Budget processing method and device based on machine learning, equipment and medium
By adopting machine learning-based budget processing methods in the budget management system, the problems of inefficiency and lack of flexibility in the traditional budget management system are solved, and efficient and accurate budget management and resource optimization allocation are achieved.
Patent Information
- Application Number
- CN202411492682.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-23
- Publication Date
- 2025-02-18
AI Technical Summary
Traditional budget management systems rely on manual data entry and processing, resulting in inefficiency, low accuracy, and lack of flexibility and adaptability, making it difficult to meet the efficient and accurate budget management needs of modern enterprises.
Using machine learning-based budget processing method, we use a pre-deployed prediction model to predict the budget, generate the budget prediction results, and perform results analysis and visualization to generate the target budget report. Generate a budget allocation plan based on the budget forecast results and business rules, and optimize and update the plan to obtain the updated budget allocation strategy.
It improves the efficiency and accuracy of budget processing, avoids manual calculation errors, enhances the flexibility and adaptability of budget allocation, and realizes the optimized allocation and effective utilization of budget resources.
Smart Images
Figure CN119476574A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence and financial technology, and in particular to a budget processing method, device, equipment and medium based on machine learning. Background Art
[0002] In today's complex and ever-changing market environment, budget management is the core link of enterprise resource allocation and strategic planning. Its efficiency and accuracy are directly related to the operational efficiency and market competitiveness of enterprises. Budget processing systems can be insurance systems, banking systems, transaction systems, and order systems. However, traditional budget management systems have gradually exposed a series of problems in response to the management needs of modern enterprises, which has limited their full effectiveness.
[0003] The traditional budget processing method relies on manual data entry, processing and analysis, which is not only time-consuming and labor-intensive, but also prone to data errors due to human factors, which in turn affects the accuracy and reliability of the budget. With the expansion of enterprise scale and the increase in business volume, this manual operation mode can no longer meet the needs of efficient and accurate budget management. The existing budget processing method is based on fixed rules and standards for budget calculation and budget allocation. However, this method lacks flexibility and adaptability. This static budget allocation method cannot make full use of modern data analysis and algorithm optimization technology, and it is difficult to achieve optimal configuration and effective utilization of budget resources. Therefore, an efficient and accurate budget processing method is urgently needed. Summary of the invention
[0004] The purpose of the embodiments of the present application is to propose a budget processing method, device, equipment and medium based on machine learning to improve the efficiency and accuracy of budget processing.
[0005] In order to solve the above technical problems, the present application embodiment provides a budget processing method based on machine learning, including:
[0006] Get real-time budget data;
[0007] Performing forecasting processing on the budget data according to a pre-deployed forecasting model to generate a budget forecasting result;
[0008] Analyze and visualize the budget forecast results to generate a visualized target budget report;
[0009] A budget allocation plan is generated according to the budget forecast result and preset business rules, and the budget allocation plan is optimized and updated to obtain an updated budget allocation strategy.
[0010] In order to solve the above technical problems, the embodiment of the present application provides a budget processing device based on machine learning, including:
[0011] A budget data acquisition unit, used to acquire real-time budget data;
[0012] A budget prediction processing unit, used to perform prediction processing on the budget data according to a pre-deployed prediction model to generate a budget prediction result;
[0013] A budget report generating unit, used for analyzing and visualizing the budget forecast results to generate a visual target budget report;
[0014] The budget allocation optimization unit is used to generate a budget allocation plan according to the budget prediction result and preset business rules, and optimize and update the budget allocation plan to obtain an updated budget allocation strategy.
[0015] In order to solve the above technical problems, a technical solution adopted by the present invention is: to provide a computer device, including one or more processors; a memory for storing one or more programs, so that the one or more processors implement any one of the above-mentioned machine learning-based budget processing methods.
[0016] In order to solve the above technical problems, a technical solution adopted by the present invention is: a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, any one of the above-mentioned machine learning-based budget processing methods is implemented.
