A Platform Risk Control Method for Financial Data Analysis
By combining financial risk prediction models with CNN convolutional neural networks, the problem of cumbersome operation in existing technologies has been solved, and the automation and efficient processing of financial data analysis have been achieved.
Patent Information
- Application Number
- CN202310550103.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-16
- Publication Date
- 2025-10-31
- Estimated Expiration
- 2043-05-16
AI Technical Summary
Existing financial data analysis methods rely on the calculation methods of binomial and normal distributions in Excel, which leads to cumbersome operations and poor analysis efficiency.
A financial risk prediction model is adopted in combination with a CNN convolutional neural network to achieve automatic data import and analysis. The financial risk prediction model is built through a logic model engine and a conceptual model engine, and the CNN convolutional neural network is used for self-learning and optimization.
It simplifies the operation process, automates and efficiently processes financial data analysis, and meets the needs for analyzing large volumes of financial big data.
Smart Images
Figure CN116611901B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of financial data analysis technology, specifically a platform risk control method for financial data analysis. Background Technology
[0002] In addition to the general characteristics of data, financial data also has its own characteristics: wide range, comprehensiveness, reliability, and continuity. The special nature of financial data makes the processing of financial data special and has special requirements. Its input verification is more stringent, its storage capacity is larger, its network transmission is more extensive, and its data maintenance is more frequent.
[0003] To reduce the impact of financial risks on users' funds, it is necessary to conduct financial data analysis regularly. However, existing financial data analysis methods mainly rely on the calculation methods of binomial distribution and normal distribution in Excel. During the calculation process, users need to manually input the values, which is cumbersome and has poor analysis efficiency.
[0004] Therefore, it is necessary to redesign and modify the risk control methods of financial data analysis platforms to effectively improve the efficiency of financial risk analysis. Summary of the Invention
[0005] To address the problems mentioned in the background section, the present invention aims to provide a platform risk control method for financial data analysis, which has the advantage of improving the efficiency of financial risk analysis. It solves the problem that existing financial data analysis methods mainly rely on the calculation methods of binomial distribution and normal distribution in Excel for analysis, which require users to manually input values during the calculation process, resulting in cumbersome operation and poor analysis efficiency.
[0006] To achieve the above objectives, the present invention provides the following technical solution: a platform risk control method for financial data analysis, including financial big data;
[0007] The financial big data is stored inside the storage module. The output of the storage module is bidirectionally electrically connected to a terminal processor and a data import module. The outputs of both the terminal processor and the data import module are bidirectionally electrically connected to a model building module. The output of the model building module is electrically connected to a financial risk prediction model. The input of the financial risk prediction model is bidirectionally electrically connected to the output of the data import module. The output of the financial risk prediction model is electrically connected to a report generation module. The output of the report generation module is bidirectionally electrically connected to a result verification unit. The output of the result verification unit is bidirectionally electrically connected to the input of the terminal processor. The output of the terminal processor is bidirectionally electrically connected to a CNN convolutional neural network. The output of the CNN convolutional neural network is bidirectionally electrically connected to the inputs of both the model building module and the financial risk prediction model.
[0008] As a preferred embodiment of the present invention, the data import module consists of a user data matching unit and a generation time matching unit.
[0009] As a preferred embodiment of the present invention, the model building module consists of a logical model engine and a conceptual model engine.
[0010] As a preferred embodiment of the present invention, the CNN convolutional neural network consists of a one-dimensional convolutional unit and a noise reduction encoder.
[0011] A risk control method for a financial data analysis platform includes the following steps:
[0012] S1: Import historical financial big data stored in the storage module into the model building module through the data import module. The terminal processor processes the model building module and builds a financial risk prediction model through the logic model engine and the conceptual model engine.
[0013] S2: The financial risk prediction model evaluates and scores the data and generates a report through the report output module. The result verification unit sends the report to the terminal processor, which compares and verifies the report. When the verification result error is higher than the preset value, the model building module uses a CNN convolutional neural network to learn itself and rebuild a new financial risk prediction model until the report result of the financial risk prediction model meets expectations.
