Multi-source data-based fuel purchase brief report automatic generation method and related device

Abstract

The invention belongs to the technical field of brief report generation, and discloses a fuel purchase brief report automatic generation method based on multi-source data and a related device. The fuel purchase brief report automatic generation method based on the multi-source data comprises the steps of collecting fuel purchase data information in real time, performing standardization processing on the data information, obtaining the data information after standardization processing, and constructing a fuel purchase data analysis model according to the data information after standardization processing, performing real-time or regular calculation and analysis on the standardized data information by using a fuel purchase data analysis model to obtain an analysis result, designing a template of a fuel purchase brief report, and generating the fuel purchase brief report according to the analysis result and the template of the fuel purchase brief report; according to the method, the efficiency of generating the purchase brief report can be improved, a more accurate and credible decision basis is provided for an enterprise management layer, enterprise management personnel can quickly know the full view and key information of the purchase condition, and the decision efficiency and scientificity are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of briefing generation, and particularly relates to an automatic generation method and related device for fuel procurement briefings based on multi-source data. Background Art

[0002] In the thermal power industry, coal procurement is a key link in ensuring power production and also a core business affecting the operating costs of thermal power enterprises. It plays an important role in the production and management of power plants. Strengthening the management of fuel procurement is of great significance for the safe production and economic operation of thermal power plants. At the same time, doing a good job in fuel procurement is also the primary task to ensure the continuous, balanced, stable and economic supply of coal. Fuel procurement has an important role in enhancing the market competitiveness, status, survival and development of thermal power enterprises.

[0003] The fuel procurement of thermal power enterprises usually involves multiple suppliers, multiple coal types, different transportation methods and procurement plans. The data sources are extensive and the formats are diverse. The data between different departments are often independent of each other and lack an effective integration mechanism, resulting in difficulties in ensuring the consistency and integrity of the data. When compiling procurement briefings, the accuracy and reliability of the data are affected, which in turn affects the procurement decisions and production operations of the enterprise. Secondly, with the expansion of the scale of thermal power enterprises and the intensification of market competition, the fuel procurement management faces many problems. The traditional compilation of procurement briefings mainly relies on manual collection, collation and analysis of data, which is a cumbersome process and prone to errors. For example, information needs to be extracted from a large number of procurement contracts, supplier shipments, inventory records and production data of each power plant, which not only consumes a large amount of manpower and time, but also easily leads to data entry errors and inconsistent formats. Summary of the Invention

[0004] The purpose of the present invention is to provide an automatic generation method and related device for fuel procurement briefings based on multi-source data to overcome the problems existing in the prior art. The present invention can improve the efficiency of generating procurement briefings, provide more accurate and credible decision-making basis for enterprise management, enable enterprise managers to quickly understand the overall situation and key information of the procurement situation, and improve the efficiency and scientificity of decision-making.

