A risk-oriented data analysis and modeling method

Abstract

The present disclosure relates to a risk-oriented data analysis and modeling method, which comprises: in response to a user triggering operation on target metadata, refreshing data in the target metadata into data of a first node; preprocessing the data refreshed into the first node to obtain initial data; and in response to a user data analysis operation on the initial data, analyzing the initial data. Since the data analysis tool is node-based, users or business personnel can assemble different nodes as needed, making data analysis more flexible and efficient. Users can use a visual page to drag and drop nodes, configure the data analysis tool, and make operations simpler. Users only need to understand the basic functions of the analysis nodes, without the need to understand structured query language, thereby reducing the learning cost of users and the difficulty of data analysis, and enabling traditional data analysts to easily perform their duties.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a risk-oriented data analysis and modeling method. Background Technology

[0002] With the widespread application and rapid development of computer technology, the data generated by various information systems is experiencing explosive growth. Large data volumes and heterogeneity are characteristics of today's information systems when storing data. However, these characteristics exacerbate the creation of data silos, resulting in this data often failing to provide the necessary value for, for example, business decision-making. Therefore, seeking effective data correlation analysis techniques to uncover the potential value of heterogeneous data has become an urgent need in the real world.

[0003] In current technologies, data analysis typically involves building a unified data warehouse for data collection and then performing analysis based on that data. However, this approach makes it difficult to perform correlation analysis between unstructured data, such as Excel files and reports, and data from databases, resulting in low data analysis efficiency. Furthermore, this method requires data analysts to be proficient in Structured Query Language (SQL), which traditional data analysts cannot readily adapt to. Summary of the Invention

[0004] To address the aforementioned technical issues, this disclosure provides a risk-oriented data analysis and modeling method to simplify data analysis operations and improve data analysis efficiency.

[0005] In a first aspect, embodiments of this disclosure provide a risk-oriented data analysis and modeling method, including:

[0006] In response to a user's trigger operation on the target metadata, the data in the target metadata is refreshed into the data of the first node;

[0007] Initial data is obtained by preprocessing the data refreshed to the first node through the first node;

[0008] In response to the user's data analysis operation on the initial data, the initial data is analyzed.

[0009] Secondly, embodiments of this disclosure provide a risk-oriented data analysis and modeling apparatus, comprising:

[0010] The refresh module is used to refresh the data in the target metadata to the data in the first node in response to the user's trigger operation on the target metadata;

[0011] The first processing module is used to preprocess the data refreshed to the first node through the first node to obtain initial data;

[0012] The analysis module is used to analyze the initial data in response to the user's data analysis operation on the initial data.

[0013] Thirdly, embodiments of this disclosure provide an electronic device, including:

[0014] Memory;

[0015] Processor; and

[0016] Computer programs;

[0017] The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in the first aspect.

[0018] Fourthly, embodiments of this disclosure provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method described in the first aspect.

[0019] Fifthly, this disclosure also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, implement a risk-oriented data analysis and modeling method as described above.

[0020] This disclosure provides a risk-oriented data analysis and modeling method. In response to a user's trigger operation on target metadata, data from the target metadata is refreshed into the data of a first node. The first node preprocesses the refreshed data to obtain initial data. In response to a user's data analysis operation on the initial data, the initial data is analyzed. By making the data analysis tool node-based, users or business personnel can assemble different nodes as needed, making data analysis more flexible and efficient. Users can use a visual interface to drag and drop nodes to configure data analysis tools, simplifying the operation. Users only need to understand the basic functions of the analysis nodes, without needing to understand structured query language, reducing the learning cost and the difficulty of data analysis. This allows traditional data analysts to easily perform the task, simplifies the operation for business personnel, improves work efficiency, and ultimately reduces the cost of data analysis. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0022] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A flowchart of a risk-oriented data analysis and modeling method provided in this disclosure embodiment;

[0024] Figure 2 A schematic diagram illustrating an application scenario provided by an embodiment of this disclosure;

[0025] Figure 3 A schematic diagram of a user interface provided for an embodiment of this disclosure;

[0026] Figure 4 A schematic diagram of a user interface provided for an embodiment of this disclosure;

[0027] Figure 5 A flowchart illustrating a risk-oriented data analysis and modeling method according to another embodiment of this disclosure;

[0028] Figure 6 A schematic diagram of a risk-oriented data analysis and modeling apparatus provided in this embodiment of the present disclosure;

[0029] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0030] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0031] Numerous specific details are set forth in the following description to provide a thorough understanding of this disclosure; however, this disclosure may also be implemented in other ways different from those described herein. Clearly, the embodiments described in the specification are only a part of, and not all, of the embodiments of this disclosure. The specific embodiments described herein are merely illustrative of the invention and not intended to limit it. All other embodiments obtained by those skilled in the art based on the described embodiments of the invention are within the scope of protection of this invention.