[0014] S3: The data import module can directly transfer the financial big data that needs to be analyzed to the internal workings of the financial risk prediction model for calculation, and generate an analysis report through the report output module.
[0015] As a preferred embodiment of the present invention, the scoring method of the financial risk prediction model is based on the generation time of the user data matching unit and the generation time matching unit and the user's personal credit status based on past data.
[0016] As a preferred embodiment of the present invention, the user's past personal credit status accounts for 75 points, and the time of generation accounts for 25 points.
[0017] As a preferred embodiment of the present invention, the report generated by the established financial risk prediction model can be transmitted to the regulatory platform for notification via wireless transmission and reception. At the same time, the regulatory platform can also supervise or manually modify the establishment steps and data of past financial big data.
[0018] Compared with the prior art, the beneficial effects of the present invention are as follows:
[0019] 1. This invention can replace the existing financial data analysis methods that mainly rely on the calculation methods of binomial distribution and normal distribution in Excel for analysis. It can directly and automatically import and calculate data using financial risk prediction models. Its operation is simple and can meet the analysis needs of large-scale financial big data. Attached Figure Description
[0020] Figure 1 This is a schematic diagram of the system of the present invention. Implementation
[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0022] like Figure 1 As shown, the present invention provides a platform risk control method for financial data analysis, including financial big data;
[0023] Financial big data is stored inside the storage module. The output of the storage module is bidirectionally electrically connected to the terminal processor and the data import module. The outputs of both the terminal processor and the data import module are bidirectionally electrically connected to the model building module. The output of the model building module is electrically connected to the financial risk prediction model. The input of the financial risk prediction model is bidirectionally electrically connected to the output of the data import module. The output of the financial risk prediction model is electrically connected to the report output module. The output of the report output module is bidirectionally electrically connected to the result verification unit. The output of the result verification unit is bidirectionally electrically connected to the input of the terminal processor. The output of the terminal processor is bidirectionally electrically connected to a CNN convolutional neural network. The output of the CNN convolutional neural network is bidirectionally electrically connected to the inputs of both the model building module and the financial risk prediction model.
[0024] refer to Figure 1 The data import module consists of a user data matching unit and a generation time matching unit.
[0025] refer to Figure 1 The model building module consists of a logical model engine and a conceptual model engine.
[0026] refer to Figure 1 A CNN (Convolutional Neural Network) consists of one-dimensional convolutional units and a noise reduction encoder.
[0027] refer to Figure 1 A risk control method for a financial data analysis platform includes the following steps:
[0028] S1: Import historical financial big data stored in the storage module into the model building module through the data import module. The terminal processor processes the model building module and builds a financial risk prediction model through the logic model engine and the conceptual model engine.
[0029] S2: The financial risk prediction model evaluates and scores the data and generates a report through the report output module. The result verification unit sends the report to the terminal processor, which compares and verifies the report. When the verification result error is higher than the preset value, the model building module uses a CNN convolutional neural network to learn itself and rebuild a new financial risk prediction model until the report result of the financial risk prediction model meets expectations.
[0030] S3: The data import module can directly transfer the financial big data that needs to be analyzed to the internal workings of the financial risk prediction model for calculation, and generate an analysis report through the report output module.
[0031] refer to Figure 1 The scoring method of the financial risk prediction model is based on the generation time of the user data matching unit and the generation time matching unit and the user's personal credit status based on past data.
[0032] refer to Figure 1 The user's past credit history accounts for 75 points, and the time of generation accounts for 25 points.
[0033] refer to Figure 1 The reports generated by the completed financial risk prediction model can be transmitted wirelessly to the regulatory platform for notification. At the same time, the regulatory platform can also supervise or manually modify the establishment steps and data of past financial big data.
