Data processing method and device, storage medium and electronic equipment

Abstract

The invention discloses a data processing method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining online transaction feature data of transaction service, carrying out the data item rule verification of the online transaction feature data, and obtaining a data item verification result, and performing transaction risk policy detection on the online transaction feature data to obtain a policy risk detection result, and performing risk data attribution processing on the policy risk detection result based on the data item verification result to obtain policy risk data attribution information.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a data processing method, device, storage medium and electronic device. Background Art

[0002] In recent years, computer technology has developed rapidly. The corresponding service platforms for transactions such as mobile payment transactions, express supermarket transactions, and financial transactions, while completing the processing of massive transaction service data, also involve risk strategy processing (referred to as risk control) of the data involved in the transaction services in combination with risk strategies. When the risk control strategy results are detected to be abnormal based on the risk strategy, it involves an abnormal analysis of the abnormal results of the risk control strategy to ensure the provision of high-quality transaction services to the outside world. Summary of the invention

[0003] This specification provides a data processing method, device, storage medium and electronic device, and the technical solution is as follows:

[0004] In a first aspect, this specification provides a data processing method, the method comprising:

[0005] Obtain online transaction feature data of transaction services;

[0006] Performing data item rule verification on the online transaction feature data to obtain a data item verification result, and performing transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result;

[0007] Based on the data item verification result, risk data attribution processing is performed on the strategy risk detection result to obtain strategy risk data attribution information.

[0008] In a second aspect, this specification provides a data processing device, the device comprising:

[0009] A data acquisition module is used to obtain online transaction feature data of transaction services;

[0010] A data verification module, used to perform data item rule verification on the online transaction feature data to obtain a data item verification result, and perform transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result;

[0011] The data attribution module is used to perform risk data attribution processing on the strategy risk detection result based on the data item verification result to obtain strategy risk data attribution information.

[0012] In a third aspect, the present specification provides a computer storage medium, wherein the computer storage medium stores at least one instruction, wherein the instruction is suitable for being loaded by a processor and executing the method steps of one or more embodiments of the present specification.

[0013] In a fourth aspect, the present specification provides a computer program product, wherein the computer program product stores at least one instruction, wherein the instruction is suitable for being loaded by a processor and executing the method steps of one or more embodiments of the present specification.

[0014] In a fifth aspect, the present specification provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps of one or more embodiments of the present specification.

[0015] The beneficial effects brought by the technical solutions provided by some embodiments of this specification include at least:

[0016] In one or more embodiments of the present specification, the service platform obtains online transaction characteristic data of the transaction service, performs data item rule verification on the online transaction characteristic data to obtain data item verification results, and performs transaction risk strategy detection on the online transaction characteristic data to obtain strategy risk detection results, and performs risk data attribution processing on the strategy risk detection results based on the data item verification results to obtain strategy risk data attribution information. Compared with the post-investigation method of risk strategy anomalies in related technologies, when an abnormality occurs in the strategy risk detection results, it is possible to quickly perform attribution analysis through the data item verification results that are parallel to the transaction risk strategy detection, and quickly locate the source of the risk, which not only reduces the time spent on investigation, but also improves the system's response speed and processing capabilities to transaction data anomalies, and effectively solves the monitoring problems of data anomalies and strategy issues in risk control strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in this specification or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a scenario diagram of a data processing system provided in this specification;

[0019] Figure 2 It is a flowchart of a data processing method provided in this specification;

[0020] Figure 3 It is a flowchart of another data processing method provided in this specification;

[0021] Figure 4 This is a flowchart of abnormal data attribution provided in this manual;

[0022] Figure 5 This specification provides a flow chart of a data processing method;

[0023] Figure 6 This is a flowchart of maintaining a data risk verification rule base provided in this specification;

[0024] Figure 7 It is a structural schematic diagram of a data processing device provided in this specification;

[0025] Figure 8 It is a structural diagram of a data attribution module provided in this specification;

[0026] Fig. 9 It is a structural schematic diagram of an electronic device provided in this manual. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in this specification to clearly and completely describe the technical solutions in this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0028] In the description of this specification, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In the description of this specification, it should be noted that, unless otherwise clearly specified and limited, "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices. For those of ordinary skill in the art, the specific meanings of the above terms in this specification can be understood in specific circumstances. In addition, in the description of this specification, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are an "or" relationship.

[0029] In related technologies, with the rapid development of transaction services such as mobile payment transactions, express supermarket transactions, and financial transactions, the number of risk strategies configured on the service platform to prevent transaction service risks is also increasing. The original monitoring based on risk strategy detection results often only alerts when the strategy results are abnormal. Only at this time will the abnormality of the risk strategy detection results begin to be checked and analyzed for massive transaction data. This method of checking and analyzing transaction data after the risk detection results are abnormal often takes a long time to check, and it is impossible to quickly determine when problems involving the transaction data itself are involved, because a risk strategy often has hundreds or thousands of data items, and it is very cumbersome to judge the data, especially when there are sudden problems online, the troubleshooting requires faster. Based on this, in related technologies, the post-data investigation and analysis method based on abnormal risk detection results has the limitations of being time-consuming, inefficient, and unable to respond quickly.

[0030] The present specification is described in detail below with reference to specific embodiments.

[0031] See also Figure 1 , is a schematic diagram of a data processing system scenario provided in this specification. Figure 1 As shown, the data processing system may include at least a client cluster and a service platform 100 .

[0032] The client cluster may include at least one client, such as Figure 1 As shown, it specifically includes client 1 corresponding to user 1, client 2 corresponding to user 2, ..., client n corresponding to user n, where n is an integer greater than 0.

[0033] Each client in the client cluster may be an electronic device with communication function, including but not limited to: wearable device, handheld device, personal computer, tablet computer, vehicle-mounted device, smart phone, computing device or other processing device connected to a wireless modem, etc. Electronic devices may be called different names in different networks, such as: user equipment, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, cellular phone, cordless phone, personal digital assistant (PDA), electronic device in 5G network or future evolution network, etc.

