Economic data efficient processing system and method based on cloud computing

Abstract

The invention relates to the technical field of economic data processing, in particular to an efficient economic data processing system and method based on cloud computing, and the system comprises a data collection module, a data preprocessing module, a data storage and distribution module, a data analysis module, a feature engineering module, a privacy protection module, a virtual economic prediction module and a self-adaptive resource allocation module. The data acquisition module is used for collecting and importing economic data; the data preprocessing module is used for performing primary processing on original economic data; according to the method, through adaptive resource allocation, the capacity of dynamically allocating computing resources according to the current task load and the economic data processing amount is achieved, it is ensured that CPU and memory resources can be effectively allocated in the peak period, data processing bottlenecks are avoided, the resource utilization efficiency is improved, and through the steps of feature selection, feature removal, feature construction and the like, the resource utilization efficiency is improved. And the precision and generalization ability of a subsequent model are improved, so that the system can better reveal economic laws and carry out predictive analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of economic data processing, and in particular to a system and method for efficiently processing economic data based on cloud computing. Background Art

[0002] Cloud computing is a computing method based on the Internet. It automatically splits huge computing programs into countless smaller subprograms through the network, and then sends the processing results back to the user after searching, computing and analyzing by a large system composed of multiple servers. It provides dynamically scalable and virtualized resources, including computing resources, storage resources and application services, so that users can obtain and use these resources on demand without worrying about the underlying implementation details. Economic data refers to various data that reflect economic activities, economic relations and economic phenomena, including GDP, inflation rate, unemployment rate, price index, trade volume, etc. These data are important bases for understanding the economic operation status, formulating economic policies and making economic forecasts.

[0003] In the article "Research on Big Data Analysis Technology Based on Cloud Computing" by scholar Luo Hua, the value and technical points of big data analysis technology based on cloud computing are discussed, which involves how to use the efficient storage and computing power of cloud computing to process and analyze big data, including economic data. However, the paper has the following problems: insufficient flexibility in resource allocation, insufficient dynamic resource allocation and adaptive optimization strategies, and in terms of privacy protection, it does not introduce more detailed descriptions of encryption and privacy protection algorithms. In terms of feature engineering, it does not deeply analyze the complexity and diversity of economic data, as well as the impact of feature selection and construction on model accuracy and generalization ability, which ultimately leads to problems such as insufficient flexibility in resource allocation, incomplete privacy protection, and insufficient depth in feature engineering.

[0004] In summary, it is necessary to propose an efficient economic data processing system and method based on cloud computing to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a system and method for efficiently processing economic data based on cloud computing to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An efficient economic data processing system based on cloud computing includes a data acquisition module, a data preprocessing module, a data storage and distribution module, a data analysis module, a feature engineering module, a privacy protection module, a virtual economic prediction module, and an adaptive resource allocation module;

[0008] The data acquisition module is used for the collection and import of economic data, and ensures that data accurately enters the system from different sources through various means;

[0009] The data preprocessing module is used to perform preliminary processing on the original economic data to ensure that the basic data for subsequent analysis is accurate;

[0010] The data storage distribution module is used to perform distributed storage on the pre-processed data and provide data services for downstream analysis and processing modules;

[0011] The data analysis module is used for the calculation and analysis of economic data, and provides basic statistical analysis, forecasting and regression modeling capabilities;

[0012] The feature engineering module is used to improve the accuracy and generalization ability of subsequent models by extracting and expanding features of data;

[0013] The privacy protection module is used to encrypt and protect data to prevent leakage of sensitive data;

[0014] The virtual economic forecasting module is used to realize virtual simulation of future economic development, and to construct a virtual environment and forecast and simulate economic policies through economic data;

[0015] The adaptive resource allocation module detects abnormal behaviors that may occur in the system when processing economic data through dynamic allocation and task optimization of cloud computing resources, and automatically corrects them, so as to ensure efficient use of computing resources when processing large-scale economic data.

[0016] Preferably, the data acquisition module further includes a real-time data acquisition unit and a batch data import unit;

[0017] The real-time data collection unit collects real-time data streams through the Apache Flink stream processing algorithm to quickly capture dynamic data streams in financial markets and price economies;

[0018] The batch data import unit performs scheduled batch data import operations through Apache Nifi or Talend to ensure regular acquisition of government reports and industry analysis static economic data.

