A method for identifying transaction objects, a method for processing transactions, an apparatus and equipment

Abstract

This application discloses a method for identifying trading objects, comprising: acquiring trading object description data for a target trading object; performing feature processing on the trading object description data to obtain trading object description features and associated object features; based on the trading object description features and associated object features, obtaining first risk information corresponding to the target trading object through a trading object identification model, wherein the first risk information is represented as a risk score or risk probability distribution; and determining a risk level label corresponding to the target trading object based on the first risk information. This application also provides a method, related apparatus, and equipment for transaction processing. This application combines basic trading object data and associated object data to jointly determine the risk identification result of the trading object. Therefore, based on the trading object description data, the risk status of the trading object can be assessed more comprehensively and objectively, thereby reducing the possibility of false interception.

Description

Technical Field

[0001] This application relates to the field of Internet technology, and in particular to a method for identifying transaction objects, a method for processing transactions, an apparatus and equipment. Background Technology

[0002] With the rapid development of internet technology, more and more people can conduct electronic transactions with other people through internet platforms. To ensure transaction security, internet platforms can identify the risks of trading partners before the electronic transaction takes place and allow the transaction to proceed only when it is safe to do so.

[0003] Currently, the verification of the legitimacy of trading partners mainly relies on complaint data. That is, the legitimacy of trading partners is determined by analyzing complaint data. However, this method of judging the legitimacy of trading partners through complaint data is prone to analytical errors and may result in false blocking. Summary of the Invention

[0004] This application provides a method for identifying transaction objects, a method for processing transactions, an apparatus, and a device. By combining basic data of the transaction object and related object data, the risk identification result of the transaction object is determined. Thus, based on the transaction object description data, the risk status of the transaction object can be assessed more comprehensively and objectively, thereby reducing the possibility of false interception.

[0005] In view of this, this application provides a method for identifying transaction objects, including:

[0006] Obtain transaction object description data for the target transaction object. The transaction object description data includes basic transaction object data and related object data. The basic transaction object data represents data related to the target transaction object, and the related object data represents data related to related objects. Related objects represent objects that have a transaction relationship with the target transaction object.

[0007] The basic data of the transaction objects included in the transaction object description data are processed to obtain the transaction object description features. In addition, the related object data included in the transaction object description data are processed to obtain the related object features.

[0008] Based on the descriptive features of the transaction object and the features of the associated objects, the first risk information corresponding to the target transaction object is obtained through the transaction object identification model. The first risk information is represented as a risk score or a risk probability distribution.

[0009] The risk level label corresponding to the target trading object is determined based on the first risk information.

[0010] This application also provides a method for transaction processing, including:

[0011] Display the payment transaction interface, which provides the first payment control;

[0012] In response to the selection instruction for the first payment control, a transaction processing request is sent to the server so that the server determines the risk level label corresponding to the target transaction object based on the transaction object identifier carried in the transaction processing request, wherein the transaction object identifier is used to indicate the target transaction object, and the risk level label is determined using the method described above;

[0013] If the risk level label indicates that the target transaction object is an illegal transaction object, a payment failure message will be displayed.

[0014] Another aspect of this application provides a transaction object identification device, comprising:

[0015] The acquisition module is used to acquire transaction object description data for the target transaction object. The transaction object description data includes basic transaction object data and related object data. The basic transaction object data represents data related to the target transaction object, and the related object data represents data related to related objects. Related objects represent objects that have a transaction relationship with the target transaction object.

[0016] The processing module is used to perform feature processing on the basic data of the transaction object included in the transaction object description data to obtain the transaction object description features, and to perform feature processing on the associated object data included in the transaction object description data to obtain the associated object features.

[0017] The acquisition module is also used to obtain the first risk information corresponding to the target transaction object through the transaction object identification model based on the transaction object description features and related object features, wherein the first risk information is represented as a risk score or risk probability distribution;

[0018] The determination module is used to determine the risk level label corresponding to the target trading object based on the first risk information.

[0019] In one possible design, in another implementation of another aspect of the embodiments of this application,

[0020] The acquisition module is specifically used to acquire description data, which includes at least one of application description data, public account description data, object description data, and external link description data.

[0021] Based on the description data, obtain the basic data of the target transaction object, which includes at least one of the following: transaction object level, investment data, investment data, active time, order amount, historical complaint rate, repurchase rate, number of successful orders, and number of failed orders;

[0022] Based on the description data, obtain the associated object data for the target transaction object. The associated object data includes at least one of the following: the account level of the associated object, the first proportion of illegal objects among the associated objects, the second proportion of reported objects among the associated objects, the third proportion of minor objects among the associated objects, and the fourth proportion of objects with historical losses among the associated objects.

[0023] In one possible design, in another implementation of another aspect of the embodiments of this application,

[0024] The processing module is specifically used to perform one-hot encoding on the transaction object level if the basic data of the transaction object includes the transaction object level, so as to obtain the transaction object level feature, wherein the transaction object level feature is included in the transaction object description feature.

[0025] If the basic data of the transaction object includes investment data, investment data, order success rate and order failure rate, then feature scaling processing is performed on the investment data, investment data, order success rate and order failure rate to obtain investment data features, investment data features, order success rate features and order failure rate features. Among them, investment data features, investment data features, order success rate features and order failure rate features are included in the transaction object description features.

[0026] If the basic data of the transaction object includes the order amount, then the order amount is binned to obtain the order amount feature, which is included in the transaction object description feature.

[0027] If the basic data of the transaction object includes active time, historical complaint ratio and repurchase ratio, then the active time, historical complaint ratio and repurchase ratio are numerically processed to obtain active time feature, historical complaint ratio feature and repurchase ratio feature. Among them, the active time feature, historical complaint ratio feature and repurchase ratio feature are included in the transaction object description feature.

[0028] The processing module is specifically used to perform one-hot encoding on the account level of the associated object if the associated object data includes the account level of the associated object, so as to obtain the account level feature and the quantity type feature, wherein the account level feature and the quantity type feature are included in the associated object feature.

[0029] If the associated object data includes the first proportion, the second proportion, the third proportion, and the fourth proportion, then the first proportion, the second proportion, the third proportion, and the fourth proportion are numerically processed to obtain the characteristics of the proportion of illegal objects, the characteristics of the proportion of reported objects, the characteristics of the proportion of minor objects, and the characteristics of the proportion of historically damaged objects. Among them, the characteristics of the proportion of illegal objects, the characteristics of the proportion of reported objects, the characteristics of the proportion of minor objects, and the characteristics of the proportion of historically damaged objects are included in the characteristics of associated objects.

[0030] In one possible design, in another implementation of another aspect of the embodiments of this application,

[0031] The acquisition module is specifically used to obtain the risk score corresponding to the target transaction object based on the description features of the transaction object and the features of related objects through the transaction object identification model;

[0032] The determination module is specifically used to determine the risk level label corresponding to the target transaction object as the first risk label if the risk score is greater than or equal to 0 and less than the first threshold.

[0033] If the risk score is greater than or equal to the first threshold and less than the second threshold, then the risk level label corresponding to the target trading object is determined to be the second risk label, wherein the degree of malice of the second risk label is higher than that of the first risk label.

[0034] In one possible design, in another implementation of another aspect of the embodiments of this application,

[0035] The acquisition module is specifically used to obtain the risk probability distribution corresponding to the target transaction object based on the description features of the transaction object and the features of the associated objects through the transaction object identification model. The risk probability distribution includes K probability values, each probability value corresponds to a risk label, and K is an integer greater than or equal to 2.

[0036] The determination module is specifically used to determine the risk label corresponding to the highest probability value from K probability values ​​based on the risk probability distribution;

[0037] The risk label corresponding to the highest probability value is determined as the risk level label.

[0038] In one possible design, in another implementation of another aspect of the embodiments of this application, the transaction object identification device further includes a sending module;

[0039] The acquisition module is also used to acquire object complaint data for the target transaction object if the risk level label indicates that the target transaction object is a pending illegal transaction object;

[0040] The acquisition module is also used to, if the object complaint data includes an image to be identified, obtain the second risk information corresponding to the image to be identified through an image recognition model, and determine the target risk level label corresponding to the target transaction object based on the second risk information, wherein the second risk information is represented as a risk score or risk probability distribution;

[0041] The sending module is used to send pending data for the target transaction object to the terminal device if the object complaint data does not include the image to be identified. The pending data includes at least one of the target transaction object's order information, fund information, and object behavior information.

[0042] In one possible design, in another implementation of another aspect of the embodiments of this application,

[0043] The acquisition module is also used to acquire object complaint data targeting the transaction object;

[0044] The acquisition module is also used to acquire the second risk information corresponding to the image to be identified through the image recognition model if the object complaint data includes the image to be identified. The second risk information is represented as a risk score or risk probability distribution.

[0045] The determination module is specifically used to determine the risk level label corresponding to the target trading object based on the first risk information and the second risk information.

[0046] In one possible design, in another implementation of another aspect of the embodiments of this application,

[0047] The acquisition module is specifically used to receive transaction processing requests sent by terminal devices, wherein the transaction processing request carries a transaction object identifier, and the transaction object identifier is used to indicate the target transaction object;

[0048] In response to a transaction processing request, obtain transaction object description data for the target transaction object;

[0049] The sending module is also used to send risk level labels to terminal devices so that the terminal devices can display corresponding prompt messages based on the risk level labels.

[0050] This application also provides a transaction processing apparatus, comprising:

[0051] The display module is used to display the payment transaction interface, wherein the payment transaction interface provides the first payment control;

[0052] The response module is used to respond to the selection instruction for the first payment control by sending a transaction processing request to the server, so that the server determines the risk level label corresponding to the target transaction object based on the transaction object identifier carried in the transaction processing request. The transaction object identifier is used to indicate the target transaction object, and the risk level label is determined by the method described above.

[0053] The display module is also used to display a payment failure message if the risk level label indicates that the target transaction object is an illegal transaction object.

[0054] In one possible design, in another implementation of another aspect of the embodiments of this application,

[0055] The display module is also used to display at least one of the following: a details viewing control and an information reporting control;

[0056] The display module is also used to display abnormal transaction information related to the target transaction object if a selection instruction is given for the details viewing control.

[0057] The display module is also used to display an information reporting interface in response to a selection instruction for the information reporting control, wherein the information reporting interface provides an object information input area.

[0058] In one possible design, in another implementation of another aspect of the embodiments of this application, the transaction processing apparatus further includes a generation module;

[0059] The display module is also used to display a risk warning message for the transaction object and a second payment control if the risk level label indicates that the target transaction object is a pending illegal transaction object and no payment amount information has been entered.

[0060] The display module is also used to respond to selection instructions for the second payment control and display the password input area;

[0061] or,

[0062] The display module is also used to display a risk warning message and a third payment control if the risk level label indicates that the target transaction object is a pending illegal transaction object and payment amount information has been entered.

[0063] The generation module is used to generate an order payment request in response to a selection instruction for a third payment control.

[0064] In one possible design, in another implementation of another aspect of the embodiments of this application,

[0065] The display module is also used to display a transaction reporting control if the risk level label indicates that the target transaction object is a pending illegal transaction object and the order payment has been completed;

[0066] The display module is also used to respond to the selection command for the transaction object reporting control and display the order reporting interface, wherein the order reporting interface provides at least one of the following: transaction object name input area, transaction object nature input area, transaction object account input area, and report content input area.

[0067] This application also provides a computer device, including: a memory, a processor, and a bus system;

[0068] The memory is used to store programs;

[0069] The processor is used to execute programs in memory, and the processor is used to execute the methods mentioned above according to the instructions in the program code;

[0070] Bus systems are used to connect memory and processor to enable communication between them.

