Enterprise comprehensive budget management visualization system based on big data and cloud computing

Abstract

The invention relates to the technical field of financial management, and particularly discloses an enterprise comprehensive budget management visualization system based on big data and cloud computing, and the system comprises a data integration module which is used for automatically collecting financial data, budget execution data, historical data and real-time data streams from all business systems of an enterprise, the collected data are stored in a cloud database; the big data analysis module is used for processing the received data through big data analysis and a deep learning model, generating a prediction result of budget execution and calculating key indexes related to budget management; by analyzing and predicting the budget execution condition in real time, reasonable configuration and optimization of budget resources are ensured, and hysteresis and inaccuracy in traditional budget management are avoided. In the budget execution process, information such as change of budget data, execution progress, trend analysis and budget deviation is visually displayed, and a decision maker is helped to quickly find potential problems or risks and make timely adjustment.

Description

Technical Field

[0001] The present invention belongs to the technical field of financial management, and particularly relates to a visualization system for enterprise comprehensive budget management based on big data and cloud computing. Background Art

[0002] In modern enterprise management, budget management, as an important part of enterprise financial management, undertakes key functions such as resource allocation, cost control, and performance appraisal. With the continuous development of big data and cloud computing technologies, the budget management work of enterprises has gradually shifted from the traditional manual operation and static management mode to an intelligent and automated management mode.

[0003] The existing budget management systems are mostly static and manually operated management modes, which have problems such as lagging budget adjustment, difficult data integration, inaccurate budget execution prediction, etc. Especially in the context of the continuous expansion of enterprise business scale and the increasingly complex operating environment, the manual operation and static budget management mode cannot adjust and respond to market changes in a timely manner. These problems lead to inefficient budget resource allocation, lack of real-time performance and flexibility, and cannot effectively utilize the large-scale data resources in enterprises. In addition, the existing budget management systems usually lack intelligent analysis and optimization mechanisms, cannot dynamically adjust the budget plan according to actual data, and do not fully apply advanced technologies such as big data, cloud computing, and artificial intelligence in the decision-making process, which limits the accuracy and flexibility of budget management. Moreover, traditional budget management often relies on simple reports and lacks effective visual analysis, making it difficult for decision-makers to deeply understand the budget execution situation.

[0004] Therefore, it is necessary to propose a visualization system for enterprise comprehensive budget management based on big data and cloud computing to solve the problems of lack of intelligent adjustment and real-time visualization in budget management in the prior art.

[0005] The above information disclosed in this background art is only used to increase the understanding of the background art of the present invention. Therefore, it may include prior art that is not known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a visualization system for enterprise comprehensive budget management based on big data and cloud computing to solve the problems raised in the above background art.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] A visualization system for enterprise comprehensive budget management based on big data and cloud computing, comprising:

[0009] A data integration module, which is used to collect financial data, budget execution data, historical data and real-time data streams from each business system of the enterprise, and store the collected original data in the cloud database;

[0010] A big data analysis module, which is used to process the original data through big data analysis and deep learning models, generate prediction results of budget execution, and calculate key indicators related to budget management;

[0011] A budget adjustment module, which is used to optimize the budget plan by using machine learning algorithms according to the prediction results and the key indicators, generate a budget optimization plan, and provide corresponding budget adjustment suggestions;

[0012] A decision support module, which is used to generate decision support suggestions for budget execution operations according to the budget optimization plan and the budget adjustment suggestions, and adjust the budget optimization strategy according to the dynamic change of data;

[0013] A visualization analysis module, which is used to present all the data generated by budget management and analysis in a graphical interface, and provide interactive data display to realize the in-depth exploration of budget-related data by users according to their needs;

[0014] A budget execution optimization module, which is used to dynamically adjust the resource allocation in the budget execution process by using an adaptive optimization algorithm based on the prediction results in combination with the real-time data stream and historical data in the budget execution;

[0015] An intelligent report generation module, which is used to automatically convert budget data into report texts for decision-makers to refer to based on the real-time budget execution situation in combination with natural language generation technology, and automatically generate customized financial reports.