[0019] Preferably, the data preprocessing module further includes an outlier detection unit and a data standardization unit;

[0020] The outlier detection unit detects outliers in the data using an Isolation Forest algorithm to filter out unreasonable economic data, including commodity data with abnormal price fluctuations;

[0021] The data standardization unit normalizes the data by using a Z-score normalization algorithm or a Min-Max normalization algorithm to ensure that data from different sources and types can remain consistent in subsequent analysis.

[0022] Preferably, the data storage and distribution module further comprises a distributed storage unit and a data distribution unit;

[0023] The distributed storage unit performs distributed storage of economic data through Hadoop HDFS or Amazon S3, providing efficient storage and reading capabilities;

[0024] The data distribution unit distributes data through Apache Kafka or RabbitMQ, and pushes the processed data to subscribed modules and users in real time, achieving low-latency data transmission.

[0025] Preferably, the data analysis module further includes a statistical analysis unit and a regression analysis unit;

[0026] The statistical analysis unit performs basic statistical analysis of economic data through the Pandas library or the statistical package of the R language, and calculates the mean and variance of GDP and inflation economic indicators;

[0027] The regression analysis unit models and predicts economic data through linear regression and logistic regression algorithms, and analyzes the relationship between variables, including the correlation between commodity price consumption index.

[0028] Preferably, the feature engineering module further includes a feature selection unit and a feature construction unit;

[0029] The feature selection unit selects the most influential features for the economic model through the LASSO regression algorithm, and removes low-impact economic variables, including irrelevant data of certain small industries;

[0030] The feature construction unit performs automatic feature construction through the Featuretools feature interaction generation tool, and generates high-order variables based on basic economic data, including combined features of investment return rate and long-term market fluctuations.

[0031] Preferably, the privacy protection module further includes a homomorphic encryption unit and a differential privacy unit;

[0032] The homomorphic encryption unit encrypts sensitive economic data using the Paillier homomorphic encryption algorithm, allowing data calculations to be performed in an encrypted state, including calculating the sum of encrypted corporate financial data;

[0033] The differential privacy unit performs economic statistical calculations under the premise of ensuring privacy through the DP-SGD differential privacy algorithm to prevent the disclosure of the precise economic status of an individual or enterprise.

[0034] Preferably, the virtual economic forecasting module further includes an economic model building unit, a policy impact simulation unit, an abnormal behavior detection unit and an automatic deviation correction unit;

[0035] The economic model building unit constructs a virtual economic environment through a multi-agent system, simulates the interaction of multiple economic entities, including the relationship between the government, enterprises and consumers, and predicts the impact of policies on economic development;

[0036] The policy impact simulation unit performs multiple random simulations on economic data through Monte Carlo simulation algorithms to analyze changes in economic variables under different policy impacts, including the impact of tax policy adjustments on inflation rates;

[0037] The abnormal behavior detection unit monitors the calculation process in the system in real time through the Bayesian network to detect possible abnormal situations when processing economic data, including calculation errors or data flow interruptions;

[0038] The automatic correction unit adjusts system parameters in real time through an adaptive control algorithm. Once an erroneous behavior in data processing is detected, the system can automatically adjust the model or restart the calculation process to ensure the accuracy of the final result.

[0039] Preferably, the adaptive resource allocation module further includes an adaptive computing resource allocation unit and a resource scheduling optimization unit;

[0040] The adaptive computing resource allocation unit dynamically allocates computing resources through the DQN reinforcement learning algorithm, and adjusts the allocation ratio of cloud resources according to the current task load, including adjusting the occupancy of storage and computing resources according to the economic data processing volume;

[0041] The resource scheduling optimization unit optimizes the scheduling scheme of computing resources through genetic algorithms to ensure that CPU and memory resources can be effectively allocated during processing peak periods to avoid the occurrence of economic data processing bottlenecks.