[0071] This application also provides a server, including: a memory, a processor, and a bus system;

[0072] The memory is used to store programs;

[0073] The processor is used to execute programs in memory, and the processor is used to execute the methods mentioned above according to the instructions in the program code;

[0074] Bus systems are used to connect memory and processor to enable communication between them.

[0075] This application also provides a terminal device, including: a memory, a processor, and a bus system;

[0076] The memory is used to store programs;

[0077] The processor is used to execute programs in memory, and the processor is used to execute the methods mentioned above according to the instructions in the program code;

[0078] Bus systems are used to connect memory and processor to enable communication between them.

[0079] Another aspect of this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described above.

[0080] Another aspect of this application provides a computer program product or computer program including 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 methods provided in the above aspects.

[0081] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0082] This application provides a method for identifying trading objects. First, it acquires trading object description data for the target trading object. Then, it performs feature processing on the basic data of the trading object included in the description data to obtain trading object description features. Furthermore, it performs feature processing on the related object data included in the description data to obtain related object features. Next, based on the trading object description features and related object features, it obtains first risk information corresponding to the target trading object through a trading object identification model. Finally, it determines the risk level label corresponding to the target trading object based on the first risk information. Through this method, the basic data of the trading object is characterized with the trading object as the center, and the related object data is characterized using the trading object and its trading behavior as the link. Combining the basic data of the trading object and the related object data together determines the risk identification result of the trading object. Therefore, based on the trading object description data, the risk situation of the trading object can be assessed more comprehensively and objectively, thereby reducing the possibility of false interception. Attached Figure Description

[0083] Figure 1 This is a schematic diagram of a communication architecture of the transaction processing system in an embodiment of this application;

[0084] Figure 2 This is a schematic diagram of a process for real-time intervention in transaction processing in an embodiment of this application;

[0085] Figure 3 This is a flowchart illustrating the transaction object identification method in an embodiment of this application;

[0086] Figure 4 This is a schematic diagram of a framework for obtaining transaction object description data in an embodiment of this application;

[0087] Figure 5 This is another flowchart illustrating the transaction object identification method in this application embodiment;

[0088] Figure 6 This is a schematic diagram of the payment transaction interface in an embodiment of this application;

[0089] Figure 7This is another schematic diagram of the payment transaction interface in the embodiments of this application;

[0090] Figure 8 This is another schematic diagram of the payment transaction interface in the embodiments of this application;

[0091] Figure 9 This is another schematic diagram of the payment transaction interface in the embodiments of this application;

[0092] Figure 10 This is another schematic diagram of the payment transaction interface in the embodiments of this application;

[0093] Figure 11 This is another schematic diagram of the payment transaction interface in the embodiments of this application;

[0094] Figure 12 This is another schematic diagram of the payment transaction interface in the embodiments of this application;

[0095] Figure 13 This is another schematic diagram of the payment transaction interface in the embodiments of this application;

[0096] Figure 14 This is another schematic diagram of the payment transaction interface in the embodiments of this application;

[0097] Figure 15 This is another schematic diagram of the payment transaction interface in the embodiments of this application;

[0098] Figure 16 This is another schematic diagram of the payment transaction interface in the embodiments of this application;

[0099] Figure 17 This is a schematic diagram of a transaction object identification device in an embodiment of this application;

[0100] Figure 18 This is a schematic diagram of a transaction processing device in an embodiment of this application;

[0101] Figure 19 This is a schematic diagram of the server structure in an embodiment of this application;

[0102] Figure 20 This is a schematic diagram of the structure of a terminal device in an embodiment of this application. Detailed Implementation

[0103] This application provides a method for identifying transaction objects, a method for processing transactions, an apparatus, and a device. By combining basic data of the transaction object and related object data, the risk identification result of the transaction object is determined. Thus, based on the transaction object description data, the risk status of the transaction object can be assessed more comprehensively and objectively, thereby reducing the possibility of false interception.

[0104] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “corresponding to,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0105] Illegal transaction partners may use illicit tools to collect illicit funds, thereby compromising the security of the recipient's funds. Illegal transaction partners refer to those used for illegal transactions. Therefore, to curb illegal transaction partners, maintain healthy transaction processes, and build a secure payment network environment, this application provides a method for identifying transaction partners and processing transactions. By identifying the risk level of transaction partners, high-risk transactions are promptly intercepted, low-risk transactions are flagged, and normal transactions can proceed for risk-free partners.

[0106] For clarity, please refer to Figure 1 , Figure 1This is a schematic diagram of a communication architecture for a transaction processing system in this application embodiment. As shown in the figure, the transaction processing system includes a transaction platform server, a description data server, a database, and terminal devices. The client is deployed on the terminal device. The client can run on the terminal device via a browser or as a standalone application (APP), etc. The specific form of the client is not limited here. The server involved in this application can be an independent physical server, a server cluster composed of multiple physical servers, or a distributed system. It can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The terminal device can be a smartphone, tablet, laptop, PDA, personal computer, smart TV, smartwatch, in-vehicle device, wearable device, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited here. The number of servers and terminal devices is also not limited. The solution provided in this application can be completed independently by the terminal device, independently by the server, or jointly by the terminal device and the server. This application does not make any specific limitations on this.

[0107] Combination Figure 1 The transaction processing system shown allows the trading platform server to directly access transaction object description data for different trading objects from the description data server. This transaction object description data can originate from order flow, fund flow, or object behavior, etc. Next, the trading platform server uses a transaction object identification model to identify the risk level of the transaction object description data for different trading objects, obtaining a risk level label for each trading object. Then, the transaction object identifier and its corresponding risk level label for each trading object are stored in a database for subsequent use by the trading platform server. When an object sends a transaction processing request to the trading platform server via a terminal device, the trading platform server retrieves the corresponding risk level label from the database based on the transaction object identifier carried in the transaction processing request. If the risk level label indicates that the trading object is risk-free, the trading platform server allows the transaction to proceed. If the risk level label indicates that the trading object is high-risk, the trading platform server blocks the transaction. If the risk level label indicates that the trading object is low-risk, the trading platform server provides a risk warning for the transaction, allowing the object to choose whether to proceed.

[0108] The following will combine Figure 2 This application describes the intervention process for transaction processing. Please refer to [link / reference]. Figure 2 , Figure 2 This is a schematic diagram of a transaction processing intervention process in this embodiment of the application. As shown in the figure, the overall intervention process is divided into pre-intervention, in-process intervention, and post-intervention. Pre-intervention mainly involves reporting business-related data, in-process intervention is the core intervention, and post-intervention refers to interception or reminders based on the results of in-process intervention. The specific process includes:

[0109] In step S1, data related to the transaction object and payment object for each order are collected and then reported to the description data server.

[0110] In step S2, the trading platform server obtains the reported data from the description data server, and then cleans and calculates the features of the reported data to obtain the description features of the trading object and the features of the associated object.

[0111] In step S3, the descriptive features of the transaction object and the features of related objects are input into the machine learning model. The machine learning model then labels the transaction object with a risk level, i.e., determines whether it is an illegal transaction object. Here, an illegal transaction object refers to a transaction object that has a certain type of risk.

[0112] In step S4, if the risk level of the trading counterpart is non-malicious, the current transaction is approved and the process ends.

[0113] In step S5, if the risk level of the trading object is high-malicious, the trading object is intercepted, and the transaction of the trading object is also intercepted, and the process ends.

[0114] In step S6, if the risk level of the trading object is mildly malicious, it is determined whether there is an image of a customer service complaint. If there is no image of a customer service complaint, step S7 is executed. If there is an image of a customer service complaint, step S8 is executed.

[0115] In step S7, if there are no customer service complaints or no images of customer service complaints, a manual review is conducted. For transactions submitted for manual review, an assessment is made based on the order flow, fund flow, and transaction behavior related to the transaction over a recent period (e.g., the last 7 days). If the transaction is found to be in violation, the transaction is blocked, the risk level label of the transaction is updated, and the process ends.

[0116] In step S8, if there are images related to customer service complaints, the image recognition model is used to check the information security of the images. The sensitive image recognition interface is called to further assess the evidence presented by the accused.

[0117] In step S9, if the image in the customer service complaint matches a sensitive image category, it indicates an illegal transaction has been identified. The transaction is then blocked, and its risk level label is updated, ending the process. If the image in the customer service complaint does not match a sensitive image category, it indicates no illegal transaction has been identified, and step S7 is executed, continuing with manual review.

[0118] Based on the above introduction, the method for identifying transaction objects in this application will be described below. Please refer to [link / reference needed]. Figure 3 One embodiment of the transaction object identification method in this application includes:

[0119] 110. The server obtains transaction object description data for the target transaction object. The transaction object description data includes basic transaction object data and related object data. The basic transaction object data represents data related to the target transaction object, and the related object data represents data related to related objects. Related objects represent objects that have a transaction relationship with the target transaction object.

[0120] In one or more embodiments, the server may obtain transaction object description data of different transaction objects. For ease of explanation, the following will take the target transaction object (e.g., a merchant) as an example. That is, the server obtains the transaction object description data of the target transaction object (e.g., merchant profile data). The transaction object description data mainly includes the basic data of the transaction object and the data of related objects. The basic data of the transaction object represents the data related to the target transaction object itself, while the data of related objects represents the data of objects that have a transaction relationship with the target transaction object. These objects are called related objects (e.g., related users).

[0121] It should be noted that the server can be a trading platform server, a server that integrates trading platform server functions and description data server functions, or a server that integrates trading platform server functions and description data server functions; there is no limitation here.

[0122] 120. The server performs feature processing on the basic data of the transaction object included in the transaction object description data to obtain the transaction object description features, and performs feature processing on the related object data included in the transaction object description data to obtain the related object features.

[0123] In one or more embodiments, the server performs feature engineering on the basic data of the transaction object and the data of related objects, respectively, to obtain the transaction object descriptive features and the related object features. The purpose of feature engineering is to extract features from the original data (i.e., the transaction object descriptive data) to the maximum extent possible for use by the algorithm and model.

[0124] 130. Based on the description features of the transaction object and the features of the associated objects, the server obtains the first risk information corresponding to the target transaction object through the transaction object identification model, wherein the first risk information is represented as a risk score or a risk probability distribution.

[0125] In one or more embodiments, the server inputs the description features of the trading object and the features of the associated objects into a trained trading object recognition model. The trading object recognition model then outputs first risk information corresponding to the target trading object, which is represented as a risk score or a risk probability distribution. If the first risk information is represented as a risk score, the value of the risk score is greater than or equal to 0 and less than or equal to 1. If the first risk information is represented as a risk probability distribution, the sum of all probability values ​​in the risk probability distribution is 1.

[0126] The transaction object identification model can be implemented based on machine learning (ML) algorithms. Machine learning is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, and many other disciplines. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to endow computers with intelligence; its applications span all areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and instructional learning.

[0127] 140. The server determines the risk level label corresponding to the target trading object based on the first risk information.

[0128] In one or more embodiments, the server can determine the risk level label corresponding to the target trading object based on the first risk information. It is understood that the server can identify multiple trading objects using the method described in steps 110 to 130, i.e., obtain the first risk information for each trading object, and determine the risk level label corresponding to each trading object based on the first risk information. Based on this, the server can also store the trading object identifier and its corresponding risk level label in a database, and update the database if the risk level label of a trading object changes.

[0129] Specifically, for ease of understanding, please refer to Table 1, which is an illustration of the relationship between transaction object identifiers and risk level labels stored in the database.

[0130] Table 1

[0131] Trading partners Transaction object identifier Risk level label "Transaction Partner A" 0001 High malice "Transaction Partner B" 0010 Mild malice "Transaction Partner C" 0011 Mild malice "Transaction Partner D" 0100 Non-malicious "Transaction Object E" 1001 Non-malicious

[0132] Each transaction object corresponds to a unique transaction object identifier, and each transaction object identifier corresponds to a risk level label.