[0034] The working principle and usage process of this invention are as follows: The financial big data stored in the storage module is imported into the model building module through the data import module. The terminal processor processes the model building module and builds a financial risk prediction model through the logic model engine and the concept model engine. The financial risk prediction model generates a report through the report output module. The result verification unit sends the report to the terminal processor. The terminal processor compares and verifies the report. When the verification result error is higher than the preset value, the model building module uses a CNN convolutional neural network to learn itself and rebuild a new financial risk prediction model until the report result of the financial risk prediction model meets expectations. The data import module can directly transmit the financial big data to be analyzed into the internal workings of the financial risk prediction model for calculation and generate an analysis report through the report output module.
[0035] In summary, the risk control method of this financial data analysis platform can replace the existing financial data analysis methods that mainly rely on the calculation of binomial and normal distributions in Excel. It can directly and automatically import and calculate data using financial risk prediction models. Its operation is simple and can meet the analysis needs of large-scale financial big data.
[0036] It should be noted that, in this document, relational terms such as "first" and "second" are used only 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 process, method, article, or apparatus.
[0037] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. A platform risk control system for financial data analysis, characterized in that: This includes financial big data; the financial big data is stored inside a storage module, the output of which is bidirectionally electrically connected to a terminal processor and a data import module, the outputs of both the terminal processor and the data import module are bidirectionally electrically connected to a model building module, the output of which is electrically connected to a financial risk prediction model, the input of which is bidirectionally electrically connected to the output of the data import module, the output of which is electrically connected to a report generation module, the output of which is bidirectionally electrically connected to a result verification unit, the output of which is bidirectionally electrically connected to the input of the terminal processor, the output of which is bidirectionally electrically connected to a CNN convolutional neural network, and the output of which is bidirectionally electrically connected to both the model building module and the input of the financial risk prediction model. The data import module imports historical financial big data stored in the storage module into the model building module. The terminal processor processes the model building module and builds a financial risk prediction model through the logic model engine and concept model engine. The financial risk prediction model evaluates and scores the data and generates a report through the report output module. The result verification unit sends the report to the terminal processor, which compares and verifies the report. When the verification result error is higher than the preset value, the model building module uses a CNN convolutional neural network to learn itself and rebuild a new financial risk prediction model until the report result of the financial risk prediction model meets expectations. The data import module can directly transfer the financial big data that needs to be analyzed to the internal workings of the financial risk prediction model for calculation, and generate analysis reports through the report output module.
2. The risk control system for a financial data analysis platform according to claim 1, characterized in that: The data import module consists of a user data matching unit and a generation time matching unit.
3. The platform risk control system for financial data analysis according to claim 1, characterized in that: The model building module consists of a logical model engine and a conceptual model engine.
4. The risk control system for a financial data analysis platform according to claim 1, characterized in that: The CNN convolutional neural network consists of one-dimensional convolutional units and a noise reduction encoder.
5. The platform risk control method for financial data analysis according to claim 1, characterized in that: Includes the following steps: S1: Import historical financial big data stored in the storage module into the model building module through the data import module. The terminal processor processes the model building module and builds a financial risk prediction model through the logic model engine and the conceptual model engine. S2: The financial risk prediction model evaluates and scores the data and generates a report through the report output module. The result verification unit sends the report to the terminal processor, which compares and verifies the report. When the verification result error is higher than the preset value, the model building module uses a CNN convolutional neural network to learn itself and rebuild a new financial risk prediction model until the report result of the financial risk prediction model meets expectations. S3: The data import module can directly transfer the financial big data that needs to be analyzed to the internal workings of the financial risk prediction model for calculation, and generate an analysis report through the report output module.
6. The platform risk control method for financial data analysis according to claim 5, characterized in that: The scoring method of the financial risk prediction model is based on the generation time of the user data matching unit and the generation time matching unit, and the user's personal credit status based on past data.
7. The platform risk control method for financial data analysis according to claim 6, characterized in that: A user's past credit history accounts for 75 points, while the time of creation accounts for 25 points.
8. The platform risk control method for financial data analysis according to claim 5, characterized in that: The reports generated by the established financial risk prediction models can be transmitted wirelessly to the regulatory platform for notification. At the same time, the regulatory platform can also supervise or manually modify the establishment steps and data of past financial big data.
Citation Information
Patent Citations
Financial big data risk analysis platform
CN114881768A