[0042] Based on the above system, the present invention also proposes a method for efficiently processing economic data based on cloud computing, comprising the following steps:

[0043] S1. Use stream processing algorithms to capture economic data in real time from financial markets and price dynamic data streams. Use ETL tools to import economic data in batches from various data sources on a regular basis to ensure the comprehensiveness and timeliness of the data.

[0044] S2. Detect outliers in economic data, filter out unreasonable or erroneous data, ensure data quality, standardize economic data, ensure consistency in data format and dimension, and facilitate subsequent analysis;

[0045] S3. Distribute and store the pre-processed economic data in the cloud computing platform to improve data storage efficiency and access speed, and push the processed data to subscribed modules and users in real time to ensure the timeliness and availability of data;

[0046] S4. Perform basic statistical analysis of economic data, including calculating the mean and variance of GDP and inflation economic indicators, providing a macroeconomic overview, using linear regression and logistic regression algorithms to model and predict economic data, analyzing the relationship between variables, and revealing economic laws;

[0047] S5. Select the most influential features for the model from a large number of economic variables, eliminate low-impact or redundant variables, improve model efficiency, and use feature interaction generation tools to automate feature construction based on basic economic data, generate high-order variables, and improve the accuracy and generalization ability of the model;

[0048] S6. Use homomorphic encryption algorithms to encrypt sensitive economic data to ensure that data can still be calculated in an encrypted state and protect data privacy. Use differential privacy algorithms to perform economic statistical calculations while ensuring privacy, and balance data utilization and privacy protection.

[0049] S7. Construct a virtual economic environment to simulate the interaction of multiple economic entities, provide a basis for predicting the impact of policies on economic development, conduct multiple random simulations of economic data through simulation algorithms, analyze the changes in economic variables under different policy shocks, and provide a basis for policy formulation. Use Bayesian networks to monitor the calculation process in the system in real time. Once an abnormal situation is detected, adjust the system parameters in real time or restart the calculation process through adaptive control algorithms to ensure the accuracy of the prediction results.

[0050] S8. According to the current task load and economic data processing volume, computing resources are dynamically allocated through reinforcement learning algorithms, including the occupancy ratio of storage and computing resources. Genetic algorithms are used to optimize the scheduling of computing resources to ensure that CPU and memory resources can be effectively allocated during peak processing periods, avoid the occurrence of data processing bottlenecks, and improve resource utilization efficiency.

[0051] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention realizes the ability to dynamically allocate computing resources according to the current task load and economic data processing volume through adaptive resource allocation, ensures that CPU and memory resources can be effectively allocated during peak periods, avoids the emergence of data processing bottlenecks, and improves resource utilization efficiency; through advanced encryption and privacy protection technologies such as homomorphic encryption and differential privacy, ensures the security and privacy of sensitive economic data, avoids the risks of data leakage and abuse, enhances the credibility and reliability of the system; through steps such as feature selection, feature elimination and feature construction, conducts in-depth processing and analysis of economic data, improves the accuracy and generalization ability of subsequent models, and enables the system to better reveal economic laws and conduct predictive analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A topological diagram of the economic data efficient processing system based on cloud computing of the present invention;

[0053] Figure 2 This is a flow chart of the efficient processing method of economic data based on cloud computing of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] Example 1

[0056] See also Figure 1 , the present invention proposes an efficient economic data processing system based on cloud computing, the system includes a data acquisition module, a data preprocessing module, a data storage distribution module, a data analysis module, a feature engineering module, a privacy protection module, a virtual economic prediction module, and an adaptive resource allocation module;

[0057] Among them, it should be noted that the data acquisition module of this system is used for the collection and import of economic data, and ensures that data enters the system accurately from different sources through various means. The data preprocessing module of this system is used for preliminary processing of the original economic data to ensure that the basic data for subsequent analysis is accurate. The data storage and distribution module of this system is used for distributed storage of preprocessed data and provides data services for downstream analysis and processing modules. The data analysis module of this system is used for the calculation and analysis of economic data, and provides basic statistical analysis, prediction and regression modeling capabilities. The feature engineering module of this system is used to improve the accuracy and generalization ability of subsequent models by extracting and expanding features of data. The privacy protection module of this system is used to encrypt and protect data to avoid leakage of sensitive data. The virtual economic forecasting module of this system is used to realize virtual simulation of future economic development, and to construct a virtual environment and predict and simulate economic policies through economic data. The adaptive resource allocation module of this system detects abnormal behaviors that may occur in the system when processing economic data through dynamic allocation and task optimization of cloud computing resources, and automatically corrects them, so as to ensure efficient use of computing resources when processing large-scale economic data.