[0133] In this embodiment of the application, a method for identifying transaction objects is provided. By taking the transaction object as the center to characterize the basic data of the transaction object, and taking the transaction object and the transaction behavior of the object as the link to characterize the data of related objects, the risk identification result of the transaction object is determined by combining the basic data of the transaction object and the data of related objects. Thus, based on the transaction object description data, the risk situation of the transaction object can be assessed more comprehensively and objectively, thereby reducing the possibility of false interception.

[0134] Optionally, in the above Figure 3 Based on the corresponding embodiments, in another optional embodiment provided by this application, the server obtains transaction object description data for the target transaction object, which may specifically include:

[0135] The server obtains description data, which includes at least one of application description data, public account description data, object description data, and external link description data;

[0136] The server obtains basic transaction data for the target transaction object based on the description data. The basic transaction data includes at least one of the following: transaction object level, investment data, investment data, active time, order amount, historical complaint rate, repurchase rate, number of successful orders, and number of failed orders.

[0137] The server obtains associated object data for the target transaction object based on the description data. The associated object data includes at least one of the following: the account level of the associated object, the first proportion of illegal objects in the associated objects, the second proportion of reported objects in the associated objects, the third proportion of underage objects in the associated objects, and the fourth proportion of objects with historical losses in the associated objects.

[0138] In one or more embodiments, a method for obtaining basic data of a transaction object and related object data is described. As can be seen from the foregoing embodiments, the transaction object description data includes basic data of the transaction object and related object data. The following will combine... Figure 4 This will be illustrated using the example of obtaining the basic data of the target transaction object.

[0139] Specifically, for ease of understanding, please refer to Figure 4 , Figure 4This is a schematic diagram illustrating a framework for obtaining transaction object description data in this application embodiment. As shown in the figure, the application description data includes descriptions related to the application, such as "Class A transaction," where the application has a certain number of unique visitors (UV) and page views (PV) making payments to the target transaction object through this application. The public account description data includes descriptions related to the public account, where the public account has a certain number of UVs and PVs making payments to the target transaction object through this public account. The object description data includes object descriptions extracted based on big data. The object description data includes transaction object suppliers and traffic drivers, where traffic drivers refer to those who guide the object to engage in illegal consumption. The external link description data includes descriptions related to external links, where the external links have a certain number of UVs and PVs making payments to the target transaction object through these external links.

[0140] For example, the basic data of the transaction object includes the following:

[0141] (1) Transaction object level: This refers to the transaction object level marked by the operators when the transaction object is registered. The transaction object level indicates the transaction security level of the transaction object. For example, the higher the transaction object level, the higher the transaction reliability.

[0142] (2) Inflow data: This refers to the amount of funds that flowed in over a period of time (e.g., within the last six months).

[0143] (3) Investment data: indicates the amount of funds spent within a certain period of time (e.g., within the last six months).

[0144] (4) Active time: Indicates the number of active days within a certain period of time (e.g., within the last month).

[0145] (5) Order amount: This indicates the number of orders whose order amount falls within a certain range (e.g., 20 to 30 yuan).

[0146] (6) Percentage of historical complaints: This indicates the percentage of complaints against the target within a certain period of time (e.g., within the last month).

[0147] (7) Repeat purchase rate: This indicates the percentage of items or services that an individual purchases again within a certain period of time (e.g., within the last month).

[0148] (8) Order success rate: This refers to the number of orders that were successfully completed within a certain period of time (e.g., within the last month).

[0149] (9) Order failures: This indicates the number of orders that failed within a certain period of time (e.g., within the last month).

[0150] It should be noted that in practical applications, the basic data of the transaction object may also include other data, which will not be listed here.

[0151] For example, the associated object data of the target transaction object includes the following:

[0152] (1) Account level of associated object: indicates the quality level of the object account of the main consumer group of the transaction object (e.g., the target transaction object).

[0153] (2) The first proportion of illegal objects in the associated objects: This refers to the proportion of illegal objects among the main consumer groups of the transaction object (e.g., the target transaction object).

[0154] (3) The second percentage of the reported object in the related objects: This refers to the percentage of the reported object in the main consumer group of the transaction object (e.g., the target transaction object). The reported object refers to the object that has been reported for a certain type of content.

[0155] (4) The third proportion of minors in the associated objects: This refers to the proportion of minors among the main consumer groups of the transaction object (e.g., the target transaction object).

[0156] (5) The fourth percentage of historically damaged objects among related objects: This represents the percentage of objects that have suffered property losses in the past among the main consumer groups of the transaction object (e.g., the target transaction object).

[0157] It should be noted that in practical applications, the associated object data may also include other data, which will not be listed here.

[0158] Secondly, this application provides a method for obtaining basic data of transaction objects and related object data. This method increases the cost of illegally transferring data between multiple different transaction objects and effectively improves the coverage of the strategy, enabling timely and effective identification and containment of transfer targets after illegal transfers. Although transaction objects can re-register accounts, applications and official accounts remain relatively unchanged; the main cost is in traffic acquisition. Therefore, using the descriptive data of applications and official accounts to characterize transaction objects makes it easier to identify some illegal transaction objects.

[0159] Optionally, in the above Figure 3 Based on the corresponding embodiments, in another optional embodiment provided by this application, the server performs feature processing on the basic data of the transaction object included in the transaction object description data to obtain transaction object description features, which may specifically include:

[0160] If the basic data of the transaction object includes the transaction object level, the server performs one-hot encoding on the transaction object level to obtain the transaction object level feature, wherein the transaction object level feature is included in the transaction object description feature.

[0161] If the basic data of the transaction object includes investment data, investment data, order success rate and order failure rate, the server performs feature scaling processing on the investment data, investment data, order success rate and order failure rate to obtain investment data features, investment data features, order success rate features and order failure rate features. Among them, the investment data features, investment data features, order success rate features and order failure rate features are included in the transaction object description features.

[0162] If the basic data of the transaction object includes the order amount, the server performs feature binning on the order amount to obtain the order amount feature, where the order amount feature is included in the transaction object description feature;

[0163] If the basic data of the transaction object includes active time, historical complaint ratio and repurchase ratio, the server performs numerical processing on the active time, historical complaint ratio and repurchase ratio to obtain active time feature, historical complaint ratio feature and repurchase ratio feature. Among them, the active time feature, historical complaint ratio feature and repurchase ratio feature are included in the transaction object description feature.

[0164] The server performs feature processing on the associated object data included in the transaction object description data to obtain associated object features, which may specifically include:

[0165] If the associated object data includes the account level of the associated object, the server performs one-hot encoding on the account level of the associated object to obtain the account level feature and the quantity type feature, wherein the account level feature and the quantity type feature are included in the associated object feature.

[0166] If the associated object data includes the first proportion, the second proportion, the third proportion, and the fourth proportion, the server performs numerical processing on the first proportion, the second proportion, the third proportion, and the fourth proportion to obtain the characteristics of the proportion of illegal objects, the characteristics of the proportion of reported objects, the characteristics of the proportion of minor objects, and the characteristics of the proportion of historically damaged objects. Among them, the characteristics of the proportion of illegal objects, the characteristics of the proportion of reported objects, the characteristics of the proportion of minor objects, and the characteristics of the proportion of historically damaged objects are included in the characteristics of associated objects.

[0167] In one or more embodiments, a method for feature processing of basic data of trading objects and related object data is described. As can be seen from the foregoing embodiments, the basic data of the target trading object and the related object data each include multiple specific indicators, and these indicators need to be feature-processed before model prediction.

[0168] Specifically, for example, one-hot encoding can be performed on the transaction object level to obtain the transaction object level feature. For example, if the target transaction object has a transaction object level of A, and there are three transaction object levels, the transaction object level feature can be represented as (1,0,0).

[0169] For example, feature scaling can be performed on the incoming investment data, outgoing investment data, order success rate, and order failure rate to obtain the incoming investment data feature, the outgoing investment data feature, the order success rate feature, and the order failure rate feature. For instance, if the incoming investment data of the target transaction object is 5000, and the highest incoming investment data among other transaction objects is 10000, then the incoming investment data feature can be represented as 0.5.

[0170] For example, for order amounts, feature binning can be performed to obtain order amount features. For instance, three bins can be set: less than or equal to 20 yuan, greater than 20 yuan and less than 30 yuan, and greater than or equal to 30 yuan. The order amounts of the target transaction object are divided into three categories: 100 orders less than or equal to 20 yuan, 800 orders greater than 20 yuan and less than 30 yuan, and 50 orders greater than or equal to 30 yuan. Based on this, the order amount feature can be represented as (100, 800, 50), or the order amount feature can be represented as the probability that the order amount falls within a certain range (e.g., 20 to 30 yuan).

[0171] For example, regarding active time, historical complaint ratio, and repurchase ratio, the server can perform numerical processing on these metrics to obtain the active time feature corresponding to active time, the historical complaint ratio feature corresponding to historical complaint ratio, and the repurchase ratio feature corresponding to repurchase ratio. For instance, if the historical complaint ratio is 10%, the historical complaint ratio feature can be represented as 0.1.

[0172] For example, for the account level of the associated object, one-hot encoding can be performed to obtain the account level feature corresponding to the account level and the quantity type feature corresponding to the number of new objects. For example, if there are many new friends, the quantity type feature is represented as 1.

[0173] For example, the following percentages can be quantified: the first percentage of illegal entities among associated entities, the second percentage of reported entities among associated entities, the third percentage of minors among associated entities, and the fourth percentage of historically harmed entities among associated entities. These percentages can be quantified to obtain the illegal entity percentage characteristic corresponding to the first percentage, the reported entity percentage characteristic corresponding to the second percentage, the minor entity percentage characteristic corresponding to the third percentage, and the historically harmed entity percentage characteristic corresponding to the fourth percentage. For instance, if the first percentage of illegal entities among associated entities is 20%, then the illegal entity percentage characteristic is represented as 0.2.

[0174] It should be noted that the feature processing methods mentioned above are only one implementation. In practical applications, appropriate feature processing methods can be selected according to requirements.

[0175] Furthermore, this application provides a method for feature processing of basic data of transaction objects and related object data. Through the above method, basic data of transaction objects and related object data can be extracted from descriptive data from different sources for feature processing, which is beneficial for machine learning models to learn and predict.

[0176] Optionally, in the above Figure 3 Based on the corresponding embodiments, in another optional embodiment provided by this application, the server obtains the first risk information corresponding to the target transaction object through a transaction object identification model based on the transaction object description features and associated object features. Specifically, this may include:

[0177] Based on the description features of the transaction object and the features of the associated objects, the server obtains the risk score corresponding to the target transaction object through a transaction object identification model;

[0178] The server determines the risk level label corresponding to the target transaction object based on the initial risk information, which may specifically include:

[0179] If the risk score is greater than or equal to 0 and less than the first threshold, the server determines the risk level label corresponding to the target transaction object as the first risk label.

[0180] If the risk score is greater than or equal to the first threshold and less than the second threshold, the server determines the risk level label corresponding to the target transaction object as the second risk label, wherein the degree of malice of the second risk label is higher than that of the first risk label.

[0181] In one or more embodiments, a method for determining risk level labels based on risk scores is described. As can be seen from the foregoing embodiments, after inputting the descriptive features of the trading object and the features of related objects into the trading object identification model, the trading object identification model outputs the risk score corresponding to the target trading object.

[0182] Specifically, the transaction object identification model can use a sigmoid function to output a risk score between 0 and 1. Based on this, if the risk score is greater than or equal to 0 and less than a first threshold, the risk level label corresponding to the target transaction object is determined to be a first risk label, which can be a "non-malicious" risk label. The first threshold can be set empirically, for example, 0.2. If the risk score is greater than or equal to the first threshold and less than a second threshold, the risk level label corresponding to the target transaction object is determined to be a second risk label, which can be a "mildly malicious" risk label. The second threshold can be set empirically, for example, 0.5.

