk control strategy associated with the second credit indicator is different from the risk control strategy associated with the first credit indicator.

[0182] In one possible implementation, the processing unit 802 performs a level adjustment process on the first credit indicator according to the identification result to obtain a second credit indicator, which is used to perform the following operations:

[0183] Obtain scenario configuration information for the business scenario, including the security verification level of the business scenario;

[0184] If the security verification level of the business scenario meets the level adjustment conditions and the identification result is successful, the first credit indicator is upgraded according to the first adjustment method to obtain the second credit indicator.

[0185] In a possible implementation, the recognition result includes recognition success or recognition failure; and the processing unit 802 is further configured to perform any one of the following operations:

[0186] If the security verification level of the business scenario does not meet the level adjustment conditions, or the identification result is identification failure, the first credit indicator is downgraded according to the second adjustment method to obtain a third credit indicator;

[0187] If the security verification level of the business scenario meets the level adjustment conditions and the identification result is identification failure, the level of the first credit indicator will be maintained;

[0188] If the security verification level of the business scenario does not meet the level adjustment conditions and the identification result is successful, the level of the first credit indicator will be maintained.

[0189] In one possible implementation, the processing unit 802 performs a level adjustment process on the first credit indicator according to the identification result to obtain a second credit indicator, which is used to perform the following operations:

[0190] If the security verification level of the business scenario does not meet the level adjustment conditions, the historical business data of the preset object is obtained and the level recognition model is trained using the historical business data;

[0191] Call the trained grade recognition model to perform grade recognition processing on the preset object to obtain the security credit grade of the preset object;

[0192] According to the security credit level of the preset object and the identification result, the first credit indicator is adjusted to obtain a second credit indicator.

[0193] In one possible implementation, the processing unit 802 performs identity recognition processing on a preset object based on the biometric recognition data, and after obtaining the recognition result of the preset object, is further configured to perform the following operations:

[0194] If the recognition result is successful, a prompt interface is output, which includes a prompt area and an adjustment control. The prompt area is used to prompt the preset object whether to authorize the adjustment of the first credit indicator level, and the adjustment control is used to receive a confirmation operation for the adjustment of the first credit indicator level;

[0195] In response to the authorization confirmation operation triggered in the prompt area, the step of obtaining the first credit indicator corresponding to the preset object in the business scenario is triggered, and the first credit indicator is adjusted according to the identification result to obtain the second credit indicator.

[0196] In one possible implementation, the level adjustment process includes: any one or more of: a level reduction process, a level increase process, and a level maintenance process; the adjustment control includes a first control, a second control, and a third control; wherein the first control is used to receive a confirmation operation of the level increase process; the second control is used to receive a confirmation operation of the level reduction process; and the third control is used to receive a confirmation operation of the level maintenance process;

[0197] The processing unit 802 is further configured to perform any of the following operations:

[0198] When the recognition result is successful, in response to an authorization confirmation operation triggered in the prompt area for the first control, the first credit indicator is adjusted to a second credit indicator;

[0199] When the recognition result is recognition failure, in response to an authorization confirmation operation triggered in the prompt area for the second control, the first credit indicator is downgraded to a third credit indicator;

[0200] When the recognition result is recognition success or recognition failure, in response to the authorization confirmation operation triggered for the third control in the prompt area, the first credit indicator is subjected to level maintenance processing.

[0201] In one possible implementation, the processing unit 802 performs identity recognition processing on a preset object based on the biometric data to obtain a recognition result of the preset object, which is used to perform the following operations:

[0202] Perform feature extraction on biometric data to obtain the biometric features of the preset object;

[0203] Obtain the registration data of the preset object. The registration data is generated after the preset object successfully registers its identity in the business scenario. The registration data includes registration characteristics.

[0204] Based on the biological features of the preset object and the registration features of the preset object, identity recognition processing is performed on the preset object to obtain an identification result of the preset object.

[0205] In one possible implementation, the biometric data includes palm data; the processing unit 802 performs feature extraction processing on the biometric data to obtain biometric features of a preset object, which are used to perform the following operations:

[0206] Performing palm vein feature extraction on the palm data to obtain the palm vein features of the preset object; and

[0207] Perform palmprint feature extraction on the palm data to obtain the palmprint features of the preset object;

[0208] Perform feature fusion processing on palm print features and palm vein features to obtain the biometric features of the preset object;

[0209] The feature fusion processing includes at least any one of the following: feature weighting processing, feature alignment processing, and feature operation processing.

