Regulatory reporting method, apparatus, storage medium, and device

Abstract

The application discloses a kind of supervision sending method, device, storage medium and equipment, the method is: to be handled data is input into automation model, obtain first result;Operation command is input into visual model, obtain second result;Based on the job shown in first result, the job shown in second result, form job set;Adjust the execution order of each job in job set, and the data volume of each job, so that the execution time sum of each job is less than preset sending time threshold value;The execution order finally adjusted is identified as optimal execution order;According to optimal execution order, each job is executed in turn.The method adjusts the execution order of each job and data volume, so that the execution time sum of each job is less than preset sending time threshold value, obtains the optimal execution order of each job, and each job is executed according to optimal execution order, so that supervision sending time is reduced, and the timeliness of supervision sending is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of regulatory reporting, and in particular to a regulatory reporting method and device, a storage medium and equipment. BACKGROUND

[0002] With the extensive development of banking business, various business systems are also managed. In order to meet the relevant regulatory requirements, a unified regulatory reporting system automatically reports each regulatory subject (such as financial data, etc.). With the continuous improvement of the regulatory system by the relevant regulatory departments of the banking industry, the requirements related to regulatory reporting are gradually increasing. On the other hand, the regulatory reporting requires strict time points, and the business analysis, related business system data screening, and reporting interface supporting work must be completed within a limited time.

[0003] At present, the existing regulatory reporting system mainly adopts an automatic reporting mode, striving to minimize human intervention or achieve the highest data accuracy. However, the automatic reporting mode adopted by the existing regulatory reporting system has the following disadvantages: low performance and poor timeliness. Specifically, the parameters of the current regulatory reporting system are set by humans and are severely limited by the experience of developers. For systems with large differences in reporting data volume, the server performance cannot be effectively used, which affects the timeliness of large batch data reporting, i.e., prolongs the regulatory reporting time.

[0004] Therefore, how to improve the timeliness of regulatory reporting has become a problem to be solved in the field. SUMMARY

[0005] The present application provides a regulatory reporting method, device, storage medium and equipment, aiming to improve the timeliness of regulatory reporting.

[0006] In order to achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0007] A regulatory reporting method, comprising:

[0008] After obtaining the user inputted to-be-processed data, inputting the to-be-processed data into an automatic model to obtain a first result output by the automatic model; the automatic model is pre-constructed based on an automatic reporting process of a regulatory reporting system; the first result comprises a job corresponding to a data processing process of the to-be-processed data;

[0009] After obtaining the user inputted operation command, inputting the operation command into a visualization model to obtain a second result output by the visualization model; the visualization model is pre-constructed based on a business scenario of the regulatory reporting system; the second result comprises a job corresponding to a visualization function shown by the operation command;

[0010] assembling a job set based on the jobs shown in the first result and the jobs shown in the second result;

[0011] adjusting execution orders of the jobs in the job set and data volumes of each job in the job set, so that a total execution time of the jobs in the job set is less than a preset submission time threshold;

[0012] identifying the execution order finally adjusted as an optimal execution order;

[0013] executing the jobs in the job set in sequence according to the optimal execution order.

[0014] Optionally, the adjusting of the execution orders of the jobs in the job set and the data volumes of each job in the job set, so that the total execution time of the jobs in the job set is less than the preset submission time threshold, comprises:

[0015] substituting the execution orders of the jobs in the job set and the data volumes of each job in the job set into a preset submission model to obtain an output result of the submission model; the output result comprises the total execution time of the jobs in the job set;

[0016] adjusting the execution orders and the data volumes by using a loss function, so that the total execution time of the jobs in the job set is less than the preset submission time threshold.

[0017] Optionally, the process of constructing the submission model comprises:

[0018] pre-acquiring sample data; the sample data comprises sample execution orders of each sample job, sample data volumes of each sample job, and sample total execution times of each sample job;

[0019] training, by using a loss function, the independent variables and the dependent variables based on the sample execution orders of each sample job, the sample data volumes of each sample job as the independent variables, and the sample total execution times of each sample job as the dependent variables, to obtain the submission model.