[0183] It should be noted that a scenario can also be set where the risk score is greater than or equal to the second threshold and less than or equal to the third threshold. The risk level label within this range will then be used as the third risk label; for example, the third risk label could be "high malice." The third threshold can be set empirically, for example, to 1. Similarly, risk level labels can be determined based on interval divisions, with the number of intervals being an integer greater than or equal to 2.

[0184] It is understandable that the transaction object recognition model belongs to the machine learning model. The transaction object recognition model can use multilayer perceptron (MLP), convolutional neural network (CNN), decision tree or deep neural network (DNN), without limitation here.

[0185] Secondly, this application provides a method for determining risk level labels based on risk scores. Using the aforementioned method, the risk score of the target trading object can be directly obtained using the Sigmoid function. While the output range of this risk score is limited, the risk level label can be determined based on the relationship between the risk score and different thresholds. Therefore, this provides a concrete means for determining risk level labels, increasing the feasibility of the solution.

[0186] Optionally, in the above Figure 3 Based on the corresponding embodiments, in another optional embodiment provided by this application, the server obtains the first risk information corresponding to the target transaction object through a transaction object identification model based on the transaction object description features and associated object features. Specifically, this may include:

[0187] Based on the characteristics of the transaction object description and the characteristics of the associated objects, the server obtains the risk probability distribution corresponding to the target transaction object through the transaction object identification model. The risk probability distribution includes K probability values, each probability value corresponds to a risk label, and K is an integer greater than or equal to 2.

[0188] The server determines the risk level label corresponding to the target transaction object based on the initial risk information, which may specifically include:

[0189] The server determines the risk label corresponding to the highest probability value from K probability values ​​based on the risk probability distribution;

[0190] The server determines the risk label corresponding to the highest probability value as the risk level label.

[0191] In one or more embodiments, a method for determining risk level labels based on risk probability distribution is described. As can be seen from the foregoing embodiments, after inputting the descriptive features of the trading object and the features of related objects into the trading object identification model, the trading object identification model outputs the risk probability distribution corresponding to the target trading object.

[0192] Specifically, the trading target identification model can use the normalized exponential (Softmax) function to output a risk probability distribution whose summates to 1. Taking a risk probability distribution with three probability values ​​(K equals 3) as an example, assuming the risk probability distribution is (0.1, 0.2, 0.7), where 0.1 represents a 10% probability of belonging to the "non-malicious" risk label, 0.2 represents a 20% probability of belonging to the "mildly malicious" risk label, and 0.7 represents a 70% probability of belonging to the "highly malicious" risk label. Therefore, the risk label corresponding to the highest probability value among the K probability values ​​is the "highly malicious" risk label. Thus, the "highly malicious" risk label is determined as the risk level label of the target trading target.

[0193] Secondly, this application provides a method for determining risk level labels based on risk probability distribution. Using the Softmax function, the results of multi-classification can be displayed in probability form, and the risk label with the highest probability value is selected as the risk level label. Because the Softmax function first amplifies the differences between the elements of the input vector and then normalizes it to a probability distribution, in classification problems, the probability differences between each risk label are more significant, and the probability of the maximum value is closer to 1. Thus, the output distribution is closer to the true distribution. Therefore, this provides a concrete means to determine risk level labels and increases the feasibility of the solution.

[0194] Optionally, in the above Figure 3 Based on the corresponding embodiments, another optional embodiment provided in this application may further include:

[0195] If the risk level label indicates that the target transaction object is a pending illegal transaction object, the server obtains object complaint data for the target transaction object;

[0196] If the complaint data includes an image to be identified, the server obtains the second risk information corresponding to the image to be identified through an image recognition model, and determines the target risk level label corresponding to the target transaction object based on the second risk information. The second risk information is represented as a risk score or risk probability distribution.

[0197] If the complaint data does not include the image to be identified, the server sends the pending data for the target transaction object to the terminal device. The pending data includes at least one of the target transaction object's order information, financial information, and object behavior information.

[0198] In one or more embodiments, a method for reviewing the results of pending risk identification based on object complaint data is described. As can be seen from the foregoing embodiments, after the server determines the risk level label of the target transaction object, if the target transaction object is determined to be a pending illegal transaction object based on the risk level label, it is necessary to further obtain object complaint data for the target transaction object. The pending illegal transaction object may have a "mildly malicious" risk label.

[0199] Specifically, the system checks whether the complaint data includes an image to be identified, where the image refers to a screenshot or photograph uploaded by the complainant through the complaint channel. If the complaint data includes the image, a trained image recognition model is invoked to identify it, and the model outputs second risk information. This second risk information can also be represented as a risk score or risk probability distribution. For example, if the risk score is greater than or equal to 0 and less than a first threshold, the target risk level label is determined as the first risk label. Alternatively, the risk label corresponding to the highest probability value from K probability values ​​is determined, and this label is then used as the target risk level label.

[0200] It should be noted that the method of determining the target risk level label based on the second risk information is similar to the method of determining the risk level label based on the first risk information in the aforementioned embodiments, so it will not be described in detail here.

[0201] If the complaint data does not include the image to be identified, the server will push pending review data for the target transaction to the terminal device used by the back-end reviewers. This pending review data includes at least one of the following: order information, financial information, and transaction behavior information. Order information includes the amount of each order within a certain period (e.g., the past month). Financial information includes the rate of increase or decrease in the target transaction's funds within a certain period (e.g., the past month). Transaction behavior information includes the number of transfers made by the target to the target transaction, the amount transferred, and the number of subscriptions made within a certain period (e.g., the past month). Based on this pending review data, the back-end reviewers will assign appropriate risk tags to the target transaction.

[0202] Secondly, this application provides a method for reviewing the risk identification results based on object complaint data. Using this method, for transaction objects with mild malicious intent, the image to be identified included in the object complaint data can be used for further identification, thereby improving the accuracy of transaction object identification and saving the cost of manual review. If the object complaint data does not include the image to be identified, then manual review is performed.

[0203] Optionally, in the above Figure 3 Based on the corresponding embodiments, another optional embodiment provided in this application may further include:

[0204] The server retrieves object complaint data targeting the intended transaction object;

[0205] If the complaint data includes an image to be identified, the server obtains the second risk information corresponding to the image to be identified through an image recognition model. The second risk information is represented as a risk score or a risk probability distribution.

[0206] The server determines the risk level label corresponding to the target transaction object based on the initial risk information, which may specifically include:

[0207] The server determines the risk level label corresponding to the target trading object based on the first risk information and the second risk information.

[0208] In one or more embodiments, another method for reviewing the risk identification results based on object complaint data is introduced. As can be seen from the foregoing embodiments, if the object complaint data includes an image to be identified, a trained image recognition model is invoked to identify the image, and the image recognition model outputs second risk information. Thus, a risk level label can be determined based on the first risk information and the second risk information.

[0209] Specifically, for example, if both the first risk information and the second risk information are represented as risk scores, then an average risk score can be calculated based on the first and second risk information. If the average risk score is greater than or equal to 0 and less than a first threshold, then the risk level label corresponding to the target trading object is determined to be a first risk label, which can be a "non-malicious" risk label. If the average risk score is greater than or equal to the first threshold and less than a second threshold, then the risk level label corresponding to the target trading object is determined to be a second risk label, which can be a "mildly malicious" risk label. If the average risk score is greater than or equal to the second threshold and less than or equal to a third threshold, then the risk level label corresponding to the target trading object is determined to be a third risk label, for example, a "highly malicious" risk label.

[0210] For example, if both the first and second risk information are represented as risk probability distributions, then an average risk probability distribution can be determined based on the first and second risk information. This average risk probability distribution also includes K probability values. For instance, if the first risk information is represented as (0.1, 0.2, 0.7) and the second risk information is represented as (0.1, 0, 0.9), then the average risk probability score is represented as (0.1, 0.1, 0.8). Here, the first 0.1 indicates a 10% probability of belonging to the "non-malicious" risk label, the second 0.1 indicates a 10% probability of belonging to the "mildly malicious" risk label, and 0.8 indicates an 80% probability of belonging to the "highly malicious" risk label. Therefore, the risk label corresponding to the highest probability value among the K probability values ​​is the "highly malicious" risk label, and thus the "highly malicious" risk label is determined as the risk level label of the target trading object.

[0211] Secondly, this application provides another method for reviewing the risk identification results based on object complaint data. In this way, when determining the risk level label of a transaction object, not only is the transaction object description data used, but also the image to be identified in the object complaint data can be used to jointly predict the risk level label, which helps to improve the accuracy of identification.

[0212] Optionally, in the above Figure 3 Based on the corresponding embodiments, in another optional embodiment provided by this application, the server obtains transaction object description data for the target transaction object, which may specifically include:

[0213] The server receives a transaction processing request sent by the terminal device, wherein the transaction processing request carries a transaction object identifier, which is used to indicate the target transaction object;

[0214] The server responds to the transaction processing request by obtaining transaction object description data for the target transaction object;

[0215] It may also include:

[0216] The server sends a risk level label to the terminal device, so that the terminal device can display a corresponding prompt message based on the risk level label.

[0217] In one or more embodiments, a method for triggering transaction processing requests based on terminal devices is described. Using this method, if a terminal device sends a transaction processing request to a server, the server can predict the risk level label of the target transaction object based on the transaction processing request. After determining the risk level label corresponding to the target transaction object, the server pushes the risk level label to the terminal device.

[0218] Specifically, the terminal device sends a transaction processing request to the server, carrying a transaction object identifier of "0001," which indicates the target transaction object. Based on this, the server obtains transaction object description data for the target transaction object, which includes basic transaction object data and related object data. Then, the server performs feature processing on the basic transaction object data to obtain transaction object description features, and performs feature processing on the related object data to obtain related object features. The transaction object description features and related object features are then input into the transaction object recognition model, thereby outputting first risk information. Finally, based on the first risk information, the risk level label corresponding to the target transaction object is determined and fed back to the terminal device, which then displays a corresponding prompt message.

[0219] Secondly, in this embodiment of the application, a method for triggering transaction processing requests based on terminal devices is provided. Through the above method, the server can also identify the risk level label of the transaction object in real time and push it to the terminal device, which will then provide corresponding reminders. This makes it easier for the object to discover the risk situation of the transaction object in a timely manner, which can reduce the possibility of property loss to a certain extent.

[0220] Based on the above introduction, the transaction processing method in this application will be described below. Please refer to [link / reference]. Figure 5 One embodiment of the transaction object identification method in this application includes:

[0221] 210. The terminal device displays a payment transaction interface, wherein the payment transaction interface provides a first payment control;

[0222] In one or more embodiments, the payment function provided by the terminal device is activated, and the terminal device displays a payment transaction interface, which displays a first payment control.

[0223] 220. The terminal device responds to the selection instruction for the first payment control and sends a transaction processing request to the server, so that the server determines the risk level label corresponding to the target transaction object based on the transaction object identifier carried in the transaction processing request, wherein the transaction object identifier is used to indicate the target transaction object, and the risk level label is determined as described in the above embodiment;

[0224] In one or more embodiments, the object triggers a selection instruction for the first payment control. The terminal device then responds to the selection instruction and further sends a transaction processing request to the server, wherein the transaction processing request carries the transaction object identifier of the target transaction object. Based on this, in one scenario, the server directly searches the database for the risk level label corresponding to the target transaction object based on the transaction object identifier. In another scenario, the server predicts the risk level label of the target transaction object online based on the transaction object identifier, using the prediction method described in steps 110 to 140 of the aforementioned embodiments, which will not be repeated here.