[0032] With the widespread application and rapid development of computer technology, the data generated by various information systems is experiencing explosive growth. Large data volumes and heterogeneity are characteristics of today's information systems when storing data. However, these characteristics exacerbate the creation of data silos, resulting in this data often failing to provide the necessary value for, for example, business decision-making. Therefore, seeking effective data correlation analysis techniques to uncover the potential value of heterogeneous data has become an urgent need in the real world.

[0033] In existing technologies, data analysis typically involves building a unified data warehouse for data collection and then performing data analysis based on that warehouse. However, this approach makes it difficult to perform correlation analysis between unstructured data, such as Excel files and reports, and data in a database, resulting in low data analysis efficiency. Furthermore, this method requires data analysts to master Structured Query Language (SQL), which traditional data analysts cannot readily adapt to. To address this issue, this disclosure provides a risk-oriented data analysis and modeling method, which will be described below with reference to specific embodiments.

[0034] Figure 1 This document provides a flowchart of a risk-oriented data analysis and modeling method according to an embodiment of the present disclosure. This method can be applied to... Figure 2 The application scenario shown includes a server 21 and a terminal 22. Terminal 22 can be a specific terminal, such as a smartphone, PDA, tablet, wearable device with a display screen, desktop computer, laptop computer, all-in-one computer, smart home device, etc. It is understood that the risk-oriented data analysis and modeling method provided in this embodiment can also be applied to other scenarios.

[0035] The following is combined Figure 2 The application scenarios shown are for Figure 1 This paper introduces a risk-oriented data analysis and modeling method, which includes the following specific steps:

[0036] S101. In response to the user's trigger operation on the target metadata, refresh the data in the target metadata to the data in the first node.

[0037] like Figure 2 The terminal 22 shown responds to the user's trigger operation on the target metadata by retrieving data from the server 21 and then refreshing the data in the target metadata into the data of the first node. The target metadata includes one or more data tables, which consist of field information and the corresponding data. The target metadata can be obtained by the user from the server or it can be user-defined data.

[0038] S102. Preprocess the data refreshed to the first node through the first node to obtain the initial data.

[0039] Optionally, developers can break down complex data analysis tools into multiple parts based on their different functions, and then encapsulate them into multiple analysis nodes. For example, the classification part of the data analysis tool can be encapsulated as a classification node, the filtering part as a filtering node, the association part as an association node, and the merging part as a merging node. In this way, users can select appropriate nodes as needed, and business personnel can also assemble different nodes as required, making the data analysis process more flexible, the data analysis operation simpler, and the efficiency higher.

[0040] Optionally, each functional category node may contain several components, where the division of these components is based on different methods or applicable conditions. For example, a category node may contain multiple different components, depending on the classification method used. Similarly, other category nodes may also contain multiple components, which are not limited here.

[0041] Optionally, users can add custom nodes to analyze the data, enhancing the scalability of data analysis methods.

[0042] S103. In response to the user's data analysis operation on the initial data, analyze the initial data.

[0043] Specifically, when a user opens the client software, the terminal responds by displaying a data analysis page, such as... Figure 3 As shown, the data analysis page has multiple categories of data analysis nodes. Users can drag and drop nodes to configure data analysis tools, responding to user operations on the initial data. Each node contains a corresponding Structured Query Language (SCL) function. In this step, users can utilize the visual interface to drag and drop analysis nodes and configure data analysis tools, making the operation simpler. Users only need to understand the basic functions of the analysis nodes, without needing to understand SCL, reducing the learning cost and the difficulty of data analysis. This allows traditional data analysts to easily perform the task, simplifying operations for business personnel, improving work efficiency, and ultimately reducing the cost of data analysis.