[0210] In one possible implementation, the acquisition unit 801 acquires biometric data collected for a preset object in a business scenario, and performs the following operations:

[0211] Calling an acquisition device to acquire biological streaming media data of a preset object, where the biological streaming media data includes a plurality of biological images acquired from the preset object;

[0212] Select and process multiple biological images according to preset selection conditions to obtain biometric data of preset objects;

[0213] The preset selection conditions include: any one or more of image size, shooting angle, image contrast, image brightness, and clarity.

[0214] In one possible implementation, the business scenario is a payment scenario, and the risk control strategy in the payment scenario is used to indicate: one credit indicator corresponds to one payment limit;

[0215] The processing unit 802 adjusts the level of the preset object from the first credit indicator according to the recognition result to obtain the second credit indicator, and is further configured to perform the following operations:

[0216] Detect the amount of assets requested for processing in payment scenarios;

[0217] If the payment amount corresponding to the second credit indicator is greater than or equal to the asset amount requested for processing, then the payment service is called to perform transfer processing on the assets corresponding to the asset amount;

[0218] If the payment amount corresponding to the second credit indicator is less than the amount of assets requested for processing, a prompt message is output. The prompt message is used to trigger the level adjustment processing of the second credit indicator of the preset object, so that the payment amount corresponding to the second credit indicator after the level adjustment processing is greater than or equal to the amount of assets requested for processing.

[0219] In one possible implementation, the first credit indicator refers to a credit indicator assigned to a preset subject after the preset subject completes identity registration in a business scenario; the business scenario is a payment scenario; and before the processing unit 802 obtains the biometric data collected for the preset subject in the business scenario, the processing further includes:

[0220] In response to a request for identity registration of a preset object in a payment scenario, obtaining scenario configuration information of the payment scenario, the scenario configuration information including a security verification level of the payment scenario;

[0221] If the security verification level of the payment scenario meets the level adjustment conditions, a credit indicator is allocated to the preset object in the payment scenario according to the security verification level of the payment scenario;

[0222] If the security verification level of the payment scenario does not meet the level adjustment conditions, the reference credit index is determined as the credit index assigned to the preset object in the payment scenario.

[0223] In the embodiments of the present application, the specific implementation of the operations performed by the various units of the data processing device and the corresponding effects that can be produced can refer to the relevant descriptions of the aforementioned embodiments and will not be repeated here.

[0224] Please refer to Figure 9, which is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. The computer device 900 is used to execute the steps performed by the terminal device or server in the aforementioned method embodiment. The computer device 900 includes: one or more processors 901; one or more input devices 902, one or more output devices 903 and a memory 904. The above-mentioned processors 901, input devices 902, output devices 903 and memory 904 are connected via a bus 905. Specifically, the memory 904 is used to store a computer program, and the computer program includes program instructions. The processor 901 is used to call the program instructions stored in the memory 904 to perform the following operations:

[0225] Obtain biometric data collected from preset objects in business scenarios;

[0226] Perform identity recognition processing on a preset object based on the biometric data to obtain an identification result of the preset object;

[0227] Obtaining a first credit indicator corresponding to a preset object in a business scenario, and adjusting the first credit indicator based on the identification result to obtain a second credit indicator;

[0228] Among them, the second credit indicator is different from the first credit indicator; in the business scenario, the risk control strategy associated with the second credit indicator is different from the risk control strategy associated with the first credit indicator.

[0229] In one possible implementation, the processor 901 performs a level adjustment process on the first credit indicator according to the identification result to obtain a second credit indicator, which is used to perform the following operations:

[0230] Obtain scenario configuration information for the business scenario, including the security verification level of the business scenario;

[0231] If the security verification level of the business scenario meets the level adjustment conditions and the identification result is successful, the first credit indicator is upgraded according to the first adjustment method to obtain the second credit indicator.

[0232] In a possible implementation, the recognition result includes recognition success or recognition failure; and the processor 901 is further configured to perform any one of the following operations:

[0233] If the security verification level of the business scenario does not meet the level adjustment conditions, or the identification result is identification failure, the first credit indicator is downgraded according to the second adjustment method to obtain a third credit indicator;

[0234] If the security verification level of the business scenario meets the level adjustment conditions and the identification result is identification failure, the level of the first credit indicator will be maintained;

[0235] If the security verification level of the business scenario does not meet the level adjustment conditions and the identification result is successful, the level of the first credit indicator will be maintained.

[0236] In one possible implementation, the processor 901 performs a level adjustment process on the first credit indicator according to the identification result to obtain a second credit indicator, which is used to perform the following operations:

[0237] If the security verification level of the business scenario does not meet the level adjustment conditions, the historical business data of the preset object is obtained and the level recognition model is trained using the historical business data;

[0238] Call the trained grade recognition model to perform grade recognition processing on the preset object to obtain the security credit grade of the preset object;

[0239] According to the security credit level of the preset object and the identification result, the first credit indicator is adjusted to obtain a second credit indicator.