[0017] The embodiment of the present invention provides a budget processing method, device, equipment and medium based on machine learning. The method includes: obtaining real-time budget data; predicting and processing the budget data according to a pre-deployed prediction model to generate a budget prediction result; analyzing and visualizing the budget prediction result to generate a visualized target budget report; generating a budget allocation plan according to the budget prediction result and preset business rules, and optimizing and updating the budget allocation plan to obtain an updated budget allocation strategy. The embodiment of the present invention predicts and processes real-time budget data through a prediction model to generate a budget prediction result, thereby avoiding manual budget calculation and improving the efficiency of budget processing; at the same time, the budget allocation plan can be optimized, the utilization rate of budget resources can be provided, and the accuracy of budget processing can be effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0019] Figure 1 is a schematic diagram of an application environment of a budget processing method based on machine learning in one embodiment of the present invention;
[0020] Figure 2 It is a flowchart of the implementation of the budget processing method based on machine learning provided in the embodiment of the present application;
[0021] Figure 3 yes Figure 2 A schematic flow chart of a specific implementation of step S1;
[0022] Figure 4 is a flowchart for implementing a sub-process in a budget processing method based on machine learning provided in another embodiment of the present application;
[0023] Figure 5 yes Figure 4 A schematic flow chart of a specific implementation of step S21;
[0024] Figure 6 yes Figure 4 A schematic flow chart of a specific implementation of step S22;
[0025] Figure 7 yes Figure 2 A schematic flow chart of a specific implementation of step S3;
[0026] Figure 8 yes Figure 4 A schematic flow chart of a specific implementation of step S4;
[0027] Fig. 9 is a schematic diagram of a budget processing device based on machine learning provided in an embodiment of the present application;
[0028] Fig.10 It is a schematic diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.
[0030] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.
[0032] The present invention is described in detail below with reference to the accompanying drawings and embodiments.
[0033] It should be noted that the budget processing method based on machine learning provided in the embodiment of the present application is generally executed by a server, and accordingly, the budget processing device based on machine learning is generally configured in the server.
[0034] The budget processing method based on machine learning provided by the embodiment of the present invention can be applied in the following aspects: Figure 1 In the application environment, the client communicates with the server through the network. The server can receive the budget processing request through the client and obtain real-time budget data; perform forecast processing on the budget data according to the pre-deployed forecast model to generate a budget forecast result; perform result analysis and visualization processing on the budget forecast result to generate a visualized target budget report; generate a budget allocation plan according to the budget forecast result and preset business rules, and optimize and update the budget allocation plan to obtain an updated budget allocation strategy. At the same time, the server can send the target budget report to the client. In the present invention, the real-time budget data is forecasted and processed by the forecast model to generate a budget forecast result, which avoids manual budget calculation and improves the efficiency of budget processing; at the same time, the budget allocation plan can be optimized, and the utilization rate of budget resources can be provided, effectively improving the accuracy of budget processing. Among them, the client can be but not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices. The server can be implemented with an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments.
[0035] See also Figure 2 , Figure 2 A specific implementation of a budget processing method based on machine learning is shown.
[0036] It should be noted that if there are substantially the same results, the method of the present invention is not limited to Figure 1 The process sequence shown is limited to the following steps:
[0037] S1: Get real-time budget data.
[0038] Specifically, since the existing budget processing method is to perform budget calculation and budget allocation based on fixed rules and standards, this method lacks flexibility and adaptability, and it is difficult to achieve the optimal configuration and effective utilization of budget resources, and it is also difficult to perform adaptive processing on real-time budget data. In the present application, budget generation and budget allocation strategy optimization can be performed on real-time budget data, and the optimal configuration and utilization of effective budget resources can be achieved, thereby improving the adaptive processing capability of budget data. Therefore, in the embodiments of the present application, it is necessary to obtain real-time budget data from multiple data sources. Among them, budget data is data covering multiple aspects such as enterprise income, cost, expense, taxes and surcharges, profit, cash flow, and budget difference.
[0039] See also Figure 3 , Figure 3 A specific implementation of step S1 is shown, which is described in detail as follows:
[0040] S11: Monitor budget data streams in real time through a streaming framework.
[0041] S12: Acquire real-time budget data in the budget data stream through a real-time database.
[0042] Specifically, the real-time generated budget data stream is processed through the stream processing framework to ensure the real-time update and feedback of the budget data. Then the real-time database is used to store and query the real-time updated budget data, so as to quickly extract the latest budget data from the budget data stream for subsequent analysis and decision-making.