[0020] Optionally, after the identifying of the execution order finally adjusted as the optimal execution order, the method further comprises:

[0021] identifying the data volume finally adjusted as an optimal data volume;

[0022] allocating the optimal data volume to each job in the job set according to a preset paging strategy.

[0023] A supervisory submission device comprises:

[0024] An automatic operation unit is configured to input the to-be-processed data into an automatic model after obtaining the to-be-processed data input by a user, to obtain a first result output by the automatic model; the automatic model is pre-constructed based on an automatic reporting process of a regulatory reporting system; and the first result includes operations corresponding to a data processing process of the to-be-processed data.

[0025] A visualization operation unit is configured to input the operation command into a visualization model after obtaining the operation command input by the user, to obtain a second result output by the visualization model; the visualization model is pre-constructed based on a business scenario of the regulatory reporting system; and the second result includes operations corresponding to a visualization function indicated by the operation command.

[0026] A set building unit is configured to build a set of operations based on the operations indicated by the first result and the operations indicated by the second result.

[0027] An adjusting unit is configured to adjust an execution order of each operation in the set of operations and a data volume of each operation in the set of operations, so that a total execution time of each operation in the set of operations is less than a preset reporting time threshold.

[0028] An identifying unit is configured to identify the execution order obtained after the final adjustment as an optimal execution order.

[0029] An operation execution unit is configured to execute each operation in the set of operations in sequence according to the optimal execution order.

[0030] Optionally, the adjusting unit is specifically configured to:

[0031] substitute the execution order of each operation in the set of operations and the data volume of each operation in the set of operations into a pre-constructed reporting model, to obtain an output result of the reporting model; and the output result includes a total execution time of each operation in the set of operations.

[0032] adjust the execution order and the data volume by using a loss function, so that the total execution time of each operation in the set of operations is less than the preset reporting time threshold.

[0033] Optionally, the adjusting unit is specifically configured to:

[0034] pre-obtain sample data; the sample data includes a sample execution order of each sample operation, a sample data volume of each sample operation, and a sample total execution time of each sample operation.

[0035] The loss function is used to train the independent variable and the dependent variable based on the sample execution sequence of each sample job, the sample data volume of each sample job as the independent variable, and the sample execution time sum of each sample job as the dependent variable, to obtain the reporting model.

[0036] Optionally, the method further comprises a distribution unit.

[0037] The distribution unit is specifically configured to: identify the final adjusted data volume as an optimal data volume; and distribute the optimal data volume to each job in the job set according to a preset paging strategy.

[0038] A computer-readable storage medium comprises a stored program, wherein the program executes the monitoring and reporting method.

[0039] A monitoring and reporting device comprises a processor, a memory and a bus, wherein the processor is connected to the memory through the bus.

[0040] The memory is configured to store a program, and the processor is configured to run the program, wherein the program runs to execute the monitoring and reporting method.

[0041] The technical solution provided in the present application comprises the following steps: after obtaining user inputted to-be-processed data, inputting the to-be-processed data into an automatic model to obtain a first result outputted by the automatic model; after obtaining a user inputted operation command, inputting the operation command into a visual model to obtain a second result outputted by the visual model; based on jobs shown in the first result and jobs shown in the second result, assembling a job set; adjusting the execution sequence of each job in the job set and the data volume of each job to make the execution time sum of each job less than a preset reporting time threshold; identifying the final adjusted execution sequence as an optimal execution sequence; and executing each job in the job set in sequence according to the optimal execution sequence. By adjusting the execution sequence and the data volume of each job to make the execution time sum of each job less than the preset reporting time threshold, the optimal execution sequence of each job is obtained, and each job is executed according to the optimal execution sequence, so that the monitoring and reporting time is reduced and the timeliness of monitoring and reporting is improved. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0043] Figure 1a A flowchart illustrating a regulatory reporting method provided in an embodiment of this application;