[0225] 230. If the risk level label indicates that the target transaction object is an illegal transaction object, the terminal device will display a payment failure message.

[0226] In one or more embodiments, if the risk level label returned by the server indicates that the target transaction object is an illegal transaction object, the transaction is blocked, and the terminal device displays a corresponding payment failure message. The risk level label indicating that the target transaction object is an illegal transaction object can be a "highly malicious" risk label.

[0227] For example, an object triggers a transaction instruction on a transaction object page, which then redirects the user to the payment application to complete the transaction. For easier understanding, please refer to [link to relevant documentation]. Figure 6 , Figure 6 This is a schematic diagram of the payment transaction interface in an embodiment of this application, such as... Figure 6 As shown in Figure (A), A1 is used to indicate the first payment control. After the object clicks the first payment control indicated by A1, it can... Figure 6 The interface shown in Figure (B) displays a payment failure message in the form of a pop-up window. The text of the payment failure message may be "The other party's account has been restricted from logging in. In order to protect your funds, the transaction cannot be completed at this time."

[0228] For example, an object triggers a transaction instruction on a transaction object page, and the transaction is then performed directly on the transaction object page. For easier understanding, please refer to [link to relevant documentation]. Figure 7 , Figure 7 This is another schematic diagram of the payment transaction interface in the embodiments of this application, such as... Figure 7As shown, A2 is used to indicate the first payment control. After the object clicks the first payment control indicated by A2, a payment failure message is displayed directly in the form of a pop-up window.

[0229] For example, an object triggers a transaction instruction on a transaction object page, which then redirects the user to the payment application to complete the transaction. For easier understanding, please refer to [link to relevant documentation]. Figure 8 , Figure 8 This is another schematic diagram of the payment transaction interface in the embodiments of this application, such as... Figure 8 As shown in Figure (A), A3 is used to indicate the first payment control. After the object clicks the first payment control indicated by A3, it can... Figure 8 The interface shown in Figure (B) displays a payment failure message in a half-interface format.

[0230] It should be noted that the interface layout shown in the above illustration is only a schematic diagram and should not be construed as a limitation of this application.

[0231] In this embodiment of the application, a transaction processing method is provided. By taking the transaction object as the center to characterize the basic data of the transaction object, and taking the transaction object and the transaction behavior of the object as the link to characterize the related object data, the risk identification result of the transaction object is determined by combining the basic data of the transaction object and the related object data. Thus, based on the transaction object description data, the risk situation of the transaction object can be assessed more comprehensively and objectively. On the one hand, it reduces the possibility of false interception, and on the other hand, it can improve the reliability of the transaction and reduce the possibility of loss of the object's property.

[0232] Optionally, in the above Figure 5 Based on the corresponding embodiments, another optional embodiment provided in this application may further include:

[0233] At least one of the following: a terminal device display details view control and an information reporting control;

[0234] If a selection command is received for viewing details, the terminal device displays abnormal transaction information related to the target transaction object;

[0235] If a selection command is received for the information reporting control, the terminal device displays the information reporting interface, which provides an input area for object information.

[0236] In one or more embodiments, a strong alert method is described when the target transaction object is determined to be an illegal transaction object. As can be seen from the foregoing embodiments, if the risk level label returned by the server indicates that the target transaction object is an illegal transaction object, then not only can the transaction be blocked, but at least one of the following can be provided: a details viewing control and an information reporting control. This will be explained below with reference to the illustrations.

[0237] For example, for ease of understanding, please refer to Figure 9 , Figure 9 This is another schematic diagram of the payment transaction interface in the embodiments of this application, such as... Figure 9 As shown in Figure (A), after the object clicks the first payment control, it can... Figure 9 The interface shown in Figure (B) displays a payment failure message and a details view control indicated by B1. After clicking the details view control, the user can... Figure 9 The interface shown in Figure (C) displays abnormal transaction information related to the target trading object. The text of the abnormal transaction information could be something like, "The XXX trading object has been reported 15 times, potentially indicating a risk of illegal transactions."

[0238] For example, for ease of understanding, please refer to Figure 10 , Figure 10 This is another schematic diagram of the payment transaction interface in the embodiments of this application, such as... Figure 10 As shown in Figure (A), after the object clicks the first payment control, a payment failure message and the details viewing control indicated by B2 are displayed directly. After the object clicks the details viewing control, it can... Figure 10 The interface shown in Figure (B) displays abnormal transaction information related to the target trading object.

[0239] For example, for ease of understanding, please refer to Figure 11 , Figure 11 This is another schematic diagram of the payment transaction interface in the embodiments of this application, such as... Figure 11 As shown in Figure (A), after the object clicks the first payment control, it can... Figure 11 The interface shown in Figure (B) displays a payment failure message and the information reporting control indicated by B3. After clicking the information reporting control, the user can... Figure 11 The information reporting interface shown in Figure (C) displays an input box for submitting reports for manual review. The recipient can request the removal of the blocking restrictions by describing the relevant transaction details.

[0240] For example, for ease of understanding, please refer to Figure 12 , Figure 12 This is another schematic diagram of the payment transaction interface in the embodiments of this application, such as... Figure 12 As shown in Figure (A), after the object clicks the first payment control, a payment failure message and the information reporting control indicated by B4 are displayed directly. After the object clicks the information reporting control, it can... Figure 12 The information reporting interface shown in Figure (B) displays an input box for submitting reports for manual review. The recipient can request the removal of the blocking restrictions by describing the relevant transaction details.

[0241] It should be noted that the interface layout shown in the above illustration is only a schematic diagram and should not be construed as a limitation of this application.

[0242] Secondly, this application provides a strong reminder method when the target transaction object is determined to be an illegal transaction object. Through the above method, after the object confirms the payment, if the server determines that the risk level label of the target transaction object is "high malicious", it will not only block the transaction and remind the transaction risk, but also provide further abnormal transaction information according to the object's choice, or allow the object to report the information of the transaction, so as to verify the reliability of the transaction through manual review, thereby improving the flexibility of the solution.

[0243] Optionally, in the above Figure 5 Based on the corresponding embodiments, another optional embodiment provided in this application may further include:

[0244] If the risk level label indicates that the target transaction object is a pending illegal transaction object, and no payment amount information has been entered, the terminal device will display a transaction object risk warning message and a second payment control;

[0245] The terminal device responds to the selection instruction for the second payment control and displays the password input area;

[0246] Alternatively, it may also include:

[0247] If the risk level label indicates that the target transaction object is a pending illegal transaction object, and the payment amount information has been entered, the terminal device will display a risk warning message for the transaction object and a third payment control.

[0248] The terminal device responds to the selection instruction for the third payment control and generates an order payment request.

[0249] In one or more embodiments, a strong alert method is described when the target transaction object is determined to be a potential illegal transaction object. As can be seen from the foregoing embodiments, if the risk level label returned by the server indicates that the target transaction object is a potential illegal transaction object, then the alert is issued regarding whether the transaction should continue. The risk level label indicating that the target transaction object is a potential illegal transaction object can be a "mildly malicious" risk label. This will be explained below with reference to the illustrations.

[0250] For example, for ease of understanding, please refer to Figure 13 , Figure 13 This is another schematic diagram of the payment transaction interface in the embodiments of this application, such as... Figure 13 As shown in Figure (A), after the object clicks the first payment control, the following is displayed: Figure 13The risk warning message for the transaction counterparty is shown in Figure (B), and the second payment control is indicated by C1. The text of the risk warning message could be, "The other party's account is not logged in from their usual location; please verify their identity." After clicking the second payment control, the counterparty can... Figure 13 The information reporting interface shown in Figure (C) displays the password input area indicated by C2, through which the recipient can enter their payment password.

[0251] For example, for ease of understanding, please refer to Figure 14 , Figure 14 This is another schematic diagram of the payment transaction interface in this embodiment. As shown in the figure, after the object enters the payment amount information, a risk warning message for the transaction object and the second payment control indicated by C3 are displayed. After the object clicks the second payment control, it can... Figure 14 The information reporting interface shown in Figure (B) displays the password input area indicated by C4, through which the recipient can enter their payment password.

[0252] For example, for ease of understanding, please refer to Figure 15 , Figure 15 This is another schematic diagram of the payment transaction interface in this embodiment of the application. As shown in the figure, after the object enters the payment amount information, a risk warning message for the transaction object and the third payment control indicated by C5 are displayed. After the object clicks the third payment control, an order payment request is generated.

[0253] It should be noted that the interface layout shown in the above illustration is only a schematic diagram and should not be construed as a limitation of this application.

[0254] Secondly, this application provides a strong reminder method when a target transaction object is determined to be a potential illegal transaction object. Through this method, after the object confirms payment, if the server determines that the target transaction object's risk level label is "mildly malicious," it will remind the object whether to continue payment or abandon payment before actually deducting the funds, thereby improving transaction reliability. Furthermore, for transaction objects with different risk level labels, the tiered intervention design not only achieves the goal of timely blocking malicious transaction objects but also avoids a "one-size-fits-all" approach to banning transaction objects, thus effectively preventing serious customer complaints caused by mistaken attacks to a certain extent.

[0255] Optionally, in the above Figure 5 Based on the corresponding embodiments, another optional embodiment provided in this application may further include:

[0256] If the risk level label indicates that the target transaction object is a pending illegal transaction object, and the order payment has been completed, the terminal device displays a transaction object reporting control;

[0257] The terminal device responds to the selection command for the reporting control of the transaction object and displays the order reporting interface, which provides at least one of the following: transaction object name input area, transaction object nature input area, transaction object account input area, and report content input area.

[0258] In one or more embodiments, a method for reporting transactions after successful payment is described. As seen in the foregoing embodiments, if the risk level label returned by the server indicates that the target transaction object is a pending illegal transaction object, then the recipient is prompted to initiate a report. The risk level label indicating that the target transaction object is a pending illegal transaction object can be a "mildly malicious" risk label. This will be explained below with reference to the illustrations.

[0259] For example, for ease of understanding, please refer to Figure 16 , Figure 16 This is another schematic diagram of the payment transaction interface in the embodiments of this application, such as... Figure 16 As shown in Figure (A), after the object clicks the report control for the transaction object indicated by D1, it enters the following... Figure 16 The order reporting interface shown in Figure (B) has the following sections: D2 indicates the input area for the name of the transaction object, D3 indicates the input area for the nature of the transaction object, D4 indicates the input area for the account of the transaction object, and D5 indicates the input area for the content of the report. In the transaction object name input area, you can enter the name of the transaction object. In the transaction object nature input area, you can enter whether the transaction object belongs to a company or an individual. In the transaction object account input area, you can enter the registered account information of the transaction object. In the report content input area, you can enter the specific content of the report against the transaction object, and you can also upload screenshots, etc., which are not limited here.

[0260] It should be noted that the interface layout shown in the above illustration is only a schematic diagram and should not be construed as a limitation of this application.

[0261] Secondly, this application provides a method for reporting after successful payment. Through this method, after successful payment, the recipient can file a complaint or report on the successful payment order, which can achieve the purpose of "public supervision" and help to uncover more illegal transaction recipients, thereby maintaining a good transaction environment.

[0262] The transaction object identification device in this application is described in detail below. Please refer to [link / reference]. Figure 17 , Figure 17This is a schematic diagram of one embodiment of the transaction object identification device in this application. The transaction object identification device 30 includes:

[0263] The acquisition module 310 is used to acquire transaction object description data for the target transaction object. The transaction object description data includes basic transaction object data and associated object data. The basic transaction object data represents data related to the target transaction object, and the associated object data represents data related to associated objects. The associated objects represent objects that have a transaction relationship with the target transaction object.

[0264] The processing module 320 is used to perform feature processing on the basic data of the transaction object included in the transaction object description data to obtain the transaction object description features, and to perform feature processing on the associated object data included in the transaction object description data to obtain the associated object features.