[0043] Using a streaming processing framework can significantly improve the speed and efficiency of data processing, especially when processing large-scale and high-speed data streams. Real-time monitoring capabilities enable companies to quickly respond to market changes and adjust budget strategies to optimize resource allocation. The use of real-time databases ensures the immediate availability of data, allowing companies to make decisions based on the latest budget data. And the low latency characteristics of real-time databases help reduce data processing and decision-making time, improving overall operational efficiency.
[0044] The stream processing framework is Apache Kafka Streams or Apache Flink, and the real-time database can be Redis or Elasticsearch.
[0045] S2: Perform forecasting processing on the budget data according to the pre-deployed forecasting model to generate a budget forecasting result.
[0046] Specifically, a machine learning algorithm is used to predict the budget data to predict the results of budget generation. The prediction model is first trained using a machine learning algorithm (such as a linear regression algorithm, a decision tree, a random forest, or a neural network), and then the trained prediction model is deployed in the budget processing system. When budget data processing is required, the budget data is predicted and processed using the pre-deployed prediction model to generate a budget prediction result.
[0047] See also Figure 4 , Figure 4 A specific implementation method before step S2 is shown, which is described in detail as follows:
[0048] S21: Collecting initial budget data from multiple data sources, and preprocessing the initial budget data to obtain basic budget data.
[0049] Specifically, before the prediction model is used to predict the budget data, the model needs to be trained. Therefore, in the embodiment of the present application, initial budget data from multiple data sources are collected, and the initial budget data is preprocessed to obtain basic budget data.
[0050] See also Figure 5 , Figure 5 A specific implementation of step S21 is shown, which is described in detail as follows:
[0051] S211: extracting the initial budget data from the plurality of data sources through an ETL tool or a preset data pipeline.
[0052] S212: Preprocessing the initial budget data using a Python data processing library to obtain the basic budget data, wherein the preprocessing includes data cleaning, missing value processing, and abnormal data detection.
[0053] Specifically, the initial budget data is extracted from multiple data sources using an ETL tool or a preset data pipeline, and then the initial budget data is preprocessed using a Python data processing library to obtain the basic budget data.
[0054] Among them, ETL (Extract, Transform, Load) is a term in the field of data warehouse, which refers to the process of extracting data from the source system, transforming it, and loading it into the target system. Here, ETL tools or preset data pipelines are used to extract initial budget data from multiple data sources (such as ERP systems, databases, Excel files, etc.). For example, the ETL tool used is Apache NiFi. The preset data pipeline is a user-defined data pipeline.
[0055] Among them, data cleaning refers to removing duplicate data from the initial budget data, processing inconsistent data, filling missing values, etc. Missing value processing can use fill values (such as mean, median, mode, etc.) or delete rows / columns containing missing values. Abnormal data detection identifies and processes data points that do not conform to the norm, which may be performed through statistical methods (such as z-score, IQR, etc.) or machine learning algorithms (such as isolation forests). Python's data processing libraries: such as Pandas, NumPy, etc., these libraries provide rich data operation and analysis functions.
[0056] S22: Perform feature selection on the basic budget data to obtain initial features.
[0057] Specifically, the most relevant budget features in the basic budget data are selected and transformed using a feature selection algorithm (such as PCA) or domain knowledge, thereby obtaining initial features.
[0058] Among them, principal component analysis (PCA) can extract the most representative features from the original feature set. PCA converts high-dimensional data into low-dimensional data through dimensionality reduction technology, while retaining the information of the original data as much as possible. Thereby removing redundant and noise features and improving the generalization ability of the model. The embodiment of the present application can also select features based on domain knowledge. For example, in budget analysis, obtaining certain specific budget items has a significant impact on the prediction results, so these features can be given priority.
[0059] See also Figure 6 , Figure 6 A specific implementation of step S22 is shown, which is described in detail as follows:
[0060] S221: Calculate a covariance matrix based on the basic budget data.
[0061] S222: Perform eigendecomposition on the covariance matrix to obtain eigenvalues and eigenvectors.
[0062] S223: Selecting an eigenvector corresponding to the eigenvalue according to the size of the eigenvalue as principal component information.
[0063] S224: Projecting the basic budget data into the space formed by the principal component information to obtain dimension-reduced data, and performing feature selection based on the dimension-reduced data to obtain the initial features.