[0044] Figure 1b A schematic diagram of data status provided in an embodiment of this application;

[0045] Figure 2 A flowchart illustrating another regulatory reporting method provided in this application embodiment;

[0046] Figure 3 This is a schematic diagram of the architecture of a regulatory reporting device provided in an embodiment of this application. Detailed Implementation

[0047] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0048] It should be noted that, in addition to its poor timeliness, the existing regulatory reporting methods also have the following drawbacks:

[0049] 1. Low reporting efficiency: Specifically, business personnel are unaware of the mechanisms of the regulatory reporting system. When problems arise during reporting, it is difficult to quickly locate the issues. Business personnel will spend a lot of time and energy on repetitive and simple tasks, which greatly reduces reporting efficiency.

[0050] 2. The lack of visual operation and excessive reliance on automation will make the regulatory reporting system a black box for business personnel.

[0051] 3. Lack of data management: Specifically, it is difficult to accurately grasp the data lifecycle. All operations are batch-based, but the similarity and differences of the data are not intuitively displayed, and the flow of data is not accurately presented, thus failing to maximize the value of the data.

[0052] Therefore, based on the above-mentioned shortcomings, this application provides a regulatory reporting method to improve the timeliness of regulatory reporting while improving reporting efficiency, enabling visual operation, achieving effective data management.

[0053] like Figure 1a The diagram shown is a flowchart illustrating a regulatory reporting method provided in an embodiment of this application, applied to a regulatory reporting system, and includes the following steps:

[0054] S101: Construct an automation model in advance based on an automation reporting process of a regulatory reporting system.

[0055] The automation reporting process of the regulatory reporting system includes a plurality of data processing processes, and each data processing process includes a data loading process, a data verification process, a message sending process, a receipt analysis process, and an error supplement reporting process. The automation model is used to generate a job corresponding to each data processing process of the data.

[0056] The so-called data loading process is used to import the data into a preset database table.

[0057] The so-called data verification process is used to verify the data to obtain verification information of the data, use the verification information to ensure that the format and content of the data are correct, and intercept data that does not meet the specifications.

[0058] The so-called message sending process is used to process the data according to an interface specification corresponding to a business type to which the data belongs, obtain a regulatory message of the data, and send the regulatory message to a regulatory agency.

[0059] The so-called receipt analysis process is used to receive feedback information sent by the regulatory agency based on the regulatory message of the data, deconstruct the feedback information to obtain a feedback result.

[0060] The so-called error supplement reporting process is used to identify the data as to-be-verified data in a case where the feedback result indicates that the message sending fails.

[0061] S102: Construct a visual model based on a business scenario of the regulatory reporting system.

[0062] The business scenario of the regulatory reporting system includes a plurality of visual functions, and each visual function includes an input / output visual function, a state visual function, a reporting visual function, an operation history visual function, and a data processing visual function. The visual model is used to generate a job corresponding to a visual function selected by a user.

[0063] The so-called input / output visual function is used to visualize the input and output of the regulatory reporting system, so that the user imports and exports the data in a preset data format to obtain an operation result of the import and export.

[0064] The so-called state visual function is used to present the change of the data state to the user in a timely manner, so that the user processes the data according to the change of the data state.

[0065] Generally, the types of the data state include new data, to-be-verified, passed verification, reporting, reporting success, reporting failure, and failed verification. The association relationship between the data states can be referred toFigure 1b The so-called report visualization function is used to present the report process and configuration information of the data to the user for viewing so as to manipulate the report progress and configuration information of the data by the user.

[0066] The so-called operation history visualization function is used to present the operation record of the user to the data to the user for viewing so as to track the change of the data by the user.

[0067] The so-called data visualization is used to present the operation result after the processing operation of the data by the user to the user for viewing.

[0068] It should be noted that based on the visualization model, the part control functions of the data processing, verification, message assembly sending, emergency import and export of the supervision report are abstracted, so that the user can manipulate the report process and can have an accurate understanding of the flow of the data, thereby fully releasing the ability of the user, letting the user participate in each processing process of the supervision report, based on the staged report of the automation, the logic of the business processing is presented at the critical point of the automation stage.

