Data processing method and device, storage medium and computer equipment

Abstract

According to the data processing method and device, the storage medium and the computer equipment provided by the invention, after the asynchronous data generated in the target application by the target user in the at least one risk control list of the target application is obtained, the target strategy corresponding to the asynchronous data and the target condition group in the target strategy are determined, a plurality of strategy condition groups are configured in the target strategy in advance, each strategy condition group corresponds to one strategy link, and after the corresponding target strategy and the target condition group are determined, asynchronous data can be processed according to the strategy link of the target condition group, and a data processing result is obtained. In the process, differentiated processing strategies can be set for different asynchronous data, and rapid and accurate processing of the asynchronous data is realized by utilizing the strategy links in the target condition groups corresponding to the processing strategies, so that the user experience can be improved while the management efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of risk control and security technology, and in particular to a data processing method, apparatus, storage medium, and computer equipment. Background Art

[0002] With the rapid development of the internet, the number and gameplay of social voice apps are increasing. As the volume of these apps grows, so too are the user groups prone to generating illegal information. These high-risk, highly exposed, and frequently violating groups not only impact the experience of regular platform users but can also lead to the loss of high-paying, high-value users, further impacting the platform's ecological security and generating public outcry. Therefore, platforms need to identify these high-risk, highly exposed, and frequently violating groups and take appropriate action to maintain the platform's ecological security and enhance the user experience.

[0003] Currently, when conducting risk management on high-risk, highly exposed, and frequently violating groups, it is necessary to rely on manual discovery and addition to the list, which leads to high management costs and makes it impossible to effectively carry out differentiated governance for specific user groups. Summary of the Invention

[0004] The purpose of this application is to solve at least one of the above-mentioned technical defects, especially the technical defects in the existing technology that when conducting risk management on high-risk, high-exposure, and frequently violating groups, it is necessary to rely on manual discovery and manual addition to the list, which leads to high management costs and the inability to effectively carry out differentiated governance for specific user groups.

[0005] The present application provides a data processing method, the method comprising:

[0006] Obtain asynchronous data generated by a target user in at least one risk control list of a target application in the target application;

[0007] Determining a target policy corresponding to the asynchronous data and a target condition group in the target policy, wherein the target policy is pre-configured with a plurality of policy condition groups, and each policy condition group corresponds to a policy link;

[0008] The asynchronous data is processed according to the policy link of the target condition group to obtain a data processing result.

[0009] Optionally, determining a target policy corresponding to the asynchronous data and a target condition group in the target policy includes:

[0010] Matching the asynchronous data with a plurality of enabled and approved policies pre-configured in a policy center, and determining a target policy corresponding to the asynchronous data and a plurality of policy condition groups pre-configured in the target policy according to a first matching result;

[0011] The asynchronous data is matched with each policy condition group respectively, and a target condition group corresponding to the asynchronous data is determined according to the second matching result.

[0012] Optionally, the policy condition group includes a default group and at least one condition group, and each condition group includes at least one policy condition;

[0013] Matching the asynchronous data with each policy condition group respectively, and determining a target condition group corresponding to the asynchronous data according to the second matching result, includes:

[0014] When there is only one condition group, the asynchronous data is matched with each policy condition in the condition group. If the asynchronous data matches all policy conditions in the condition group, the condition group is used as the target condition group. If the asynchronous data does not match all policy conditions in the condition group, the default group is used as the target condition group.

[0015] When there are multiple condition groups, the asynchronous data is matched with each policy condition in each condition group in the order of the condition groups. If the asynchronous data hits all policy conditions in one of the condition groups, one of the condition groups is used as the target condition group. If the asynchronous data does not hit all policy conditions in all condition groups, the default group is used as the target condition group.

[0016] Optionally, the target strategy includes a machine review strategy and a human review strategy;

[0017] The processing of the asynchronous data according to the policy link of the target condition group to obtain a data processing result includes:

[0018] When the target policy is a machine review policy, the asynchronous data is processed according to the policy link of the target condition group under the machine review policy to obtain a first processing result;

[0019] When the target policy is a human review policy, the asynchronous data is processed according to the policy link of the target condition group under the human review policy to obtain a second processing result.

[0020] Optionally, the processing of the asynchronous data according to the policy link of the target condition group under the machine review policy to obtain a first processing result includes:

[0021] Determine the target factor configured in the policy link of the target condition group under the machine review policy;

[0022] Processing the asynchronous data according to the configuration information of the target factor and obtaining a factor output result;

[0023] A first processing result is determined according to the factor output result.

[0024] Optionally, the configuration information of the target factor includes at least recognition capability and corresponding configuration items, the recognition capability is one or more, and the factor output result includes outputting a KEY value and calling the recognition capability;

[0025] When the target factor has multiple recognition capabilities, determining the first processing result according to the factor output result includes:

[0026] If the factor output result is an output KEY value, the machine review result of the asynchronous data is output as the KEY value, and a first processing result is obtained;

[0027] If the factor output result is to call recognition capability, the next recognition capability is selected according to the level corresponding to each recognition capability in the target factor, and the asynchronous data is processed according to the configuration item of the next recognition capability until the factor output result is the output KEY value.

[0028] Optionally, the target factor is one or more. When there are multiple target factors and all recognition capabilities in the current target factor output the calling recognition capability, determining the first processing result according to the factor output result includes:

[0029] The next target factor is selected according to the hierarchy of each target factor, and the asynchronous data is processed according to the configuration information of the next target factor until the factor output result is the output KEY value, thereby obtaining a first processing result.

