Data processing method and apparatus

Abstract

The embodiments of the present specification provide a data processing method and device, wherein the data processing method comprises: performing structural conversion on resource portrait data of each user in a plurality of users and abnormal event data of each user, performing data analysis and parameter identification on the structured data set obtained by conversion through a data analysis model to obtain user processing parameters of each user, performing processing parameter mapping of data anomaly processing based on the structured data set of each user, the user processing parameters and the abnormal configuration parameters of the detection system through an abnormal processing engine, obtaining a plurality of processing parameter links of each user, performing parameter link screening in the plurality of processing parameter links of each user based on a preset bias parameter, and obtaining a target processing parameter link of each user, so as to determine the target processing parameter link of each user from a global dimension in combination with the resource portrait data and the abnormal event data of a plurality of users.

Description

Technical Field

[0001] This document relates to the field of data processing technology, and in particular to a data processing method and apparatus. Background Technology

[0002] With the continuous development and promotion of internet technology, online services provided by internet technology have emerged. Online services provide a convenient means of providing services to users. As users use online services more frequently, user data from various online services is also accumulating, making user profile data richer and more complete. In this process, with the diversification of user service needs for online services, online service providers also face certain pressures and challenges in managing user data. Summary of the Invention

[0003] This specification provides one or more embodiments of a data processing method, comprising: acquiring resource profile data of multiple users and acquiring abnormal event data of each user through a data interface of a detection system; performing a structured transformation on the resource profile data and abnormal event data of each user; inputting the transformed structured dataset into a data parsing model for data parsing and parameter identification to obtain user processing parameters for each user; performing user data fusion on the structured datasets of each user through an anomaly processing engine, and mapping data anomaly processing parameters based on the fused user data, the user processing parameters, and the anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user; and filtering the multiple processing parameter links of each user based on preset bias parameters to obtain the target processing parameter links for each user, for use in data anomaly processing of the abnormal event data.

[0004] This specification provides one or more embodiments of a data processing apparatus, comprising: a data acquisition module configured to acquire resource profile data of multiple users and acquire abnormal event data of each user through a data interface of a detection system; a data parsing module configured to perform structured transformation on the resource profile data and abnormal event data of each user, input the transformed structured dataset into a data parsing model for data parsing and parameter identification, and obtain user processing parameters for each user; a parameter mapping module configured to perform user data fusion on the structured dataset of each user through an anomaly processing engine, and perform data anomaly processing parameter mapping based on the fused user data, the user processing parameters, and the anomaly configuration parameters of the detection system, to obtain multiple processing parameter links for each user; and a parameter filtering module configured to filter parameter links in the multiple processing parameter links of each user based on preset bias parameters, to obtain the target processing parameter links for each user, for use in data anomaly processing of the abnormal event data.

[0005] This specification provides one or more embodiments of a data processing device, including: a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to: acquire resource profile data of multiple users and acquire abnormal event data of each user through a data interface of a detection system; perform a structured transformation on the resource profile data and abnormal event data of each user, input the structured dataset obtained by the transformation into a data parsing model for data parsing and parameter identification, and obtain user processing parameters for each user; perform user data fusion on the structured dataset of each user through an anomaly processing engine, and perform data anomaly processing parameter mapping based on the fused user data, the user processing parameters, and the anomaly configuration parameters of the detection system, to obtain multiple processing parameter links for each user; and perform parameter link filtering on the multiple processing parameter links of each user based on preset bias parameters to obtain the target processing parameter link for each user, for use in data anomaly processing of the abnormal event data.

[0006] This specification provides one or more embodiments of a computer-readable storage medium for storing computer-executable instructions, which, when executed, perform the following steps: acquiring resource profile data of multiple users and acquiring abnormal event data of each user through a data interface of a detection system; performing a structured transformation on the resource profile data and abnormal event data of each user, inputting the transformed structured dataset into a data parsing model for data parsing and parameter identification to obtain user processing parameters for each user; performing user data fusion on the structured datasets of each user through an anomaly processing engine, and mapping data anomaly processing parameters based on the fused user data, the user processing parameters, and the anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user; and filtering parameter links in the multiple processing parameter links of each user based on preset bias parameters to obtain the target processing parameter links for each user, used for data anomaly processing of the abnormal event data. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 A schematic diagram illustrating the implementation environment of a data processing method provided in one or more embodiments of this specification; Figure 2 A data processing method flowchart provided for one or more embodiments of this specification; Figure 3 A flowchart illustrating a data processing method for a resource scenario provided in one or more embodiments of this specification; Figure 4 A schematic diagram of an embodiment of a data processing apparatus provided in one or more embodiments of this specification; Figure 5 This is a schematic diagram of the structure of a data processing device provided for one or more embodiments of this specification. Detailed Implementation

[0008] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0009] The data processing methods provided in one or more embodiments of this specification are applicable to the implementation environment of data anomaly handling. (Refer to...) Figure 1 The implementation environment includes at least: The exception handling system 101, in addition, the implementation environment may also include a data parsing model 102 and an exception handling engine 103; The anomaly handling system 101 is used to perform structured transformation on the resource profile data and anomaly event data of each user among multiple users. The structured dataset obtained by the transformation is input into the data parsing model for data parsing and parameter identification to obtain the user processing parameters of each user. The anomaly handling engine performs user data fusion on the structured dataset of each user, and performs data anomaly handling parameter mapping based on the user fusion data, user processing parameters, and anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user. Based on the preset bias parameters, parameter links are filtered in the multiple processing parameter links of each user to obtain the target processing parameter links for each user. The data parsing model 102 is used to parse data and identify parameters based on structured datasets to obtain user processing parameters for each user; the anomaly processing engine 103 is used to perform user data fusion on the structured datasets of each user, and to perform data anomaly processing parameter mapping based on the fused user data, user processing parameters, and anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user. In addition, the implementation environment may also include a detection system 104, which can be used to send abnormal event data of each user to the abnormality handling system 101 through a data interface; In this implementation environment, the anomaly handling system 101 performs structured transformation on the resource profile data and anomaly event data of each user among multiple users. The data parsing model 102 performs data parsing and parameter identification on the structured dataset obtained by the transformation to obtain the user processing parameters of each user. The anomaly handling engine 103 performs data anomaly handling parameter mapping based on the structured dataset of each user, the user processing parameters and the anomaly configuration parameters of the detection system 104 to obtain multiple processing parameter links for each user. Based on preset bias parameters, parameter links are filtered in the multiple processing parameter links of each user to obtain the target processing parameter links for each user. In this way, the target processing parameter links of each user are determined from a global perspective by combining the resource profile data and anomaly event data of multiple users.