[0016] Preferably, the data integration module is further used for:

[0017] Adopting a microservices architecture to achieve seamless connection with each business system, and identifying and cleaning abnormal data in the collected data through machine learning algorithms;

[0018] Among them, the reconstruction error formula of the autoencoder is introduced to discover abnormal data in the original data;

[0019]

[0020] In the formula, X i is the input data, X′ j is the output reconstructed by the autoencoder, and L is the reconstruction error;

[0021] Using Apache Hadoop or Spark to perform parallel computing and integration on the original data, and synchronizing the updated data obtained in real time to the cloud database;

[0022] Introduce a time series analysis model, and dynamically adjust the fusion strategy in data integration by analyzing and processing the historical data and the real-time data stream;

[0023] In the cloud database, adaptively adjust the data weights of each business system according to the data quality and reliability of each business system using the following weighted aggregation algorithm formula;

[0024]

[0025] In the formula, D a is the data source after adjusting the data weight, w i is the weight of the data source D i , and n is the number of data sources.

[0026] Preferably, the big data analysis module is further configured to:

[0027] Train and predict the historical data and the real-time data stream through a multi-layer neural network or a long short-term memory network, and automatically generate a prediction result of budget execution;

[0028] Use association rule learning and clustering algorithms to mine the potential relationships between the collected data, and combine anomaly detection techniques to identify potential resource allocation problems and budget deviations in budget execution;

[0029] Introduce a graph convolutional network, and capture the complex dependency relationships between decision points by establishing a graph structure between various decision-making indicators in budget management using the following graph convolution formula;

[0030] H (k+1) =σ(αH (k) W (k) )

[0031] In the formula, H( k+1 ) is the node of the k+1 layer, α is the normalized adjacency matrix, H( k ) is the node representation of the k layer, W( k ) is the weight matrix of the k layer, and σ is the activation function;

[0032] Based on the reinforcement learning model, adjust the budget optimization strategy according to the real-time budget deviation to cope with changes in different business environments.

[0033] Preferably, the budget adjustment module is further configured to:

[0034] Combine the cloud computing environment and use the elastic computing and storage resources of the cloud platform to dynamically adjust the budget plan;

[0035] Based on the analyzed data, by combining a reinforcement learning model with a genetic algorithm and through multiple budget simulations and optimizations, the adaptive optimization of budget allocation and optimization strategies is achieved;

[0036] Combined with the key indicators related to budget management, through a multi-objective optimization algorithm and a Pareto optimization model, comprehensive optimized budget adjustment suggestions are generated;

[0037] A dynamic budget adjustment feedback mechanism is introduced. According to the real-time data stream and the budget deviation, the feedback loop is used to make real-time adjustments to the budget execution situation.

[0038] Preferably, the decision support module is further configured to:

[0039] By integrating a multi-layer decision support model, combining a decision tree with a deep learning algorithm, different focused budget optimization schemes are generated in real time, and the budget allocation strategy is optimized based on model iteration;

[0040] An adaptive time series prediction algorithm is adopted to perform predictive analysis on the budget-related data that changes in real time, so as to provide real-time adjustment suggestions based on the budget execution trend;

[0041] A game theory optimization model is introduced, and the following formula is used to simulate the interest game among departments, and corresponding budget decision suggestions are generated through multi-faceted analysis;

[0042]

[0043] In the formula, U z is the utility of decision maker z, A zr is the strategy influence matrix in the game, and p r is the strategy of other decision makers.

[0044] Preferably, the visualization analysis module is further configured to:

[0045] Through visualization technology, all the data generated by the budget management and analysis and the real-time budget execution situation are converted into corresponding visualization reports, and corresponding decision support texts are generated;

[0046] Based on the deep reinforcement learning algorithm, by simulating and optimizing different decision-making behaviors during the budget execution process, the budget-related data content displayed visually is adjusted in real time;

[0047] Through the incremental learning algorithm formula, continuously learn the feedback of users on the budget-related data displayed visually, and automatically adjust the display form of the visualization analysis results according to the feedback information;

[0048] θ t+1 =θ t +η·▽L(θ t )

[0049] In the formula, θ t+1 is the parameter after learning, and θ t is the current parameter, L(θ t ) is the loss function, η is the learning rate, and ▽L(θ t ) is the gradient.