[0265] The acquisition module 310 is also used to acquire the first risk information corresponding to the target transaction object through the transaction object identification model based on the transaction object description features and associated object features, wherein the first risk information is represented as a risk score or risk probability distribution;

[0266] The determination module 330 is used to determine the risk level label corresponding to the target trading object based on the first risk information.

[0267] In this application embodiment, a transaction object identification device is provided. Using the above device, the basic data of the transaction object is characterized with the transaction object as the center, and the transaction object and the transaction behavior of the object are used as the link to characterize the related object data. The risk identification result of the transaction object is determined by combining the basic data of the transaction object and the related object data. Thus, the risk situation of the transaction object can be more comprehensively and objectively assessed based on the transaction object description data, thereby reducing the possibility of false interception.

[0268] Optionally, in the above Figure 17 Based on the corresponding embodiments, in another embodiment of the transaction object identification device 30 provided in this application,

[0269] The acquisition module 310 is specifically used to acquire description data, wherein the description data includes at least one of application description data, public account description data, object description data, and external link description data;

[0270] Based on the description data, obtain the basic data of the target transaction object, which includes at least one of the following: transaction object level, investment data, investment data, active time, order amount, historical complaint rate, repurchase rate, number of successful orders, and number of failed orders;

[0271] Based on the description data, obtain the associated object data for the target transaction object. The associated object data includes at least one of the following: the account level of the associated object, the first proportion of illegal objects among the associated objects, the second proportion of reported objects among the associated objects, the third proportion of minor objects among the associated objects, and the fourth proportion of objects with historical losses among the associated objects.

[0272] In this embodiment of the application, a transaction object identification device is provided. Using the above device, the server can extract basic data of the transaction object and related object data from description data from different sources, thereby improving the diversity and richness of feature types and improving the reliability of model prediction.

[0273] Optionally, in the above Figure 17 Based on the corresponding embodiments, in another embodiment of the transaction object identification device 30 provided in this application,

[0274] The processing module 320 is specifically used to perform one-hot encoding on the transaction object level if the basic data of the transaction object includes the transaction object level, so as to obtain the transaction object level feature, wherein the transaction object level feature is included in the transaction object description feature.

[0275] If the basic data of the transaction object includes investment data, investment data, order success rate and order failure rate, then feature scaling processing is performed on the investment data, investment data, order success rate and order failure rate to obtain investment data features, investment data features, order success rate features and order failure rate features. Among them, investment data features, investment data features, order success rate features and order failure rate features are included in the transaction object description features.

[0276] If the basic data of the transaction object includes the order amount, then the order amount is binned to obtain the order amount feature, which is included in the transaction object description feature.

[0277] If the basic data of the transaction object includes active time, historical complaint ratio and repurchase ratio, then the active time, historical complaint ratio and repurchase ratio are numerically processed to obtain active time feature, historical complaint ratio feature and repurchase ratio feature. Among them, the active time feature, historical complaint ratio feature and repurchase ratio feature are included in the transaction object description feature.

[0278] The processing module 320 is specifically used to perform one-hot encoding on the account level of the associated object if the associated object data includes the account level of the associated object, so as to obtain the account level feature and the quantity type feature, wherein the account level feature and the quantity type feature are included in the associated object feature.

[0279] If the associated object data includes the first proportion, the second proportion, the third proportion, and the fourth proportion, then the first proportion, the second proportion, the third proportion, and the fourth proportion are numerically processed to obtain the characteristics of the proportion of illegal objects, the characteristics of the proportion of reported objects, the characteristics of the proportion of minor objects, and the characteristics of the proportion of historically damaged objects. Among them, the characteristics of the proportion of illegal objects, the characteristics of the proportion of reported objects, the characteristics of the proportion of minor objects, and the characteristics of the proportion of historically damaged objects are included in the characteristics of associated objects.

[0280] In this application embodiment, a transaction object identification device is provided. Using the above device, basic data of the transaction object and related object data can be extracted from descriptive data from different sources for feature processing, which is beneficial for machine learning models to learn and predict.

[0281] Optionally, in the above Figure 17 Based on the corresponding embodiments, in another embodiment of the transaction object identification device 30 provided in this application,

[0282] The acquisition module 310 is specifically used to obtain the risk score corresponding to the target transaction object through the transaction object identification model based on the transaction object description features and related object features;

[0283] The determination module 330 is specifically used to determine the risk level label corresponding to the target transaction object as the first risk label if the risk score is greater than or equal to 0 and less than the first threshold.

[0284] If the risk score is greater than or equal to the first threshold and less than the second threshold, then the risk level label corresponding to the target trading object is determined to be the second risk label, wherein the degree of malice of the second risk label is higher than that of the first risk label.

[0285] This application provides a transaction object identification device. Using this device, the risk score of the target transaction object can be directly obtained using the Sigmoid function. The output range of this risk score is limited, and a risk level label can be determined based on the relationship between the risk score and different thresholds. Therefore, a concrete means for determining the risk level label is provided, increasing the feasibility of the solution.

[0286] Optionally, in the above Figure 17 Based on the corresponding embodiments, in another embodiment of the transaction object identification device 30 provided in this application,

[0287] The acquisition module 310 is specifically used to obtain the risk probability distribution corresponding to the target transaction object through the transaction object identification model based on the transaction object description features and related object features. The risk probability distribution includes K probability values, each probability value corresponds to a risk label, and K is an integer greater than or equal to 2.

[0288] The determination module 330 is specifically used to determine the risk label corresponding to the maximum probability value from K probability values ​​based on the risk probability distribution;

[0289] The risk label corresponding to the highest probability value is determined as the risk level label.

[0290] This application provides a transaction object identification device. Using this device, the Softmax function can display the results of multi-classification in the form of probabilities, and select the risk label with the highest probability value as the risk level label. Because the Softmax function first amplifies the differences between the elements of the input vector and then normalizes it to a probability distribution, in classification problems, the probability differences between each risk label are more significant, and the probability of the maximum value is closer to 1. Thus, the output distribution is closer to the true distribution. Therefore, this provides a concrete means to determine the risk level label and increases the feasibility of the solution.

[0291] Optionally, in the above Figure 17 Based on the corresponding embodiments, in another embodiment of the transaction object identification device 30 provided in this application, the transaction object identification device 30 further includes a sending module 340;

[0292] The acquisition module 310 is also used to acquire object complaint data for the target transaction object if the risk level label indicates that the target transaction object is a pending illegal transaction object;

[0293] The acquisition module 310 is also used to, if the object complaint data includes an image to be identified, obtain the second risk information corresponding to the image to be identified through an image recognition model, and determine the target risk level label corresponding to the target transaction object based on the second risk information, wherein the second risk information is represented as a risk score or a risk probability distribution;

[0294] The sending module 340 is used to send pending data for the target transaction object to the terminal device if the object complaint data does not include the image to be identified. The pending data includes at least one of the target transaction object's order information, fund information, and object behavior information.

[0295] This application provides a transaction object identification device. Using this device, for transaction objects with mild malicious intent, the device can further identify the transaction object by combining the image to be identified included in the object complaint data, thereby improving the accuracy of transaction object identification and saving the cost of manual review. If the object complaint data does not include the image to be identified, then manual review is performed.

[0296] Optionally, in the above Figure 17Based on the corresponding embodiments, in another embodiment of the transaction object identification device 30 provided in this application,

[0297] The acquisition module 310 is also used to acquire object complaint data for the target transaction object;

[0298] The acquisition module 310 is also used to acquire the second risk information corresponding to the image to be identified through the image recognition model if the object complaint data includes the image to be identified, wherein the second risk information is represented as a risk score or a risk probability distribution;

[0299] The determination module 330 is specifically used to determine the risk level label corresponding to the target trading object based on the first risk information and the second risk information.

[0300] In this application embodiment, a transaction object identification device is provided. When using the above device to determine the risk level label of a transaction object, not only is the transaction object description data used, but also the image to be identified in the object complaint data can be further used, that is, the risk level label is jointly predicted, which helps to improve the accuracy of identification.

[0301] Optionally, in the above Figure 17 Based on the corresponding embodiments, in another embodiment of the transaction object identification device 30 provided in this application,

[0302] The acquisition module 310 is specifically used to receive a transaction processing request sent by the terminal device, wherein the transaction processing request carries a transaction object identifier, and the transaction object identifier is used to indicate the target transaction object;

[0303] In response to a transaction processing request, obtain transaction object description data for the target transaction object;

[0304] The sending module 340 is also used to send a risk level label to the terminal device so that the terminal device can display a corresponding prompt message based on the risk level label.

[0305] In this embodiment of the application, a transaction object identification device is provided. Using the above device, the server can also identify the risk level label of the transaction object in real time and push it to the terminal device, and then the terminal device will make corresponding reminders. This makes it easier for the object to discover the risk situation of the transaction object in a timely manner, which can reduce the possibility of property loss to a certain extent.

[0306] The transaction processing apparatus in this application is described in detail below. Please refer to [link / reference]. Figure 18 , Figure 18 This is a schematic diagram of one embodiment of the transaction processing apparatus in this application. The transaction processing apparatus 40 includes:

[0307] Display module 410 is used to display the payment transaction interface, wherein the payment transaction interface provides a first payment control;

[0308] The response module 420 is used to respond to the selection instruction for the first payment control by sending a transaction processing request to the server, so that the server determines the risk level label corresponding to the target transaction object based on the transaction object identifier carried in the transaction processing request, wherein the transaction object identifier is used to indicate the target transaction object, and the risk level label is determined by the method described above.

[0309] The display module 410 is also used to display a payment failure message if the risk level label indicates that the target transaction object is an illegal transaction object.

[0310] In this embodiment of the application, a transaction object identification device is provided. Using the above device, the basic data of the transaction object is characterized with the transaction object as the center, and the transaction object and the transaction behavior of the object are used as the link to characterize the related object data. The risk identification result of the transaction object is determined by combining the basic data of the transaction object and the related object data. Thus, based on the transaction object description data, the risk situation of the transaction object can be assessed more comprehensively and objectively. On the one hand, it reduces the possibility of false interception, and on the other hand, it can improve the reliability of the transaction and reduce the possibility of loss of the object's property.

[0311] Optionally, in the above Figure 18 Based on the corresponding embodiments, in another embodiment of the transaction processing apparatus 40 provided in this application,

[0312] The display module 410 is also used to display at least one of the details viewing control and the information reporting control;

[0313] The display module 410 is also used to display abnormal transaction information related to the target transaction object if a selection instruction for the details viewing control is received;

[0314] The display module 410 is also configured to display an information reporting interface in response to a selection instruction for the information reporting control, wherein the information reporting interface provides an object information input area.

[0315] In this embodiment of the application, a transaction object identification device is provided. Using the above device, after the object confirms payment, if the server determines that the risk level label of the target transaction object is "high malicious", it will not only intercept the transaction and remind the transaction risk, but also provide further abnormal transaction information according to the object's choice, or allow the object to report the information of the transaction, so as to verify the reliability of the transaction through manual review, thereby improving the flexibility of the solution.

[0316] Optionally, in the above Figure 18Based on the corresponding embodiments, in another embodiment of the transaction processing apparatus 40 provided in this application, the transaction processing apparatus 40 further includes a generation module 430;

[0317] The display module 410 is also used to display a risk warning message for the transaction object and a second payment control if the risk level label indicates that the target transaction object is a pending illegal transaction object and no payment amount information has been entered.

[0318] The display module 410 is also used to display the password input area in response to a selection instruction for the second payment control;

[0319] or,

[0320] The display module 410 is also used to display a risk warning message for the transaction object and a third payment control if the risk level label indicates that the target transaction object is a pending illegal transaction object and payment amount information has been entered.