[0005] To achieve the above object, the technical solutions adopted by the present invention are as follows: In a first aspect, the present invention provides an automatic generation method for fuel procurement brief based on multi-source data, comprising the following steps: collecting data information on fuel procurement in real time, performing standardized processing on the data information to obtain the standardized data information; constructing a fuel procurement data analysis model based on the standardized data information; using the fuel procurement data analysis model to perform real-time or regular calculation and analysis on the standardized data information to obtain an analysis result; designing a template for the fuel procurement brief, and generating the fuel procurement brief according to the analysis result and the template of the procurement brief; Further, the step of collecting data information on fuel procurement in real time specifically includes: Establishing a data acquisition interface for connecting with a fuel management system, a transportation system, an ERP system, and an external coal market data platform, and collecting data information on fuel procurement in real time through the data acquisition interface, and storing the collected data information in a database; Further, the data information on fuel procurement specifically includes: Basic information of coal suppliers, supply capacity data, coal quality data, procurement contract data, transportation data, coal consumption demand plans of each power plant, inventory data, and production data; Further, the standardized processing specifically includes: Data extraction, data filtering, data conversion, data loading, data cleaning, and data correlation verification; Further, the step of constructing a fuel procurement data analysis model based on the standardized data information specifically includes: Dividing the standardized data information into a training set, a test set, and a validation set, customizing labels for the data information in the training set, constructing a model according to the custom labels, selecting the behavioral characteristics of the model, training the behavioral pattern recognition model using the training set to obtain a trained model, optimizing the trained model using the gradient descent method to obtain an optimized model, then setting evaluation indicators for the model, evaluating the optimized model through the test set to obtain an evaluated model, and then adjusting the parameters of the evaluated model through the validation set to obtain a fuel procurement data analysis model; Further, the gradient descent method specifically includes: Selecting an initial point as the starting value of the parameter, calculating the partial derivative of the objective function with respect to each parameter to obtain a gradient vector, updating the parameter according to the gradient vector and the learning rate, and repeatedly calculating the partial derivative of the objective function with respect to each parameter until the maximum number of iterations is reached; The specific formula includes: ; In the formula, represents the parameter, represents the learning rate; Denote the objective function with respect to the gradient; Furthermore, the generation of the fuel procurement briefing according to the analysis results and the template of the procurement briefing specifically includes: Generate a fuel procurement briefing through a report generation tool and a data visualization tool according to the analysis results and the template of the procurement briefing.

[0006] In a second aspect, the present invention provides an automatic fuel procurement briefing generation system based on multi-source data, including: a data collection and processing module for real-time collecting data information on fuel procurement, performing standardized processing on the data information to obtain standardized data information; a model construction module for constructing a fuel procurement data analysis model according to the standardized data information; a data information analysis module for performing real-time or periodic calculation and analysis on the standardized data information using the fuel procurement data analysis model to obtain analysis results; a briefing generation module for designing a template for the fuel procurement briefing and generating a fuel procurement briefing according to the analysis results and the template of the procurement briefing.

[0007] In a third aspect, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the above method are implemented.

[0008] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0009] The above technical solutions have the following advantages or beneficial effects: In a first aspect, the present invention provides a method for automatically generating a fuel procurement briefing based on multi-source data. The automated data collection and analysis process significantly reduces manual intervention and improves the efficiency of generating the procurement briefing. Through standardized data processing and analysis models, the consistency and reliability of the analysis results are ensured, providing a more accurate and credible decision-making basis for enterprise management. The analysis results help enterprises optimize procurement strategies and reduce costs. By using data visualization techniques, the analysis results are presented in the procurement briefing in the form of intuitive and easy-to-understand charts and graphs, enabling enterprise managers to quickly understand the overall picture and key information of the procurement situation, and improving the efficiency and scientific nature of decision-making. The real-time data collection and analysis function enables the procurement briefing to promptly reflect market changes and the latest dynamics of the enterprise's procurement situation. Enterprise management can obtain the latest procurement information and analysis results at any time and make decisions in a timely manner to respond to market changes and risks. The data from multiple internal departments and external relevant systems of the enterprise is integrated, breaking data silos, promoting information sharing and collaborative work among various internal departments of the enterprise, and improving the overall operation efficiency of the enterprise.

[0010] In a second aspect, the present invention provides a system for automatically generating a fuel procurement briefing based on multi-source data. The data collection and processing module helps eliminate noise and errors in the data and improves the reliability of subsequent data analysis. The model construction module helps enterprises gain a more comprehensive understanding of the fuel procurement situation and provides stronger support for decision-making. The data information analysis module helps enterprises promptly identify problems and take corresponding measures, improving the efficiency and effectiveness of fuel procurement. The briefing generation module reduces the workload of manually preparing the briefing and improves the efficiency and accuracy of briefing generation. Through the present invention, enterprises can obtain more comprehensive, accurate, and timely data analysis results and fuel procurement briefings, providing a more scientific and refined basis for decision-making.