[0050] Preferably, the budget execution optimization module is further configured to automatically migrate the optimal strategy learned from the historical data to a new budget execution task for different business cycles and budget execution scenarios, so as to quickly adapt to the budget adjustment requirements in different environments;

[0051] The intelligent report generation module is further configured to generate a budget report in real time in the cloud in combination with the cloud computing environment, and generate a customized report and automatically distribute it by using the automation tools of the cloud platform.

[0052] Preferably, the system is further configured to monitor the budget execution difference in real time during the budget execution process through a machine learning algorithm, predict the trend of budget execution within a preset time period, automatically issue a warning and generate an optimization suggestion.

[0053] Compared with the prior art, the beneficial effects of the present invention are:

[0054] By analyzing and predicting the budget execution situation in real time, the present invention ensures the reasonable allocation and optimization of budget resources, and avoids the lag and inaccuracy in traditional budget management. During the budget execution process, it intuitively displays information such as changes in budget data, execution progress, trend analysis, and budget deviation, helping decision-makers quickly discover potential problems or risks and make timely adjustments. This real-time visualization display method not only improves the accuracy of decision-makers' grasp of budget data, but also enhances the response ability and flexibility of budget management. At the same time, through intelligent analysis and optimization technologies, the budget allocation is adaptively adjusted according to changes in the market environment and enterprise needs, significantly improving the accuracy of budget execution, further enhancing the scientific nature of budget management and the timeliness and effectiveness of decision-making support. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a framework diagram of an enterprise comprehensive budget management visualization system based on big data and cloud computing of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0057] Example 1:

[0058] Please refer to Figure 1 As shown, the enterprise comprehensive budget management visualization system based on big data and cloud computing includes:

[0059] A data integration module, which is used to collect financial data, budget execution data, historical data and real-time data streams from each business system of the enterprise, and store the collected raw data in the cloud database;

[0060] Adopt a microservices architecture to achieve seamless connection with each business system, and automatically identify and clean abnormal data in the raw data through machine learning algorithms;

[0061] Among them, introduce the reconstruction error formula of the autoencoder to discover abnormal data in the raw data;

[0062] Use Apache Hadoop or Spark to perform parallel computing and integration on the collected data, and synchronize the updated data obtained in real time to the cloud database;

[0063] Introduce a time series analysis model, and dynamically adjust the fusion strategy in data integration by analyzing and processing historical data and real-time data streams;

[0064] In the cloud database, according to the data quality and reliability of each business system, use the weighted aggregation algorithm to adaptively adjust the data weights of each business system.

[0065] Furthermore, automatically collect data on budget management from each business system of the enterprise, and use machine learning algorithms to effectively identify and process abnormal data to ensure the accuracy and consistency of the data. Introduce a time series analysis model and a weighted aggregation algorithm to dynamically adjust the data integration strategy and adaptively optimize the data weights, thereby improving the efficiency and accuracy of data integration. In addition, use Apache Hadoop or Spark for parallel computing to ensure the rapid update of real-time data and the synchronization of the cloud database.

[0066] A big data analysis module, which is used to process the raw data through big data analysis and deep learning models, generate prediction results of budget execution, and calculate key indicators related to budget management;

[0067] Train and predict historical data and real-time data streams through a multi-layer neural network or a long short-term memory network to automatically generate prediction results of budget execution;

[0068] Use association rule learning and clustering algorithms to mine potential relationships between raw data, and combine anomaly detection techniques to identify potential resource allocation problems and budget deviations in budget execution;

[0069] Introduce a graph convolutional network. By establishing a graph structure among various decision-making indicators in budget management, the graph convolutional network is used to capture the complex dependency relationships between decision-making points;

[0070] Based on a reinforcement learning model, adjust the budget optimization strategy according to real-time budget deviations to cope with changes in different business environments.