[0069] S103: After obtaining the user-inputted to-be-processed data, input the to-be-processed data into the automation model to obtain the first result output by the automation model.

[0070] The first result includes the job corresponding to the data processing process of the to-be-processed data.

[0071] S104: After obtaining the operation command inputted by the user, input the operation command into the visualization model to obtain the second result output by the visualization model.

[0072] The second result includes the job corresponding to the visualization function indicated by the operation command.

[0073] S105: Based on the job indicated by the first result and the job indicated by the second result, a job set is established.

[0074] S106: The execution order of each job in the job set and the data volume of each job in the job set are substituted into the pre-constructed report model to obtain the output result of the report model.

[0075] The output result includes the total execution time of each job in the job set.

[0076] The output result includes the total execution time of each job in the job set.

[0077] Optionally, the construction process of the report model includes the following steps:

[0078] 1. Pre-acquire sample data, wherein the sample data comprises sample execution orders of respective sample jobs, sample data volumes of respective sample jobs, and sample execution time sums of respective sample jobs.

[0079] 2. Based on the sample execution orders of respective sample jobs, the sample data volumes of respective sample jobs as independent variables, and the sample execution time sums of respective sample jobs as dependent variables, train the independent variables and the dependent variables by using a loss function (which can be a stochastic gradient descent function in particular), to obtain a submission model.

[0080] It should be noted that the specific expression of the submission model shown in the embodiments of the present application is as shown in formula (1):

[0081]

[0082] In formula (1), θ i represents the execution time of a job, m represents the total number of sample jobs of h(θ i ), i represents the index of each job in the job set, y i represents the dependent variable, and h(θ i ) represents the fitting function of θ i . Specifically, the specific expression of the fitting function is as shown in formula (2):

[0083]

[0084] In formula (2), n represents the total number of jobs contained in the job set, represents a preset first intermediate variable, represents the execution order of each job in the job set, represents a preset second intermediate variable, represents the data volume corresponding to each job in the job set.

[0085] S107: Adjust the execution order and the data volume by using the loss function, so that the execution time sum of each job in the job set is less than a preset submission time threshold.

[0086] S108: Identify the final adjusted execution order as an optimal execution order.

[0087] S109: Identify the final adjusted data volume as an optimal data volume.

[0088] S110: Execute each job in the job set in turn according to the optimal execution order.

[0089] S111: Allocate the optimal data volume to each job in the job set according to a preset paging strategy.

[0090] The so-called paging strategy is well known to those skilled in the art and will not be described here. In addition, assigning each job with an optimal data amount can avoid wasting too much database data resources to process a job with a small amount of data, thereby saving database data resources.

[0091] It should be noted that the jobs generated by the visualization model interfere with the jobs generated by the automation model in terms of timeliness, affecting the reporting efficiency of the regulatory reporting system. According to the frequency of user operation, a penalty value is set for the jobs generated by the visualization model. The higher the frequency of operation, the higher the penalty value. Accordingly, the jobs with higher penalty values can be executed after the jobs with lower penalty values.

[0092] Based on the above-mentioned processes S101-S111, the embodiment can achieve the following beneficial effects:

[0093] I. High maintainability. The visualization technology is applied throughout the reporting process, and the management of the data life cycle is maintained. Different processing methods are adopted for different states to avoid ineffective data management caused by complete automation, making the entire regulatory reporting system maintainable.

[0094] II. High universality. For different regulatory processes, this scheme starts from data management, maintains the state of data, focuses on system scheme design, and uses appropriate technology stack to complete the reporting process, which can be applied to the design of many regulatory reporting systems.

[0095] III. Good user experience. Operation visualization, data operation traceability, and phased automation process enable business personnel to clearly understand the operation principle of the regulatory reporting system.

[0096] IV. More standardized data management. Complete life cycle tracking makes the state change of data regular, problem troubleshooting more efficient, and data management more standardized.