[0044] Optionally, the operation method is not limited to single click, double click, drag, slide, touch, etc.

[0045] This embodiment of the disclosure, in response to a user's trigger operation on the target metadata, refreshes the data in the target metadata to the data in the first node. The first node then preprocesses the refreshed data to obtain initial data. Finally, in response to a user's data analysis operation on the initial data, the initial data is analyzed. By making the data analysis tool node-based, users or business personnel can assemble different nodes as needed, making data analysis more flexible and efficient. Users can use a visual interface to drag and drop nodes to configure the data analysis tool, simplifying the operation. Users only need to understand the basic functions of the analysis nodes, without needing to understand structured query language, reducing the user's learning cost and the difficulty of data analysis. This allows traditional data analysts to easily perform the task, simplifies the operation for business personnel, improves work efficiency, and ultimately reduces the cost of data analysis.

[0046] Figure 5 A flowchart of a risk-oriented data analysis and modeling method provided in another embodiment of this disclosure is shown below. Figure 5 As shown, the method includes the following steps:

[0047] S501, In response to the user's selection of a data source, select a data source.

[0048] The terminal can use multiple data sources for data analysis. It can select a target data source and configure different data sources for operation, facilitating subsequent data processing. For example... Figure 4 As shown, users can extract data from multiple data sources such as A, B, and C, which is simple and fast. For example, if the user's target data source is data source A, the user only needs to click on data source A, and the terminal responds to the user's click operation by determining the metadata list of data source A.

[0049] Optionally, the operation method is not limited to single click, double click, drag, slide, touch, etc.

[0050] S502. Based on the user's trigger operation on the data source, determine the metadata list, which includes the target metadata.

[0051] Optionally, when a user triggers an operation on the data source, the terminal responds by determining a list of metadata. This list includes target metadata and other metadata. The target metadata can be one or more data tables, and the user can analyze multiple data tables simultaneously.

[0052] S503. In response to the user's trigger operation on the target metadata, refresh the data in the target metadata to the data in the first node.

[0053] Specifically, the implementation process and principle of S503 and S101 are the same, and will not be repeated here.

[0054] S504. The initial data is obtained by preprocessing the data refreshed to the first node through the first node.

[0055] Specifically, the implementation process and principle of S504 and S102 are the same, and will not be repeated here.

[0056] S505. Synchronize the initial data to the data on the second node.

[0057] After the data is processed by the first node, the initial data obtained from the processing by the first node is synchronized to the second node for further data processing.

[0058] S506. Intermediate data is obtained by reprocessing the data synchronized to the second node through the second node.

[0059] The data synchronized to the second node is reprocessed to obtain intermediate data, which is then further analyzed.

[0060] S507. In response to the user's data analysis operation on the intermediate data, analyze the intermediate data.

[0061] Specifically, when a user opens the client software, the terminal responds by displaying a data analysis page, such as... Figure 3 As shown, the data analysis page has multiple categories of data analysis nodes. Users can drag and drop nodes to configure data analysis tools, responding to user operations on intermediate data. Each node contains a corresponding Structured Query Language (SCL) function. In this step, users can utilize a visual interface to drag and drop analysis nodes and configure data analysis tools, making the operation simpler. Users only need to understand the basic functions of the analysis nodes, without needing to understand SCL, reducing the learning curve and the difficulty of data analysis. This allows traditional data analysts to easily perform the task, simplifying operations for business personnel, improving work efficiency, and ultimately reducing the cost of data analysis.

[0062] Optionally, multiple data analysis nodes can be used for data analysis, which is compatible with data analysis across multiple data sources.

[0063] This embodiment of the disclosure responds to a user's selection of a data source, selects a data source, and determines a metadata list based on the user's triggering operation on the data source. The metadata list includes target metadata. Responding to the user's triggering operation on the target metadata, the data in the target metadata is refreshed into the data of a first node. The first node preprocesses the refreshed data to obtain initial data. Further, the initial data is synchronized into the data of a second node, and the second node reprocesses the synchronized data to obtain intermediate data. Responding to the user's data analysis operation on the intermediate data, the intermediate data is analyzed. Since a data source can be selected, analysis of data from multiple data sources can be performed. Synchronizing the data obtained after processing at the first node to the second node for further processing allows for more in-depth data analysis. Multiple analyses can be performed on the data according to user needs, improving the flexibility of data analysis.