[0030] Optionally, the processing the asynchronous data according to the policy link of the target condition group under the human review policy to obtain a second processing result includes:

[0031] Determine a policy chain for the target condition group under the human review policy, wherein the policy chain includes the review round, review mode, machine review result, risk label, human review result, and disposal method of the first round of review;

[0032] Processing the asynchronous data according to the audit round, the audit mode, the machine audit result, the risk tag, the human audit result, and the disposal method, and obtaining a disposal result;

[0033] A second processing result is determined according to the processing result.

[0034] Optionally, the processing result includes result callback and assigned person review, and the policy link also includes the review round, review mode and review role of the next review;

[0035] Determining a second processing result according to the processing result includes:

[0036] When the processing result is a result callback, the human review result is used as the second processing result;

[0037] When the handling result is assignment of human review, human review is assigned according to the review round, review mode and review role of the next review, until the handling result is result callback.

[0038] Optionally, the method further includes:

[0039] Get pre-created strategy testing tasks;

[0040] According to the strategy testing task, sample data is extracted from the processed asynchronous data to perform strategy testing, and strategy execution data is counted.

[0041] Optionally, the method further includes:

[0042] Summarize the execution status of each strategy in the strategy center in different dimensions, and save and visualize the summary results.

[0043] The present application also provides a data processing device, comprising:

[0044] A data acquisition module, configured to acquire asynchronous data generated by a target user in at least one risk control list of a target application in the target application;

[0045] a policy determination module, configured to determine a target policy corresponding to the asynchronous data and a target condition group in the target policy, wherein the target policy is pre-configured with a plurality of policy condition groups, each policy condition group corresponding to a policy link;

[0046] The data processing module is used to process the asynchronous data according to the policy link of the target condition group to obtain a data processing result.

[0047] The present application also provides a computer-readable storage medium, which stores computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the data processing method described in any of the above embodiments.

[0048] The present application also provides a computer device, comprising: one or more processors, and a memory;

[0049] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the data processing method described in any one of the above embodiments are performed.

[0050] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0051] The data processing method, device, storage medium and computer equipment provided by the present application, after obtaining the asynchronous data generated by the target user in at least one risk control list of the target application in the target application, determine the target policy corresponding to the asynchronous data and the target condition group in the target policy, wherein the target policy of the present application is pre-configured with multiple policy condition groups, each policy condition group corresponds to a policy link, and after the present application determines the corresponding target policy and target condition group, it can process the asynchronous data according to the policy link of the target condition group and obtain the data processing result. In this process, the present application can set differentiated processing strategies for different asynchronous data, and use the policy link in the target condition group corresponding to the processing strategy to realize fast and accurate processing of asynchronous data, which can improve management efficiency while improving user experience, and the present application also decouples timing dependencies by processing asynchronous data, thereby further optimizing management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0053] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0054] Figure 2 Schematic diagram of the policy management page provided in this embodiment of the application;

[0055] Figure 3 This is a diagram showing one of the policy configuration pages provided in an embodiment of the present application;

[0056] Figure 4 Another policy configuration page display diagram provided in an embodiment of the present application;

[0057] Figure 5 A diagram showing the factor management page provided in an embodiment of the present application;

[0058] Figure 6This is a diagram showing the machine review policy details page provided in the embodiment of this application;

[0059] Figure 7 A diagram showing the factor configuration page provided in an embodiment of the present application;

[0060] Figure 8 This is a diagram showing the details page of the human review strategy provided in the embodiment of this application;

[0061] Figure 9 A schematic diagram of the human review strategy triggering process provided in an embodiment of the present application;

[0062] Figure 10 This is a diagram showing the configuration page for the strategy test task provided in the embodiment of the present application;

[0063] Figure 11 A schematic diagram of the strategy testing process provided in an embodiment of the present application;

[0064] Figure 12 A flowchart of a data processing device provided in an embodiment of the present application;

[0065] Figure 13 A schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0067] In one embodiment, Figure 1 As shown, Figure 1 A flowchart of a data processing method provided in an embodiment of the present application is provided; the present application provides a data processing method, which may include:

[0068] S110: Acquire asynchronous data generated in a target application by a target user in at least one risk control list of the target application.

[0069] In this step, when risk control is performed on the high-risk, high-exposure, and frequent and multiple-violation groups in the target application, the risk control list of the target application can be obtained. Since the group portrait corresponding to the user group in the risk control list is a subject portrait covering various characteristics formed after multi-dimensional data evaluation, the target users in the risk control list are one or more of the above-mentioned high-risk, high-exposure, and frequent and multiple-violation groups. This application can monitor the data generated by the target users in the risk control list and the target user subjects, thereby ensuring that the illegal content generated by the subjects and the illegal behavior of the subjects themselves can be effectively handled.

[0070] Furthermore, the target application's risk control list in this application can be one or more lists, with the target users on each list corresponding to one or more categories of people with high-risk characteristics, such as user attributes, user behaviors, and behavior sequences that meet violation criteria. Therefore, after obtaining at least one risk control list for a target application, this application can obtain the asynchronous data generated by the target users on that list in the target application, allowing for appropriate processing of the target users and the asynchronous data generated by them.