[0034] The service platform 100 can be a separate server device, such as a rack-mounted, blade, tower, or cabinet-mounted server device, or a workstation, mainframe computer, or other hardware device with strong computing power; it can also be a server cluster composed of multiple servers, and the servers in the service cluster can be composed in a symmetrical manner, wherein each server has equivalent functions and status in the transaction link, and each server can provide services to the outside independently, and the independent service can be understood as not requiring the assistance of other servers.

[0035] In one or more embodiments of the present specification, the service platform 100 may establish a communication connection with at least one client in the client cluster, and complete data interaction in the data processing process based on the communication connection, such as online transaction data interaction. For example, the service platform 100 may perform data processing based on the data processing method of the present specification, for example, obtaining online transaction feature data of a transaction service, performing data item rule verification on the online transaction feature data to obtain a data item verification result, performing transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result, and performing risk data attribution processing on the strategy risk detection result based on the data item verification result to obtain strategy risk data attribution information.

[0036] It should be noted that the service platform 100 and at least one client in the client cluster establish a communication connection through a network for interactive communication, wherein the network can be a wireless network or a wired network, the wireless network includes but is not limited to a cellular network, a wireless local area network, an infrared network or a Bluetooth network, and the wired network includes but is not limited to Ethernet, a universal serial bus (USB) or a controller local area network. In one or more embodiments of the specification, technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. are used to represent data (such as a target compressed package) exchanged through a network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec), etc. can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above data communication technologies.

[0037] The data processing system embodiments provided in this specification and the data processing methods in one or more embodiments belong to the same concept. The execution subject corresponding to the data processing method involved in one or more embodiments of the specification can be the above-mentioned service platform 100; the execution subject corresponding to the data processing method involved in one or more embodiments of the specification can also be the electronic device corresponding to the client, which is determined based on the actual application environment. The implementation process of the data processing system embodiment can be found in the following method embodiment, which will not be repeated here.

[0038] based on Figure 1 The scene diagram is shown, and the data processing method provided by one or more embodiments of this specification is introduced in detail below.

[0039] See also Figure 2 , is a flow chart of a data processing method for one or more embodiments of this specification, which can be implemented by a computer program and can be run on a data processing device based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application. The data processing device can be a service platform.

[0040] Specifically, the data processing method includes:

[0041] S102: Acquire online transaction feature data of transaction services;

[0042] In this specification, transaction services may include mobile payment transactions, express supermarket transactions, financial service transactions, etc. Online transaction feature data is the data object for data processing in this specification. The service platform may collect online transaction feature data in the transaction service process. The online transaction feature data comes from the data collection of the transaction service. The type of transaction feature data is not limited in this specification.

[0043] For example, taking insurance affairs as an example, the service platform can provide insurance affairs to the outside world. Users of one or more clients can perform related insurance operations based on the insurance affairs provided by the service platform, such as selecting a certain type of insurance, initiating an insurance claim, etc. The service platform can collect online insurance affairs characteristic data related to insurance affairs with the authorization of the user or full authorization of all parties, such as historical claims records, insurance time, accident time, insurance period, user information and other online insurance affairs characteristic data.

[0044] For example, taking transaction services as consumer finance transactions, the service platform can provide consumer finance transactions to the outside world. Users of one or more clients can perform related consumer finance operations based on the consumer finance transactions provided by the service platform, such as selecting a certain type of insurance, initiating an insurance claim, etc. The service platform can collect consumer finance data related to consumer finance transactions with the authorization of the user or full authorization of all parties, such as consumer finance records, transaction item time, consumer finance flow, balance data and other consumer finance transaction data.

[0045] Optionally, the online transaction feature data may be in the form of transaction data (table). The online transaction feature data (table) is a database table model consisting of a plurality of data item fields, and may also be understood as a wide table model, which is a database table that associates transaction service-related indicators, user characteristics, transaction attributes, etc.; it may be understood that the online transaction feature data is composed of multiple data item characteristics.

[0046] S104: performing data item rule verification on the online transaction feature data to obtain a data item verification result, and performing transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result;

[0047] In one or more embodiments of the present specification, the steps of “performing data item rule verification on the online transaction feature data to obtain a data item verification result” and “performing transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result” are performed online in parallel;

[0048] Exemplarily, data risk verification rules are pre-set for one or more data items of online transaction feature data, and online transaction feature data are verified item by item based on the pre-defined data risk verification rules, such as data value range rules, field null value rules, enumeration distribution rules, etc. During the verification process, data item verification results corresponding to the data risk verification rules are generated for each data item. The data item verification results may include which data items are normal and which data items are abnormal, so that whether each data item of the transaction data itself is abnormal can be located in real time and quickly;

[0049] Optionally, the data item verification result includes abnormal data items in abnormal form and their abnormal types (such as a value exceeding a range, a field being empty, inconsistent enumeration distribution, etc.) and the verification status of normal data items in normal form.

[0050] Optionally, data risk inspection rules include but are not limited to data value range rules, value 0 rules, field null value rules, field enumeration rules, field length constraint rules, field enumeration distribution rules, data mean, value stability rules, etc.;

[0051] For example, the numerical value range rule indicates the value range of the numerical field. If the data item within the value range is no longer indicated, it can be considered that there is an abnormal numerical value range data item. For example, the normal value range of the interest rate of a certain financial transaction loan item is 15,000 to 60,000.