[0064] In some embodiments, refreshing the data in the target metadata to the data in the first node includes: comparing the data in the target metadata with the data in the first node to determine the difference between the data in the first node and the data in the target metadata; and refreshing the data in the first node based on the difference between the data in the first node and the data in the target metadata.

[0065] For example, the data in the target metadata is compared with the data in the first node to determine the addition or deletion of fields in the data table, and the data in the first node is refreshed based on the addition or deletion of fields in the data table.

[0066] Optionally, synchronizing the initial data to the data of the second node includes: comparing the data in the second node with the initial data to determine the differences between the data in the second node and the initial data; and synchronizing the data of the second node based on the differences between the data in the second node and the initial data.

[0067] For example, by comparing the data in the second node with the initial data, the addition or deletion of fields in the data table can be determined. Based on the addition or deletion of fields in the data table, the data in the second node can be synchronized to facilitate subsequent data processing and analysis.

[0068] Optionally, after analyzing the initial data, the method further includes: obtaining data analysis results; or, generating a data analysis model to perform real-time analysis on the initial data using the data analysis model.

[0069] After analyzing the initial data, the data analysis results will be obtained. Users can export the results for viewing or generate a data analysis model to perform real-time analysis on the initial data, and promptly verify, warn, identify indicators, or predict risk data.

[0070] Optionally, the plurality of data analysis nodes include at least one of the following: a filtering node, a classification node, a correlation node, and a merging node.

[0071] Optionally, the information stored in the first node and the second node includes at least one of the following: the node's location coordinates, the node's operation type, the node's field information, and the structured operation statements for node assembly.

[0072] Optionally, the above steps can be completed in the model lab. The model lab is used to customize a new model according to user needs, and supports setting model parameters and publishing the model. The generated model can be used for early warning, verification, indicator analysis, and prediction. The model lab can include model development, model maintenance, model scheduling, and model evaluation.

[0073] Model maintenance refers to the management of a business model throughout its configuration, verification, deployment, and the entire model lifecycle, including its basic information, operational steps, batch processing parameters, business parameters, business attributes, processing of model execution results, and model authorization. Model maintenance is further divided into sections such as permission maintenance, model type maintenance, and level maintenance.

[0074] Access control refers to maintaining the permissions of the model, and maintaining permissions according to different user permissions. Under normal circumstances, only the model designer has the authority to change information such as parameters, types, attributes, and operation steps of the model. Approval personnel from the model business line cannot directly modify the information of the model.

[0075] Model type maintenance refers to maintaining the types of models and making corresponding divisions based on different model types.

[0076] Level maintenance refers to maintaining the risk level of the model and classifying it accordingly based on different model levels.

[0077] Optionally, model scheduling can be divided into single model scheduling, batch model scheduling, and data preprocessing.

[0078] Model scheduling primarily involves batch running the generated model results. Based on the model rules written by business personnel, the risk model results are run at regular intervals. For example, batch running the model results generated in the editor can be scheduled to run the previous month's risk model results at the beginning of each month, according to the model rules written by business personnel.

[0079] Optionally, when you click the “Model Batch Scheduling” icon or button on the left, all the models that have been applied for and approved will be displayed on the right.

[0080] Optionally, the model lab also includes icons such as "Batch Set Tasks", "Batch Modify Tasks", "Add to Batch Run", "Remove from Batch Run", "Progress View", and "Start Now". The specific functions of these icons are as follows.

[0081] Batch task setup: Set the batch running time for models in batches. No need to select models, just click the button to set all. Optionally, you can set the batch running cycle of the models, generally set to "Loop" with a cycle of 1 month.

[0082] Batch Modify Tasks: Batch modify the set batch run time of the models.

[0083] Add to batch run: You can set a specific model to run in batch or not. If you want to run in batch, select the model and then add it to the batch run.

[0084] Remove batch run: Cancel batch running for models that have already been added to the batch run.

[0085] Progress tracking: You can view the progress of the batch processing of the model and keep track of the batch processing status at any time.

[0086] Start immediately: You can select a batch of models and start the batch run immediately, only running the models that have been added to the batch run.