[0071] Furthermore, in order to decouple timing dependencies and further optimize risk management efficiency, this application can obtain asynchronous data when acquiring relevant data generated by the target user in the target application. The core feature of this asynchronous data is non-blocking: the sender does not need to wait for the receiver's response after sending the data, and can continue to perform other tasks, while the receiver processes the data when it is ready. Among them, the asynchronous data acquired by this application mainly refers to the data content generated by the subject in the target application, such as the user's nickname, user signature, user avatar, user album, square posting, or the room's public screen message, room name, room welcome, room topic, room topic content, etc. The specific data content acquired and the data generation period can be set according to the actual situation and are not restricted here.

[0072] S120: Determine a target policy corresponding to the asynchronous data and a target condition group in the target policy.

[0073] In this step, after obtaining the asynchronous data generated by the target user in at least one risk control list of the target application in the target application through S110, the present application can also determine the target policy corresponding to the asynchronous data and the target condition group in the target policy, so that the policy link corresponding to the asynchronous data can be determined, and the asynchronous data can be processed according to the policy link to obtain the final data processing result.

[0074] Schematically, as Figure 2 As shown, Figure 2 Schematic diagram of the policy management page provided in the embodiment of this application; Figure 2It can be seen that this application can pre-configure multiple policies by adding, deleting, modifying, copying, etc. Each policy includes but is not limited to the policy name, policy ID, policy attributes, policy type, application to which it belongs, subject type, audit scenario, etc. Moreover, in the process of configuring policies, each time a policy is modified, a new version of the policy will be added. At this point, this application can obtain policies of multiple types and different versions of each type. When asynchronous data needs to be processed, the asynchronous data can be matched with multiple policies to determine the target policy that matches the asynchronous data.

[0075] Furthermore, the present application can also configure a corresponding policy condition group for each policy. Each policy includes at least two policy condition groups, and each policy condition group corresponds to the same or different policy links. In this way, the asynchronous data can be further matched with each policy condition group under the target policy, and the target condition group corresponding to the asynchronous data can be determined based on the matching results. The present application can improve the accuracy of data processing and avoid illegal omissions by performing differentiated processing on different asynchronous data and outputting the same or different data processing results.

[0076] It is understandable that the policy link of this application refers to the data processing flow when processing the asynchronous data. Different asynchronous data corresponds to different policy links, which can be set according to application, subject type, audit scenario, policy type, risk control list and other conditions. After the setting is completed, the platform will carry out layered treatment with different intensities for different applications, different scenarios, different risk control list users, and set conditions. For example, when it is identified that the message sent by the user on the risk control list A in the voice live broadcast platform hits a certain violation label in the room, the room message of this user can be checked according to the corresponding policy link.

[0077] S130: Process the asynchronous data according to the policy link of the target condition group to obtain a data processing result.

[0078] In this step, after the target condition group is determined in S120, the present application can process the asynchronous data according to the policy link of the target condition group to obtain a data processing result.

[0079] Specifically, when different asynchronous data in this application are processed according to the corresponding policy links, the data processing results obtained may be the same or different. Among them, the data processing results of this application include but are not limited to machine review passed, machine review failed, assigned human review, simulated human review and marking, suspected risk, simulated human review passed, retrieval, human review passed, human review marked, etc. Specifically, "machine review passed" and "human review passed" refer to sending a "PASS" result to the business application, indicating that the content can be released; "machine review failed" refers to sending a "REJECT" result to the business application, indicating that the content is blocked and cannot be released; "human review assignment" refers to assigning the content to a reviewer for review, and selecting the corresponding review round, review mode, and corresponding review role. When there are multiple review roles, the assigned weight ratio can be configured, and multi-role weight ratio allocation is supported; "simulated human review labeling" refers to selecting the human review label configuration, the system simulates human review labeling, and sends the human review labeling results to the business application, which then blocks the content; "human review labeling" refers to labeling the data by the reviewer and sending it to the business application, which then blocks the content; "suspected risk" refers to sending a "REVIEW" result to the business application, which blocks the content and cannot be released; "simulated human review passed" refers to sending the human review pass result to the business application, which then releases the content; "recall" refers to querying the data that has passed the machine review but not pushed for human review in the specified scenario based on the ID of the risk control list and the business scenario, and then recalling it for human review. This application processes different asynchronous data differently and outputs the same or different data processing results, which can not only improve the accuracy of data processing but also avoid illegal omissions.

[0080] In the above embodiment, after obtaining the asynchronous data generated by the target user in at least one risk control list of the target application in the target application, the target policy corresponding to the asynchronous data and the target condition group in the target policy are determined, wherein the target policy of the present application is pre-configured with multiple policy condition groups, and each policy condition group corresponds to a policy link. After the present application determines the corresponding target policy and target condition group, the asynchronous data can be processed according to the policy link of the target condition group, and the data processing result can be obtained. In this process, the present application can set differentiated processing strategies for different asynchronous data, and use the policy link in the target condition group corresponding to the processing strategy to realize fast and accurate processing of asynchronous data. This can improve management efficiency while enhancing user experience. The present application also decouples timing dependencies by processing asynchronous data, thereby further optimizing management efficiency.

[0081] In one embodiment, determining the target policy corresponding to the asynchronous data and the target condition group in the target policy in S120 may include:

[0082] S121: Match the asynchronous data with multiple enabled and approved policies pre-configured in the policy center, and determine a target policy corresponding to the asynchronous data and multiple policy condition groups pre-configured in the target policy based on a first matching result.