[0010] One or more embodiments of a data processing method provided in this specification are as follows: Reference Figure 2 The data processing method provided in this embodiment specifically includes steps S202 to S208.

[0011] Step S202: Obtain resource profile data for multiple users and obtain abnormal event data for each user through the data interface of the detection system.

[0012] The resource profile data mentioned in this embodiment refers to resource-related user profile data. Specifically, the resource profile data of multiple users can be the individual resource profile data of multiple users. For example, the resource profile data includes income data, expenditure data, credit rating and / or historical performance records. The abnormal event data of each user can be the resource event data of each user that occurs abnormally in the detection system. The abnormal event data can be risky resource event data, such as overdue resource event data.

[0013] In practice, resource profile data of multiple users is obtained and abnormal event data of each user is obtained through the data interface of the detection system; optionally, the abnormal event data of each user belongs to the same detection system.

[0014] Specifically, it can obtain the resource profile data of each user uploaded through the interactive interface, or it can obtain the resource profile data of each user based on the authorized access instructions submitted by each user through the interactive interface; specifically, it can obtain the abnormal event data of each user through the data interface of the detection system; the detection system can be a third-party detection system, specifically a third-party resource detection system.

[0015] It should be noted that the above-mentioned operation of obtaining resource profile data of multiple users and obtaining abnormal event data of each user through the data interface of the detection system can be replaced by obtaining resource profile data of multiple users and abnormal event data of each user in the detection system; or it can be replaced by obtaining resource profile data of multiple users and abnormal event data of each user obtained by the detection system; or it can be replaced by obtaining resource profile data of multiple users and / or obtaining abnormal event data of each user through the data interface of the detection system; and combined with other processing steps provided in this embodiment to form a new implementation method.

[0016] Step S204: Perform a structured transformation on the resource profile data and abnormal event data of each user, input the structured dataset obtained by the transformation into the data parsing model for data parsing and parameter identification, and obtain the user processing parameters of each user.

[0017] The above-mentioned acquisition of resource profile data of multiple users and acquisition of abnormal event data of each user through the data interface of the detection system. In this step, the resource profile data and abnormal event data of each user are transformed into a structured form, and the structured dataset obtained by the transformation is input into the data parsing model for data parsing and parameter identification to obtain the user processing parameters of each user. This achieves data integration and improves the convenience and accuracy of the data parsing model in data parsing and parameter identification.

[0018] The structured dataset mentioned in this embodiment refers to the structured dataset of each user, that is, each user can have their own structured dataset. The structured dataset can be a collection of structured data. The user processing parameters can be user behavior parameters, specifically behavior confidence parameters. For example, the user processing parameters are the user's ability to eliminate anomalies in abnormal event data.

[0019] In practical implementation, to improve the readability and organization of each user's resource profile data and abnormal event data, the resource profile data and abnormal event data of each user can be structured to obtain structured datasets for each user. Specifically, the resource profile data and abnormal event data of each user can be cleaned, and the cleaned resource profile data and abnormal event data of each user can be fused according to data dimensions to obtain structured datasets for each user. In addition, the resource profile data of each user can be distributed to the corresponding distributed nodes for offline structured processing to obtain structured resource data for each user, and the abnormal event data of each user can be read in real time from the data partition for structured processing to obtain structured event data for each user. The structured resource data and structured event data can be merged to obtain structured datasets for each user. Distributed nodes can be distributed cluster nodes, and data partitions can be physical storage units, such as Kafka (distributed messaging system) partitions.

[0020] In the specific execution process, in order to improve the efficiency and accuracy of data parsing and parameter identification, a data parsing model can be introduced. This model uses structured datasets to enhance the comprehensiveness and effectiveness of the determined user processing parameters from multiple data dimensions. In one optional implementation method provided in this embodiment, the following operations are performed during the data parsing and parameter identification process: Multi-source feature distillation is performed on the structured dataset to obtain multi-source structured features, and the multi-source structured features are input into the encapsulation container for standard structure encapsulation to obtain standard user features; User processing parameters for each user are obtained by projecting user parameters based on standard user characteristics.

[0021] Among them, multi-source structured features can be feature vectors with multiple dimensions, such as user expenditure features and abnormal event features; standard user features can be feature vectors encapsulated using standard data structures; the encapsulation container can be a pre-built standard feature template, which can contain the field identifiers, data types, value ranges and / or units of standard user features.

[0022] Specifically, in the process of obtaining multi-source structured features by multi-source feature distillation of structured datasets, feature extraction can be performed on the structured datasets to obtain multi-source initial features, feature alignment can be performed on the multi-source initial features to obtain multi-source aligned features, feature pruning and / or noise reduction can be performed on the multi-source aligned features, and weighted fusion and feature compression can be performed on the pruned or denoised multi-source aligned features to obtain multi-source structured features.

[0023] Based on this, in an optional implementation of this embodiment, the following operations are performed during the process of obtaining user processing parameters for each user by projecting user parameters based on standard user characteristics: Standard user features are transformed from the initial semantic space to the behavioral feature space to obtain behavioral representation features; Behavioral confidence parameters for each user are calculated based on behavioral representation characteristics and used as user processing parameters.

[0024] In addition, in the process of obtaining user processing parameters for each user by projecting user parameters based on standard user characteristics, the standard user characteristics can also be input into a lightweight projection engine to project user parameters and obtain user processing parameters for each user.

[0025] Furthermore, in the process of inputting the structured dataset obtained from the transformation into the data parsing model for data parsing and parameter identification to obtain the user processing parameters of each user, the initial processing parameters of each user can be calculated based on the structured data in each user's structured dataset, and the initial processing parameters of each user can be weighted to obtain the user processing parameters of each user; for example, the initial processing parameters include income stability parameters, expenditure intensity parameters, credit assessment parameters and / or environmental risk parameters.