[0240] In one possible implementation, the processor 901 performs identity recognition processing on a preset object based on the biometric recognition data, and after obtaining the recognition result of the preset object, is further configured to perform the following operations:

[0241] If the recognition result is successful, a prompt interface is output, which includes a prompt area and an adjustment control. The prompt area is used to prompt the preset object whether to authorize the adjustment of the first credit indicator level, and the adjustment control is used to receive a confirmation operation for the adjustment of the first credit indicator level;

[0242] In response to the authorization confirmation operation triggered in the prompt area, the step of obtaining the first credit indicator corresponding to the preset object in the business scenario is triggered, and the first credit indicator is adjusted according to the identification result to obtain the second credit indicator.

[0243] In one possible implementation, the level adjustment process includes: any one or more of: a level reduction process, a level increase process, and a level maintenance process; the adjustment control includes a first control, a second control, and a third control; wherein the first control is used to receive a confirmation operation of the level increase process; the second control is used to receive a confirmation operation of the level reduction process; and the third control is used to receive a confirmation operation of the level maintenance process;

[0244] The processor 901 is further configured to perform any one of the following operations:

[0245] When the recognition result is successful, in response to an authorization confirmation operation triggered in the prompt area for the first control, the first credit indicator is adjusted to a second credit indicator;

[0246] When the recognition result is recognition failure, in response to an authorization confirmation operation triggered in the prompt area for the second control, the first credit indicator is downgraded to a third credit indicator;

[0247] When the recognition result is recognition success or recognition failure, in response to the authorization confirmation operation triggered for the third control in the prompt area, the first credit indicator is subjected to level maintenance processing.

[0248] In one possible implementation, the processor 901 performs identity recognition processing on a preset object based on the biometric data to obtain a recognition result of the preset object, which is used to perform the following operations:

[0249] Perform feature extraction on biometric data to obtain the biometric features of the preset object;

[0250] Obtain the registration data of the preset object. The registration data is generated after the preset object successfully registers its identity in the business scenario. The registration data includes registration characteristics.

[0251] Based on the biological features of the preset object and the registration features of the preset object, identity recognition processing is performed on the preset object to obtain an identification result of the preset object.

[0252] In one possible implementation, the biometric data includes palm data; the processor 901 performs feature extraction processing on the biometric data to obtain biometric features of a preset object, which are used to perform the following operations:

[0253] Performing palm vein feature extraction on the palm data to obtain the palm vein features of the preset object; and

[0254] Perform palmprint feature extraction on the palm data to obtain the palmprint features of the preset object;

[0255] Perform feature fusion processing on palm print features and palm vein features to obtain the biometric features of the preset object;

[0256] The feature fusion processing includes at least any one of the following: feature weighting processing, feature alignment processing, and feature operation processing.

[0257] In one possible implementation, the processor 901 obtains biometric data collected for a preset object in a business scenario, and performs the following operations:

[0258] Calling an acquisition device to acquire biological streaming media data of a preset object, where the biological streaming media data includes a plurality of biological images acquired from the preset object;

[0259] Select and process multiple biological images according to preset selection conditions to obtain biometric data of preset objects;

[0260] The preset selection conditions include: any one or more of image size, shooting angle, image contrast, image brightness, and clarity.

[0261] In one possible implementation, the business scenario is a payment scenario, and the risk control strategy in the payment scenario is used to indicate: one credit indicator corresponds to one payment limit;

[0262] The processor 901 adjusts the level of the preset object from the first credit indicator according to the recognition result to obtain the second credit indicator, and is further configured to perform the following operations:

[0263] Detect the amount of assets requested for processing in payment scenarios;

[0264] If the payment amount corresponding to the second credit indicator is greater than or equal to the asset amount requested for processing, then the payment service is called to perform transfer processing on the assets corresponding to the asset amount;

[0265] If the payment amount corresponding to the second credit indicator is less than the amount of assets requested for processing, a prompt message is output. The prompt message is used to trigger the level adjustment processing of the second credit indicator of the preset object, so that the payment amount corresponding to the second credit indicator after the level adjustment processing is greater than or equal to the amount of assets requested for processing.