[0097] V. More efficient regulatory reporting system operation. The optimal algorithm is used to predict the operation result, and the operation parameters are automatically adjusted to effectively solve the problems of low performance and poor timeliness in the operation of the regulatory reporting system.

[0098] In summary, by using the automation model and the visualization model, a job set is generated, the execution order and data amount of each job in the job set are adjusted to make the total execution time of each job less than a preset reporting time threshold, the optimal execution order of each job is obtained, and each job is executed according to the optimal execution order, so that the regulatory reporting time is reduced and the timeliness of regulatory reporting is improved.

[0099] It should be noted that S108 mentioned in the above embodiment is an optional implementation of the supervision reporting method shown in the present application. In addition, S110 mentioned in the above embodiment is also an optional implementation of the supervision reporting method shown in the present application. Therefore, the process mentioned in the above embodiment can be summarized as Figure 2 the method shown in the present application.

[0100] As Figure 2 shown, another process schematic diagram of the supervision reporting method provided by the embodiment of the present application includes the following steps:

[0101] S201: After obtaining the user inputted to-be-processed data, input the to-be-processed data into the automation model to obtain the first result outputted by the automation model.

[0102] Among them, the automation model is pre-constructed based on the automation reporting process of the supervision reporting system; the first result includes a job corresponding to the data processing process of the to-be-processed data.

[0103] S202: After obtaining the user inputted operation command, input the operation command into the visualization model to obtain the second result outputted by the visualization model.

[0104] Among them, the visualization model is pre-constructed based on the business scenario of the supervision reporting system; the second result includes a job corresponding to the visualization function shown by the operation command.

[0105] S203: Based on the job shown by the first result and the job shown by the second result, a job set is established.

[0106] S204: Adjust the execution order of each job in the job set and the data volume of each job in the job set, so that the total execution time of each job in the job set is less than the preset reporting time threshold.

[0107] S205: The finally adjusted execution order is identified as the optimal execution order.

[0108] S206: According to the optimal execution order, each job in the job set is executed in turn.

[0109] In summary, by using the automation model and the visualization model, a job set is generated, the execution order and data volume of each job in the job set are adjusted so that the total execution time of each job is less than the preset reporting time threshold, the optimal execution order of each job is obtained, and each job is executed according to the optimal execution order, so that the supervision reporting time is reduced and the timeliness of supervision reporting is improved.

[0110] Corresponding to the supervision reporting method provided by the above embodiment of the present application, the embodiment of the present application also provides a supervision reporting device.

[0111] As Figure 3 shown, an architecture schematic diagram of a supervision reporting device provided by an embodiment of the present application is shown, which comprises:

[0112] An automatic operation unit 100 is configured to input the to-be-processed data into an automatic model after obtaining the to-be-processed data input by a user, to obtain a first result output by the automatic model; the automatic model is pre-constructed based on an automatic reporting process of a supervision reporting system; and the first result comprises operations corresponding to a data processing process of the to-be-processed data.

[0113] A visual operation unit 200 is configured to input an operation command into a visual model after obtaining the operation command input by the user, to obtain a second result output by the visual model; the visual model is pre-constructed based on a business scenario of the supervision reporting system; and the second result comprises operations corresponding to a visual function shown by the operation command.

[0114] A set building unit 300 is configured to build a set of operations based on the operations shown by the first result and the operations shown by the second result.

[0115] An adjustment unit 400 is configured to adjust an execution order of each operation in the set of operations and a data volume of each operation in the set of operations, so that a total execution time of each operation in the set of operations is less than a preset reporting time threshold.

[0116] Optionally, the adjustment unit 400 is specifically configured to: substitute the execution order of each operation in the set of operations and the data volume of each operation in the set of operations into a pre-constructed reporting model, to obtain an output result of the reporting model; the output result comprises the total execution time of each operation in the set of operations; and the execution order and the data volume are adjusted by using a loss function, so that the total execution time of each operation in the set of operations is less than the preset reporting time threshold.