[0321] The generation module 430 is used to generate an order payment request in response to a selection instruction for the third payment control.

[0322] This application provides a transaction object identification device. Using this device, after the object confirms payment, if the server determines that the target transaction object's risk level label is "mildly malicious," it will remind the object whether to continue payment or abandon payment before actually deducting the funds, thereby improving transaction reliability. Furthermore, designing tiered intervention for transaction objects with different risk level labels not only achieves the goal of timely blocking malicious transaction objects but also avoids a "one-size-fits-all" approach to banning transaction objects, thus effectively preventing serious customer complaints caused by mistaken attacks to a certain extent.

[0323] Optionally, in the above Figure 18 Based on the corresponding embodiments, in another embodiment of the transaction processing apparatus 40 provided in this application,

[0324] The display module 410 is also used to display a transaction object reporting control if the risk level label indicates that the target transaction object is a pending illegal transaction object and the order payment has been completed;

[0325] The display module 410 is also used to respond to the selection instruction for the transaction object reporting control and display the order reporting interface, wherein the order reporting interface provides at least one of the following: transaction object name input area, transaction object nature input area, transaction object account input area, and report content input area.

[0326] In this embodiment of the application, a transaction object identification device is provided. Using the above device, after the actual payment is successful, the object can also file a complaint or report on the successful payment order, which can achieve the purpose of "public supervision" and help to uncover more illegal transaction objects, thereby maintaining a good transaction environment.

[0327] The transaction object identification device provided in this application can be deployed on a server. For clarity, please refer to [link to relevant documentation]. Figure 19 , Figure 19 This is a schematic diagram of a server structure provided in an embodiment of this application. The server 500 can vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 522 (e.g., one or more processors) and memory 532, and one or more storage media 530 (e.g., one or more mass storage devices) for storing application programs 542 or data 544. The memory 532 and storage media 530 can be temporary or persistent storage. The program stored in the storage media 530 may include one or more modules (not shown in the diagram), each module may include a series of instruction operations on the server. Furthermore, the CPU 522 may be configured to communicate with the storage media 530 and execute the series of instruction operations in the storage media 530 on the server 500.

[0328] Server 500 may also include one or more power supplies 526, one or more wired or wireless network interfaces 550, one or more input / output interfaces 558, and / or one or more operating systems 541, such as Windows Server. TM Mac OS X TM Unix TM Linux TM FreeBSD TM etc.

[0329] The steps performed by the server in the above embodiments can be based on this Figure 19 The server structure shown.

[0330] The transaction processing apparatus provided in this application can be deployed on terminal devices. For clarity, please refer to [link to relevant documentation]. Figure 20For ease of explanation, only the parts relevant to the embodiments of this application are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of this application. The terminal device can be any terminal device including mobile phones, tablets, personal digital assistants (PDAs), point-of-sale (POS) terminals, in-vehicle computers, etc. Taking a mobile phone as an example:

[0331] Figure 20 This diagram illustrates a partial structural representation of a mobile phone related to the terminal device provided in this embodiment. (Reference) Figure 20 The mobile phone includes components such as a radio frequency (RF) circuit 610, a memory 620, an input unit 630, a display unit 640, a sensor 650, an audio circuit 660, a wireless fidelity (WiFi) module 670, a processor 680, and a power supply 690. Those skilled in the art will understand that... Figure 20 The mobile phone structure shown does not constitute a limitation on the mobile phone and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0332] The following is combined with Figure 20 A detailed introduction to each component of a mobile phone:

[0333] RF circuit 610 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and processes it with processor 680; additionally, it transmits uplink data to the base station. Typically, RF circuit 610 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier (LNA), a duplexer, etc. Furthermore, RF circuit 610 can also communicate wirelessly with networks and other devices. The aforementioned wireless communication can use any communication standard or protocol, including but not limited to Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

[0334] The memory 620 can be used to store software programs and modules. The processor 680 executes various functions and data processing of the mobile phone by running the software programs and modules stored in the memory 620. The memory 620 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 620 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0335] The input unit 630 can be used to receive input numerical or character information, and to generate key signal inputs related to user settings and function control of the mobile phone. Specifically, the input unit 630 may include a touch panel 631 and other input devices 632. The touch panel 631, also known as a touch screen, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel 631), and drive the corresponding connection devices according to a pre-set program. Optionally, the touch panel 631 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, sends it to the processor 680, and can receive and execute commands sent by the processor 680. In addition, the touch panel 631 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 631, the input unit 630 may also include other input devices 632. Specifically, other input devices 632 may include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0336] The display unit 640 can be used to display information input by the user or information provided to the user, as well as various menus of the mobile phone. The display unit 640 may include a display panel 641, which may optionally be configured as a liquid crystal display (LCD), organic light-emitting diode (OLED), or similar display. Furthermore, a touch panel 631 may cover the display panel 641. When the touch panel 631 detects a touch operation on or near it, it transmits the information to the processor 680 to determine the type of touch event. Subsequently, the processor 680 provides corresponding visual output on the display panel 641 based on the type of touch event. Although in Figure 20 In this embodiment, the touch panel 631 and the display panel 641 are two separate components to realize the input and output functions of the mobile phone. However, in some embodiments, the touch panel 631 and the display panel 641 can be integrated to realize the input and output functions of the mobile phone.

[0337] The mobile phone may also include at least one sensor 650, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 641 according to the ambient light level, and the proximity sensor can turn off the display panel 641 and / or backlight when the phone is moved to the ear. As a type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity, and can be used for applications that recognize the phone's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition-related functions (such as pedometer, taps), etc. Other sensors that may be configured in the mobile phone, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0338] Audio circuit 660, speaker 661, and microphone 662 provide an audio interface between the user and the mobile phone. Audio circuit 660 converts received audio data into electrical signals and transmits them to speaker 661, where speaker 661 converts them into sound signals for output. On the other hand, microphone 662 converts collected sound signals into electrical signals, which are received by audio circuit 660, converted into audio data, and then output to processor 680 for processing. The audio data is then transmitted via RF circuit 610 to, for example, another mobile phone, or output to memory 620 for further processing.

[0339] WiFi is a short-range wireless transmission technology. Through the WiFi module 670, mobile phones can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 20The WiFi module 670 is shown, but it is understood that it is not an essential component of a mobile phone and can be omitted as needed without changing the essence of the invention.

[0340] The processor 680 is the control center of the mobile phone, connecting various parts of the phone through various interfaces and lines. It performs various functions and processes data by running or executing software programs and / or modules stored in the memory 620, and by calling data stored in the memory 620. Optionally, the processor 680 may include one or more processing units; optionally, the processor 680 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the aforementioned modem processor may also not be integrated into the processor 680.

[0341] The mobile phone also includes a power supply 690 (such as a battery) that supplies power to various components. Optionally, the power supply can be logically connected to the processor 680 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0342] Although not shown, mobile phones may also include a camera, Bluetooth module, etc., which will not be described in detail here.

[0343] The steps performed by the terminal device in the above embodiments can be based on this Figure 20 The terminal device structure is shown.

[0344] This application also provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the methods described in the foregoing embodiments.

[0345] This application also provides a computer program product including a program, which, when run on a computer, causes the computer to perform the methods described in the foregoing embodiments.

[0346] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0347] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0348] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0349] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0350] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0351] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for identifying transaction objects, characterized in that, include: Obtaining transaction object description data for the target transaction object specifically includes: obtaining description data, which includes at least one of application description data, public account description data, object description data, and external link description data; obtaining basic transaction object data for the target transaction object based on the description data; and obtaining associated object data for the target transaction object based on the description data. The application description data includes descriptions of the applications used by visitors and those making payments to the target transaction object; the public account description data includes descriptions of the public accounts used by visitors and those making payments to the target transaction object; the object description data includes descriptions of the traffic-driving personnel who guide the object to make illegal consumption; the external link description data includes descriptions of the external links used by visitors and those making payments to the target transaction object; the transaction object description data includes basic data of the transaction object and related object data, wherein the basic data of the transaction object represents data related to the target transaction object, the related object data represents data related to related objects, and the related objects represent objects that have a transaction relationship with the target transaction object; The transaction object description data includes the basic data of the transaction object, which is then processed to obtain transaction object description features. In addition, the associated object data included in the transaction object description data is processed to obtain associated object features. Based on the description features of the transaction object and the features of the associated object, the first risk information corresponding to the target transaction object is obtained through the transaction object identification model, wherein the first risk information is represented as a risk score or a risk probability distribution; The risk level label corresponding to the target transaction object is determined based on the first risk information.

2. The method according to claim 1, characterized in that, The basic data of the transaction object includes at least one of the following: transaction object level, capital inflow data, capital outflow data, active time, order amount, historical complaint rate, repurchase rate, number of successful orders, and number of failed orders; The associated object data includes at least one of the following: the account level of the associated object, the first proportion of illegal objects in the associated objects, the second proportion of reported objects in the associated objects, the third proportion of underage objects in the associated objects, and the fourth proportion of objects with historical damage in the associated objects.

3. The method according to claim 2, characterized in that, The step of performing feature processing on the basic data of the transaction object included in the transaction object description data to obtain transaction object description features includes: If the basic data of the transaction object includes the transaction object level, then the transaction object level is subjected to one-hot encoding to obtain the transaction object level feature, wherein the transaction object level feature is included in the transaction object description feature; If the basic data of the transaction object includes the investment data, the investment data, the order success rate, and the order failure rate, then feature scaling processing is performed on the investment data, the investment data, the order success rate, and the order failure rate to obtain investment data features, investment data features, order success rate features, and order failure rate features, wherein the investment data features, the investment data features, the order success rate features, and the order failure rate features are included in the transaction object description features; If the basic data of the transaction object includes the order amount, then the order amount is subjected to feature binning to obtain the order amount feature, wherein the order amount feature is included in the transaction object description feature; If the basic data of the transaction object includes the active time, the historical complaint ratio, and the repurchase ratio, then the active time, the historical complaint ratio, and the repurchase ratio are numerically processed to obtain the active time feature, the historical complaint ratio feature, and the repurchase ratio feature, wherein the active time feature, the historical complaint ratio feature, and the repurchase ratio feature are included in the transaction object description features. The step of performing feature processing on the associated object data included in the transaction object description data to obtain associated object features includes: If the associated object data includes the account level of the associated object, then the account level of the associated object is subjected to one-hot encoding to obtain the account level feature and the quantity type feature, wherein the account level feature and the quantity type feature are included in the associated object feature; If the associated object data includes the first proportion, the second proportion, the third proportion, and the fourth proportion, then the first proportion, the second proportion, the third proportion, and the fourth proportion are numerically processed to obtain the illegal object proportion feature, the reported object proportion feature, the underage object proportion feature, and the historically damaged object proportion feature, wherein the illegal object proportion feature, the reported object proportion feature, the underage object proportion feature, and the historically damaged object proportion feature are included in the associated object features.

4. The method according to claim 1, characterized in that, The step of obtaining the first risk information corresponding to the target transaction object through a transaction object identification model based on the transaction object description features and the associated object features includes: Based on the description features of the transaction object and the features of the associated object, the risk score corresponding to the target transaction object is obtained through the transaction object identification model; The step of determining the risk level label corresponding to the target transaction object based on the first risk information includes: If the risk score is greater than or equal to 0 and less than the first threshold, then the risk level label corresponding to the target transaction object is determined to be the first risk label; If the risk score is greater than or equal to the first threshold and less than the second threshold, then the risk level label corresponding to the target transaction object is determined to be the second risk label, wherein the degree of malice of the second risk label is higher than the degree of malice of the first risk label.