[0052] For example, the value 0 rule indicates whether the value field can be empty, 0, or non-0. Assuming that a certain value data item indicates that it can only be empty or 0, if a certain value data item is non-0, it is considered that the value 0 rule data item is abnormal;

[0053] For example, field null value rule: indicates the distribution of null values ​​and non-null values ​​of each field in the data feature table. For example, field enumeration rule: indicates the value range of the enumerable field (state or attribute field);

[0054] For example, the field length constraint rule: indicates the length range of the field value;

[0055] For example, field enumeration distribution rules: characterize the values ​​of enumeration fields and the distribution of each value;

[0056] For example, the data mean rule: represents the range of the field mean value;

[0057] For example, the numerical stability rule: the PSI (Population Stability Index) fluctuation range of the characterization field;

[0058] Exemplarily, in combination with a preconfigured risk strategy, risk detection is performed on online transaction feature data to determine whether the online transaction feature data complies with the risk control strategy, so as to complete transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result;

[0059] If the strategy risk detection result indicates an abnormal result, there is no need to check the data problem of the online transaction feature data itself from the beginning. Instead, the risk data attribution processing can be directly performed on the current abnormal strategy risk detection result in combination with the data item verification result, so as to quickly locate the cause of the abnormality in the risk strategy without the need for subsequent data investigation and analysis. This is time-saving, efficient and can achieve rapid response.

[0060] Optionally, a risk strategy often has hundreds or thousands of data items, and the inspection rate of each data item of online transaction feature data is faster than the risk strategy detection. When the verification results of one or more verification data items indicate abnormalities and these verification data items are key data items of a target risk strategy, an early warning of abnormal strategy risk detection results can be issued to a target risk strategy, that is, risk data attribution processing is performed on the strategy risk detection results directly based on the data item verification results to obtain strategy risk data attribution information. At this time, the strategy risk detection process for abnormal strategy risk detection results is often not completed, thereby achieving rapid risk abnormality warning and zero-delay risk attribution for strategy risk detection results.

[0061] S106: Perform risk data attribution processing on the strategy risk detection result based on the data item verification result to obtain strategy risk data attribution information.

[0062] Exemplarily, based on the data item verification results in the previous step, the strategy risk detection results are analyzed for attribution. That is, if the risk control strategy detects an anomaly, the data item verification results can be analyzed first to determine whether the strategy risk anomaly is caused by a problem with the data itself, improper strategy configuration, or other reasons. Through this strategy risk attribution processing, the system can quickly combine the parallel data item verification results to quickly lock the source of the strategy risk and generate strategy risk data attribution information.

[0063] In a feasible implementation, the strategic risk attribution analysis process first determines the correspondence between each characteristic data item in the transaction service and the strategic risk detection rule. For example, whether an abnormal data item (such as a payment amount exceeding the range) directly affects the judgment of strategic risk detection (such as high risk);

[0064] Abnormal data items are then screened out based on the data item verification results, and abnormal policy rules are determined in the policy risk detection results. For example, if a payment risk policy is detected based on payment amount, account status and transaction time, then the anomalies triggered by these policies can be matched with the abnormal data items screened out in the previous step.

[0065] Furthermore, for each abnormal policy rule that triggers a policy risk anomaly, check whether the characteristic data item (that is, the policy trigger point) that the abnormal policy rule depends on is marked as abnormal in the data item verification result (marked as abnormal can be regarded as a match with the trigger point). If the data item anomaly matches the policy trigger point, it can be attributed to the risk caused by the data problem of the abnormal data item. If the data item is marked as normal in the data item verification result, but the policy trigger point still shows an abnormality, it can be determined that there is a problem in the policy rule design and analyze the abnormal risk policy configuration. These policy risk attribution analysis processes will form "policy risk data attribution information". "Policy risk data attribution information" includes but is not limited to: which data items cause the policy detection results to be abnormal, the specific reasons for the risk data attribution (data problems or policy problems), and subsequent suggestions (such as adjusting the data source, redesigning the policy rules, etc.).

[0066] In one or more embodiments of the present specification, the service platform obtains online transaction characteristic data of the transaction service, performs data item rule verification on the online transaction characteristic data to obtain data item verification results, and performs transaction risk strategy detection on the online transaction characteristic data to obtain strategy risk detection results, and performs risk data attribution processing on the strategy risk detection results based on the data item verification results to obtain strategy risk data attribution information. Compared with the post-investigation method of risk strategy anomalies in related technologies, when an abnormality occurs in the strategy risk detection results, it is possible to quickly perform attribution analysis through the data item verification results that are parallel to the transaction risk strategy detection, and quickly locate the source of the risk, which not only reduces the time spent on investigation, but also improves the system's response speed and processing capabilities to transaction data anomalies, and effectively solves the monitoring problems of data anomalies and strategy issues in risk control strategies.

[0067] See also Figure 3 , Figure 3 This is a flowchart of a data processing method proposed in one or more embodiments of this specification. Specifically:

[0068] S202: Acquire online transaction feature data of the transaction service;

[0069] For details, please refer to the method steps in other embodiments of this specification, which will not be repeated here.

[0070] S204: performing data item rule verification on the online transaction feature data to obtain a data item verification result, and performing transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result;

[0071] For details, please refer to the method steps in other embodiments of this specification, which will not be repeated here.

[0072] S206: Detecting the strategy detection type of the strategy risk detection result;

[0073] After the service platform determines the policy risk detection result, it first needs to determine which policy detection type the policy risk detection result belongs to. Policy detection types can generally be divided into "policy normal type" and "policy abnormal type".

[0074] For example, when the service platform performs policy risk detection on transaction data through a risk decision mechanism, the detection results can be marked as different types according to pre-set risk levels or rule judgment criteria. The distinction of detection types is mainly to clarify whether the policy detection results have potential risks.

[0075] “Policy Normal Type”: indicates that the transaction data complies with the expected service risk control policy rules and no abnormalities are found.

[0076] "Policy anomaly type": indicates that the transaction data does not conform to the expected service risk control policy rules, and the service risk control policy rules detect possible risks or anomalies in the (online) transaction feature data;

[0077] S208: If the policy detection type is a policy abnormality type, abnormal data attribution processing is performed on the policy risk detection result based on the data item verification result to obtain policy risk data attribution information corresponding to the abnormal risk policy result.

[0078] In S206, the detected policy detection type is "policy abnormal type", that is, the transaction data has triggered the policy risk detection rule. Then, the policy risk detection result can be processed for abnormal data attribution based on the data item verification result to obtain the policy risk data attribution information corresponding to the abnormal risk policy result. By analyzing the association between the data item and the policy rule, the root cause of the abnormal policy result is determined. The system can identify whether it is a problem with the data itself or the policy rule configuration;

[0079] In a feasible implementation manner, if the policy detection type is a normal policy type, the policy risk detection result is recorded to facilitate subsequent data analysis and system auditing.