[0071] Furthermore, by combining deep learning models and various advanced algorithms, accurately predict the budget execution results and automatically generate key indicator analyses, and be able to flexibly adjust and optimize the budget execution effect in a dynamic business environment, thereby improving the efficiency and flexibility of overall budget management.

[0072] A budget adjustment module, which is used to optimize the budget plan by using machine learning algorithms according to the prediction data and key indicators, generate a budget optimization plan, and provide corresponding budget adjustment suggestions;

[0073] In combination with the cloud computing environment, utilize the elastic computing and storage resources of the cloud platform to dynamically adjust the budget plan;

[0074] Based on the analysis data, combine the reinforcement learning model and genetic algorithm, and through multiple budget simulations and optimizations, achieve the adaptive optimization of budget allocation and optimization strategies;

[0075] Combine the key indicators related to budget management, and generate comprehensively optimized budget adjustment suggestions through multi-objective optimization algorithms and Pareto optimization models;

[0076] Introduce a dynamic budget adjustment feedback mechanism. According to real-time data streams and budget deviations, use feedback loops to adjust the budget execution situation in real time.

[0077] Furthermore, utilize the elastic resources of cloud computing. By combining big data analysis and machine learning algorithms, automatically optimize the budget plan according to the analysis data, and provide accurate budget adjustment suggestions to ensure that the budget allocation and optimization strategies adapt to different business environments. And according to real-time data streams and budget deviations, automatically adjust the budget execution, thereby supporting enterprises to make timely and accurate decisions in a changing environment.

[0078] A decision support module, which is used to generate decision support suggestions for budget execution operations according to the budget optimization plan and budget adjustment suggestions, and adjust the budget optimization strategy according to the dynamic changes of data;

[0079] By integrating a multi-layer decision support model, combining decision trees and deep learning algorithms, generate budget optimization plans with different focuses in real time, and iteratively optimize the budget allocation strategy based on the model;

[0080] Adopt an adaptive time series prediction algorithm to predict and analyze the budget data that changes in real time, so as to provide real-time adjustment suggestions based on the budget execution trend;

[0081] Introduce a game theory optimization model to simulate the interest game among departments, and generate corresponding budget decision-making suggestions through multi-faceted analysis.

[0082] Furthermore, by integrating multi-layer decision support models and advanced algorithms, generate accurate decision support suggestions in real time according to the budget adjustment data, and flexibly optimize the budget strategy according to the dynamic changes of the data, optimize resource allocation, improve the budget execution efficiency, and ensure the scientificity and flexibility of decision-making.

[0083] A visualization analysis module is used to present all the data generated by budget management and analysis in a graphical interface, and provide interactive data display to enable users to deeply explore the budget-related data according to their needs;

[0084] Through visualization technology, all the data generated by budget management and analysis and the real-time budget execution situation are converted into corresponding visualization reports, and corresponding decision support texts are generated;

[0085] Based on the deep reinforcement learning algorithm, by simulating and optimizing different decision-making behaviors during the budget execution process, the budget-related data content displayed visually is adjusted in real time;

[0086] Continuously learn the feedback of users on the budget-related data displayed visually through the incremental learning algorithm, and automatically adjust the display form of the visualization analysis results according to the feedback information.

[0087] Furthermore, by graphically and interactively displaying budget data, enabling users to deeply explore and track the budget execution situation in real time, automatically generating visualization reports and decision support texts, combining with the deep reinforcement learning algorithm to optimize the decision-making behaviors during the budget execution process in real time, dynamically adjusting the display content, while the incremental learning algorithm continuously optimizes the display form according to user feedback, improving the accuracy of data analysis and user experience.

[0088] A budget execution optimization module is used to dynamically adjust the resource allocation during the budget execution process based on the prediction results, combined with the real-time data stream and historical data in the budget execution, using an adaptive optimization algorithm;

[0089] For different business cycles and budget execution scenarios, automatically migrate the optimal strategies learned from historical data to new budget execution tasks to quickly adapt to the budget adjustment requirements in different environments.