5. The method according to claim 1, characterized in that, The step of obtaining the first risk information corresponding to the target transaction object through a transaction object identification model based on the transaction object description features and the associated object features includes: Based on the description features of the transaction object and the features of the associated object, the risk probability distribution corresponding to the target transaction object is obtained through the transaction object identification model. The risk probability distribution includes K probability values, each probability value corresponds to a risk label, and K is an integer greater than or equal to 2. The step of determining the risk level label corresponding to the target transaction object based on the first risk information includes: Based on the risk probability distribution, determine the risk label corresponding to the maximum probability value from the K probability values; The risk label corresponding to the maximum probability value is determined as the risk level label.

6. The method according to claim 1, characterized in that, The method further includes: If the risk level label indicates that the target transaction object is a pending illegal transaction object, then obtain the object complaint data for the target transaction object; If the object complaint data includes an image to be identified, then the second risk information corresponding to the image to be identified is obtained through an image recognition model, and the target risk level label corresponding to the target transaction object is determined based on the second risk information, wherein the second risk information is represented as a risk score or a risk probability distribution; If the object complaint data does not include the image to be identified, then pending review data for the target transaction object is sent to the terminal device, wherein the pending review data includes at least one of the target transaction object's order information, fund information, and object behavior information.

7. The method according to claim 1, characterized in that, The method further includes: Obtain object complaint data for the target transaction object; If the object complaint data includes an image to be identified, then the second risk information corresponding to the image to be identified is obtained through an image recognition model, wherein the second risk information is represented as a risk score or a risk probability distribution; The step of determining the risk level label corresponding to the target transaction object based on the first risk information includes: Based on the first risk information and the second risk information, the risk level label corresponding to the target trading object is determined.

8. The method according to any one of claims 1 to 7, characterized in that, The acquisition of transaction object description data for the target transaction object includes: The system receives a transaction processing request sent by a terminal device, wherein the transaction processing request carries a transaction object identifier, and the transaction object identifier is used to indicate the target transaction object; In response to the transaction processing request, obtain the transaction object description data for the target transaction object; The method further includes: The risk level label is sent to the terminal device so that the terminal device displays a corresponding prompt message based on the risk level label.

9. A method for transaction processing, characterized in that, include: Display a payment transaction interface, wherein the payment transaction interface provides a first payment control; In response to the selection instruction for the first payment control, a transaction processing request is sent to the server so that the server determines the risk level label corresponding to the target transaction object based on the transaction object identifier carried in the transaction processing request, wherein the transaction object identifier is used to indicate the target transaction object, and the risk level label is determined by any one of the methods in claims 1 to 8; If the risk level label indicates that the target transaction object is an illegal transaction object, a payment failure message will be displayed.

10. The method according to claim 9, characterized in that, The method further includes: At least one of the following: display details view control and information reporting control; If a selection instruction is received for the details viewing control, abnormal transaction information related to the target transaction object is displayed; If a selection instruction is received for the information reporting control, an information reporting interface is displayed, wherein the information reporting interface provides an object information input area.

11. The method according to claim 9, characterized in that, The method further includes: If the risk level label indicates that the target transaction object is a pending illegal transaction object, and no payment amount information has been entered, then a transaction object risk warning message and a second payment control will be displayed; In response to a selection command for the second payment control, the password input area is displayed; Alternatively, the method may further include: If the risk level label indicates that the target transaction object is a pending illegal transaction object, and payment amount information has been entered, then a transaction object risk warning message and a third payment control will be displayed; In response to the selection instruction for the third payment control, an order payment request is generated.

12. A transaction object identification device, characterized in that, include: The acquisition module is used to acquire transaction object description data for a target transaction object, specifically including: acquiring description data, which includes at least one of application description data, public account description data, object description data, and external link description data; acquiring basic transaction object data for the target transaction object based on the description data; acquiring associated object data for the target transaction object based on the description data, wherein the application description data includes descriptions related to the application used by visitors and order payments to the target transaction object; the public account description data includes descriptions related to the public account used by visitors and order payments to the target transaction object; the object description data includes descriptions related to traffic drivers who guide objects to make illegal consumption; the external link description data includes descriptions related to external links used by visitors and order payments to the target transaction object; the transaction object description data includes the basic transaction object data and the associated object data, whereby the basic transaction object data represents data related to the target transaction object, the associated object data represents data related to associated objects, and the associated objects represent objects that have a transaction relationship with the target transaction object; The processing module is used to perform feature processing on the basic data of the transaction object included in the transaction object description data to obtain transaction object description features, and to perform feature processing on the associated object data included in the transaction object description data to obtain associated object features. The acquisition module is further configured to acquire first risk information corresponding to the target transaction object based on the transaction object description features and the associated object features through a transaction object identification model, wherein the first risk information is represented as a risk score or a risk probability distribution; The determination module is used to determine the risk level label corresponding to the target transaction object based on the first risk information.

13. The apparatus according to claim 12, characterized in that, The basic data of the transaction object includes at least one of the following: transaction object level, capital inflow data, capital outflow data, active time, order amount, historical complaint rate, repurchase rate, number of successful orders, and number of failed orders; The associated object data includes at least one of the following: the account level of the associated object, the first proportion of illegal objects in the associated objects, the second proportion of reported objects in the associated objects, the third proportion of underage objects in the associated objects, and the fourth proportion of objects with historical damage in the associated objects.

14. The apparatus according to claim 13, characterized in that, The processing module is specifically used for: If the basic data of the transaction object includes the transaction object level, then the transaction object level is subjected to one-hot encoding to obtain the transaction object level feature, wherein the transaction object level feature is included in the transaction object description feature; If the basic data of the transaction object includes the investment data, the investment data, the order success rate, and the order failure rate, then feature scaling processing is performed on the investment data, the investment data, the order success rate, and the order failure rate to obtain investment data features, investment data features, order success rate features, and order failure rate features, wherein the investment data features, the investment data features, the order success rate features, and the order failure rate features are included in the transaction object description features; If the basic data of the transaction object includes the order amount, then the order amount is subjected to feature binning to obtain the order amount feature, wherein the order amount feature is included in the transaction object description feature; If the basic data of the transaction object includes the active time, the historical complaint ratio, and the repurchase ratio, then the active time, the historical complaint ratio, and the repurchase ratio are numerically processed to obtain the active time feature, the historical complaint ratio feature, and the repurchase ratio feature, wherein the active time feature, the historical complaint ratio feature, and the repurchase ratio feature are included in the transaction object description features. The processing module is specifically used for: If the associated object data includes the account level of the associated object, then the account level of the associated object is subjected to one-hot encoding to obtain the account level feature and the quantity type feature, wherein the account level feature and the quantity type feature are included in the associated object feature; If the associated object data includes the first proportion, the second proportion, the third proportion, and the fourth proportion, then the first proportion, the second proportion, the third proportion, and the fourth proportion are numerically processed to obtain the illegal object proportion feature, the reported object proportion feature, the underage object proportion feature, and the historically damaged object proportion feature, wherein the illegal object proportion feature, the reported object proportion feature, the underage object proportion feature, and the historically damaged object proportion feature are included in the associated object features.

15. The apparatus according to claim 12, characterized in that, The acquisition module is specifically used for: Based on the description features of the transaction object and the features of the associated object, the risk score corresponding to the target transaction object is obtained through the transaction object identification model; The determining module is specifically used for: If the risk score is greater than or equal to 0 and less than the first threshold, then the risk level label corresponding to the target transaction object is determined to be the first risk label; If the risk score is greater than or equal to the first threshold and less than the second threshold, then the risk level label corresponding to the target transaction object is determined to be the second risk label, wherein the degree of malice of the second risk label is higher than the degree of malice of the first risk label.

16. The apparatus according to claim 12, characterized in that, The acquisition module is specifically used for: Based on the description features of the transaction object and the features of the associated object, the risk probability distribution corresponding to the target transaction object is obtained through the transaction object identification model. The risk probability distribution includes K probability values, each probability value corresponds to a risk label, and K is an integer greater than or equal to 2. The determining module is specifically used for: Based on the risk probability distribution, determine the risk label corresponding to the maximum probability value from the K probability values; The risk label corresponding to the maximum probability value is determined as the risk level label.

17. The apparatus according to claim 12, characterized in that, The device further includes: a transmitting module; The acquisition module is further configured to acquire object complaint data for the target transaction object if the risk level label indicates that the target transaction object is a pending illegal transaction object; The acquisition module is further configured to, if the object complaint data includes an image to be identified, acquire the second risk information corresponding to the image to be identified through an image recognition model, and determine the target risk level label corresponding to the target transaction object based on the second risk information, wherein the second risk information is represented as a risk score or a risk probability distribution; The sending module is configured to send pending review data for the target transaction object to the terminal device if the object complaint data does not include the image to be identified. The pending review data includes at least one of the target transaction object's order information, fund information, and object behavior information.

18. The apparatus according to claim 12, characterized in that, The acquisition module is also used to acquire object complaint data for the target transaction object; The acquisition module is further configured to, if the object complaint data includes an image to be identified, acquire the second risk information corresponding to the image to be identified through an image recognition model, wherein the second risk information is represented as a risk score or a risk probability distribution; The determining module is specifically used for: Based on the first risk information and the second risk information, the risk level label corresponding to the target trading object is determined.

19. The apparatus according to any one of claims 12 to 18, characterized in that, The acquisition module is specifically configured to receive a transaction processing request sent by a terminal device, wherein the transaction processing request carries a transaction object identifier, wherein the transaction object identifier is used to indicate the target transaction object; and in response to the transaction processing request, acquire the transaction object description data for the target transaction object; The device further includes: The sending module is used to send the risk level label to the terminal device so that the terminal device displays a corresponding prompt message based on the risk level label.

20. A transaction processing apparatus, characterized in that, include: The display module is used to display the payment transaction interface, wherein the payment transaction interface provides a first payment control; A response module is configured to respond to a selection instruction for the first payment control by sending a transaction processing request to the server, so that the server determines the risk level label corresponding to the target transaction object based on the transaction object identifier carried in the transaction processing request, wherein the transaction object identifier is used to indicate the target transaction object, and the risk level label is determined by any one of the methods described in claims 1 to 8. The display module is also configured to display a payment failure message if the risk level label indicates that the target transaction object is an illegal transaction object.

21. The apparatus according to claim 20, characterized in that, The display module is also used for: At least one of the following: display details view control and information reporting control; If a selection instruction is received for the details viewing control, abnormal transaction information related to the target transaction object is displayed; If a selection instruction is received for the information reporting control, an information reporting interface is displayed, wherein the information reporting interface provides an object information input area.

22. The apparatus according to claim 20, characterized in that, The device further includes: a generation module; The display module is further configured to display a risk warning message for the transaction object and a second payment control if the risk level label indicates that the target transaction object is a pending illegal transaction object and no payment amount information has been entered. The display module is also used to display the password input area in response to a selection instruction for the second payment control; or, The display module is further configured to display a risk warning message and a third payment control if the risk level label indicates that the target transaction object is a pending illegal transaction object and payment amount information has been entered; The generation module is used to generate an order payment request in response to a selection instruction for the third payment control.

23. A computer device, characterized in that, include: Memory, processor, and bus system; The memory is used to store programs; The processor is configured to execute a program in the memory, and the processor is configured to execute the method of any one of claims 1 to 8 according to the instructions in the program code, or to execute the method of any one of claims 9 to 11; The bus system is used to connect the memory and the processor to enable communication between the memory and the processor.

24. A computer-readable storage medium comprising instructions, when executed on a computer, causing the computer to perform the method as claimed in any one of claims 1 to 8, or to perform the method as claimed in any one of claims 9 to 11.

25. A computer program product, characterized in that, The method 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 to cause the computer device to perform the method as claimed in any one of claims 1 to 8, or to perform the method as claimed in any one of claims 9 to 11.

Images