[0080] For example, the system can record the normal results of each policy test in the database or log system, including: the transaction feature data of the current test, relevant information of the policy test (such as the rule ID, version, test time, etc.), and the verification results of the associated data items (that is, whether all data items in the test process have passed the verification).

[0081] Optionally, the policy risk detection results are fed back to the system policy engine, which controls the system policy engine to continuously adjust and optimize the policy risk detection rules through a machine learning model. By recording the policy risk detection results, the machine learning model can accumulate a large amount of data, and combine the data item verification results with the policy risk detection results to train the system policy engine, predict possible future risks, and further optimize the current policy risk detection rules through the system policy engine.

[0082] The system strategy engine helps the system to improve itself. Through automatic learning, it can gradually reduce the frequency of strategy anomalies and improve the system's risk prediction capabilities.

[0083] In one or more embodiments of this specification, the above method is used to further refine the risk detection process, and the type of strategy detection results can be first determined to distinguish between normal and abnormal strategy detection results. If the detection type is an abnormal type, abnormal data attribution processing will be immediately performed based on the data item verification results to quickly generate corresponding attribution information. This processing method not only improves the response speed to abnormal strategies, but also improves the accuracy of locating and attributing abnormal risk strategies, ensuring that problems can be quickly and accurately identified and processed, thereby further enhancing the stability and efficiency of the system.

[0084] Please refer to Figure 4 , Figure 4 It is a flowchart of abnormal data attribution, performing abnormal data attribution processing on the strategy risk detection result based on the data item verification result, and obtaining strategy risk data attribution information corresponding to the abnormal risk strategy result, which can refer to the following implementation method:

[0085] S302: Determine abnormal data item inspection information from the data item inspection result;

[0086] The data item verification results usually include the verification status of all data items (such as passed or failed), and each data item is verified in advance based on whether it complies with the rules (such as value range, field null value, etc.).

[0087] All abnormal data item verification information is extracted from the verification results. The abnormal data item verification information includes data items that do not conform to the expected rules and data item abnormal types (such as exceeding the value range, fields being empty, etc.). The abnormal data item verification information can serve as the basis for subsequent analysis. Through the abnormal data item verification information, the system focuses on the data part of the potential problem, providing data support for subsequent attribution processing and risk assessment.

[0088] S304: Determine abnormal data items for abnormal risk policy results from the abnormal data item verification information based on the policy risk detection result, and generate policy risk data attribution information based on the abnormal data items.

[0089] Exemplarily, after determining that the policy risk detection result is abnormal, the abnormal data item verification information is further combined to determine the specific data items that cause the policy abnormality, and generate risk attribution information based on these data items.

[0090] Specifically, the abnormal risk strategy is determined according to the strategy risk detection result. Then, the system will filter out the abnormal data items related to these abnormal risk strategies from the abnormal data item inspection information determined in the previous step (S302). For example, a certain abnormal strategy may rely on multiple data items. The system will check which of these data items do not comply with the rules, so as to determine which abnormal data items cause the strategy abnormality. Finally, the strategy risk data attribution information is generated based on the abnormal data items. The strategy risk data attribution information includes the root cause of the abnormal data items causing the abnormal risk strategy. In this way, the source of the strategy risk anomaly can be quickly and accurately located, and clear attribution information can be generated to help decision makers or system managers understand the root cause of the problem and take action.

[0091] In a feasible implementation, the policy risk data attribution can be performed based on a pre-trained rule policy processing large model, and the abnormal data item for the abnormal risk policy result is determined from the abnormal data item verification information based on the policy risk detection result, and the policy risk data attribution information is generated based on the abnormal data item. The following implementation can be referred to:

[0092] A2: Determine the abnormal data item verification rule corresponding to the abnormal data item verification information;

[0093] A4: Based on the abnormal data item verification rules, the policy risk detection results and the abnormal data item verification information, the rule policy processing large model is used to determine the abnormal data items for the abnormal risk policy results from the abnormal data item verification information, and based on the abnormal data item verification rules and the abnormal data items, the policy risk parsing information, the abnormal rule parsing information and the normal data item reference information for the policy risk detection results are determined, and based on the policy risk parsing information, the abnormal rule parsing information and the normal data item reference information, the policy risk data attribution information is generated

[0094] Pre-create a strategic risk data attribution prompt for "the abnormal data item verification rule, the strategic risk detection result, and the abnormal data item verification information", the strategic risk data attribution prompt is used to instruct the rule strategy processing big model to perform risk attribution based on the model input data to generate strategic risk data attribution information;

[0095] In practical applications, the "abnormal data item verification rules, the policy risk detection results and the abnormal data item verification information" and the "policy risk data attribution prompt words" are input into the rule policy processing big model, and the rule policy processing big model is used to determine the abnormal data items for the abnormal risk policy results from the abnormal data item verification information, and determine the policy risk parsing information, abnormal rule parsing information and normal data item reference information for the policy risk detection results based on the abnormal data item verification rules and the abnormal data items, generate the policy risk data attribution information based on the policy risk parsing information, abnormal rule parsing information and normal data item reference information, and finally output the policy risk data attribution information;

[0096] In this specification, a rule policy processing model is pre-trained, and the rule policy processing model is obtained after the basic large language model is trained for rule policy processing scenario migration. The basic large language model can be quickly applied to a new rule policy processing scenario field without retraining a new model. Only fine-tuning training of the basic large language model is required. Usually, the basic large language model is adapted to the character understanding processing scenario. Based on this, the basic large language model (which can be called LLM model) is migrated and converted in the rule policy processing scenario, and a multimodal large-scale language model (which can be called MLLM) compatible with multimodal data such as text and images can be realized. The multimodal large-scale language model can perform policy risk data attribution processing, with "abnormal data item verification rules, the policy risk detection results and the abnormal data item verification information" as model input. The multimodal large-scale language model obtained by migration training can be called a rule policy processing large model;

[0097] Optionally, the following is an explanation of the process of obtaining a rule strategy processing model after adapting the rule strategy processing scenario based on the basic large language generative model, as follows:

[0098] A basic large language model is obtained in advance. The basic large language model may be, for example, the Tongyi Qianwen large model, the Vicuna-7B model, the ChatGPT large model, the Wenxin Yiyan large model, the Angedis large model, etc.