[0090] An intelligent report generation module, which is used to automatically convert budget data into report texts for decision-makers' reference based on the real-time budget execution situation, combining natural language generation technology, and automatically generate customized financial reports;

[0091] Combined with the cloud computing environment, generate budget reports in real-time on the cloud, and use the automation tools of the cloud platform to generate customized reports and distribute them automatically.

[0092] During the budget execution process, the system monitors the budget execution differences in real-time and predicts the trend of budget execution within a preset time period through machine learning algorithms, automatically issues early warnings and generates optimization suggestions.

[0093] Embodiment 2:

[0094] Application example: Enterprise employees use the comprehensive budget management visualization system based on big data and cloud computing for business budget management

[0095] In a large manufacturing enterprise, budget management, as an important part of the enterprise's financial management, is responsible for the overall planning and monitoring of the company's resource allocation, expenditure control, and performance assessment. With the expansion of the enterprise scale and the increasing complexity of the operating environment, the traditional budget management model can no longer meet the needs of efficient and real-time budget adjustment. To solve this problem, the enterprise decides to implement a comprehensive budget management visualization system based on big data and cloud computing.

[0096] I. User roles

[0097] Financial supervisor: Responsible for the formulation and adjustment of the company's overall budget.

[0098] Department manager: Responsible for the execution and monitoring of the department budget.

[0099] Senior management: Responsible for the company's strategic decision-making and major budget adjustments.

[0100] Data analyst: Provide data support to help the financial supervisor conduct budget analysis.

[0101] II. Usage process

[0102] The financial supervisor logs in to the comprehensive budget management visualization system based on big data and cloud computing. The system first automatically collects the latest financial data, budget execution data, historical data, and real-time data streams from various business systems (such as procurement, production, sales, etc.). These data are stored in the cloud database and integrated.

[0103] Data analysts use the big data analysis module in the system to process the data collected from various business systems. The system analyzes historical and real-time data through deep learning models and multi-layer neural networks to predict the possible trends of future budget execution. Through the budget execution prediction module, the system generates key indicators of budget execution, such as budget deviation, resource allocation efficiency, etc., and outputs a preliminary budget execution report.

[0104] Based on the analysis data provided by the big data analysis module, the financial supervisor optimizes the existing budget plan within the budget adjustment module. This module uses machine learning algorithms to automatically optimize the budget plan and gives budget adjustment suggestions. For example, if the budget deviation of the sales department is too large, the system will recommend reallocating the budget to ensure that resources are preferentially invested in key areas of sales growth. The financial supervisor can also dynamically adjust the budget allocation according to the system's suggestions.

[0105] The decision support module in the system combines real-time data and historical data to automatically generate decision support suggestions for budget execution through a multi-layer decision support model. These suggestions are based on real-time budget execution trends and market changes to help senior management make accurate budget adjustment decisions. If a certain department has a lag in budget execution, the decision support module will automatically propose how to adjust the strategy to improve budget execution efficiency.

[0106] The financial supervisor and department managers can view the budget execution situation in real time through the visual analysis module. The system converts all data into forms such as charts and trend analysis so that decision-makers can more intuitively understand the budget execution status. For example, Gantt charts of budget execution progress, bar charts of budget deviation, heat maps of resource allocation among departments, etc. Users can explore the budget execution situation in depth through interactive data display and quickly identify potential problems.

[0107] During the process of budget execution, the system monitors the budget execution situation in real time. Through the budget execution optimization module, combining historical data and real-time data streams, the system dynamically adjusts resource allocation. For example, if the raw material procurement cost of the production department exceeds the budget, the system will remind the financial supervisor in real time and give suggestions on adjusting the budget. The financial supervisor can generate an adjustment report through the system automatically and make decisions quickly.

[0108] After the budget execution reaches a certain stage, the system will automatically generate intelligent reports. Combining natural language generation technology, the system converts complex budget execution data into text reports that are easy for decision-makers to understand. The financial supervisor and senior management can evaluate the overall effect of budget execution based on these reports and adjust future budget plans.