[0266] In one possible implementation, the first credit indicator refers to a credit indicator assigned to a preset subject after the preset subject completes identity registration in a business scenario; the business scenario is a payment scenario; and before the processor 901 obtains biometric data collected for the preset subject in the business scenario, the process further includes:

[0267] In response to a request for identity registration of a preset object in a payment scenario, obtaining scenario configuration information of the payment scenario, the scenario configuration information including a security verification level of the payment scenario;

[0268] If the security verification level of the payment scenario meets the level adjustment conditions, a credit indicator is allocated to the preset object in the payment scenario according to the security verification level of the payment scenario;

[0269] If the security verification level of the payment scenario does not meet the level adjustment conditions, the reference credit index is determined as the credit index assigned to the preset object in the payment scenario.

[0270] In the embodiments of the present application, the specific implementation of each operation performed by the processor of the computer device and the corresponding effects that can be produced can be referred to the relevant descriptions of the aforementioned embodiments and will not be repeated here.

[0271] In addition, it should be noted here that: the embodiment of the present application also provides a computer storage medium, and a computer program is stored in the computer storage medium, and the computer program includes program instructions. When the processor executes the above program instructions, it can execute the method in the corresponding embodiment above, so it will not be described in detail here. For technical details not disclosed in the computer storage medium embodiment involved in this application, please refer to the description of the method embodiment of this application. As an example, the program instructions can be deployed on a computer device, or executed on multiple computer devices located in one place, or, executed on multiple computer devices distributed in multiple locations and interconnected by a communication network.

[0272] According to one aspect of the present application, embodiments of the present application further provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, so that the computer device can perform the methods described in the corresponding embodiments above. Therefore, these methods will not be described in detail here.

[0273] The above disclosure is only a preferred embodiment of the present application, and certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A data processing method, It is characterized in that include: Obtain biometric data collected for preset objects in business scenarios; Performing identity recognition processing on the preset object based on the biometric recognition data to obtain a recognition result of the preset object; Acquire a first credit indicator corresponding to the preset object in the business scenario, and perform a grade adjustment process on the first credit indicator according to the recognition result to obtain a second credit indicator; The second credit indicator is different from the first credit indicator; in the business scenario, the risk control strategy associated with the second credit indicator is different from the risk control strategy associated with the first credit indicator.

2. The method according to claim 1, It is characterized in that The step of performing a grade adjustment process on the first credit indicator according to the identification result to obtain a second credit indicator includes: Acquire scenario configuration information of the business scenario, wherein the scenario configuration information includes a security verification level of the business scenario; If the security verification level of the business scenario meets the level adjustment conditions and the identification result is successful identification, the first credit indicator is upgraded according to the first adjustment method to obtain a second credit indicator.

3. The method according to claim 1 or 2, It is characterized in that The recognition result includes recognition success or recognition failure; the method also includes any of the following: If the security verification level of the business scenario does not meet the level adjustment condition, or the identification result is an identification failure, the first credit indicator is downgraded according to the second adjustment method to obtain a third credit indicator; If the security verification level of the business scenario meets the level adjustment condition and the identification result is identification failure, maintaining the level of the first credit indicator; If the security verification level of the business scenario does not meet the level adjustment condition and the identification result is successful identification, maintaining the level of the first credit indicator; The first adjustment method is different from the second adjustment method.

4. The method according to any one of claims 1 to 3, It is characterized in that The step of performing a grade adjustment process on the first credit indicator according to the identification result to obtain a second credit indicator includes: If the security verification level of the business scenario does not meet the level adjustment conditions, obtaining the historical business data of the preset object, and using the historical business data to train the level recognition model; Calling the trained grade recognition model to perform grade recognition processing on the preset object to obtain the security credit grade of the preset object; According to the security credit level of the preset object and the identification result, the first credit indicator is adjusted to obtain a second credit indicator.

5. The method according to any one of claims 1 to 4, It is characterized in that After performing identity recognition processing on the preset object based on the biometric recognition data to obtain the recognition result of the preset object, the method further includes: If the recognition result is successful, a prompt interface is output, the prompt interface includes a prompt area and an adjustment control, the prompt area is used to prompt the preset object whether to authorize the adjustment of the level of the first credit indicator, and the adjustment control is used to receive a confirmation operation of the adjustment of the level of the first credit indicator; In response to the authorization confirmation operation triggered in the prompt area, the step of triggering the execution of obtaining the first credit indicator corresponding to the preset object in the business scenario, and adjusting the level of the first credit indicator according to the identification result to obtain the second credit indicator.