[0011] In a third aspect, the present invention provides a computer device. By executing a specific computer program through a processor, the steps of the method of the present invention can be efficiently implemented. When the computer device performs data processing tasks, it can accurately perform numerical calculations and logical judgments, avoiding errors caused by human factors. At the same time, due to the high stability and reliability of the computer program, the accuracy and consistency of the data processing results can be ensured.

[0012] In a fourth aspect, the present invention provides a computer-readable storage medium. By programming the steps of the method of the present invention into a computer program and storing it on the computer-readable storage medium, users can easily load these programs onto any compatible computer device and execute them without having to rewrite or convert the code, greatly improving the convenience and flexibility of program execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1Schematic flowchart of an automatic fuel procurement briefing generation method based on multi-source data according to the present invention; Figure 2 Schematic flowchart of the process of collecting fuel procurement data information in an embodiment of the present invention; Figure 3 Schematic flowchart of the process of performing standardization processing in an embodiment of the present invention; Figure 4 Schematic flowchart of the process of constructing a fuel procurement data analysis model in an embodiment of the present invention; Figure 5 Schematic flowchart of the process of generating a fuel procurement briefing in an embodiment of the present invention; Figure 6 Schematic diagram of the structure of a computer device according to the present invention. Detailed implementation manners

[0014] The present invention will be further described in detail below with reference to specific embodiments, which are explanations of the present invention rather than limitations. In order to enable those skilled in the art to better understand the solution of the present invention, 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 the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention. It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0015] Embodiment: Refer to Figure 1 , the present invention provides an automatic fuel procurement briefing generation method based on multi-source data, including the following steps: Step 1, refer to Figure 2, combined with the data transmission methods supported by the platform, establish data acquisition interfaces for connecting with the fuel management system, transportation system, ERP system, and external coal market data platform through http, webservice, and message queue modes. Real-time collect the data information of fuel procurement through the data acquisition interfaces, and store the collected data information in the postgresql, hdfs, and es databases according to different data types. Among them, the data information of fuel procurement includes: basic information of coal suppliers, supply capacity data, coal quality data, procurement contract data, transportation data, coal consumption demand plans of each power plant, inventory data, and production data. Then, perform standardized processing on the collected data information to obtain the standardized data information. Among them, see Figure 3 , the standardized processing includes: data extraction, data filtering, data conversion, data loading, data cleaning, and data correlation verification; Preferably, the basic information of coal suppliers includes name, location, contact information, etc.; the supply capacity data includes daily output, inventory, shipping capacity, etc.; the coal quality data includes calorific value, sulfur content, ash content, volatile matter, etc.; the procurement contract data includes contract number, signing date, coal quantity, price, delivery time and location; the transportation data includes transportation method, transportation route, transportation cost, in-transit vehicle information, etc.; the coal consumption demand plans of each power plant include monthly and annual coal demand and coal quality requirements; the inventory data includes the real-time inventory quantity, coal type distribution, inventory location, etc. of each power plant; the production data includes unit load, power generation efficiency, etc.; Preferably, the specific steps of performing standardized processing on the collected data information are as follows: First, use kettle to perform data extraction on the collected data information, that is, extract the required data from the original data source, which may involve full extraction or incremental extraction. Then, perform data filtering on the extracted data information, that is, preliminarily screen the extracted data information to remove invalid or non-compliant data information. Next, perform data conversion on the filtered data information, that is, format and standardize the data, such as date format conversion, data type conversion, etc. Then, perform data loading on the converted data information, that is, load the converted data information into the target system or storage. After that, perform data cleaning on the loaded data information. Data cleaning includes missing value processing, error detection and correction, and duplicate data processing. Missing value processing includes estimating (such as filling with mean or median) the missing data information according to the proportion and importance of the missing values. Error detection and correction include identifying and correcting the error values in the data, such as spelling mistakes, inconsistent formats, etc. Duplicate data processing includes deleting duplicate records and retaining uniqueness. Finally, perform data correlation verification on the cleaned data information to ensure the quality of the data information; Standardized processing can standardize the data according to the pre-set data standards and specifications to ensure the consistency and comparability of the data.