[0099] Then determine a rule policy processing module for the rule policy processing scenario and a large language generation module corresponding to the basic large language model, and create an initial rule policy processing large model including at least the rule policy processing module and the large language generation module;

[0100] Sample data acquisition: obtain a large amount of sample data, which consists of sample abnormal data item verification rules, sample strategy risk detection results, and sample abnormal data item inspection information, and construct strategy risk data attribution prompt words for the sample data;

[0101] Sample data labeling: Introduce expert-side services to manually label sample data with corresponding sample labels. Sample labels are strategy risk data attribution information labels.

[0102] Model training process: input the sample data into the initial rule strategy processing large model for at least one round of model training. The initial rule strategy processing large model determines the sample abnormal data items for the sample abnormal risk strategy results from the sample abnormal data item verification information, and determines the sample strategy risk analysis information, sample abnormal rule analysis information and sample normal data item reference information for the sample strategy risk detection results based on the sample abnormal data item verification rules and the sample abnormal data items, and generates prediction strategy risk data attribution information based on the sample strategy risk analysis information, the sample abnormal rule analysis information and the sample normal data item reference information;

[0103] Based on the predicted strategy risk data attribution information and the strategy risk data attribution information label, the model loss function is used to determine the model loss value. Based on the model loss value, the model parameters of the initial rule strategy processing large model are adjusted until the model training end conditions are met to obtain the rule strategy processing large model.

[0104] Optionally, in the subsequent model training process, a model loss function is used to determine the model loss value based on the predicted strategy risk data attribution information and the strategy risk data attribution information label, and the model recognition loss is used to adjust the model parameters only of the rule strategy processing module in the initial rule strategy processing large model, and the model module parameters of the large language generation module are controlled to remain unchanged.

[0105] Optionally, the model loss function includes but is not limited to fitting one or more of a hinge loss function, a cross entropy loss function, a Euclidean distance loss function, and the like.

[0106] In one or more embodiments of the present specification, the above method can be used to quickly and accurately locate the source of policy risk anomalies and generate clear attribution information to help decision makers or system managers understand the root cause of the problem and take action.

[0107] See also Figure 5 , Figure 5 This is a flowchart of a data processing method proposed in one or more embodiments of this specification. Specifically:

[0108] S4002: monitor the online transaction data of the risk strategy detection system for transaction services;

[0109] The service platform can be associated with a risk strategy detection system, which uses one or more risk strategies to monitor and evaluate strategy risks by collecting online transaction data of transaction services. The risk strategy detection system will obtain various types of data related to transactions in real time (such as transaction amount, time, account information, etc.), and perform strategy risk assessment on these online transaction data. Therefore, the service platform can monitor the online transaction data of transaction services of the risk strategy detection system, and the collected online transaction data provides a basis for subsequent rule verification, strategy detection and risk attribution processing. Through this real-time data collection, potential risks can be discovered more effectively and countermeasures can be taken in a timely manner.

[0110] S4004: Perform data filtering processing on the online transaction data in the risk strategy detection system to obtain filtered online transaction feature data, and transmit the online transaction feature data to a rule verification engine.

[0111] Exemplarily, a real-time verification module can be added to the risk strategy detection system to prepare in advance the online transaction feature data that needs to be verified. That is, the real-time verification module is configured in the risk strategy detection system to filter the online transaction data to obtain filtered online transaction feature data, and the online transaction feature data is transmitted to the associated rule verification engine.

[0112] S4006: Based on the rule verification engine, a data risk verification rule library is used to perform data item rule verification on the online transaction feature data to obtain a data item verification result;

[0113] Exemplarily, the data risk verification rule base in the rule verification engine is used to perform data item rule verification on the filtered online transaction feature data to obtain a data item verification result.

[0114] The data risk inspection rule base includes multiple data risk inspection rules;

[0115] S4008: A risk strategy detection system is used to perform transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result.

[0116] S4010: Perform risk data attribution processing on the strategy risk detection result based on the data item verification result to obtain strategy risk data attribution information.

[0117] In one or more embodiments of the present specification, the service platform monitors the online transaction data of the transaction service of the risk strategy detection system, and the risk strategy detection system performs data filtering processing on the online transaction data to obtain the filtered online transaction feature data, and transmits the online transaction feature data to the rule verification engine, and the rule verification engine uses the data risk verification rule library to perform data item rule verification on the online transaction feature data to obtain data item verification results, and uses the risk strategy detection system to perform transaction risk strategy detection on the online transaction feature data to obtain strategy risk detection results, and based on the data item verification results, the strategy risk detection results are subjected to risk data attribution processing to obtain strategy risk data attribution information. Compared with the post-investigation method of risk strategy anomalies in related technologies, when an abnormality occurs in the strategy risk detection result, attribution analysis can be quickly performed through the data item verification results that are parallel to the transaction risk strategy detection, so as to quickly locate the source of the risk, which not only reduces the time spent on investigation, but also improves the system's response speed and processing capability to transaction data anomalies, and effectively solves the monitoring problem of data anomalies and strategy problems in risk control strategies.

[0118] See also Figure 6 , Figure 6 This is a flowchart of maintaining a data risk verification rule base proposed in one or more embodiments of this specification. Specifically:

[0119] S5002: Acquire a transaction feature data sample for the transaction service;

[0120] A portion of sample data is extracted from the historical transaction data or real-time transaction data of the transaction service as the transaction feature data sample. The transaction feature data sample can represent the typical data features in the transaction service. The transaction feature data sample can be based on a specific time period, a specific type of transaction, a specific user group, etc., to ensure that the transaction feature data sample can cover common transaction scenarios.