6. The method according to any one of claims 1 to 5, wherein the level adjustment process include: Any one or more of level reduction processing, level increase processing, and level maintenance processing; the adjustment control includes a first control, a second control, and a third control; wherein the first control is used to receive a confirmation operation of the level increase processing; the second control is used to receive a confirmation operation of the level reduction processing; and the third control is used to receive a confirmation operation of the level maintenance processing; The method also includes any of the following: When the recognition result is successful recognition, in response to an authorization confirmation operation triggered in the prompt area for the first control, the first credit indicator is graded and adjusted to a second credit indicator; When the recognition result is recognition failure, in response to the authorization confirmation operation triggered in the prompt area for the second control, the first credit indicator is downgraded to a third credit indicator; When the recognition result is recognition success or recognition failure, in response to the authorization confirmation operation triggered for the third control in the prompt area, the first credit indicator is subjected to level maintenance processing.

7. The method according to any one of claims 1 to 6, It is characterized in that The performing identity recognition processing on the preset object based on the biometric recognition data to obtain the recognition result of the preset object includes: Performing feature extraction processing on the biometric data to obtain the biometric features of the preset object; Acquire registration data of the preset object, where the registration data is generated after the preset object successfully registers its identity in the business scenario, and the registration data includes registration features; Based on the biological features of the preset object and the registration features of the preset object, identity recognition processing is performed on the preset object to obtain a recognition result of the preset object.

8. The method according to any one of claims 1 to 7, It is characterized in that The biometric data includes palm data; the feature extraction process is performed on the biometric data to obtain the biometric features of the preset object, including: Performing palm vein feature extraction processing on the palm data to obtain the palm vein features of the preset object; and, Performing palmprint feature extraction processing on the palm data to obtain the palmprint features of the preset object; Performing feature fusion processing on the palm print feature and the palm vein feature to obtain the biological feature of the preset object; The feature fusion processing includes at least any one of the following: feature weighting processing, feature alignment processing, and feature operation processing.

9. The method according to any one of claims 1 to 8, It is characterized in that The obtaining of biometric data collected from a preset object in a business scenario includes: Calling a collection device to collect biological streaming media data of the preset object, wherein the biological streaming media data includes a plurality of biological images collected from the preset object; Select and process the plurality of biological images according to a preset selection condition to obtain the biological recognition data of the preset object; The preset selection conditions include: any one or more of image size, shooting angle, image contrast, image brightness, and clarity.

10. The method according to any one of claims 1 to 9, It is characterized in that The business scenario is a payment scenario, and the risk control strategy in the payment scenario is used to indicate: one credit indicator corresponds to one payment amount; After the preset object is graded and adjusted from the first credit indicator according to the recognition result to obtain the second credit indicator, the method further includes: Detecting the amount of assets requested to be processed in the payment scenario; If the payment amount corresponding to the second credit indicator is greater than or equal to the asset amount requested for processing, calling the payment service to perform transfer processing on the assets corresponding to the asset amount; If the payment amount corresponding to the second credit indicator is less than the asset amount requested for processing, a prompt message is output, and the prompt message is used to trigger the level adjustment processing of the second credit indicator of the preset object, so that the payment amount corresponding to the second credit indicator after the level adjustment processing is greater than or equal to the asset amount requested for processing.

11. The method according to any one of claims 1 to 10, It is characterized in that The first credit index refers to the credit index assigned to the preset object after the preset object completes identity registration in the business scenario; the business scenario is a payment scenario; before acquiring the biometric data collected for the preset object in the business scenario, it also includes: In response to an identity registration request of a preset object in the payment scenario, acquiring scenario configuration information of the payment scenario, the scenario configuration information including a security verification level of the payment scenario; If the security verification level of the payment scenario satisfies the level adjustment condition, allocating a credit indicator to the preset object in the payment scenario according to the security verification level of the payment scenario; If the security verification level of the payment scenario does not meet the level adjustment condition, the reference credit index is determined as the credit index allocated to the preset object in the payment scenario.

12. A data processing device, It is characterized in that include: An acquisition unit, used to acquire biometric data collected for a preset object in a business scenario; A processing unit, configured to perform recognition processing on the preset object based on the biometric recognition data to obtain a recognition result of the preset object; The processing unit is further configured to obtain a first credit indicator corresponding to the preset object in the business scenario, and to perform a level adjustment process on the first credit indicator according to the recognition result to obtain a second credit indicator; The second credit indicator is different from the first credit indicator; in the business scenario, the risk control strategy associated with the second credit indicator is different from the risk control strategy associated with the first credit indicator.

13. A computer device, It is characterized in that include: storage devices and processors; a memory storing one or more computer programs; A processor, configured to load the one or more computer programs to implement the data processing method according to any one of claims 1 to 11.

14. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the data processing method according to any one of claims 1 to 11.

15. A computer program product, It is characterized in that The computer program product comprises a computer program, which is suitable for being loaded by a processor and executing the data processing method according to any one of claims 1 to 11.

Images