[0016] Step 2, refer to Figure 4 , classify the data information after standardization, where 70% is the training set, 15% is the test set, and 15% is the validation set. In Python, use the apply and map functions of pandas and the LabelEncoder of sklearn to customize labels for the data information in the training set. Secondly, judge the characteristics of the data information required by the model and the business requirements, construct the model according to the custom labels, and select the behavioral characteristics of the model, including feature selection, feature extraction, and feature construction. Then use the training set to train the behavior pattern recognition model to obtain the trained model; use the gradient descent method to optimize the trained model to obtain the optimized model. The optimization goal is to reduce the prediction error and improve the accuracy and efficiency of the model. Then set the evaluation index of the model, evaluate the optimized model through the test set to obtain the evaluated model, and then adjust the parameters of the evaluated model through the validation set to obtain the fuel procurement data analysis model; Preferably, selecting a suitable model includes: if the data label is categorical data, select a classification model. The classification model is suitable for predicting discrete category labels, such as supplier classification, fuel type, etc. Through the decision tree model, in-depth analysis of procurement data can be carried out to optimize procurement decisions and cost control; if the data label is continuous data, select a regression model. The regression model is suitable for predicting continuous procurement costs or quantities. For example, predict fuel prices or procurement volumes through linear regression, and make predictions by fitting the linear relationship between features and target variables; Preferably, the fuel procurement data analysis model includes a supplier evaluation model, a procurement cost analysis model, an inventory analysis model, a plan fulfillment rate analysis model, etc.; the supplier evaluation model evaluates suppliers from multiple dimensions, such as the unit price of factory-standard coal (comparing the price competitiveness of different suppliers by calculating the coal price per unit of heat), the proportion of supply quantity (calculating the proportion of the supply volume of each supplier in the total procurement volume of the enterprise to reflect the importance of its supply), the plan fulfillment rate (the ratio of the actual arrival quantity to the contractually agreed arrival quantity to measure the supplier's performance ability), the coal quality difference (comparing the deviation degree between the actual quality of the coal entering the factory and the contractually agreed quality standard to comprehensively evaluate the stability and compliance of the coal quality), and the market spot performance (analyzing the activity of the supplier in the market spot transaction, the competitiveness of the winning bid price, etc.); the inventory analysis model calculates indicators such as the inventory turnover rate (the ratio of the coal out-of-stock quantity within a certain period to the average inventory level to reflect the inventory management efficiency), the available days of inventory (the current inventory quantity divided by the average daily coal consumption to evaluate the sustainable supply ability of the inventory), etc. by statistically analyzing the inventory data of each power plant, and conducts early warning monitoring on the inventory level, and issues an alarm when the inventory is lower than the safety inventory or higher than the warning inventory; the plan fulfillment rate analysis model calculates the procurement plan fulfillment rate of each power plant according to the procurement contract and the actual arrival situation in time cycles such as daily, weekly, and monthly, as well as the fulfillment situation of different suppliers and different coal types, providing a reference basis for procurement decisions; Preferably, the gradient descent method includes: first, initialize the parameters, that is, select an initial point as the starting value of the parameters (usually randomly selected), then calculate the partial derivative of the objective function with respect to each parameter to obtain the gradient vector. The gradient vector points in the direction of the fastest function growth. Update the parameters according to the gradient vector and the learning rate. The learning rate refers to a hyperparameter used to control the step size of each update, and then repeat the calculation of the partial derivative of the objective function with respect to each parameter until the maximum number of iterations is reached; the specific formulas include: ; In the formula, represents the parameter, represents the learning rate; represents the objective function with respect to gradient; Preferably, for classification models, common evaluation indicators include accuracy, precision, recall, F1 score, and area under the ROC curve (AUC); for regression models, common evaluation indicators include mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and R² score; Preferably, the model parameters after evaluation are adjusted through a validation set, such as the learning rate, regularization parameter, etc., to avoid overfitting or underfitting. For example, cross-validation is used to select the optimal regularization strength.