[0058] In this embodiment, it should also be noted that the data acquisition module of this system also includes a real-time data acquisition unit and a batch data import unit. The real-time data acquisition unit performs real-time data stream acquisition through the Apache Flink stream processing algorithm to process the rapid capture of dynamic data streams in financial markets and price economies. The batch data import unit performs scheduled data batch import operations through Apache Nifi or Talend to ensure regular acquisition of static economic data from government reports and industry analysis.

[0059] In this embodiment, it should also be noted that the data preprocessing module of the system also includes an outlier detection unit and a data standardization unit. The outlier detection unit detects outliers in the data through the Isolation Forest algorithm to filter out unreasonable economic data, including commodity data with abnormal price fluctuations. The data standardization unit normalizes the data through the Z-score normalization algorithm or the Min-Max normalization algorithm to ensure that data from different sources and types can remain consistent in subsequent analysis.

[0060] In this embodiment, it should also be noted that the data storage and distribution module of the system also includes a distributed storage unit and a data distribution unit. The distributed storage unit performs distributed storage of economic data through Hadoop HDFS or Amazon S3, providing efficient storage and reading capabilities. The data distribution unit distributes data through Apache Kafka or RabbitMQ, and pushes the processed data to subscribed modules and users in real time, thereby achieving low-latency data transmission.

[0061] In this embodiment, it should also be noted that the data analysis module of the system also includes a statistical analysis unit and a regression analysis unit. The statistical analysis unit performs basic statistical analysis of economic data through the Pandas library or the statistical package of the R language, and calculates the mean and variance of GDP and inflation economic indicators. The regression analysis unit models and predicts economic data through linear regression and logistic regression algorithms, and analyzes the relationship between variables, including the correlation between commodity price consumption index.

[0062] In this embodiment, it should also be noted that the feature engineering module of this system also includes a feature selection unit and a feature construction unit. The feature selection unit selects the features that have the greatest influence on the economic model through the LASSO regression algorithm, and eliminates low-impact economic variables, including irrelevant data of certain small industries. The feature construction unit performs automated feature construction through the Featuretools feature interaction generation tool, and generates high-order variables based on basic economic data, including a combination of features of return on investment and long-term market fluctuations.

[0063] In this embodiment, it should also be noted that the privacy protection module of this system also includes a homomorphic encryption unit and a differential privacy unit. The homomorphic encryption unit encrypts sensitive economic data through the Paillier homomorphic encryption algorithm, allowing data calculations to be performed in an encrypted state, including calculating the sum of encrypted corporate financial data. The differential privacy unit performs economic statistical calculations while ensuring privacy through the DP-SGD differential privacy algorithm to prevent the disclosure of the precise economic status of individuals or enterprises.

[0064] In this embodiment, it should also be noted that the virtual economic forecasting module of the system also includes an economic model construction unit, a policy impact simulation unit, an abnormal behavior detection unit and an automatic correction unit. The economic model construction unit constructs a virtual economic environment through a Multi-agent system, simulates the interaction of multiple economic entities, including the relationship between the government, enterprises and consumers, and predicts the impact of policies on economic development. The policy impact simulation unit performs multiple random simulations of economic data through a Monte Carlo simulation algorithm to analyze the changes in economic variables under different policy shocks, including the impact of tax policy adjustments on the inflation rate. The abnormal behavior detection unit monitors the calculation process in the system in real time through a Bayesian network to detect possible abnormal situations when processing economic data, including calculation errors or data flow interruptions. The automatic correction unit adjusts system parameters in real time through an adaptive control algorithm. Once erroneous behavior in data processing is detected, the system can automatically adjust the model or restart the calculation process to ensure the accuracy of the final result.