[0117] Optionally, the adjustment unit 400 is specifically configured to: pre-obtain sample data; the sample data comprises a sample execution order of each sample operation, a sample data volume of each sample operation, and a sample total execution time of each sample operation; based on the sample execution order of each sample operation, the sample data volume of each sample operation as independent variables, and the sample total execution time of each sample operation as a dependent variable, the independent variables and the dependent variable are trained by using a loss function, to obtain the reporting model.

[0118] An identification unit 500 is configured to identify the execution order obtained finally as an optimal execution order.

[0119] An operation execution unit 600 is configured to execute each operation in the set of operations in sequence according to the optimal execution order.

[0120] The distribution unit 700 is specifically configured to: identify the final adjusted data amount as an optimal data amount; and distribute the optimal data amount to each job in the job set according to a preset paging strategy.

[0121] To sum up, the job set is generated by using the automation model and the visualization model, the execution order and the data amount of each job in the job set are adjusted so that the total execution time of each job in the job set is less than the preset submission time threshold, the optimal execution order of each job is obtained, and each job is executed according to the optimal execution order, so that the supervision submission time is reduced and the timeliness of supervision submission is improved.

[0122] The application further provides a computer-readable storage medium, which comprises a stored program, wherein the program executes the supervision submission method provided by the application.

[0123] The application further provides a supervision submission device, which comprises a processor, a memory and a bus. The processor is connected with the memory through the bus. The memory is used for storing a program, and the processor is used for running the program. When the program is run, the supervision submission method provided by the application is executed, and comprises the following steps:

[0124] After obtaining the user-inputted to-be-processed data, the to-be-processed data is inputted into the automation model to obtain a first result output by the automation model; the automation model is pre-constructed based on an automatic submission process of a supervision submission system; and the first result comprises jobs corresponding to a data processing process of the to-be-processed data.

[0125] After obtaining the user-inputted operation command, the operation command is inputted into the visualization model to obtain a second result output by the visualization model; the visualization model is pre-constructed based on a business scenario of the supervision submission system; and the second result comprises jobs corresponding to a visualization function shown by the operation command.

[0126] Based on the jobs shown by the first result and the jobs shown by the second result, a job set is established;

[0127] The execution order of each job in the job set and the data amount of each job in the job set are adjusted so that the total execution time of each job in the job set is less than a preset submission time threshold.

[0128] The final adjusted execution order is identified as an optimal execution order.

[0129] Each job in the job set is executed in sequence according to the optimal execution order.

[0130] Specifically, on the basis of the above-mentioned embodiments, the adjustment of the execution order of each job in the job set and the data volume of each job in the job set so that the total execution time of each job in the job set is less than the preset submission time threshold comprises:

[0131] Substitute the execution order of each job in the job set and the data volume of each job in the job set into the pre-constructed submission model to obtain an output result of the submission model; the output result comprises the total execution time of each job in the job set;

[0132] Adjust the execution order and the data volume by using a loss function so that the total execution time of each job in the job set is less than the preset submission time threshold.

[0133] Specifically, on the basis of the above-mentioned embodiments, the construction process of the submission model comprises:

[0134] Pre-acquire sample data; the sample data comprises a sample execution order of each sample job, a sample data volume of each sample job, and a sample total execution time of each sample job;

[0135] Based on the sample execution order of each sample job, the sample data volume of each sample job as independent variables, and the sample total execution time of each sample job as a dependent variable, train the independent variables and the dependent variable by using a loss function to obtain the submission model.

[0136] Specifically, on the basis of the above-mentioned embodiments, after identifying the finally adjusted execution order as the optimal execution order, the method further comprises:

[0137] Identify the finally adjusted data volume as the optimal data volume;

[0138] According to a preset paging strategy, allocate the optimal data volume to each job in the job set.