[0017] Step 3: Use the fuel procurement data analysis model to perform real-time or regular calculations and analyses on the standardized data information to obtain analysis results. Preferably, the analysis results are stored in a database in the form of structured data for subsequent invocation when generating procurement briefs.

[0018] Step 4: Design a template for the fuel procurement brief, and use a report generation tool and a data visualization tool to generate a fuel procurement brief based on the analysis results and the template of the procurement brief. Preferably, referring to Figure 5 , designing the template of the fuel procurement brief includes designing the template and format of the procurement brief. The brief template should include parts such as a cover, table of contents, main body, and appendix, covering content sections such as the company's monthly procurement overview, procurement details of each supplier, procurement progress and inventory status of each unit, monthly main long-term agreement loading requests, and relevant analyses and suggestions, etc.; in the main body, the analysis results are presented in various forms such as text descriptions, chart displays, and data tables, making the brief content concise, clear, intuitive, and easy to understand. For example, a bar chart is used to show the comparison of procurement volumes of different suppliers, a line chart is used to show the historical trend and predicted trend of coal prices, and a table is used to list the inventory data and procurement plan fulfillment rates of each power plant, etc. Preferably, generating a fuel procurement brief through a report generation tool and a data visualization tool based on the analysis results and the template of the procurement brief includes extracting corresponding data from the database through FineReport, and selecting ordinary reports, aggregated reports, and decision-making reports for filling and typesetting according to the format and layout of the template. At the same time, ensure the accuracy and consistency of charts and data, as well as the overall aesthetics and readability of the brief. The generated procurement brief can be output in formats such as HTML, PDF, or Word, which is convenient for enterprise management personnel to view and share on different devices. In addition, the system also provides an online preview function, and users can directly view the content of the brief in the browser after generating the brief without downloading the file.

[0019] Step 5: Obtain feedback from users on the brief to understand their needs and concerns. According to the feedback, improve the content and form of the brief to enhance the quality and practicality of the brief. With the accumulation of data and the development of business, continuously optimize the data analysis algorithm and model to improve the accuracy and efficiency of analysis, and continuously pay attention to new data sources and data types, such as the coal transportation logistics system, etc., and incorporate them into the data sources for generating the brief to enrich the content and perspective of the brief.

[0020] In an embodiment of the present invention, an automatic fuel procurement briefing generation system based on multi-source data is provided, including: A data collection and processing module, configured to collect data information on fuel procurement in real time, perform standardized processing on the data information, and obtain the standardized data information; A model construction module, configured to construct a fuel procurement data analysis model based on the standardized data information; A data information analysis module, configured to perform real-time or regular calculation and analysis on the standardized data information using the fuel procurement data analysis model, and obtain an analysis result; A briefing generation module, configured to design a template for the fuel procurement briefing, and generate a fuel procurement briefing according to the analysis result and the procurement briefing template; A feedback optimization module, configured to understand the needs and concerns of users by having them submit feedback on the briefing, and improve the content and form of the briefing according to the feedback, so as to improve the quality and practicality of the briefing.

[0021] See Figure 6 , in an embodiment of the present invention, a computer device is provided. The computer device includes a processor and a memory. The memory is used to store a computer program. The computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium; the processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the automatic fuel procurement briefing generation method based on multi-source data.

[0022] In one embodiment of the present invention, a computer-readable storage medium is provided, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in a computer device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and, of course, the extended storage medium supported by the computer device; the computer-readable storage medium provides a storage space, and the operating system of the terminal is stored in this storage space; and, one or more instructions suitable for being loaded and executed by the processor are also stored in this storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory; the processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for automatically generating a fuel procurement briefing based on multi-source data in the embodiment.