[0026] The data parsing model can be a machine learning model, and the model structure of the data parsing model can be LightGBM (Light Gradient Boosting Machine) or XGBoost (Extreme Gradient Boosting).

[0027] It should be noted that the above-mentioned operation of performing structured transformation on the resource profile data and abnormal event data of each user, and inputting the structured dataset obtained by transformation into the data parsing model for data parsing and parameter identification to obtain the user processing parameters of each user can be replaced by performing structured transformation on the resource profile data and / or abnormal event data of each user, and performing data parsing and parameter identification on the structured dataset obtained by transformation to obtain the user processing parameters of each user; and forming a new implementation method with other processing steps provided in this embodiment.

[0028] Step S206: The structured datasets of each user are fused using the anomaly processing engine, and the data anomaly processing parameters are mapped based on the fused user data, the user processing parameters, and the anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user.

[0029] The above-mentioned resource profile data and abnormal event data of each user are transformed into a structured form. The structured dataset obtained by the transformation is input into the data parsing model for data parsing and parameter identification to obtain the user processing parameters of each user. In this step, the structured dataset of each user is fused by the anomaly processing engine, and the data anomaly processing parameters are mapped based on the user fused data, user processing parameters and anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user. In this way, multiple selectable data anomaly processing parameter links are provided for the abnormal event data of each user.

[0030] The abnormal configuration parameters of the detection system described in this embodiment can be the configuration parameters set by the detection system for each user to handle abnormal event data, such as the abnormal configuration conditions set by the detection system for each user to handle abnormal event data. Specifically, the abnormal configuration parameters can be the resource return configuration parameters set for each user, such as the lower limit of the resource return ratio and / or the lower limit of the resource return duration.

[0031] Each of the multiple processing parameter links for each user can be a link composed of processing parameters for each user to perform data anomaly processing on abnormal event data; for example, the processing parameters that make up the processing parameter link include the reduction ratio of the amount of abnormal resources in the abnormal event data and / or the amount of resource return.

[0032] In specific implementation, to improve the effectiveness of data anomaly handling for abnormal event data of each user, this embodiment provides an optional implementation method. In the process of mapping processing parameters for data anomaly handling based on user fusion data, user processing parameters, and anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user, the user fusion data, user processing parameters, and anomaly configuration parameters are assembled into a data body. This data body is then written into an anomaly handling queue in memory. Based on the data body in the anomaly handling queue, the anomaly handling parameters for each abnormal event node in the abnormal event data are determined, and the links are assembled to obtain multiple processing parameter links for each user. Specifically, the following operations can be performed: The user fusion data, user processing parameters, and exception configuration parameters are assembled into a data body, which is then written into the exception handling queue in memory. Based on the data body in the exception handling queue, node collaborative parsing is performed on each exception event node in the exception event data to obtain the exception handling parameters of each exception event node; Link assembly based on anomaly handling parameters yields multiple processing parameter links for each user.

[0033] Among them, user fusion data can be user fusion data of individual users or global user fusion data, that is, it can be the overall user fusion data obtained by fusing user data from the structured datasets of all users; the data body can be a data package obtained by packaging user fusion data, user processing parameters, and abnormal configuration parameters; each abnormal event node in the abnormal event data can be an abnormal resource node of an abnormal resource event. For example, if the abnormal event data is overdue resource event data, then each abnormal event node includes the resource amount node of the overdue resource event, the return amount node of the scheduled resource return, and / or the resource return expenditure node; the abnormal handling parameters of each abnormal event node can be the abnormal handling parameters for abnormal handling at each abnormal event node. For example, the abnormal handling parameters of each abnormal event node include the resource reduction ratio of the resource amount node, the scheduled resource return amount of the return amount node, and / or the resource return expenditure amount of the resource return expenditure node. The resource return expenditure amount can be the expenditure amount of additional expenses incurred during the resource return process.

[0034] Based on this, in an optional implementation of this embodiment, during the process of obtaining the exception handling parameters of each exception event node by performing node collaborative parsing for each exception event node in the exception handling queue according to the data body in the exception handling queue, the following operations are performed: The data body is obtained from the exception handling queue by a distributed thread in the thread pool, and exception handling parameters are obtained by parsing each exception event node based on the data body within the data sandbox configured by the distributed thread.

[0035] This improves the efficiency of exception handling parameter determination by using distributed threads in the thread pool.

[0036] In practical applications, during the process of obtaining the exception handling parameters for each exception event node through node collaborative parsing in the exception event data, since the node parsing is performed by distributed threads, in order to improve the comprehensiveness and accuracy of the exception handling parameters for each exception event node, in an optional implementation of this embodiment, the following operation is also performed during the process of obtaining the exception handling parameters for each exception event node through node collaborative parsing based on the data body in the exception handling queue: Cross-verify the anomaly handling parameters for each abnormal event node; If the verification fails, incompatible parameters are identified in the anomaly handling parameters of each abnormal event node based on the pre-built parameter relationship graph, and the incompatible parameters are fine-tuned.

[0037] Incompatible parameters can be those exception handling parameters of each exception event node that are not compatible with each other or whose compatibility is lower than the compatibility threshold. The parameter relationship graph can be a parameter knowledge graph constructed based on the exception handling parameters of each exception event node. The parameter relationship graph can be a directed or undirected knowledge graph. Specifically, the nodes in the parameter relationship graph can represent the exception handling parameters of each exception event node, and the edges in the parameter relationship graph can represent the parameter relationships between the exception handling parameters of each exception event node. The parameter relationships can include compatibility relationships, mutual exclusion relationships, and dependency relationships. Incompatible parameters can be exception handling parameters of each exception event node whose number of mutual exclusion relationships with other exception handling parameters exceeds the number threshold.

[0038] Specifically, the cross-verification of the anomaly handling parameters of each anomaly event node can be used to verify whether the anomaly handling parameters of each anomaly event node are compatible. If they are compatible, the verification is deemed to have passed; if they are not compatible, the verification is deemed to have failed. The parameter relationships between the anomaly handling parameters of each anomaly event node in the parameter relationship graph can be determined based on the resource profile data of each user.