[0121] S5004: Perform data attribute rule analysis on the transaction feature data sample to obtain data risk verification rules, and write the data risk verification rules into a data risk verification rule library.

[0122] Exemplarily, by analyzing the data attributes in the transaction feature data sample, the risk detection rules applicable to the transaction are extracted according to the data attributes, so that risks can be identified more accurately when the transaction data is subsequently tested.

[0123] Exemplarily, by parsing the various data fields and data attributes (such as the value range, data type, common distribution, etc. of the field) of the transaction feature data sample, the corresponding data attribute rules for the transaction feature data are extracted. Data risk verification rules include data value range rules, field null value rules, enumeration rules, etc. Data risk verification rules are formulated based on data attribute rules. The rules will be used to detect whether the data in future transactions meets the expected data item standards to prevent risks from occurring. The risk verification rules finally generated will be stored in the data risk verification rule library for use by the rule verification engine.

[0124] In this specification, we obtain transaction feature data samples of transaction services, analyze them, and extract rules applicable to transaction risk verification to ensure that the system can timely and accurately assess data risks in future transactions. This lays the foundation for the entire risk detection process and improves the accuracy and efficiency of the system.

[0125] In a feasible implementation manner, the data attribute rule parsing of the transaction feature data sample to obtain the data risk inspection rule may be implemented as follows:

[0126] Based on the transaction feature data sample, a rule strategy processing big model is used to perform transaction data item analysis on the transaction feature data sample to determine at least one data attribute rule dimension and transaction data item characteristics corresponding to the data attribute rule dimension, and risk verification rule generation processing is performed on the transaction data item characteristics according to the data attribute rule dimension to obtain data risk verification rules.

[0127] Exemplarily, a risk verification rule prompt word for a transaction feature data sample is obtained, and then the risk verification rule prompt word and the transaction feature data sample are input into a rule policy processing macro model, and based on the risk verification rule prompt word, the rule policy processing macro model is instructed to perform transaction data item analysis on the transaction feature data sample to determine at least one data attribute rule dimension and a transaction data item feature corresponding to the data attribute rule dimension;

[0128] Conduct in-depth analysis of transaction feature data samples to determine the data attribute rule dimensions. During the analysis process, the big model will identify the attribute rule dimensions of each data item (such as the data value range, distribution, null value check, etc.) through analysis. The data attribute rule dimensions are used to define the expression form of data item characteristics.

[0129] Mining the data item features under the data attribute rule dimension, parsing the sample data for transaction data items through the model, parsing out the various data items of the transaction data and their corresponding transaction data item features. For example, parsing out the characteristic data items such as payment amount, transaction time, user account status, etc. and

[0130] And the rule strategy processing big model performs risk inspection rule generation processing on the transaction data item features according to the data attribute rule dimension to obtain data risk inspection rules, and then outputs the data risk inspection rules;

[0131] Exemplarily, data risk verification rules applicable to each data item are generated based on the data attribute rule dimensions (such as value range, data type, and distribution) of each data item. Data risk verification rules include a series of verification criteria for transaction data items.

[0132] In one or more embodiments of this specification, by parsing transaction data samples with a large model, the system can accurately extract the features of data items and generate corresponding risk inspection rules based on the attribute rule dimension. This not only improves the intelligence of the system, but also ensures that transaction data can be more accurate and effective in future risk detection.

[0133] The following will be combined Figure 7 , the data processing device provided in this specification is introduced in detail. It should be noted that, Figure 7 The data processing device shown is used to execute the Figure 1 to Figure 6 For the convenience of explanation, only the parts related to this specification are shown. For the specific technical details not disclosed, please refer to this specification. Figure 1 to Figure 6 The embodiment shown.

[0134] See also Figure 7 , which shows a schematic diagram of the structure of the data processing device of this specification. The data processing device 1 can be implemented as all or part of the device through software, hardware or a combination of both. According to some embodiments, the data processing device 1 includes a data acquisition module 11, a data verification module 12 and a data attribution module 13, which are specifically used to:

[0135] A data acquisition module 11 is used to acquire online transaction feature data of the transaction service;

[0136] The data verification module 12 is used to perform data item rule verification on the online transaction feature data to obtain a data item verification result, and perform transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result;

[0137] The data attribution module 13 is used to perform risk data attribution processing on the strategy risk detection result based on the data item verification result to obtain strategy risk data attribution information.

[0138] Optional, such as Figure 8 As shown, the data attribution module 13 includes:

[0139] A detection unit 131, configured to detect a policy detection type of the policy risk detection result;

[0140] The attribution unit 132 is configured to, if the policy detection type is a policy abnormality type, perform abnormal data attribution processing on the policy risk detection result based on the data item verification result to obtain policy risk data attribution information corresponding to the abnormal risk policy result.

[0141] Optionally, the attribution unit 132 is configured to:

[0142] Determining abnormal data item inspection information from the data item inspection results;

[0143] Based on the policy risk detection result, an abnormal data item for an abnormal risk policy result is determined from the abnormal data item verification information, and policy risk data attribution information is generated based on the abnormal data item.

[0144] Optionally, the attribution unit 132 is configured to:

[0145] Determine an abnormal data item verification rule corresponding to the abnormal data item verification information;

[0146] Based on the abnormal data item verification rules, the policy risk detection results and the abnormal data item verification information, a rule policy processing large model is used to determine the abnormal data items for the abnormal risk policy results from the abnormal data item verification information, and based on the abnormal data item verification rules and the abnormal data items, policy risk parsing information, abnormal rule parsing information and normal data item reference information for the policy risk detection results are determined, and policy risk data attribution information is generated based on the policy risk parsing information, abnormal rule parsing information and normal data item reference information.

[0147] Optionally, the data verification module 12 is used to:

[0148] Based on the rule verification engine, a data risk verification rule library is used to perform data item rule verification on the online transaction feature data to obtain a data item verification result;

[0149] A risk strategy detection system is used to perform transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result.