[0083] S122: Match the asynchronous data with each policy condition group respectively, and determine a target condition group corresponding to the asynchronous data according to the second matching result.

[0084] In this embodiment, when determining the target condition group corresponding to asynchronous data, the present application can first determine the target policy corresponding to the asynchronous data and multiple policy condition groups pre-configured in the target policy, so that the asynchronous data can be matched with each policy condition group, and the target condition group corresponding to the asynchronous data can be determined based on the second matching result. Then, the present application can process the asynchronous data according to the policy link of the target condition group to obtain the corresponding data processing result.

[0085] Among them, since a new version of the policy will be added to the policy center every time the user modifies a policy, when there are too many policies configured in this application, this application can enable or delete different versions of policies according to actual needs. At the same time, this application can also approve the enabled policies, so as to ensure that there are no abnormalities in the policy configuration process, and after approval at all levels, the security of production configuration can also be guaranteed.

[0086] Based on this, when this application obtains the asynchronous data generated by the target user in the target application, it can match the asynchronous data with multiple enabled and approved policies pre-configured in the policy center, and obtain a first matching result. The first matching result indicates the policy that currently matches the asynchronous data, which is the target policy. Since this application pre-configures the corresponding policy condition group for each policy, when this application determines the target policy, it can determine multiple policy condition groups corresponding to the target policy. In this way, the policy condition group can be used to determine the policy link corresponding to the asynchronous data, and the policy link can be used to process the asynchronous data, thereby achieving differentiated handling.

[0087] In one embodiment, the policy condition group may include a default group and at least one condition group, and each condition group includes at least one policy condition.

[0088] Matching the asynchronous data with each policy condition group respectively in S122, and determining a target condition group corresponding to the asynchronous data according to the second matching result, may include:

[0089] S1221: When there is one condition group, the asynchronous data is matched with each policy condition in the condition group. If the asynchronous data hits all policy conditions in the condition group, the condition group is used as the target condition group. If the asynchronous data does not hit all policy conditions in the condition group, the default group is used as the target condition group.

[0090] S1222: When there are multiple condition groups, the asynchronous data is matched with each policy condition in each condition group in the order of each condition group. If the asynchronous data hits all policy conditions in one of the condition groups, one of the condition groups is used as the target condition group. If the asynchronous data does not hit all policy conditions in all condition groups, the default group is used as the target condition group.

[0091] In this embodiment, Figure 3 、 4 As shown, Figure 3 This is a diagram showing one of the policy configuration pages provided in the embodiment of this application. Figure 4 Another policy configuration page display diagram provided in the embodiment of the present application; Figure 3 and Figure 4 As can be seen, the policy condition groups of this application can include a default group and at least one condition group. Each condition group contains at least one policy condition, including but not limited to user ID, room ID, guild ID, group ID, historical violation level, historical violation tag, room tab, vest package, room gameplay, user attributes, room type, risk control list (user profile), etc. When a condition group sets multiple policy conditions, each policy condition must be met before the policy link corresponding to the condition group will be executed.

[0092] It is understandable that the purpose of setting up conditional groups in this application is to enrich the flexibility of the policy, meet the policy requirements of special processing logic for review work orders with the same content but different conditions, and achieve independent isolation of events for the review of special processing logic, so as to meet the diverse and complex business scenarios without interfering with the default group, and support the provision of policy configuration to combat risk response capabilities.

[0093] Based on this, when matching asynchronous data with each policy condition group respectively, the present application can first determine the number of condition groups in the policy condition group. When there is only one condition group, the asynchronous data can be matched with each policy condition in the condition group. If the asynchronous data hits all policy conditions in the condition group, the condition group is used as the target condition group. If the asynchronous data does not hit all policy conditions in the condition group, the default group is used as the target condition group. When there are multiple condition groups, the asynchronous data can be matched with each policy condition in each condition group in the order of each condition group. If the asynchronous data hits all policy conditions in one of the condition groups, one of the condition groups is used as the target condition group. If the asynchronous data does not hit all policy conditions in all condition groups, the default group is used as the target condition group. In this way, it can be ensured that each asynchronous data can match the corresponding policy condition group, and the flexibility of the policy can be enriched by setting the condition group.

[0094] In one embodiment, the target policy may include a machine review policy and a human review policy.

[0095] S130 processes the asynchronous data according to the policy link of the target condition group to obtain a data processing result, which may include:

[0096] S131: When the target policy is a machine review policy, the asynchronous data is processed according to the policy link of the target condition group under the machine review policy to obtain a first processing result.

[0097] S132: When the target policy is a human review policy, the asynchronous data is processed according to the policy link of the target condition group under the human review policy to obtain a second processing result.

[0098] In this embodiment, when configuring a policy, you can configure basic policy information, such as the policy name and policy type, which are divided into scenario policies and general policies (universal for all applications), the application to which it belongs, the audit business, the subject type, the audit scenario, and policy attributes, which are divided into machine-based audit policies and human-based audit policies. Therefore, the policy attributes of the target policy of this application also include machine-based audit policies and human-based audit policies. Among them, the machine-based audit policy refers to the policy for data auditing by machines, and the human-based audit policy refers to the policy for data auditing by humans, so that different data scenarios can be met.