[0064] In the embodiment of the present application, feature selection based on principal component analysis (PCA) is adopted. The covariance matrix is calculated based on the basic budget data. The covariance matrix is subjected to eigendecomposition to obtain eigenvalues and eigenvectors. The eigenvector corresponding to the eigenvalue is selected according to the size of the eigenvalue as the principal component information. The basic budget data is projected into the space formed by the principal component information to obtain the data after dimensionality reduction, and feature selection is performed based on the data after dimensionality reduction to obtain the initial features.
[0065] Among them, the covariance matrix refers to a matrix that measures the degree of linear correlation between variables in a data set. Eigendecomposition is the decomposition of the covariance matrix to obtain eigenvalues and eigenvectors. The eigenvalue represents the importance (i.e., the amount of information) of the corresponding eigenvector. Principal component information is to select eigenvectors with larger eigenvalues as principal components, which represent the main trends of change in the data. Dimensionality reduction refers to projecting the basic budget data into the space composed of principal components, reducing the dimension of the data while retaining the information of the original data as much as possible. Feature selection is to select features with high correlation with the target budget data or large amount of information as initial features in the data after dimensionality reduction.
[0066] S23: performing data standardization processing on the basic features and the target budget data to obtain target features and target budget data.
[0067] Specifically, data standardization techniques (such as MinMaxScaler or StandardScaler) are used to convert data into a uniform numerical range to improve the effect and stability of subsequent model training.
[0068] S24: Performing model training on a preset algorithm model according to the target features and the target budget data to obtain the prediction model, and deploying the prediction model.
[0069] Specifically, the preset algorithm model can be any machine learning model suitable for regression or classification tasks, such as linear regression, decision tree, random forest, neural network, etc. Model training: Use cross-validation, grid search, or Bayesian optimization techniques to train and tune parameters of the model based on target features and target budget data, so that it can learn patterns and relationships in the data and improve prediction accuracy and generalization capabilities. Finally, the prediction model is integrated into the application, service, or system for use in a real environment.
[0070] S3: Analyze and visualize the budget forecast results to generate a visualized target budget report.
[0071] Specifically, the budget forecast results are analyzed to generate a budget report, which can clarify the budget situation. At the same time, the budget report is visualized to generate a visual target budget report, which is convenient for users to view the budget data.
[0072] See also Figure 7 , Figure 7 A specific implementation of step S3 is shown, which is described in detail as follows:
[0073] S31: Using a preset generation tool to generate an initial budget analysis report and a visualization dashboard based on the budget forecast results.
[0074] S32: Generate a target budget analysis report based on the initial budget analysis report and the visualization dashboard using a Python report generation library.
[0075] Specifically, use business intelligence tools (such as Tableau or Power BI) to generate initial budget analysis reports and visualization dashboards. Use Python report generation libraries (such as ReportLab) to generate detailed target budget analysis reports.
[0076] S4: generating a budget allocation plan according to the budget forecast result and preset business rules, and optimizing and updating the budget allocation plan to obtain an updated budget allocation strategy.
[0077] Specifically, a budget allocation plan is generated according to the budget forecast result and the preset business rules; then a real-time optimization algorithm (such as a genetic algorithm or a simulated annealing algorithm) is used to dynamically optimize and adjust the budget allocation strategy generated in real time to obtain an updated budget allocation strategy. The preset business rules are set according to actual conditions and are not limited here.
[0078] See also Figure 8 , Figure 8 A specific implementation of step S4 is shown, which is described in detail as follows:
[0079] S41: generating the budget allocation plan according to the budget forecast result and preset business rules.
[0080] S42: Individuals randomly generated based on the budget allocation strategy are used as the initial population.
[0081] S43: Calculate the fitness of each individual based on the budget prediction result.
[0082] S44: Select a target individual based on the fitness, and perform crossover and mutation processing on the target individual to obtain a new individual.
[0083] S45: adding the new individual to the initial population to obtain a new population, and optimizing and updating the budget allocation strategy based on the new population to obtain the updated budget allocation strategy.