[0139] If the functions of the method of the embodiments of the present application are realized in the form of software function units and sold or used as independent products, they can be stored in a computer device readable storage medium. Based on this understanding, the part of the prior art or the part of the technical solution of the embodiments of the present application that makes contributions to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, a mobile computing device or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk and various program code storage media.

[0140] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0141] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A regulatory reporting method, characterized in that, include: After obtaining the user-inputted data to be processed, the data to be processed is input into the automation model to obtain the first result output by the automation model; The automation model is pre-built based on the automated reporting process of the regulatory reporting system; The first result includes the job corresponding to the data processing procedure of the data to be processed; After receiving the user's input command, the command is input into the visualization model to obtain a second result output by the visualization model. The visualization model is pre-built based on the business scenario of the regulatory reporting system. The second result includes the job corresponding to the visualization function shown by the command. Based on the assignments shown in the first result and the assignments shown in the second result, construct an assignment set; The execution order of each job in the job set and the data volume of each job in the job set are substituted into the pre-built reporting model to obtain the output result of the reporting model; the output result includes the total execution time of each job in the job set; The execution order and the amount of data are adjusted using a loss function so that the total execution time of each job in the job set is less than a preset reporting time threshold. The final adjusted execution order is marked as the optimal execution order; According to the optimal execution order, each job in the job set is executed sequentially.

2. The method according to claim 1, characterized in that, The construction process of the reporting model includes: Pre-acquire sample data; the sample data includes the sample execution order of each sample job, the amount of sample data of each sample job, and the total sample execution time of each sample job; The reporting model is obtained by using the execution order of each sample job and the amount of sample data of each sample job as independent variables, and the total execution time of each sample job as dependent variable. The loss function is used to train the independent variables and the dependent variables.

3. The method according to claim 1, characterized in that, After marking the final adjusted execution order as the optimal execution order, the process also includes: The final adjusted data volume is marked as the optimal data volume; Based on a preset pagination strategy, the optimal amount of data is allocated to each job in the job set.

4. A regulatory reporting device, characterized in that, include: An automated task unit is used to input the data to be processed into an automated model after receiving the data to be processed from the user, and to obtain the first result output by the automated model. The automation model is pre-built based on the automated reporting process of the regulatory reporting system; the first result includes the job corresponding to the data processing process of the data to be processed. A visualization task unit is used to input the operation command input by the user into a visualization model after obtaining the operation command input by the user, and obtain a second result output by the visualization model; the visualization model is pre-built based on the business scenario of the regulatory reporting system; the second result includes the task corresponding to the visualization function shown by the operation command; A set-building unit is used to build a set of jobs based on the jobs shown in the first result and the jobs shown in the second result. The adjustment unit is used to substitute the execution order of each job in the job set and the data volume of each job in the job set into a pre-built reporting model to obtain the output result of the reporting model. The output result includes the total execution time of each job in the job set. The execution order and the amount of data are adjusted using a loss function so that the total execution time of each job in the job set is less than a preset reporting time threshold. The identification unit is used to identify the final adjusted execution order as the optimal execution order; The job execution unit is used to execute each job in the job set sequentially according to the optimal execution order.

5. The apparatus according to claim 4, characterized in that, The adjustment unit is specifically used for: Pre-acquire sample data; the sample data includes the sample execution order of each sample job, the amount of sample data of each sample job, and the total sample execution time of each sample job; The reporting model is obtained by using the execution order of each sample job and the amount of sample data of each sample job as independent variables, and the total execution time of each sample job as dependent variable. The loss function is used to train the independent variables and the dependent variables.

6. The apparatus according to claim 4, characterized in that, It also includes allocation units; The allocation unit is specifically used to: identify the final adjusted data volume as the optimal data volume; and allocate the optimal data volume to each job in the job set according to a preset paging strategy.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program executes the regulatory reporting method according to any one of claims 1-3.

8. A regulatory reporting device, characterized in that, include: Processor, memory, and bus; The processor and the memory are connected via the bus; The memory is used to store a program, and the processor is used to run the program, wherein the program executes the regulatory reporting method according to any one of claims 1-3 when it runs.

Images