[0039] In addition, in the process of mapping the processing parameters for data anomaly handling based on the above-mentioned user fusion data, user processing parameters, and abnormal configuration parameters of the detection system to obtain multiple processing parameter links for each user, boundary conditions can be constructed based on the user processing parameters and abnormal configuration parameters of the detection system to obtain boundary conditions. Then, the processing parameter indicators under the boundary conditions are calculated based on the user fusion data, and multiple processing parameter links for each user are determined in the initial processing parameter links formed by the boundary conditions based on the processing parameter indicators.

[0040] In specific implementation, to meet the diverse needs of determining multiple processing parameter links for each user, in another optional implementation provided in this embodiment, the following operations are performed during the process of mapping data anomaly handling processing parameters based on user fusion data, user processing parameters, and anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user: A set of processing parameter links is generated based on user processing parameters and abnormal configuration parameters, and cross-operations are performed on the processing parameter links at specific link levels in the set of processing parameter links to obtain an intermediate set of processing parameter links. The merged parameter link set and the intermediate processing parameter link set are merged to obtain a merged parameter link set. Based on the user fusion data, parameter link matching is performed in the merged parameter link set to obtain multiple processing parameter links.

[0041] The processing parameter link set can be a set of links consisting of one or more processing parameter links for each user; the specific link level can be a specified link level. The link level of the processing parameter link can characterize the link quality of the processing parameter link in at least one dimension. At least one dimension can include the user rights dimension and / or the institutional rights dimension of the testing institution corresponding to the testing system, that is, the dimension of protecting user rights and / or the dimension of protecting the rights of the testing institution.

[0042] Specifically, in the process of generating a set of processing parameter links based on user processing parameters and exception configuration parameters, a set of processing parameter links that satisfies the user processing parameters and exception configuration parameters can be initialized. In the process of obtaining an intermediate set of processing parameter links by performing cross-operations on processing parameter links at specific link levels within the set of processing parameter links, the cross-operation probability of processing parameter links at link levels before the preset link level can be lowered, and the cross-operation probability of processing parameter links at link levels after the preset link level can be increased. Cross-operations on processing parameter links are performed according to the increased or decreased cross-operation probabilities to obtain an intermediate set of processing parameter links. In the process of performing cross-operations on processing parameter links according to the increased cross-operation probability, cross-operations can be performed on every two processing parameter links at link levels after the preset link level according to the increased cross-operation probability to obtain cross-processing parameter links, thus forming the subsequent set of intermediate processing parameter links. The cross-operation can be adaptive cross-operation, hybrid cross-operation, simulated binary cross-operation, and / or average cross-operation. For example, hybrid cross-operation includes randomly selecting simulated binary cross-operation and average cross-operation, with simulated binary cross-operation being SBX (Simulated Binary Crossover).

[0043] To improve the effectiveness of multiple processing parameter links for each user and to increase the efficiency of determining multiple processing parameter links, in an optional implementation of this embodiment, the following operations are performed during the process of obtaining multiple processing parameter links by matching parameter links in the merged parameter link set based on user fusion data: Calculate the parameter link metrics for each processing parameter link in the merged parameter link set based on the user fusion data, and determine the link level of each processing parameter link based on the parameter link metrics; If merging the parameter link set triggers the link extraction condition, the processing parameter link at the first link level is extracted from the merged parameter link set as multiple processing parameter links.

[0044] Among them, the parameter link index can be an indicator that represents the degree of protection of user rights and / or the degree of protection of the rights and interests of the testing agency after data anomaly processing using each processing parameter link; the link extraction condition for merging the parameter link set can include the number of calculations of the parameter link index for each processing parameter link exceeding the number threshold.

[0045] Specifically, in determining the link level of each processing parameter link based on the parameter link index, the number of links with a dominance relationship for each processing parameter link and / or the set of processing parameter links dominated by each processing parameter link can be determined based on the parameter link index, and the link level of each processing parameter link can be determined based on the number of links and / or the set of processing parameter links.

[0046] It should be noted that the above-mentioned operation of fusing user data in the structured datasets of each user through the anomaly processing engine, and mapping the processing parameters for data anomaly processing based on the fused user data, user processing parameters, and anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user can be replaced by mapping the processing parameters for data anomaly processing based on the structured datasets of each user, user processing parameters, and anomaly configuration parameters of the detection system through the anomaly processing engine to obtain multiple processing parameter links for each user, and combining this with other processing steps provided in this embodiment to form a new implementation method.

[0047] Step S208: Based on preset bias parameters, parameter link filtering is performed on multiple processing parameter links of each user to obtain the target processing parameter link of each user for data anomaly processing of the abnormal event data.

[0048] The above-mentioned anomaly processing engine performs user data fusion on the structured datasets of each user, and performs data anomaly processing parameter mapping based on the user fused data, user processing parameters, and anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user. In this step, parameter links are filtered in multiple processing parameter links for each user based on preset bias parameters to obtain the target processing parameter links for each user, which are used for data anomaly processing of abnormal event data.

[0049] The preset bias parameter mentioned in this embodiment refers to a pre-set bias parameter. The preset bias parameter can be a bias parameter that represents the degree of tendency to protect the rights and interests of each user and the detection system, that is, a bias parameter that represents the tendency to protect the rights and interests of users or the rights and interests of the detection agency corresponding to the detection system; the preset bias parameter can be a preset bias weight.

[0050] In specific implementation, to improve the comprehensiveness of the preset bias parameters, in one optional implementation of this embodiment, the preset bias parameters are calculated based on the abnormal bias data uploaded by each user and the detection system through the interactive interface. The calculation is performed after the abnormal bias data uploaded by each user and the detection system through the interactive interface has passed signature verification. Specifically, the preset bias parameters can be obtained in the following way: Obtain the abnormal bias data uploaded by each user and the detection system through the interactive interface; optionally, the abnormal bias data is obtained by signing the initial bias data. After the signature verification of the abnormal bias data is passed, the bias weight is calculated based on the abnormal bias data to obtain the abnormal bias weight for each user.

[0051] The initial bias data uploaded by each user can be supporting evidence materials showing that the preset bias parameters are biased towards each user; the initial bias data uploaded by the detection system can be supporting evidence materials showing that the preset bias parameters are biased towards the detection system.

[0052] Specifically, in the process of calculating the bias weights for each user based on the abnormal bias data, the initial bias parameters can be calculated separately based on the abnormal bias data, and the mean of the initial bias parameters can be used as the abnormal bias weights for each user.