[0023] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects; moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0024] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0025] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions in Figure 1 one process or multiple processes and / or blocksFigure 1 The functions specified in one or more boxes.

[0026] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the steps of the functions specified in one or more processes and / or boxes Figure 1 One process or more processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes.

[0027] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or equivalently replace some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic generation method for fuel procurement briefing based on multi-source data, characterized in that, It includes the following steps: Collect the data information of fuel procurement in real time, perform standardized processing on the data information to obtain the standardized data information; Construct a fuel procurement data analysis model based on the standardized data information; Use the fuel procurement data analysis model to perform real-time or regular calculations and analyses on the standardized data information to obtain analysis results; Design the template of the fuel procurement briefing, and generate the fuel procurement briefing according to the analysis results and the template of the procurement briefing.

2. The automatic generation method of a fuel procurement briefing based on multi-source data according to claim 1, wherein, The real-time collection of the data information of fuel procurement specifically includes: Establish a data acquisition interface connected to the fuel management system, transportation system, ERP system, and external coal market data platform, and collect the data information of fuel procurement in real time through the data acquisition interface, and store the collected data information in the database.

3. The automatic generation method of a fuel procurement briefing based on multi-source data according to claim 1, characterized in that, The data information of the fuel procurement specifically includes: The basic information of coal suppliers, supply capacity data, coal quality data, procurement contract data, transportation data, coal consumption demand plans of each power plant, inventory data, and production data.

4. The automatic generation method of a fuel procurement briefing based on multi-source data according to claim 1, characterized in that, The standardized processing specifically includes: Data extraction, data filtering, data conversion, data loading, data cleaning, and data correlation verification.

5. The automatic generation method of a fuel procurement briefing based on multi-source data according to claim 1, characterized in that The construction of the fuel procurement data analysis model according to the standardized data information specifically includes: Divide the standardized data information into a training set, a test set, and a validation set, customize labels for the data information in the training set, construct a model according to the customized labels, select the behavioral characteristics of the model, use the training set to train the behavior pattern recognition model to obtain the trained model, optimize the trained model using the gradient descent method to obtain the optimized model, then set the evaluation index of the model, evaluate the optimized model through the test set to obtain the evaluated model, and then adjust the parameters of the evaluated model through the validation set to obtain the fuel procurement data analysis model.

6. The automatic generation method of a fuel procurement briefing based on multi-source data according to claim 5, characterized in that, The gradient descent method specifically includes: Select an initial point as the starting value of the parameters, calculate the partial derivatives of the objective function with respect to each parameter to obtain the gradient vector, update the parameters according to the gradient vector and the learning rate, and repeatedly calculate the partial derivatives of the objective function with respect to each parameter until the maximum number of iterations is reached; The specific formula includes: ； In the formula, represents a parameter, represents the learning rate; represents the objective function with respect to gradient.

7. A method for automatically generating a fuel procurement briefing based on multi-source data according to claim 1, characterized in that, The generation of the fuel procurement briefing according to the analysis results and the template of the procurement briefing specifically includes: Generate the fuel procurement briefing according to the analysis results and the template of the procurement briefing through a report generation tool and a data visualization tool.

8. An automatic fuel procurement briefing generation system based on multi-source data, characterized in that, It includes: A data acquisition and processing module, which is used to collect the data information of fuel procurement in real time, perform standardized processing on the data information to obtain the standardized data information; A model construction module, which is used to construct a fuel procurement data analysis model according to the standardized data information; A data information analysis module, which is used to perform real-time or regular calculations and analyses on the standardized data information using the fuel procurement data analysis model to obtain analysis results; A briefing generation module, which is used to design the template of the fuel procurement briefing and generate the fuel procurement briefing according to the analysis results and the template of the procurement briefing.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images