[0084] In the embodiment of the present application, a genetic algorithm is used to dynamically update the budget allocation strategy generated in real time. Specifically, the budget forecast results (such as the expected income and expenditure in the next year) are used as input, and a preliminary budget allocation plan is generated in combination with preset business rules (such as the budget proportion, priority, historical allocation of each department, etc.). The budget allocation plan is converted into a series of quantifiable indicators or parameters (such as the budget amount of each department, project budget, etc.). These parameters are used as individual characteristics to randomly generate an initial population. Each individual represents a possible budget allocation strategy. The budget forecast results are used as a benchmark to evaluate the pros and cons of each individual (i.e., budget allocation strategy). The fitness value of each individual is calculated, usually by comparing the difference between the actual allocation and the forecast results, the degree of meeting the business rules, etc. to measure. Select individuals with higher fitness from the current population as target individuals. The target individual is subjected to crossover (i.e., combining the characteristics of different individuals) and mutation (i.e., randomly changing certain characteristics of the individual) to generate a new individual. The newly generated individual is added to the initial population to form a new population. The new population is used to repeat the fitness calculation, target individual selection, crossover and mutation processing until the stopping condition is met (such as reaching the maximum number of iterations, the fitness reaching the preset threshold, etc.), and finally the optimized budget allocation strategy is obtained.
[0085] In an embodiment of the present application, real-time budget data is obtained; the budget data is predicted and processed according to a pre-deployed prediction model to generate a budget prediction result; the budget prediction result is analyzed and visualized to generate a visualized target budget report; a budget allocation plan is generated according to the budget prediction result and preset business rules, and the budget allocation plan is optimized and updated to obtain an updated budget allocation strategy. The embodiment of the present invention predicts and processes real-time budget data through a prediction model to generate a budget prediction result, thereby avoiding manual budget calculation and improving the efficiency of budget processing; at the same time, the budget allocation plan can be optimized, the utilization rate of budget resources can be provided, and the accuracy of budget processing can be effectively improved.
[0086] The budget generation and allocation process that can be automated by the embodiment of the present application greatly reduces manual operations and human intervention, improves the efficiency and accuracy of budget management, and avoids common errors and delays in traditional budget management. The embodiment of the present application uses machine learning and optimization algorithms to automatically adjust the budget allocation strategy according to real-time data and business rules, making it more in line with actual needs and market changes, and improving the flexibility and adaptability of budget allocation. Through intelligent and real-time budget management, enterprises can better control budget costs and risks, avoid the problem of over- or under-budgeting, and improve the financial stability and competitiveness of the enterprise. Data-driven decision support and visual reports enable managers to understand business conditions and trends more clearly, so as to make more accurate and rational decisions, which is conducive to the long-term development and strategic planning of the enterprise.
[0087] Please refer to Fig. 9 , as a response to the above Figure 2 The present application provides an embodiment of a budget processing device based on machine learning, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.
[0088] like Fig. 9 As shown, the budget processing device based on machine learning in this embodiment includes: a budget data acquisition unit 51, a budget prediction processing unit 52, a budget report generation unit 53 and a budget allocation optimization unit 54, wherein:
[0089] A budget data acquisition unit 51 is used to acquire real-time budget data;
[0090] A budget prediction processing unit 52 is used to perform prediction processing on the budget data according to a pre-deployed prediction model to generate a budget prediction result;
[0091] A budget report generating unit 53 is used to analyze and visualize the budget forecast results to generate a visualized target budget report;
[0092] The budget allocation optimization unit 54 is used to generate a budget allocation plan according to the budget prediction result and preset business rules, and optimize and update the budget allocation plan to obtain an updated budget allocation strategy.
[0093] Furthermore, the budget prediction processing unit 52 further includes:
[0094] A data collection unit, used to collect initial budget data from multiple data sources, and pre-process the initial budget data to obtain basic budget data;
[0095] A feature selection unit, used for performing feature selection on the basic budget data to obtain initial features;
[0096] A data standardization unit, used for performing data standardization processing on the basic features and the target budget data to obtain target features and target budget data;
[0097] The model training unit is used to perform model training on a preset algorithm model according to the target characteristics and the target budget data to obtain the prediction model and deploy the prediction model.