[0087] Optionally, a model execution scheduling strategy can be preset. Models are categorized by size into ultra-large models (execution time over 2 hours), large models (execution time over 30 minutes but less than 2 hours), and normal models (less than half an hour). Only one ultra-large model or large model is running in the scheduler at any given time, while other submitted ultra-large models or large models are in a waiting state in the execution pool.

[0088] In this embodiment of the disclosure, after analyzing the initial data, the method further includes: obtaining data analysis results; or, generating a data analysis model to perform real-time analysis of the initial data using the data analysis model. Obtaining data analysis results provides strong data support and graphical representation for business operations, making the analysis more intuitive and clear. Furthermore, generating a data analysis model allows for real-time analysis of the initial data, facilitating subsequent data operations and enabling timely verification, early warning, indicator setting, or prediction of risk data.

[0089] Figure 6This is a schematic diagram of a risk-oriented data analysis and modeling apparatus provided in an embodiment of this disclosure. A risk-oriented data analysis and modeling apparatus can be a terminal as described in the above embodiment, or a component or assembly within that terminal. The risk-oriented data analysis and modeling apparatus provided in this disclosure can execute the processing flow provided in an embodiment of a risk-oriented data analysis and modeling method, such as... Figure 6 As shown, a risk-oriented data analysis and modeling device 60 includes: a refresh module 61, a first processing module 62, and an analysis module 63; wherein, the refresh module 61 is used to refresh the data in the target metadata to the data of the first node in response to a user's trigger operation on the target metadata; the first processing module 62 is used to preprocess the data refreshed to the first node through the first node to obtain initial data; and the analysis module 63 is used to analyze the initial data in response to a user's data analysis operation on the initial data.

[0090] Optionally, the device further includes: a synchronization module 64 and a second processing module 65; the synchronization module 64 is used to synchronize the initial data to the data of the second node; the second processing module 65 is used to reprocess the data synchronized to the second node through the second node to obtain intermediate data.

[0091] Accordingly, when the analysis module 63 analyzes the initial data in response to the user's data analysis operation on the initial data, it is specifically used to: analyze the intermediate data in response to the user's data analysis operation on the intermediate data.

[0092] Optionally, the device further includes: a selection module 66 and a determination module 67; the selection module 66 is used to select a data source in response to a user's selection operation on the data source; the determination module 67 is used to determine a metadata list based on a user's trigger operation on the data source, the metadata list including target metadata.

[0093] Optionally, when the refresh module 61 responds to the user's trigger operation on the target metadata and refreshes the data in the target metadata to the data in the first node, it is specifically used to: compare the data in the target metadata with the data in the first node to determine the difference between the data in the first node and the data in the target metadata; and refresh the data in the first node based on the difference between the data in the first node and the data in the target metadata.

[0094] Optionally, when synchronizing the initial data to the data of the second node, the synchronization module 64 is specifically used to: compare the data in the second node with the initial data to determine the difference between the data in the second node and the initial data; and synchronize the data of the second node based on the difference between the data in the second node and the initial data.

[0095] Optionally, the apparatus further includes: a obtaining module 68 and / or a generating module 69; the obtaining module 68 is used to obtain data analysis results; the generating module 69 is used to generate a data analysis model to perform real-time analysis on the initial data through the data analysis model.

[0096] Figure 6 The risk-oriented data analysis and modeling apparatus of the embodiment shown can be used to execute the technical solutions of the above method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0097] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. The electronic device can be a terminal as described in the above embodiments. The electronic device provided in this disclosure can execute the processing flow provided in an embodiment of a risk-oriented data analysis and modeling method, such as... Figure 7 As shown, the electronic device 70 includes: a memory 71, a processor 72, a computer program, and a communication interface 73; wherein the computer program is stored in the memory 71 and configured to be executed by the processor 72 as described above, a risk-oriented data analysis and modeling method.

[0098] In addition, this disclosure also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement a risk-oriented data analysis and modeling method as described in the above embodiments.

[0099] Furthermore, this disclosure also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, implement a risk-oriented data analysis and modeling method as described above.

[0100] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0101] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0102] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0103] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:

[0104] In response to a user's trigger operation on the target metadata, the data in the target metadata is refreshed into the data of the first node;

[0105] Initial data is obtained by preprocessing the data refreshed to the first node through the first node;

[0106] In response to the user's data analysis operation on the initial data, the initial data is analyzed.