[0065] In this embodiment, it should also be noted that the adaptive resource allocation module of the system also includes an adaptive computing resource allocation unit and a resource scheduling optimization unit. The adaptive computing resource allocation unit dynamically allocates computing resources through the DQN reinforcement learning algorithm, and adjusts the allocation ratio of cloud resources according to the current task load, including adjusting the occupancy of storage and computing resources according to the economic data processing volume. The resource scheduling optimization unit optimizes the scheduling plan of computing resources through a genetic algorithm to ensure that CPU and memory resources can be effectively allocated during peak processing periods to avoid the emergence of economic data processing bottlenecks.

[0066] Example 2

[0067] See also Figure 2 In practical applications, the economic data efficient processing method based on the above system specifically includes the following steps:

[0068] S1. Data collection

[0069] S1.1. Real-time data collection

[0070] Use Apache Flink or Apache Storm to capture real-time economic data from financial markets and price dynamics data streams;

[0071] S1.2. Batch data import

[0072] Import economic data in batches from databases and file systems regularly through Apache Nifi or Talend;

[0073] S1.3. Data integration

[0074] Integrate real-time collected and batch imported data to ensure the comprehensiveness and timeliness of the data;

[0075] S2. Data Preprocessing

[0076] S2.1. Outlier Detection

[0077] Use the 3σ principle statistical method to detect abnormal points in economic data and filter out unreasonable or erroneous data;

[0078] S2.2. Data cleaning

[0079] Clean the detected outliers, including replacing them with the mean, median or deleting them;

[0080] S2.3. Data Standardization

[0081] The economic data is normalized to ensure the consistency of data format and dimension. Z-score is used for normalization, as shown in formula (1):

[0082] x'=(x-μ) / σ (1);

[0083] Where x' is the standardized data point, x is the original data point, μ is the mean, and σ is the standard deviation;

[0084] S3. Data storage and distribution

[0085] S3.1. Distributed Storage

[0086] Distribute and store the pre-processed economic data in the cloud computing platform;

[0087] S3.2. Data index

[0088] Create indexes for stored data to improve data access speed;

[0089] S3.3. Data distribution

[0090] Use Apache Kafka message queues or Amazon Kinesis data streams for data distribution, pushing processed data to subscribed modules and users in real time;

[0091] S4. Data Analysis

[0092] S4.1. Statistical analysis

[0093] Use the mean statistical method to calculate economic indicators and perform basic economic data statistical analysis, as shown in formula (2):

[0094] μ=∑x / n (2);

[0095] In the formula, x is the data point and n is the number of data points;

[0096] S4.2. Regression modeling

[0097] The linear regression and logistic regression algorithms are used to model economic data, as shown in formula (3) and formula (4):

[0098] y=β0+β1x+ε (3);

[0099] P(y=1)=1 / (1+e^(-(β0+β1x))) (4);

[0100] In the formula, y is the dependent variable, x is the independent variable, β0 and β1 are regression coefficients, ε is the error term, and P(y=1) is the probability of y=1;

[0101] S4.3. Predictive analysis

[0102] Use regression models to conduct forecasting analysis and reveal economic laws;

[0103] S5. Feature Engineering

[0104] S5.1. Feature selection

[0105] Lasso regression is used to select the most influential features of the model from a large number of economic variables;

[0106] S5.2. Feature elimination

[0107] Eliminate low-impact or redundant variables;

[0108] S5.3. Feature construction

[0109] The polynomial feature construction algorithm is used to automatically construct features, as shown in formula (5):

[0110] x'=[x1, x2, x1*x2, x12,...] (5);

[0111] In the formula, x' is the constructed feature set, x1 and x2 are the original features;

[0112] S6. Privacy Protection

[0113] S6.1. Homomorphic encryption

[0114] The Paillier algorithm is used to encrypt sensitive economic data using a homomorphic encryption algorithm, as shown in formula (6):

[0115] E(x) = g^x*r^n mod n^2 (6);

[0116] In the formula, E(x) is the encrypted data, g is the generator, x is the plaintext data, r is the random number, and n is the modulus;

[0117] S6.2. Differential Privacy

[0118] The Laplace noise differential privacy algorithm is used for economic statistical calculations, as shown in formula (7):

[0119] y=f(x)+Lap(ε / Δf) (7);