[0099] Furthermore, when the target strategy of the present application is a machine review strategy, since the strategy link of the target condition group configured under the machine review strategy is different from the strategy link of the target condition group configured under the human review strategy, the present application can process the asynchronous data according to the strategy link of the target condition group under the machine review strategy, and then obtain the first processing result. The first processing result here includes but is not limited to machine review passed, machine review failed, human review assigned, simulated human review marking, suspected risk, simulated human review passed and salvage. Among them, simulated human review marking and simulated human review are the operations of simulating human review by the system, performing human review and marking operations on the data, and telling the business application the final human review results. In this way, some scenarios that meet specific condition groups no longer need manual review, and some data scenarios that require both machine review and human review can be met, and the effect of reducing labor costs can be achieved.

[0100] When the target strategy of this application is a human review strategy, the asynchronous data can be processed according to the strategy link of the target condition group under the human review strategy, and a second processing result can be obtained. The second processing result includes but is not limited to result callback and assignment of human review. Result callback means processing using the result of human review, and the human review results include three results: pass, label (fail), and submit; assignment of human review means assigning the data to the reviewer for processing. This application can configure the corresponding strategy link in the strategy center: after the data is passed, labeled, or submitted by human review, the data can continue to be assigned to human review, which can meet some data scenarios that require multiple rounds of human review.

[0101] In one embodiment, in S131, the asynchronous data is processed according to the policy link of the target condition group under the machine review policy to obtain a first processing result, which may include:

[0102] S1311: Determine the target factor configured in the policy link of the target condition group under the machine review policy.

[0103] S1312: Process the asynchronous data according to the configuration information of the target factor, and obtain a factor output result.

[0104] S1313: Determine a first processing result according to the factor output result.

[0105] In this embodiment, since the machine review strategy of this application can configure factors, after selecting the corresponding factor, the configuration corresponding to the factor can be associated, and the policy processing method can also be configured, which includes but is not limited to pass, fail, assign human review, call factors, simulate human review marking, suspected risk, simulate human review pass, and retrieve, a total of eight processing results. Therefore, when this application processes asynchronous data according to the policy link of the target condition group under the machine review strategy, it can first determine the target factor configured in the policy link, and then process the asynchronous data according to the configuration information of the target factor, and obtain the factor output result.

[0106] It is understandable that the present application can pre-configure multiple factors through the policy center, such as Figure 5 As shown, Figure 5 A diagram showing the factor management page provided for an embodiment of the present application; the present application can set the factor name, factor ID, description, factor version, etc. of each factor through the factor management page, and in the process of configuring factors, the present application can add, delete, modify, and copy factors. Each modification of a factor will add a new version, so the present application can select the corresponding version factor to enable. After the present application configures multiple versions of factors, the corresponding factors can be selected for association under the machine review strategy. Schematically, as shown in Figure 6 As shown, Figure 6 This is a diagram showing the details page of the machine review strategy provided in the embodiment of this application; Figure 6 It can be seen that in this application, a machine review strategy can select one or more factors to be associated, and each factor can be associated with one or more machine review strategies. The specific settings can be made according to actual conditions and are not restricted here.

[0107] In addition, this application can not only set the factor name, factor ID, description, and factor version for each factor, but also set the corresponding configuration information for each factor, so that the asynchronous data can be processed according to the configuration information of the target factor and the factor output result can be obtained. Figure 7 As shown, Figure 7 A diagram showing the factor configuration page provided in the embodiment of this application; Figure 7It can be seen that the present application can configure detailed information of factors, such as configuring the recognition capability of factors, factor descriptions, factor machine review results, factor risk labels and factor output results. Among them, the recognition capability components of the factors of the present application include machine review suppliers, keyword libraries, sample libraries and image sample libraries. When the recognition capability of the factors selects the machine review supplier, the description of the factors, machine review suppliers, machine review results, risk labels, recognition scores and factor output results can be configured; when the recognition capability of the factors selects the keyword library, the vocabulary, factor description, machine review results, risk labels and factor output results can be configured; when the recognition capability of the factors selects the sample library, the sample library, factor description, machine review results and factor output results can be configured; when the recognition capability of the factors selects the image sample library, the image sample library, factor description, machine review results and factor output results can be configured. Through these configuration information, differentiated processing operations on abnormal data can be achieved.

[0108] Furthermore, since some business scenarios in this application require not only machine-reviewed data but also human-reviewed data, the business application will temporarily release data to a certain group of people based on the data that has passed the machine review, and will release the data in full only after the subsequent human review results come out. In other words, when the machine review result is passed, the policy center can also configure the policy to pass or assign human review processing, or it can configure the policy to fail. Based on this, after this application obtains the factor output result under the machine review policy, it is necessary to further determine the final first processing result based on the factor output result.

[0109] In one embodiment, the configuration information of the target factor includes at least recognition capability and corresponding configuration items. The recognition capability may be one or more. The factor output result may include outputting a KEY value and calling the recognition capability.

[0110] When the target factor has multiple recognition capabilities, determining the first processing result according to the factor output result in S1313 may include:

[0111] S13131: If the factor output result is an output KEY value, the machine review result of the asynchronous data is output as the KEY value, and a first processing result is obtained.

[0112] S13132: If the factor output result is to call recognition capability, the next recognition capability is selected according to the level corresponding to each recognition capability in the target factor, and the asynchronous data is processed according to the configuration item of the next recognition capability until the factor output result is the output KEY value.