[0053] In practical applications, since there are multiple processing parameter links for each user, in order to improve the effectiveness of the determined target processing parameter links for each user and ensure that each user's resource rights are protected when handling data anomalies according to the target processing parameter links, the following operation is performed in an optional implementation of this embodiment during the process of filtering parameter links from multiple processing parameter links for each user based on preset bias parameters to obtain the target processing parameter links for each user: Based on the anomaly bias weight and the anomaly processing parameters of each anomaly event node contained in multiple processing parameter links, the link metrics of each processing parameter link are calculated to obtain the link metrics. The target processing parameter link is determined from multiple processing parameter links based on the link metrics.

[0054] Among them, the link index can be an indicator that characterizes the quality of each processing parameter link, specifically a utility value.

[0055] Specifically, in the process of calculating link metrics for each processing parameter link based on the anomaly bias weight and the anomaly handling parameters of each anomaly event node included in multiple processing parameter links, the first link metric and the second link metric of each processing parameter link can be calculated according to the anomaly handling parameters of each anomaly event node included in multiple processing parameter links. The link metrics are then calculated based on the first link metric, the second link metric, and the anomaly bias weight. In the process of determining the target processing parameter link among multiple processing parameter links based on the link metrics, the multiple processing parameter links can be sorted according to the link metrics, and the processing parameter link whose sorting position is before the preset position in the sorting result can be determined as the target processing parameter link. Here, the first link metric can be the resource intensity of each user under each processing parameter link, specifically the resource return intensity; the second link metric can be the resource recovery rate of the detection system under each processing parameter link.

[0056] After obtaining the target processing parameter links for each user, these links can be pushed to users via SMS, applications, and / or email. Each user can edit the target processing parameter links. Alternatively, a structured file can be generated based on each user's target processing parameter links. The signature interface of the detection system can then be used to digitally sign the structured file. The signed structured file is then pushed to each user for signature. The signed structured file is then hashed to obtain a hash value, which is submitted to a third-party evidence storage platform for evidence storage.

[0057] In specific implementation, in order to improve the processing efficiency of each user in resource processing and to urge each user to process resources, in an optional implementation of this embodiment, after filtering the parameter links in multiple processing parameter links of each user based on preset bias parameters to obtain the target processing parameter link execution for each user, the following operations are also performed: Resource processing data for user groups within a geographic region is obtained based on the geographic region where each user is located; Resource processing reports are generated based on resource processing data and then pushed to various users.

[0058] Among them, resource processing data can be resource return data.

[0059] In one optional implementation of this embodiment, after filtering the parameter links in multiple processing parameter links for each user based on preset bias parameters to obtain the target processing parameter link execution for each user, the following operations are also performed: Detect abnormal response data from each user to abnormal event data; Determine whether the abnormal response data matches the current accounting data of each user. If they do not match, change the abnormal handling parameters of the abnormal event nodes in the target processing parameter chain that do not match.

[0060] Among them, the abnormal response data can be the resource return data of each user in response to abnormal resource event data; whether the abnormal response data matches the current accounting data of each user can be whether the resource return data matches the current income data of each user.

[0061] After filtering the parameter links in multiple processing parameter links for each user based on preset bias parameters and obtaining the target processing parameter link execution for each user, the abnormal event data of each user can also be detected as having a data anomaly processing status. If the data anomaly processing status is cleared, a reminder message indicating that the data anomaly processing is complete can be generated and pushed to each user.

[0062] In practical applications, after obtaining the target processing parameter links for each user, to ensure legal execution according to the target processing parameter links, resource files can be constructed based on the target processing parameter links of each user to obtain the resource files for each user and sent to the detection system. The signed resource files after electronic signature processing, which are returned by the detection system, are then distributed to the user terminals of each user. Specifically, in an optional implementation of this embodiment, after filtering the parameter links in multiple processing parameter links of each user based on preset bias parameters to obtain the target processing parameter links for each user, the following operations are also performed: Based on the target processing parameter link of each user, resource files are constructed, and the resource files of each user are obtained and sent to the detection system through the file interface of the detection system. The system receives the electronically signed resource file returned by the detection system via a file interface and then distributes the signed resource file to each user's terminal.

[0063] To meet the editing needs of various users for the signature resource file and to flexibly incorporate the requirements of each user for the signature resource file, in one optional implementation of this embodiment, after the signature resource file is distributed to each user's terminal for execution, the following operations are also performed: Obtain the edited resource content obtained by editing the signature resource file corresponding to any user submitted by any user's user terminal; The detection interface of the detection system is called to perform content verification on the edited resource content. After the verification is passed, the signature resource file corresponding to any user is updated based on the edited resource content to obtain the edited resource file and then distributed to any user.

[0064] Specifically, during the content verification process for edited resources, it is possible to verify whether the edited resource content is correct. If it is correct, the verification is deemed successful. And / or it is possible to verify whether the edited resource content conforms to the resource policy of the corresponding testing agency of the testing system. If it does, the verification is deemed successful.

[0065] It should be noted that the user data obtained in this manual, such as user resource profile data and abnormal event data, has been authorized by the user and does not involve user privacy.

[0066] It should be added that each optional implementation method and each feasible execution method in steps S202 to S208 provided in this embodiment can be executed independently as needed, or they can be combined and referenced with each other. At the same time, each specific execution step in each optional implementation method or each feasible execution method can also be executed independently or combined as needed. The execution conditions of "if" or "under what circumstances" involved in each step or operation can be directly deleted, and subsequent operations can be executed. The limitation of "with" involved in each step or operation can also be deleted. This embodiment does not make specific limitations in this regard.

[0067] It should also be added that, depending on the actual application scenario, step S202 and any of the subsequent steps S204 to S208 can be deleted, or any feature in any step can be deleted. For example, "through the data interface of the detection system" in step S202 can be deleted, and the execution order of steps S202 to S208 can also be arbitrary.

[0068] The following description uses the application of a data processing method provided in this embodiment in a resource scenario as an example to further illustrate the data processing method provided in this embodiment. (See also...) Figure 3 The data processing method applied to resource scenarios includes the following steps.

[0069] Step S302: Obtain resource profile data of multiple users and obtain abnormal resource data of each user through the data interface of the detection system.