[0120] Where y is the noisy result, f(x) is the original calculation result, Lap(ε / Δf) is the Laplace noise, ε is the privacy budget, and Δf is the sensitivity of the function;

[0121] S6.3. Privacy Balance

[0122] Adjust privacy parameters and algorithms according to specific application scenarios to balance the needs of data utilization and privacy protection;

[0123] S7. Virtual Economic Forecast

[0124] S7.1. Economic model construction

[0125] Use DSGE economic models to build a virtual economic environment and simulate the interaction of multiple economic entities;

[0126] S7.2. Policy shock simulation

[0127] The economic data is simulated multiple times by Monte Carlo simulation, as shown in formula (8):

[0128] y=f(x)+ε (8);

[0129] In the formula, y is the simulation result, f(x) is the economic model, and ε is the random noise;

[0130] S7.3. Anomaly detection and correction

[0131] The Bayesian network is used to monitor the calculation process in the system in real time and make corrections, as shown in formula (9):

[0132] P(A|B)=P(B|A)*P(A) / P(B) (9);

[0133] In the formula, P(A|B) is the conditional probability, P(B|A) is the posterior probability, P(A) is the prior probability, and P(B) is the evidence probability. Correction may involve adjusting model parameters or restarting the calculation process.

[0134] S8. Adaptive resource allocation

[0135] S8.1. Dynamic allocation of resources

[0136] According to the current task load and economic data processing volume, the system needs to dynamically allocate computing resources to ensure that CPU and memory resources can be effectively allocated during peak processing periods, avoid data processing bottlenecks, and improve resource utilization efficiency.

[0137] In summary, this system uses adaptive resource allocation to dynamically allocate computing resources according to the current task load and economic data processing volume, ensuring that CPU and memory resources can be effectively allocated during peak periods, avoiding the emergence of data processing bottlenecks, and improving resource utilization efficiency. Advanced encryption and privacy protection technologies such as homomorphic encryption and differential privacy are used to ensure the security and privacy of sensitive economic data, avoid the risks of data leakage and abuse, and enhance the credibility and reliability of the system. Through steps such as feature selection, feature elimination, and feature construction, the economic data is deeply processed and analyzed to improve the accuracy and generalization ability of subsequent models, so that the system can better reveal economic laws and conduct predictive analysis.

[0138] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An efficient economic data processing system based on cloud computing, characterized in that: It includes data acquisition module, data preprocessing module, data storage distribution module, data analysis module, feature engineering module, privacy protection module, virtual economy prediction module, and adaptive resource allocation module; The data acquisition module is used for collecting and importing economic data; The data preprocessing module is used to perform preliminary processing on the original economic data; The data storage distribution module is used to perform distributed storage on the pre-processed data; The data analysis module is used for calculating and analyzing economic data; The feature engineering module is used to improve the accuracy and generalization ability of subsequent models by extracting and expanding features of data; The privacy protection module is used to encrypt and protect data; The virtual economic forecasting module is used to realize virtual simulation of future economic development, and to construct a virtual environment and forecast and simulate economic policies through economic data; The adaptive resource allocation module detects abnormal behaviors that may occur in the system when processing economic data through dynamic allocation and task optimization of cloud computing resources, and automatically corrects them, so as to ensure efficient use of computing resources when processing large-scale economic data.

2. The economic data efficient processing system based on cloud computing according to claim 1 is characterized by: The data acquisition module also includes a real-time data acquisition unit and a batch data import unit; The real-time data collection unit collects real-time data streams through stream processing algorithms, and processes the rapid capture of dynamic data streams of financial markets and price economies; The batch data import unit performs a scheduled batch data import operation through an ETL tool.

3. The economic data efficient processing system based on cloud computing according to claim 2 is characterized by: The data preprocessing module also includes an outlier detection unit and a data standardization unit; The outlier detection unit is used to detect outliers in the data and filter out unreasonable economic data; The data standardization unit is used to perform normalization processing on the data.

4. The economic data efficient processing system based on cloud computing according to claim 3 is characterized by: The data storage distribution module also includes a distributed storage unit and a data distribution unit; The distributed storage unit is used to perform distributed storage of economic data; The data distribution unit performs data distribution to push the processed data to subscribed modules and users in real time.