[0113] In this embodiment, since the recognition capability of the target factor in this application includes but is not limited to machine review suppliers, keyword libraries, sample libraries and image sample libraries, and each recognition capability is configured with different configuration items. For example, when the recognition capability of the target factor selects the machine review supplier, its corresponding configuration items can be the description of the factor, the machine review supplier, the machine review result, the risk label, the recognition score and the factor output result; when the recognition capability of the target factor selects the keyword library, its corresponding configuration items can be the vocabulary, factor description, machine review result, risk label and factor output result; when the recognition capability of the target factor selects the sample library, its corresponding configuration items can be the sample library, factor description, machine review result and factor output result; when the recognition capability of the target factor selects the image sample library, its corresponding configuration items can be the image sample library, factor description, machine review result and factor output result. Among them, the factor output results of this application are divided into output KEY value and call recognition capability. Outputting KEY value means outputting the original machine review result, and calling recognition capability means calling other pre-configured recognition capabilities. This application can configure recognition capabilities incrementally until the output KEY value is finally matched.

[0114] Based on this, when the target factor in this application has multiple recognition capabilities, if the current factor output result is the output KEY value, the machine review result of the asynchronous data can be output as the KEY value, and the first processing result can be obtained; if the current factor output result is the call recognition capability, the next recognition capability can be selected according to the level corresponding to each recognition capability in the target factor, and the asynchronous data can be processed according to the configuration item of the next recognition capability until the factor output result is the output KEY value.

[0115] It is understandable that the factors corresponding to different strategies in this application can be customized according to different business scenarios, and this application can also select corresponding recognition capabilities based on the risk filtering funnel principle, so that the machine review recognition capabilities with high accuracy and low judgment cost can be called first, and when it leaks to the next recognition capability, other forms of violations of the previous recognition capability can be supplemented, and filtering can be carried out layer by layer to achieve a policy logic with controllable cost, appropriate efficiency and optimal accuracy.

[0116] In one embodiment, the target factor is one or more. When there are multiple target factors and all recognition capabilities in the current target factor output the calling recognition capability, determining the first processing result according to the factor output result in S1313 may include:

[0117] The next target factor is selected according to the hierarchy of each target factor, and the asynchronous data is processed according to the configuration information of the next target factor until the factor output result is the output KEY value, thereby obtaining a first processing result.

[0118] In this embodiment, when there are multiple target factors of this application, if the current target factor is only configured with one recognition capability, and the recognition capability outputs the calling recognition capability, or the current target factor is configured with multiple recognition capabilities, and multiple recognition capabilities all output the calling recognition capability, it indicates that the current target factor cannot output the KEY value, that is, the current target factor cannot output other machine review results other than the calling recognition capability. At this time, this application can select the next target factor according to the hierarchical relationship of each target factor, and process the asynchronous data according to the configuration information of the next target factor to obtain the factor output result of the next target factor. When the factor output result is the output KEY value, the machine review result of the asynchronous data can be output as the KEY value, and the first processing result can be obtained; if the current factor output result is the calling recognition capability, the next recognition capability can be selected according to the hierarchy corresponding to each recognition capability in the next target factor, and the asynchronous data can be processed according to the configuration item of the next recognition capability until the factor output result is the output KEY value, so that a more accurate data processing result can be obtained.

[0119] In one embodiment, in S132, the asynchronous data is processed according to the policy link of the target condition group under the human review policy to obtain the second processing result, which may include:

[0120] S1321: Determine the policy link of the target condition group under the human review policy, wherein the policy link includes the review round of the first round of review, the review mode, the machine review result, the risk label, the human review result and the disposal method.

[0121] S1322: Process the asynchronous data according to the audit round, the audit mode, the machine audit result, the risk label, the human audit result and the disposal method, and obtain a disposal result.

[0122] S1323: Determine a second processing result according to the processing result.

[0123] In this embodiment, when the target strategy is a human review strategy, the present application can first determine the strategy link of the target condition group under the human review strategy. The strategy link includes but is not limited to the review round, review mode, machine review results, risk labels, human review results and disposal methods of the first round of review. After the present application determines the strategy link, it can process the asynchronous data according to the review round, review mode, machine review results, risk labels, human review results and disposal methods under the strategy link and obtain the disposal result. Then, the present application can determine the second processing result based on the disposal result.

[0124] Schematically, as Figure 8 As shown, Figure 8 This is a diagram showing the details page of the human review strategy provided in the embodiment of this application; Figure 8 It can be seen that in the human review strategy of this application, different strategy links are configured under different condition groups. The strategy link includes but is not limited to the review round, review mode, machine review results, risk labels, human review results and disposal methods of the first round of review. The disposal method results in callback and assignment of human review. The result callback is output as the result of human review. The assignment of human review continues to be based on the configured review round, review mode and review role, and then performs refined human review at different strategy levels according to different risk control lists.

[0125] Furthermore, because some data scenarios require multiple rounds of human review, the present application can configure a corresponding policy link in the policy: after the asynchronous data is approved, marked, or submitted by human review, the data can also be assigned to human review. Therefore, when the present application processes the asynchronous data according to the review rounds, review mode, machine review results, risk tags, human review results, and disposal methods under the policy link and obtains the disposal result, it can further determine the second processing result based on the disposal result.

[0126] In one embodiment, the handling result may include result callback and assigned person for review, and the policy link may also include the review round, review mode, and review role of the next review round.

[0127] Determining a second processing result according to the processing result in S1323 may include:

[0128] S13231: When the processing result is a result callback, the human review result is used as the second processing result.

[0129] S13232: When the handling result is assignment of human review, human review is assigned according to the review round, review mode and review role of the next review, until the handling result is result callback.