[0070] Step S304: Perform a structured transformation on the resource profile data and abnormal event data of each user, and input the structured dataset obtained from the transformation into the data parsing model.

[0071] Step S306: Multi-source structured features are obtained by performing multi-source feature distillation on the structured dataset through a data parsing model. The multi-source structured features are then input into a packaging container for standard structure packaging to obtain standard user features. User parameters are then projected based on the standard user features to obtain user processing parameters for each user.

[0072] Step S308: Perform user data fusion on the structured datasets of each user through the exception handling engine.

[0073] Step S310: The anomaly handling engine performs data anomaly handling parameter mapping based on user fused data, user processing parameters, and anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user.

[0074] Step S312: Based on the abnormal bias weight and the abnormal processing parameters of each abnormal event node contained in multiple processing parameter links, calculate the link index of each processing parameter link to obtain the link index.

[0075] Step S314: Determine the target processing parameter link for each user among multiple processing parameter links based on the link indicators, so as to perform data anomaly processing for abnormal event data.

[0076] It should be noted that any one or more of steps S302 to S314 can be replaced by the corresponding technical means provided in steps S202 to S208 as needed for implementation and deployment. Any one or more of steps S302 to S314 can also be combined into a new implementation method as needed for implementation and deployment. Furthermore, any one or more of steps S302 to S314 can also be combined with one or more of the steps provided in steps S202 to S208 to form a new implementation method, or combined with one or more of the optional implementation methods provided in steps S202 to S208 to form a new implementation method, as needed for actual deployment. These will not be elaborated on here.

[0077] The following is an embodiment of a data processing device provided in this specification: In the above embodiments, a data processing method is provided, and correspondingly, a data processing device is also provided, which will be described below with reference to the accompanying drawings.

[0078] Reference Figure 4 This illustration shows a schematic diagram of an embodiment of a data processing device provided in this embodiment.

[0079] Since the apparatus embodiments correspond to the method embodiments, the descriptions are relatively simple. For relevant parts, please refer to the corresponding descriptions of the method embodiments provided above. The apparatus embodiments described below are merely illustrative.

[0080] This embodiment provides a data processing apparatus, including: The data acquisition module 402 is configured to acquire resource profile data of multiple users and acquire abnormal event data of each user through the data interface of the detection system; The data parsing module 404 is configured to perform structured transformation on the resource profile data and abnormal event data of each user, input the structured dataset obtained by transformation into the data parsing model for data parsing and parameter identification, and obtain the user processing parameters of each user. The parameter mapping module 406 is configured to perform user data fusion on the structured datasets of each user through the anomaly processing engine, and perform data anomaly processing parameter mapping based on the user fused data, the user processing parameters, and the anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user. The parameter filtering module 408 is configured to filter parameter links in multiple processing parameter links of each user based on preset bias parameters to obtain the target processing parameter links of each user for data anomaly processing of the abnormal event data.

[0081] For ease of description, the above devices are described by dividing them into various modules or units based on their functions. Of course, when implementing one or more of these specifications, the functions of each module or unit can be implemented in the same or different software and / or hardware, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0082] The following is an embodiment of a data processing device provided in this specification: Corresponding to the data processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a data processing apparatus for performing the data processing method provided above. Figure 5 This is a schematic diagram of the structure of a data processing device provided for one or more embodiments of this specification.

[0083] This embodiment provides a data processing device, including: like Figure 5As shown, device 500 mainly consists of a communication interface 502, a user interface 504, a processor 506, and a data storage 508. These components are interconnected and communicate with each other via a system bus, network, or other connection mechanism 510. The communication interface 502 enables device 500 to communicate with other devices, access networks, and transmission networks via analog or digital modulation. For example, the communication interface 502 may include a chipset and antenna for wireless communication with a radio access network or access point. Furthermore, the communication interface 502 can be a wired interface such as Ethernet, Token Ring, or a USB port, or a wireless interface such as Wi-Fi, Bluetooth, Global Positioning System (GPS), or a wide-area wireless interface (e.g., WiMAX or LTE). Of course, the communication interface 502 can also support other forms of physical layer interfaces and standard or proprietary communication protocols. The communication interface 502 may also include multiple physical communication interfaces, such as Wi-Fi, Bluetooth, and wide-area wireless interfaces. The user interface 504 includes receiving user input and providing output to the user. Therefore, user interface 504 may include input components such as a keypad, keyboard, touch-sensitive or presence-sensitive panel, computer mouse, trackball, joystick, microphone, still camera, and video camera, and output components such as a display screen (which may be combined with a touch-sensitive panel), CRT, LCD, LED, display using DLP technology, printer, and other similar devices known or developed in the future. User interface 504 may also generate auditory output via speakers, speaker jacks, audio output ports, audio output devices, headphones, and other similar devices known or developed in the future. In some embodiments, user interface 504 may include software, circuitry, or other forms of logic capable of transmitting and receiving data to and from external user input / output devices. Additionally or alternatively, device 500 may support remote access from other devices via communication interface 502 or another physical interface (not shown). User interface 504 may be configured to receive user input, the position and movement of which may be indicated by indicators or cursors described herein. User interface 504 may also be configured as a display device for rendering or displaying text fragments.

[0084] Processor 506 may include one or more general-purpose processors and / or special-purpose processors. Data storage 508 may include one or more volatile and / or non-volatile storage components and may be integrated wholly or partially with processor 506. Data storage 508 may include removable and non-removable components.

[0085] Processor 506 is capable of executing program instructions 518 (e.g., compiled or uncompiled program logic and / or machine code) stored in data storage 508 to perform the various functions described herein. Data storage 508 may contain a non-transitory computer-readable medium on which program instructions are stored, which, when executed by device 500, enable device 500 to perform any methods, processes, or functions disclosed in this specification and / or the accompanying drawings. Execution of program instructions 518 by processor 506 may result in processor 506 using data 512. For example, program instructions 518 may include an operating system 522 (e.g., an operating system kernel, device drivers, and / or other modules) installed on device 500 and one or more application programs 520 (e.g., a browser, social application, or game application). Similarly, data 512 may include operating system data 516 and application data 514. Operating system data 516 is primarily accessible to operating system 522, while application data 514 is primarily accessible to one or more application programs 520. Application data 514 may reside in a file system visible or hidden from the user of device 500. Application 520 can communicate with operating system 522 through one or more application programming interfaces (APIs). These APIs facilitate application 520 in reading and / or writing application data 514, transmitting or receiving information via communication interface 502, and receiving or displaying information on user interface 504. In some terms, application 520 may be simply referred to as "app". Furthermore, application 520 can be downloaded to device 500 through one or more online app stores or app markets. However, applications can also be installed on device 500 in other ways, such as through a web browser or a physical interface on device 500 (e.g., a USB port).