[0109] During the budget adjustment process, the system will use multi-objective optimization algorithms and game theory optimization models to provide comprehensive budget adjustment suggestions based on the interest games and resource allocation among departments. These adjustment suggestions not only focus on financial goals but also take into account the synergy among departments and the long-term strategic goals of the company.

[0110] III. Application Results

[0111] Through the application of this system, enterprises can not only achieve real-time monitoring and dynamic adjustment of the budget but also allocate and optimize the budget more accurately. The finance director and senior management can use the prediction and analysis functions of the system to promptly identify deviations and potential problems in budget execution and make quick adjustments based on real-time data, thereby effectively improving the accuracy and flexibility of budget execution. Through interactive visual analysis, budget management becomes more intuitive, helping enterprises maintain the ability to adapt flexibly in a complex market environment.

[0112] Example 3:

[0113] The embodiment of the present invention also provides a computer-readable storage medium. A program of the enterprise comprehensive budget management visualization system based on big data and cloud computing as described in any one of the above is stored on the computer-readable storage medium. When the program is executed by a processor, it realizes each process of the above visualization system embodiment and can achieve the same technical effects. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0114] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without conflict, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0115] In the drawings of the disclosed embodiments of the present invention, only the structures related to the disclosed embodiments of the present invention are involved. Other structures can refer to the general design. Without conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0116] The flowcharts shown in the accompanying drawings are merely illustrative examples, and do not necessarily include all contents and operations / steps, nor are they necessarily executed in the order described. For example, some operations / steps can also be decomposed, combined or partially merged, so the actual execution order may be changed according to the actual situation.

[0117] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A visualization system for enterprise comprehensive budget management based on big data and cloud computing, characterized in that, It includes: A data integration module, which is used to collect financial data, budget execution data, historical data, and real-time data streams from each business system of the enterprise, and store the collected raw data in the cloud database; A big data analysis module, which is used to process the raw data through big data analysis and deep learning models, generate a prediction result of budget execution, and calculate key indicators related to budget management; A budget adjustment module, which is used to optimize the budget plan by using a machine learning algorithm according to the prediction result and the key indicators, generate a budget optimization plan, and provide corresponding budget adjustment suggestions; A decision support module, which is used to generate decision support suggestions for budget execution operations according to the budget optimization plan and the budget adjustment suggestions, and adjust the budget optimization strategy according to dynamic data changes; A visualization analysis module, which is used to present all the data generated by budget management and analysis in a graphical interface, and provide interactive data display to enable users to deeply explore budget-related data according to their needs.

2. The visualization system for enterprise comprehensive budget management based on big data and cloud computing according to claim 1, characterized in that, The data integration module is further used for: Implementing seamless connection with each business system by using a microservices architecture, and identifying and cleaning abnormal data in the collected data through a machine learning algorithm; Among them, the reconstruction error formula of the autoencoder is introduced to discover abnormal data in the raw data; where X i is the input data, X' j is the output reconstructed by the autoencoder, and L is the reconstruction error; Using Apache Hadoop or Spark to perform parallel computing and integration on the raw data, and synchronizing the updated data obtained in real time to the cloud database; Introducing a time series analysis model, and dynamically adjusting the fusion strategy in data integration through the analysis and processing of the historical data and the real-time data stream; In the cloud database, according to the data quality and reliability of each business system, the following weighted aggregation algorithm formula is used to adaptively adjust the data weights of each business system; Where D a is the data source after adjusting the data weight, and w i is the weight of the data source D i , and n is the number of data sources.

3. The visualization system for enterprise comprehensive budget management based on big data and cloud computing according to claim 2, wherein, The big data analysis module is further used for: Training and predicting the historical data and the real-time data stream through a multi-layer neural network or a long short-term memory network, and automatically generating a prediction result of budget execution; Using association rule learning and clustering algorithms to mine the potential relationships between the raw data, and combining anomaly detection techniques to identify potential resource allocation problems and budget deviations in budget execution; Introducing a graph convolutional network, and capturing the complex dependencies between decision points by using the following graph convolution formula by establishing a graph structure between various decision-making indicators in budget management; H (k+1) = σ(αH (k) W (k) ) where, H( k+1 ) is the node of the (k + 1)-th layer, α is the normalized adjacency matrix, H( k ) is the node representation of the k-th layer, W( k ) is the weight matrix of the k-th layer, and σ is the activation function; Based on a reinforcement learning model, adjusting the budget optimization strategy according to the real-time budget deviation to cope with changes in different business environments.