[0130] In this embodiment, Figure 9 As shown, Figure 9 Schematic diagram of the human review strategy triggering process provided in the embodiment of this application; Figure 9 It can be seen that during the human review process of this application, the first-instance reviewer can process asynchronous data through the judgment component. The disposal results include result callback and assignment of human review. The result callback includes pass, submission and marking. When the disposal result is pass, the pass result can be output through the corresponding interface, and the pass result can be saved to the component kafka through the callback component. Similarly, when the disposal result of this application is of other types, it can also be processed through the above process.

[0131] In addition, if the result of this application is assigned to human review, human review can be assigned according to the review round, review mode, and review role configured in the policy link for the next review, and the review process will continue according to the review process of the first reviewer until the result is a result callback. In this way, the final processing result of the asynchronous data can be obtained.

[0132] In one embodiment, the method may further include:

[0133] S140: Obtain a pre-created strategy testing task.

[0134] S150: extracting sample data from the processed asynchronous data according to the strategy testing task to perform strategy testing, and collecting statistics on strategy execution data.

[0135] In this embodiment, the strategy test task created in advance can be used to perform strategy test on the sample data and calculate the strategy execution data. Figure 10 As shown, Figure 10 This is a diagram showing the configuration page for the strategy test task provided in the embodiment of the present application; Figure 10 In this application, when configuring a policy test task, you can associate the configured policy and policy version, and Figure 10 In the configuration page shown, select the event range, audit scenario, data format, machine review results, human review results, and human review labels that need to be tested. The number of sample data can be configured according to proportion or quantity.

[0136] Further, if Figure 11 As shown, Figure 11 A schematic diagram of the strategy testing process is provided for an embodiment of the present application. After the present application configures the strategy testing task according to the above configuration process, the strategy testing task can be executed. During the execution process, the present application can extract sample data from the processed asynchronous data according to the event range and extraction quantity or extraction ratio configured for the strategy testing task, and use machine review strategy and / or human review strategy to process the sample data. When the test is completed, the present application can also view the data results of the strategy test, such as viewing the specific hit samples, and can also export the data results.

[0137] In one embodiment, the method may further include:

[0138] S160: Summarize the execution status of each strategy of the strategy center in different dimensions, and save and visualize the summary results.

[0139] In this embodiment, the policy center can not only be used to configure various versions of policies, but also to summarize the execution status of various policies in different dimensions, and save and visualize the summary results.

[0140] For example, this application can summarize the policy execution status according to the scenario dimension and policy dimension respectively, and display it visually. Users can view the policy execution summary. When viewing, they can also query according to the date, application scenario, policy name or policy ID. In this way, the page can display summary information including date, application, policy name, scenario, total data volume, policy pass volume, policy intercept volume, human review volume, human review penalty volume, policy pass rate, policy intercept rate, human review rate, and human review penalty rate.

[0141] The data processing device provided in an embodiment of the present application is described below. The data processing device described below and the data processing method described above can be referenced to each other.

[0142] In one embodiment, Figure 12 As shown, Figure 12 This is a flow chart of a data processing device provided in an embodiment of the present application. The present application also provides a data processing device, which may include a data acquisition module 210, a policy determination module 220, and a data processing module 230, specifically including the following:

[0143] The data acquisition module 210 is configured to acquire asynchronous data generated by a target user in at least one risk control list of a target application in the target application.

[0144] The policy determination module 220 is configured to determine a target policy corresponding to the asynchronous data and a target condition group in the target policy, wherein the target policy is pre-configured with multiple policy condition groups, and each policy condition group corresponds to a policy link.

[0145] The data processing module 230 is configured to process the asynchronous data according to the policy link of the target condition group to obtain a data processing result.

[0146] In the above embodiment, after obtaining the asynchronous data generated by the target user in at least one risk control list of the target application in the target application, the target policy corresponding to the asynchronous data and the target condition group in the target policy are determined, wherein the target policy of the present application is pre-configured with multiple policy condition groups, and each policy condition group corresponds to a policy link. After the present application determines the corresponding target policy and target condition group, the asynchronous data can be processed according to the policy link of the target condition group, and the data processing result can be obtained. In this process, the present application can set differentiated processing strategies for different asynchronous data, and use the policy link in the target condition group corresponding to the processing strategy to realize fast and accurate processing of asynchronous data. This can improve management efficiency while enhancing user experience. The present application also decouples timing dependencies by processing asynchronous data, thereby further optimizing management efficiency.

[0147] In one embodiment, the present application also provides a computer-readable storage medium, which stores computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the data processing method described in any of the above embodiments.

[0148] In one embodiment, the present application further provides a computer device, including: one or more processors, and a memory.

[0149] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the data processing method described in any one of the above embodiments are performed.

[0150] Schematically, as Figure 13 As shown, Figure 13 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 300 can be provided as a server. Figure 13 Computer device 300 includes a processing component 302, which further includes one or more processors, and a memory resource represented by memory 301 for storing instructions executable by processing component 302, such as an application. The application stored in memory 301 may include one or more modules, each corresponding to a set of instructions. In addition, processing component 302 is configured to execute the instructions to perform the data processing method of any of the above embodiments.

[0151] The computer device 300 may further include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate based on an operating system stored in the memory 301, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or the like.

[0152] Those skilled in the art will understand that Figure 13 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0153] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0154] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referenced to each other.