[0086] In one specific embodiment, the data processing device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the data processing device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following: Acquire resource profile data of multiple users and obtain abnormal event data of each user through the data interface of the detection system; The resource profile data and abnormal event data of each user are transformed into a structured data. The structured dataset obtained by the transformation is then input into a data parsing model for data parsing and parameter identification to obtain the user processing parameters of each user. The structured datasets of each user are fused using an anomaly processing engine, and the data anomaly processing parameters are mapped based on the fused user data, the user processing parameters, and the anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user. Based on preset bias parameters, parameter links are filtered in multiple processing parameter links of each user to obtain the target processing parameter links of each user for data anomaly processing of the abnormal event data.

[0087] This specification provides an embodiment of a computer-readable storage medium as follows: Corresponding to the data processing method described above, and based on the same technical concept, one or more embodiments of this specification also provide a computer-readable storage medium.

[0088] The computer-readable storage medium provided in this embodiment is used to store computer-executable instructions, which, when executed, perform the following steps: Acquire resource profile data of multiple users and obtain abnormal event data of each user through the data interface of the detection system; The resource profile data and abnormal event data of each user are transformed into a structured data. The structured dataset obtained by the transformation is then input into a data parsing model for data parsing and parameter identification to obtain the user processing parameters of each user. The structured datasets of each user are fused using an anomaly processing engine, and the data anomaly processing parameters are mapped based on the fused user data, the user processing parameters, and the anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user. Based on preset bias parameters, parameter links are filtered in multiple processing parameter links of each user to obtain the target processing parameter links of each user for data anomaly processing of the abnormal event data.

[0089] It should be noted that the embodiments of a computer-readable storage medium described in this specification and the embodiments of a data processing method described in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0090] This specification provides an example of a computer program product as follows: Corresponding to the data processing method described above, and based on the same technical concept, one or more embodiments of this specification also provide a computer program product.

[0091] A computer program product includes a computer program / instructions that, when executed by a processor, perform the following steps: Acquire resource profile data of multiple users and obtain abnormal event data of each user through the data interface of the detection system; The resource profile data and abnormal event data of each user are transformed into a structured data. The structured dataset obtained by the transformation is then input into a data parsing model for data parsing and parameter identification to obtain the user processing parameters of each user. The structured datasets of each user are fused using an anomaly processing engine, and the data anomaly processing parameters are mapped based on the fused user data, the user processing parameters, and the anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user. Based on preset bias parameters, parameter links are filtered in multiple processing parameter links of each user to obtain the target processing parameter links of each user for data anomaly processing of the abnormal event data.

[0092] It should be noted that the embodiments of a computer program product described in this specification and the embodiments of a data processing method described in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0093] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments. For example, the device embodiment, equipment embodiment and computer-readable storage medium embodiment are all similar to the method embodiment, so the description is relatively simple. When reading the relevant content of the device embodiment, equipment embodiment and computer-readable storage medium embodiment, please refer to the description of the method embodiment.

[0094] Although one or more embodiments of this specification provide method steps as described in the embodiments or flowcharts, it is understood that the order of steps listed in the embodiments or flowcharts is only one of many possible execution orders and does not represent the only execution order. Therefore, when the claims involve method steps, any changes or adjustments to the order of such steps, or the parallelism between steps, are also within the scope of protection of the claims.

[0095] This specification uses specific terms to describe embodiments thereof. Terms such as "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Furthermore, those skilled in the art can combine and integrate the different embodiments or examples described herein, as well as the features of those different embodiments or examples, without contradiction.

[0096] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0097] In the 1930s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many improvements to the methodology today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that an improvement to the methodology cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0098] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0099] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0100] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0101] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, system, or computer program product. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable test processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable test processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0103] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable test processing equipment to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0104] These computer program instructions can also be loaded onto a computer or other programmable test processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0105] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0106] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0107] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0108] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of features includes not only those features but also other features not expressly listed, or features inherent to such process, method, article, or apparatus. Without further limitations, a feature defined by the phrase "comprising one..." does not exclude the presence of other identical features in the process, method, article, or apparatus that includes said feature.

[0109] One or more embodiments of this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a particular task or implement a particular abstract data type. One or more embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0110] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0111] The above description is merely an embodiment of this document and is not intended to limit the scope of this document. Various modifications and variations can be made to this document by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this document should be included within the scope of the claims of this document.

Claims

1. A data processing method, comprising: Acquire resource profile data of multiple users and obtain abnormal event data of each user through the data interface of the detection system; The resource profile data and abnormal event data of each user are transformed into a structured data. The structured dataset obtained by the transformation is then input into a data parsing model for data parsing and parameter identification to obtain the user processing parameters of each user. The structured datasets of each user are fused using an anomaly processing engine, and the data anomaly processing parameters are mapped based on the fused user data, the user processing parameters, and the anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user. Based on preset bias parameters, parameter links are filtered in multiple processing parameter links of each user to obtain the target processing parameter links of each user for data anomaly processing of the abnormal event data.

2. The data processing method according to claim 1, after the step of filtering the parameter links in the multiple processing parameter links of each user based on a preset bias parameter to obtain the target processing parameter link operation execution for each user, further includes: Based on the target processing parameter links of each user, resource files are constructed, the resource files of each user are obtained, and they are sent to the detection system through the file interface of the detection system. The system receives the electronically signed resource file returned by the detection system through the file interface, and then distributes the signed resource file to the user terminals of each user.

3. The data processing method according to claim 2, after the step of distributing the signature resource file to the user terminals of each user is executed, further includes: Obtain edited resource content by editing the signature resource file corresponding to any user submitted by any user's user terminal; The detection interface of the detection system is invoked to perform content verification on the edited resource content. After the verification is passed, the signature resource file corresponding to any user is updated based on the edited resource content, the edited resource file is obtained, and it is sent to any user.