[0098] Furthermore, the feature selection unit includes:
[0099] A covariance matrix calculation unit, used for calculating a covariance matrix based on the basic budget data;
[0100] An eigendecomposition unit, used for performing eigendecomposition on the covariance matrix to obtain eigenvalues and eigenvectors;
[0101] A feature vector selection unit, used for selecting a feature vector corresponding to the feature value as principal component information according to the size of the feature value;
[0102] A data projection unit is used to project the basic budget data into the space formed by the principal component information to obtain the data after dimension reduction, and perform feature selection based on the data after dimension reduction to obtain the initial features.
[0103] Furthermore, the data acquisition unit comprises:
[0104] A data extraction unit, configured to extract the initial budget data from the plurality of data sources through an ETL tool or a preset data pipeline;
[0105] A preprocessing unit is used to preprocess the initial budget data using a Python data processing library to obtain the basic budget data, wherein the preprocessing includes data cleaning, missing value processing and abnormal data detection.
[0106] Furthermore, the budget report generating unit 53 includes:
[0107] An initial analysis unit, configured to generate an initial budget analysis report and a visual dashboard based on the budget forecast result using a preset generation tool;
[0108] The target report generating unit is used to generate a target budget analysis report according to the initial budget analysis report and the visual dashboard by using a report generating library of Python.
[0109] Furthermore, the budget allocation optimization unit 54 includes:
[0110] A budget allocation scheme generating unit, configured to generate the budget allocation scheme according to the budget forecast result and preset business rules;
[0111] An initial population generating unit, used for randomly generating individuals as an initial population based on the budget allocation strategy;
[0112] A fitness calculation unit, used for calculating the fitness of each individual based on the budget prediction result;
[0113] A new individual generation unit is used to select a target individual based on the fitness, and perform crossover and mutation processing on the target individual to obtain a new individual;
[0114] The optimization unit is used to add the new individual to the initial population to obtain a new population, and optimize and update the budget allocation strategy based on the new population to obtain the updated budget allocation strategy.
[0115] Furthermore, the budget data acquisition unit 51 includes:
[0116] A data stream monitoring unit, used for monitoring the budget data stream in real time through a stream processing framework;
[0117] The data acquisition unit is used to acquire the real-time budget data in the budget data stream through a real-time database.
[0118] In an embodiment of the present application, real-time budget data is obtained; the budget data is predicted and processed according to a pre-deployed prediction model to generate a budget prediction result; the budget prediction result is analyzed and visualized to generate a visualized target budget report; a budget allocation plan is generated according to the budget prediction result and preset business rules, and the budget allocation plan is optimized and updated to obtain an updated budget allocation strategy. The embodiment of the present invention predicts and processes real-time budget data through a prediction model to generate a budget prediction result, thereby avoiding manual budget calculation and improving the efficiency of budget processing; at the same time, the budget allocation plan can be optimized, the utilization rate of budget resources can be provided, and the accuracy of budget processing can be effectively improved.
[0119] To solve the above technical problems, the present application also provides a computer device. Fig.10 , Fig.10 This is a basic structural block diagram of the computer device in this embodiment.
[0120] The computer device 7 includes a memory 71, a processor 72, and a network interface 73 which are interconnected and communicated with each other through a system bus. It should be noted that: Fig.10Only a computer device 7 having three components, memory 71, processor 72, and network interface 73, is shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), digital signal processors (DSP), embedded devices, etc.
[0121] Computer devices can be computing devices such as desktop computers, notebooks, PDAs, and cloud servers. Computer devices can interact with users through keyboards, mice, remote controls, touch pads, or voice control devices.
[0122] The memory 71 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 71 can be an internal storage unit of the computer device 7, such as a hard disk or memory of the computer device 7. In other embodiments, the memory 71 can also be an external storage device of the computer device 7, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 7. Of course, the memory 71 can also include both the internal storage unit of the computer device 7 and its external storage device. In this embodiment, the memory 71 is generally used to store the operating system and various application software installed on the computer device 7, such as the program code of the budget processing method based on machine learning, etc. In addition, the memory 71 can also be used to temporarily store various types of data that have been output or are to be output.
[0123] The processor 72 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 72 is generally used to control the overall operation of the computer device 7. In this embodiment, the processor 72 is used to run the program code stored in the memory 71 or process data, such as running the program code of the budget processing method based on machine learning to implement various embodiments of the budget processing method based on machine learning.