[0150] Optionally, the data acquisition module 11 is used to:

[0151] Monitor the online transaction data of transaction services provided by the risk strategy detection system;

[0152] The risk strategy detection system performs data filtering processing on the online transaction data to obtain filtered online transaction feature data, and transmits the online transaction feature data to a rule verification engine.

[0153] Optionally, the device 1 is used for:

[0154] Obtaining a transaction feature data sample for the transaction service;

[0155] The transaction feature data sample is subjected to data attribute rule analysis to obtain a data risk verification rule, and the data risk verification rule is written into a data risk verification rule library.

[0156] It should be noted that, when the data processing device provided in the above embodiment executes the data processing method, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the data processing device provided in the above embodiment and the data processing method embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0157] The above serial numbers in this specification are for description only and do not represent the advantages or disadvantages of the embodiments.

[0158] In one or more embodiments of the present specification, the service platform obtains online transaction characteristic data of the transaction service, performs data item rule verification on the online transaction characteristic data to obtain data item verification results, and performs transaction risk strategy detection on the online transaction characteristic data to obtain strategy risk detection results, and performs risk data attribution processing on the strategy risk detection results based on the data item verification results to obtain strategy risk data attribution information. Compared with the post-investigation method of risk strategy anomalies in related technologies, when an abnormality occurs in the strategy risk detection results, it is possible to quickly perform attribution analysis through the data item verification results that are parallel to the transaction risk strategy detection, and quickly locate the source of the risk, which not only reduces the time spent on investigation, but also improves the system's response speed and processing capabilities to transaction data anomalies, and effectively solves the monitoring problems of data anomalies and strategy issues in risk control strategies.

[0159] The present specification also provides a computer storage medium, which can store multiple instructions, which are suitable for being loaded and executed by a processor as described above. Figure 1 to Figure 6 The data processing method of the embodiment shown in the figure can be specifically executed by referring to Figure 1 to Figure 6 The specific description of the illustrated embodiment will not be repeated here.

[0160] The present specification also provides a computer program product, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor as described above. Figure 1 to Figure 6 The data processing method of the embodiment shown in the figure can be specifically executed by referring to Figure 1 to Figure 6 The specific description of the illustrated embodiment will not be repeated here.

[0161] Please refer to Fig. 9 , is a block diagram of a structure of an electronic device provided in an embodiment of this specification. The electronic device in this specification may include one or more of the following components: a processor 1010, a memory 1020, an input device 1030, an output device 1040, and a bus 1050. The processor 1010, the memory 1020, the input device 1030, and the output device 1040 may be connected via a bus 1050.

[0162] The processor 1010 may include one or more processing cores. The processor 1010 uses various interfaces and lines to connect various parts of the entire terminal, and executes various functions and processes data of the terminal 100 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1020, and calling data stored in the memory 1020. Optionally, the processor 1010 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 1010 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1010, but may be implemented separately through a communication chip.

[0163] The memory 1020 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 1020 includes a non-transitory computer-readable storage medium. The memory 1020 may be used to store instructions, programs, codes, code sets, or instruction sets.

[0164] The input device 1030 is used to receive input instructions or data, and the input device 1030 includes but is not limited to a keyboard, a mouse, a camera, a microphone, or a touch device. The output device 1040 is used to output instructions or data, and the output device 1040 includes but is not limited to a display device and a speaker. In the embodiment of this specification, the input device 1030 can be a temperature sensor for obtaining the operating temperature of the terminal. The output device 1040 can be a speaker for outputting audio signals.

[0165] In addition, those skilled in the art will appreciate that the structure of the terminal shown in the above drawings does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown, or combine certain components, or arrange the components differently. For example, the terminal also includes a radio frequency circuit, an input unit, a sensor, an audio circuit, a wireless fidelity (WIFI) module, a power supply, a Bluetooth module, and other components, which will not be described in detail here.

[0166] In the embodiments of this specification, the execution subject of each step may be the terminal described above. Optionally, the execution subject of each step is the operating system of the terminal. The operating system may be an Android system, an IOS system, or other operating systems, which is not limited in the embodiments of this specification.

[0167] exist Fig. 9 In the electronic device, the processor 1010 may be used to call the program stored in the memory 1020 and execute the following methods, specifically: obtaining online transaction feature data of the transaction service;

[0168] Performing data item rule verification on the online transaction feature data to obtain a data item verification result, and performing transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result;

[0169] Based on the data item verification result, risk data attribution processing is performed on the strategy risk detection result to obtain strategy risk data attribution information.

[0170] In a feasible implementation manner, the processor 1010 performs the risk data attribution processing on the strategy risk detection result based on the data item verification result to obtain strategy risk data attribution information, and performs the following steps:

[0171] A strategy detection type for detecting the strategy risk detection result;

[0172] If the policy detection type is a policy abnormality type, abnormal data attribution processing is performed on the policy risk detection result based on the data item verification result to obtain policy risk data attribution information corresponding to the abnormal risk policy result.

[0173] In a feasible implementation manner, the processor 1010 performs the abnormal data attribution processing on the strategy risk detection result based on the data item verification result to obtain the strategy risk data attribution information corresponding to the abnormal risk strategy result, and performs the following steps:

[0174] Determining abnormal data item inspection information from the data item inspection results;

[0175] Based on the policy risk detection result, an abnormal data item for an abnormal risk policy result is determined from the abnormal data item verification information, and policy risk data attribution information is generated based on the abnormal data item.

[0176] In a feasible implementation manner, the processor 1010 performs the steps of determining the abnormal data item for the abnormal risk policy result from the abnormal data item verification information based on the policy risk detection result, generating policy risk data attribution information based on the abnormal data item, and performing the following steps:

[0177] Determine an abnormal data item verification rule corresponding to the abnormal data item verification information;

[0178] Based on the abnormal data item verification rules, the policy risk detection results and the abnormal data item verification information, a rule policy processing large model is used to determine the abnormal data items for the abnormal risk policy results from the abnormal data item verification information, and based on the abnormal data item verification rules and the abnormal data items, policy risk parsing information, abnormal rule parsing information and normal data item reference information for the policy risk detection results are determined, and policy risk data attribution information is generated based on the policy risk parsing information, abnormal rule parsing information and normal data item reference information.