4. The enterprise comprehensive budget management visualization system based on big data and cloud computing according to claim 3, characterized in that The budget adjustment module is further used for: Combining with the cloud computing environment, and dynamically adjusting the budget plan by using the elastic computing and storage resources of the cloud platform; Based on the analysis data, combining a reinforcement learning model and a genetic algorithm, and realizing the adaptive optimization of budget allocation and optimization strategy through multiple budget simulations and optimizations; Combining key indicators related to budget management, and generating comprehensive optimized budget adjustment suggestions through a multi-objective optimization algorithm and a Pareto optimization model; Introducing a dynamic budget adjustment feedback mechanism, and performing real-time adjustment on the budget execution situation by using a feedback loop according to the real-time data stream and the budget deviation.

5. The enterprise comprehensive budget management visualization system based on big data and cloud computing according to claim 4, characterized in that, The decision support module is further configured to: Integrate multi-layer decision support models, combine decision trees with deep learning algorithms, and generate the budget optimization plans with different focuses in real time, and iteratively optimize the budget allocation strategy based on the models; Adopt an adaptive time series prediction algorithm to perform predictive analysis on the budget-related data that changes in real time, and provide real-time adjustment suggestions based on the budget execution trend; Introduce a game theory optimization model, use the following formula to simulate the interest game among departments, and generate corresponding budget decision-making suggestions through multi-faceted analysis; where, U z is the utility of decision maker z, A zr is the strategy influence matrix in the game, and p r is the strategy of other decision makers.

6. The visualized system for comprehensive budget management of enterprises based on big data and cloud computing according to claim 5, wherein The visualization analysis module is further configured to: Convert all the data generated by the budget management and analysis and the real-time budget execution situation into corresponding visualization reports through visualization technology, and generate corresponding decision support texts; Based on the deep reinforcement learning algorithm, simulate and optimize different decision-making behaviors during the budget execution process, and adjust the budget-related data content displayed visually in real time; Continuously learn the user's feedback on the budget-related data displayed visually through the incremental learning algorithm formula, and automatically adjust the display form of the visualization analysis results according to the feedback information; θ t+1 = θ t + η · ∇L(θ t ) Where, θ t+1 is the parameter after learning, θ t is the current parameter, L(θ t ) is the loss function, η is the learning rate, and ▽L(θ t ) is the gradient.

7. The visualized system for enterprise comprehensive budget management based on big data and cloud computing according to claim 6, characterized in that The system further includes: A budget execution optimization module, which is used to dynamically adjust the resource allocation during the budget execution process by using an adaptive optimization algorithm based on the prediction result in combination with the real-time data stream and historical data during the budget execution; An intelligent report generation module, which is used to automatically convert the budget-related data into report texts for decision-makers to refer to based on the real-time budget execution situation in combination with natural language generation technology, and automatically generate customized financial reports.

8. The enterprise comprehensive budget management visualization system based on big data and cloud computing according to claim 7, characterized in that The budget execution optimization module is further configured to automatically transfer the optimal strategy learned from the historical data to a new budget execution task for different business cycles and budget execution scenarios, and quickly adapt to the budget adjustment requirements in different environments; The intelligent report generation module is further configured to generate budget reports in real time in the cloud in combination with the cloud computing environment, and use the automation tools of the cloud platform to generate customized reports and automatically distribute them.

9. The visualization system for enterprise comprehensive budget management based on big data and cloud computing according to claim 8, wherein: The system is further configured to monitor the budget execution difference in real time during the budget execution process through a machine learning algorithm, predict the trend of budget execution within a preset time period, automatically issue early warnings and generate optimization suggestions.

Images