5. The economic data efficient processing system based on cloud computing according to claim 4 is characterized by: The data analysis module also includes a statistical analysis unit and a regression analysis unit; The statistical analysis unit is used to perform basic statistical analysis of economic data and calculate the mean and variance of GDP and inflation economic indicators; The regression analysis unit models and predicts economic data through linear regression and logistic regression algorithms, and analyzes the relationship between variables.

6. The economic data efficient processing system based on cloud computing according to claim 5 is characterized by: The feature engineering module also includes a feature selection unit and a feature construction unit; The feature selection unit is used to select the features that have the greatest impact on the economic model and eliminate economic variables with low impact; The feature construction unit performs automated feature construction through a feature interaction generation tool, and generates high-order variables based on basic economic data.

7. The economic data efficient processing system based on cloud computing according to claim 6 is characterized by: The privacy protection module also includes a homomorphic encryption unit and a differential privacy unit; The homomorphic encryption unit encrypts sensitive economic data using a homomorphic encryption algorithm, allowing data calculation to be performed in an encrypted state; The differential privacy unit performs economic statistical calculations under the premise of ensuring privacy through a differential privacy algorithm.

8. The economic data efficient processing system based on cloud computing according to claim 7 is characterized by: The virtual economic forecasting module also includes an economic model building unit, a policy impact simulation unit, an abnormal behavior detection unit and an automatic deviation correction unit; The economic model building unit is used to build a virtual economic environment, simulate the interaction of multiple economic entities, and predict the impact of policies on economic development; The policy impact simulation unit performs multiple random simulations on economic data through a simulation algorithm to analyze changes in economic variables under different policy impacts; The abnormal behavior detection unit monitors the calculation process in the system in real time through the Bayesian network to detect possible abnormal situations when processing economic data; The automatic correction unit adjusts system parameters in real time through an adaptive control algorithm. Once an erroneous behavior in data processing is detected, the system can automatically adjust the model or restart the calculation process to ensure the accuracy of the final result.

9. The economic data efficient processing system based on cloud computing according to claim 8 is characterized by: The adaptive resource allocation module also includes an adaptive computing resource allocation unit and a resource scheduling optimization unit; The adaptive computing resource allocation unit dynamically allocates computing resources through a reinforcement learning algorithm, and adjusts the allocation ratio of cloud resources according to the current task load, including adjusting the occupancy of storage and computing resources according to the economic data processing volume; The resource scheduling optimization unit optimizes the scheduling scheme of computing resources through genetic algorithms to ensure that CPU and memory resources can be effectively allocated during processing peak periods to avoid the occurrence of economic data processing bottlenecks.

10. A method for efficiently processing economic data based on cloud computing, according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1. Capture economic data in real time from financial markets and price dynamics data streams, and import economic data in batches from various data sources regularly through ETL tools; S2. Detect outliers in economic data, filter out unreasonable or erroneous data, and normalize economic data; S3. Distribute and store the pre-processed economic data in the cloud computing platform, and push the processed data to subscribed modules and users in real time; S4. Perform basic statistical analysis of economic data, provide macroeconomic overview, use linear regression and logistic regression algorithms to model and predict economic data, and analyze the relationship between variables; S5. Select the most influential features of the model from a large number of economic variables, eliminate low-impact or redundant variables, construct features based on basic economic data, generate high-order variables, and improve the accuracy and generalization ability of the model; S6. Use homomorphic encryption algorithms to encrypt sensitive economic data, ensure that data can still be calculated in an encrypted state, perform economic statistical calculations while ensuring privacy, and balance data utilization and privacy protection; S7. Construct a virtual economic environment to simulate the interaction of multiple economic entities, perform multiple random simulations on economic data through simulation algorithms, analyze the changes in economic variables under different policy shocks, use Bayesian networks to monitor the calculation process in the system in real time, and adjust system parameters or restart the calculation process in real time through adaptive control methods when abnormal situations are detected; S8. According to the current task load and economic data processing volume, computing resources are dynamically allocated through reinforcement learning algorithms, and genetic algorithms are used to optimize the scheduling of computing resources.

Images