[0124] The network interface 73 may include a wireless network interface or a wired network interface, and the network interface 73 is generally used to establish a communication connection between the computer device 7 and other electronic devices.
[0125] The present application also provides another implementation, namely, providing a computer-readable storage medium, which stores a computer program, and the computer program can be executed by at least one processor to enable the at least one processor to perform the steps of a budget processing method based on machine learning as described above.
[0126] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods of each embodiment of the present application.
[0127] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to replace some of the technical features therein with equivalents. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.
Claims
1. A budget processing method based on machine learning, characterized in that: include: Get real-time budget data; Performing forecasting processing on the budget data according to a pre-deployed forecasting model to generate a budget forecasting result; Analyze and visualize the budget forecast results to generate a visualized target budget report; A budget allocation plan is generated according to the budget forecast result and preset business rules, and the budget allocation plan is optimized and updated to obtain an updated budget allocation strategy.
2. The budget processing method based on machine learning according to claim 1, characterized in that: Before performing forecasting processing on the budget data according to the pre-deployed forecasting model to generate a budget forecast result, the method further includes: Collecting initial budget data from multiple data sources, and preprocessing the initial budget data to obtain basic budget data; Performing feature selection on the basic budget data to obtain initial features; Performing data standardization processing on the basic features and the target budget data to obtain target features and target budget data; The preset algorithm model is trained according to the target characteristics and the target budget data to obtain the prediction model, and the prediction model is deployed.
3. The budget processing method based on machine learning according to claim 2, characterized in that: The step of performing feature selection on the basic budget data to obtain initial features includes: Calculate a covariance matrix based on the basic budget data; Performing eigendecomposition on the covariance matrix to obtain eigenvalues and eigenvectors; Selecting an eigenvector corresponding to the eigenvalue as principal component information according to the size of the eigenvalue; The basic budget data is projected into the space formed by the principal component information to obtain dimension-reduced data, and feature selection is performed based on the dimension-reduced data to obtain the initial features.
4. The budget processing method based on machine learning according to claim 2, characterized in that: The collecting of initial budget data from multiple data sources and preprocessing of the initial budget data to obtain basic budget data includes: Extracting the initial budget data from the plurality of data sources through an ETL tool or a preset data pipeline; The initial budget data is preprocessed using a Python data processing library to obtain the basic budget data, wherein the preprocessing includes data cleaning, missing value processing, and abnormal data detection.
5. The budget processing method based on machine learning according to claim 1, characterized in that: The budget forecast results are analyzed and visualized to generate a visualized target budget report, including: Using a preset generation tool to generate an initial budget analysis report and a visualization dashboard based on the budget forecast results; A Python report generation library is used to generate a target budget analysis report based on the initial budget analysis report and the visual dashboard.
6. The budget processing method based on machine learning according to any one of claims 1 to 5, characterized in that: Generating a budget allocation plan according to the budget forecast result and preset business rules, and optimizing and updating the budget allocation plan to obtain an updated budget allocation strategy, includes: Generate the budget allocation plan according to the budget forecast result and preset business rules; Individuals randomly generated based on the budget allocation strategy are used as the initial population; Calculating the fitness of each of the individuals based on the budget prediction result; Selecting a target individual based on the fitness, and performing crossover and mutation processing on the target individual to obtain a new individual; The new individual is added to the initial population to obtain a new population, and the budget allocation strategy is optimized and updated based on the new population to obtain the updated budget allocation strategy.
7. The budget processing method based on machine learning according to any one of claims 1 to 5, characterized in that: The obtaining of real-time budget data includes: Monitor budget data streams in real time through a streaming framework; The real-time budget data in the budget data stream is acquired through a real-time database.
8. A budget processing device based on machine learning, characterized in that: include: A budget data acquisition unit, used to acquire real-time budget data; A budget prediction processing unit, used to perform prediction processing on the budget data according to a pre-deployed prediction model to generate a budget prediction result; A budget report generating unit, used for analyzing and visualizing the budget forecast results to generate a visual target budget report; The budget allocation optimization unit is used to generate a budget allocation plan according to the budget prediction result and preset business rules, and optimize and update the budget allocation plan to obtain an updated budget allocation strategy.
9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the budget processing method based on machine learning as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the budget processing method based on machine learning is implemented as described in any one of claims 1 to 7.