[0155] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data processing method, characterized in that: The method comprises: Obtain asynchronous data generated by a target user in at least one risk control list of a target application in the target application; Determining a target policy corresponding to the asynchronous data and a target condition group in the target policy, wherein the target policy is pre-configured with a plurality of policy condition groups, and each policy condition group corresponds to a policy link; The asynchronous data is processed according to the policy link of the target condition group to obtain a data processing result.

2. The data processing method according to claim 1, wherein: The determining of a target policy corresponding to the asynchronous data and a target condition group in the target policy includes: Matching the asynchronous data with a plurality of enabled and approved policies pre-configured in a policy center, and determining a target policy corresponding to the asynchronous data and a plurality of policy condition groups pre-configured in the target policy according to a first matching result; The asynchronous data is matched with each policy condition group respectively, and a target condition group corresponding to the asynchronous data is determined according to the second matching result.

3. The data processing method according to claim 2, characterized in that: The policy condition group includes a default group and at least one condition group, each condition group includes at least one policy condition; Matching the asynchronous data with each policy condition group respectively, and determining a target condition group corresponding to the asynchronous data according to the second matching result, includes: When there is only one condition group, the asynchronous data is matched with each policy condition in the condition group. If the asynchronous data matches all policy conditions in the condition group, the condition group is used as the target condition group. If the asynchronous data does not match all policy conditions in the condition group, the default group is used as the target condition group. When there are multiple condition groups, the asynchronous data is matched with each policy condition in each condition group in the order of the condition groups. If the asynchronous data hits all policy conditions in one of the condition groups, one of the condition groups is used as the target condition group. If the asynchronous data does not hit all policy conditions in all condition groups, the default group is used as the target condition group.

4. The data processing method according to claim 1, wherein: The target strategy includes machine review strategy and human review strategy; The processing of the asynchronous data according to the policy link of the target condition group to obtain a data processing result includes: When the target policy is a machine review policy, the asynchronous data is processed according to the policy link of the target condition group under the machine review policy to obtain a first processing result; When the target policy is a human review policy, the asynchronous data is processed according to the policy link of the target condition group under the human review policy to obtain a second processing result.

5. The data processing method according to claim 4, characterized in that: The step of processing the asynchronous data according to the policy link of the target condition group under the machine review policy to obtain a first processing result includes: Determine the target factor configured in the policy link of the target condition group under the machine review policy; Processing the asynchronous data according to the configuration information of the target factor and obtaining a factor output result; A first processing result is determined according to the factor output result.

6. The data processing method according to claim 5, characterized in that: The configuration information of the target factor includes at least recognition capability and corresponding configuration items. The recognition capability may be one or more. The factor output result includes outputting a KEY value and calling the recognition capability. When the target factor has multiple recognition capabilities, determining the first processing result according to the factor output result includes: If the factor output result is an output KEY value, the machine review result of the asynchronous data is output as the KEY value, and a first processing result is obtained; If the factor output result is to call recognition capability, the next recognition capability is selected according to the level corresponding to each recognition capability in the target factor, and the asynchronous data is processed according to the configuration item of the next recognition capability until the factor output result is the output KEY value.

7. The data processing method according to claim 6, characterized in that: The target factor is one or more. When there are multiple target factors and all recognition capabilities in the current target factor output the calling recognition capability, determining the first processing result according to the factor output result includes: The next target factor is selected according to the hierarchy of each target factor, and the asynchronous data is processed according to the configuration information of the next target factor until the factor output result is the output KEY value, thereby obtaining a first processing result.

8. The data processing method according to claim 4, characterized in that: The processing of the asynchronous data according to the policy link of the target condition group under the human review policy to obtain a second processing result includes: Determine a policy chain for the target condition group under the human review policy, wherein the policy chain includes the review round, review mode, machine review result, risk label, human review result, and disposal method of the first round of review; Processing the asynchronous data according to the audit round, the audit mode, the machine audit result, the risk tag, the human audit result, and the disposal method, and obtaining a disposal result; A second processing result is determined according to the processing result.

9. The data processing method according to claim 8, characterized in that: The processing result includes result callback and assigned reviewer, and the policy link also includes the review round, review mode and review role of the next review round; Determining a second processing result according to the processing result includes: When the processing result is a result callback, the human review result is used as the second processing result; When the handling result is assignment of human review, human review is assigned according to the review round, review mode and review role of the next review, until the handling result is result callback.

10. The data processing method according to any one of claims 1 to 9, characterized in that: The method further comprises: Get pre-created strategy testing tasks; According to the strategy testing task, sample data is extracted from the processed asynchronous data to perform strategy testing, and strategy execution data is counted.

11. The data processing method according to any one of claims 1 to 9, characterized in that: The method further comprises: Summarize the execution status of each strategy in the strategy center in different dimensions, and save and visualize the summary results.

12. A data processing device, characterized in that: include: A data acquisition module, configured to acquire asynchronous data generated by a target user in at least one risk control list of a target application in the target application; a policy determination module, configured to determine a target policy corresponding to the asynchronous data and a target condition group in the target policy, wherein the target policy is pre-configured with a plurality of policy condition groups, each policy condition group corresponding to a policy link; The data processing module is used to process the asynchronous data according to the policy link of the target condition group to obtain a data processing result.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the data processing method according to any one of claims 1 to 11.

14. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, which, when executed by the one or more processors, perform the steps of the data processing method according to any one of claims 1 to 11.

Images