[0179] In a feasible implementation manner, the processor 1010 performs the data item rule verification on the online transaction feature data to obtain a data item verification result, and performs transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result, and performs the following steps:

[0180] Based on the rule verification engine, a data risk verification rule library is used to perform data item rule verification on the online transaction feature data to obtain a data item verification result;

[0181] A risk strategy detection system is used to perform transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result.

[0182] In a feasible implementation manner, the processor 1010 executes the method of obtaining online transaction feature data of the transaction service, and performs the following steps:

[0183] Monitor the online transaction data of transaction services provided by the risk strategy detection system;

[0184] The risk strategy detection system performs data filtering processing on the online transaction data to obtain filtered online transaction feature data, and transmits the online transaction feature data to a rule verification engine.

[0185] In a feasible implementation manner, the processor 1010 executes the data processing method and further performs the following steps:

[0186] Obtaining a transaction feature data sample for the transaction service;

[0187] The transaction feature data sample is subjected to data attribute rule analysis to obtain a data risk verification rule, and the data risk verification rule is written into a data risk verification rule library.

[0188] In a feasible implementation manner, the processor 1010 performs the data attribute rule parsing of the transaction feature data sample to obtain a data risk inspection rule, and performs the following steps:

[0189] Based on the transaction feature data sample, a rule strategy processing big model is used to perform transaction data item analysis on the transaction feature data sample to determine at least one data attribute rule dimension and transaction data item characteristics corresponding to the data attribute rule dimension, and risk verification rule generation processing is performed on the transaction data item characteristics according to the data attribute rule dimension to obtain data risk verification rules.

[0190] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0191] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in the embodiments of this specification are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions. For example, the online transaction feature data involved in this specification are all obtained with full authorization.

[0192] The above disclosure is only the preferred embodiment of this specification, which certainly cannot be used to limit the scope of rights of this specification. Therefore, equivalent changes made according to the claims of this specification are still within the scope covered by this specification.

Claims

1. A data processing method, the method comprising: Obtain online transaction feature data of transaction services; Performing data item rule verification on the online transaction feature data to obtain a data item verification result, and performing transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result; Based on the data item verification result, risk data attribution processing is performed on the strategy risk detection result to obtain strategy risk data attribution information.

2. According to the method of claim 1, the step of performing risk data attribution processing on the strategy risk detection result based on the data item verification result to obtain strategy risk data attribution information comprises: Detect the strategy detection type of the strategy risk detection result; If the policy detection type is a policy abnormality type, abnormal data attribution processing is performed on the policy risk detection result based on the data item verification result to obtain policy risk data attribution information corresponding to the abnormal risk policy result.

3. The method according to claim 2, wherein the abnormal data attribution processing is performed on the strategy risk detection result based on the data item verification result to obtain the strategy risk data attribution information corresponding to the abnormal risk strategy result, including: Determining abnormal data item inspection information from the data item inspection results; Based on the policy risk detection result, an abnormal data item for an abnormal risk policy result is determined from the abnormal data item verification information, and policy risk data attribution information is generated based on the abnormal data item.

4. The method according to claim 3, wherein determining the abnormal data item for the abnormal risk policy result from the abnormal data item verification information based on the policy risk detection result, and generating the policy risk data attribution information based on the abnormal data item comprises: Determine an abnormal data item verification rule corresponding to the abnormal data item verification information; Based on the abnormal data item verification rules, the policy risk detection results and the abnormal data item verification information, a rule policy processing large model is used to determine the abnormal data items for the abnormal risk policy results from the abnormal data item verification information, and based on the abnormal data item verification rules and the abnormal data items, policy risk parsing information, abnormal rule parsing information and normal data item reference information for the policy risk detection results are determined, and policy risk data attribution information is generated based on the policy risk parsing information, abnormal rule parsing information and normal data item reference information.

5. The method according to claim 1, wherein the step of performing data item rule verification on the online transaction feature data to obtain a data item verification result, and performing transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result, comprises: Based on the rule verification engine, a data risk verification rule library is used to perform data item rule verification on the online transaction feature data to obtain a data item verification result; A risk strategy detection system is used to perform transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result.

6. The method according to claim 5, wherein obtaining online transaction characteristic data of the transaction service comprises: Monitor the online transaction data of transaction services provided by the risk strategy detection system; The risk strategy detection system performs data filtering processing on the online transaction data to obtain filtered online transaction feature data, and transmits the online transaction feature data to a rule verification engine.

7. The method according to claim 1, further comprising: Obtaining a transaction feature data sample for the transaction service; The transaction feature data sample is subjected to data attribute rule analysis to obtain a data risk verification rule, and the data risk verification rule is written into a data risk verification rule library.

8. According to the method of claim 7, the step of performing data attribute rule analysis on the transaction feature data sample to obtain a data risk inspection rule comprises: Based on the transaction feature data sample, a rule strategy processing big model is used to perform transaction data item analysis on the transaction feature data sample to determine at least one data attribute rule dimension and transaction data item characteristics corresponding to the data attribute rule dimension, and risk verification rule generation processing is performed on the transaction data item characteristics according to the data attribute rule dimension to obtain data risk verification rules.

9. A data processing device, comprising: A data acquisition module is used to obtain online transaction feature data of transaction services; A data verification module, used to perform data item rule verification on the online transaction feature data to obtain a data item verification result, and perform transaction risk strategy detection on the online transaction feature data to obtain a strategy risk detection result; The data attribution module is used to perform risk data attribution processing on the strategy risk detection result based on the data item verification result to obtain strategy risk data attribution information.

10. A computer storage medium storing a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 8.

11. A computer program product, the computer program product storing at least one instruction, wherein the at least one instruction is loaded by a processor and executes the method steps according to any one of claims 1 to 8.

12. An electronic device comprising: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps as claimed in any one of claims 1 to 8.

Images