[0107] In addition, the electronic device can also perform other steps in a risk-oriented data analysis and modeling method as described above.

[0108] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0109] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0110] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0111] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0112] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0113] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, 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 elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0114] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A risk-oriented data analysis and modeling method, characterized in that, include: In response to a user's trigger operation on the target metadata, the data in the target metadata is refreshed into the data of the first node; Initial data is obtained by preprocessing the data refreshed to the first node through the first node; In response to the user's data analysis operation on the initial data, the initial data is analyzed; The data analysis operation is implemented based on dragging and dropping visual nodes. The visual nodes include multiple data analysis nodes, which include at least one of the following: filtering nodes, classification nodes, association nodes, and merging nodes; wherein, the filtering nodes are used to filter data, the classification nodes are used to classify data, the association nodes are used to associate data, and the merging nodes are used to merge data. After obtaining the initial data by preprocessing the data refreshed to the first node through the first node, the method further includes: Synchronize the initial data to the data on the second node; Intermediate data is obtained by reprocessing the data synchronized to the second node through the second node; Accordingly, in response to the user's data analysis operation on the initial data, the initial data is analyzed, including: In response to the user's data analysis operation on the intermediate data, the intermediate data is analyzed; The target metadata includes one or more data tables; The various nodes used for data analysis operations can be combined and assembled based on user needs; The method is based on a model lab, which includes model development, model maintenance, model scheduling, and model evaluation. Model maintenance includes permission maintenance, which refers to maintaining the permissions of the model and maintaining permissions according to different user permissions. Before refreshing the data in the target metadata to the data of the first node in response to a user's triggered operation on the target metadata, the method further includes: In response to the user's selection of a data source, select the data source; Based on the user's triggering operation on the data source, a metadata list is determined, which includes the target metadata.

2. The method according to claim 1, characterized in that, The step of refreshing the data in the target metadata to the data in the first node includes: The data in the target metadata is compared with the data in the first node to determine the differences between the data in the first node and the data in the target metadata. The data in the first node is refreshed based on the difference between the data in the first node and the data in the target metadata.

3. The method according to claim 1, characterized in that, The process of synchronizing the initial data to the data on the second node includes: The data in the second node is compared with the initial data to determine the differences between the data in the second node and the initial data; Based on the difference between the data in the second node and the initial data, the data in the second node is synchronized.

4. The method according to claim 1, characterized in that, After analyzing the initial data, the method further includes: Obtain data analysis results; or Generate a data analysis model to perform real-time analysis on the initial data.

5. A risk-oriented data analysis and modeling device, characterized in that, include: The refresh module is used to refresh the data in the target metadata to the data in the first node in response to the user's trigger operation on the target metadata; The first processing module is used to preprocess the data refreshed to the first node through the first node to obtain initial data; The analysis module is used to analyze the initial data in response to the user's data analysis operation on the initial data; The data analysis operation is implemented based on dragging and dropping visual nodes. The visual nodes include multiple data analysis nodes, which include at least one of the following: filtering nodes, classification nodes, association nodes, and merging nodes; wherein, the filtering nodes are used to filter data, the classification nodes are used to classify data, the association nodes are used to associate data, and the merging nodes are used to merge data. The device further includes: The synchronization module is used to synchronize the initial data to the data of the second node; The second processing module is used to reprocess the data synchronized to the second node through the second node to obtain intermediate data; Accordingly, when the analysis module analyzes the initial data in response to the user's data analysis operation on the initial data, it is specifically used to: analyze the intermediate data in response to the user's data analysis operation on the intermediate data; The target metadata includes one or more data tables; The various nodes used for data analysis operations can be combined and assembled based on user needs; The operation performed by the device is based on the model laboratory, which includes model compilation, model maintenance, model scheduling and model evaluation. The model maintenance includes permission maintenance, which refers to maintaining the permissions of the model and maintaining permissions according to different user permissions. The device further includes: a selection module and a determination module; The selection module is used to respond to the user's selection of a data source and select the data source. The determination module is used to determine a list of metadata based on the user's triggering operation on the data source, the list of metadata including target metadata.

6. An electronic device, characterized in that, include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-4.

Images