4. The data processing method according to claim 1, wherein the preset bias parameter is obtained in the following manner: Obtain the abnormal bias data uploaded by each user and the detection system through their respective interactive interfaces; the abnormal bias data is obtained by signing the initial bias data. After the signature verification of the abnormal bias data is passed, the bias weight is calculated based on the abnormal bias data to obtain the abnormal bias weight for each user.

5. The data processing method according to claim 4, wherein the step of filtering parameter links in multiple processing parameter links of each user based on a preset bias parameter to obtain the target processing parameter link of each user includes: Based on the abnormal bias weight and the abnormal processing parameters of each abnormal event node included in the multiple processing parameter links, the link index of each processing parameter link is calculated to obtain the link index. The target processing parameter link is determined from among the multiple processing parameter links based on the link metrics.

6. The data processing method according to claim 1, wherein the data parsing and parameter identification are performed in the following manner: Multi-source feature distillation is performed on the structured dataset to obtain multi-source structured features, and the multi-source structured features are input into a packaging container for standard structure packaging to obtain standard user features; User processing parameters for each user are obtained by projecting user parameters based on the standard user characteristics.

7. The data processing method according to claim 6, wherein obtaining the user processing parameters of each user by projecting user parameters based on the standard user characteristics includes: The standard user features are transformed from the initial semantic space to the behavioral feature space to obtain behavioral representation features; The behavioral confidence parameters of each user are calculated based on the behavioral representation features and used as the user processing parameters.

8. The data processing method according to claim 1, wherein the step of mapping the processing parameters for data anomaly handling based on user fusion data and the user processing parameters and the anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user includes: The user fusion data, the user processing parameters, and the exception configuration parameters are assembled into a data body, which is then written into the exception handling queue in memory. Based on the data body in the exception handling queue, node collaborative parsing is performed on each exception event node in the exception event data to obtain the exception handling parameters of each exception event node. Based on the anomaly handling parameters, link assembly is performed to obtain multiple processing parameter links for each user.

9. The data processing method according to claim 8, wherein the step of obtaining the exception handling parameters of each exception event node by performing node collaborative parsing for each exception event node in the exception handling queue based on the data body in the exception handling queue includes: The data body is obtained from the exception handling queue by a distributed thread in the thread pool, and the exception handling parameters are obtained by performing exception parsing on each exception event node based on the data body within the data sandbox configured by the distributed thread.

10. The data processing method according to claim 9, wherein the step of obtaining the exception handling parameters of each exception event node by performing node collaborative parsing for each exception event node in the exception handling queue based on the data body in the exception handling queue further includes: Cross-verify the anomaly handling parameters for each of the aforementioned abnormal event nodes; If the verification fails, incompatible parameters are identified in the anomaly handling parameters of each abnormal event node based on the pre-constructed parameter relationship graph, and the incompatible parameters are fine-tuned.

11. The data processing method according to claim 1, further comprising, after performing parameter link filtering on multiple processing parameter links of each user based on a preset bias parameter to obtain the target processing parameter link operation execution for each user: Resource processing data of user groups within the geographical region where each user is located is obtained; Based on the resource processing data, a resource processing report is constructed and pushed to each user.

12. The data processing method according to claim 1, further comprising, after performing parameter link filtering on multiple processing parameter links of each user based on a preset bias parameter to obtain the target processing parameter link operation for each user, the method further comprises: Detect abnormal response data from each user in response to the abnormal event data; Determine whether the abnormal response data matches the current account data of each user. If they do not match, change the abnormal handling parameters of the abnormal event nodes that do not match in the target processing parameter chain.

13. The data processing method according to claim 1, wherein the step of mapping the processing parameters for data anomaly handling based on user fusion data and the user processing parameters and the anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user includes: A processing parameter link set is generated based on the user processing parameters and the abnormal configuration parameters, and cross-operations are performed on the processing parameter links at a specific link level in the processing parameter link set to obtain an intermediate processing parameter link set. The processing parameter link set and the intermediate processing parameter link set are merged to obtain a merged parameter link set, and the multiple processing parameter links are obtained by matching the parameter links in the merged parameter link set based on the user fusion data.

14. The data processing method according to claim 13, wherein obtaining the plurality of processing parameter links by matching parameter links in the merged parameter link set based on the user fusion data includes: Calculate the parameter link index for each processing parameter link in the merged parameter link set based on the user fusion data, and determine the link level of each processing parameter link based on the parameter link index; If the merged parameter link set triggers the link extraction condition, the processing parameter link at the first link level is extracted from the merged parameter link set as the plurality of processing parameter links.

15. A data processing apparatus, comprising: The data acquisition module is configured to acquire resource profile data of multiple users and acquire abnormal event data of each user through the data interface of the detection system; The data parsing module is configured to perform structured transformation on the resource profile data and abnormal event data of each user, input the structured dataset obtained by transformation into the data parsing model for data parsing and parameter identification, and obtain the user processing parameters of each user. The parameter mapping module is configured to perform user data fusion on the structured datasets of each user through the anomaly processing engine, and perform data anomaly processing parameter mapping based on the user fused data, the user processing parameters, and the anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user. The parameter filtering module is configured to filter parameter links in multiple processing parameter links of each user based on preset bias parameters to obtain the target processing parameter links of each user for data anomaly processing of the abnormal event data.

16. A data processing apparatus, comprising: processor; And, a memory configured to store computer-executable instructions, which, when executed, cause the processor to: Acquire resource profile data of multiple users and obtain abnormal event data of each user through the data interface of the detection system; The resource profile data and abnormal event data of each user are transformed into a structured data. The structured dataset obtained by the transformation is then input into a data parsing model for data parsing and parameter identification to obtain the user processing parameters of each user. The structured datasets of each user are fused using an anomaly processing engine, and the data anomaly processing parameters are mapped based on the fused user data, the user processing parameters, and the anomaly configuration parameters of the detection system to obtain multiple processing parameter links for each user. Based on preset bias parameters, parameter links are filtered in multiple processing parameter links of each user to obtain the target processing parameter links of each user for data anomaly processing of the abnormal event data.

17. A computer-readable storage medium for storing computer-executable instructions that, when executed, implement the steps of the method of claim 1.

Images