Methods, devices, storage media, and computer equipment for assessing the electricity price sensitivity of high-energy-consuming enterprises

Abstract

The embodiment of the present application discloses a method, device, storage medium and computer equipment for evaluating the sensitivity of electricity prices of high-energy-consuming enterprises, and relates to the field of enterprise management. The present application collects multiple operational data of an enterprise at different time points within a historical time interval, and generates a data set based on the collected operational data; divides the data set into a training set and a test set; obtains a cost evaluation model after model training and model verification using the training set and the test set; monitors the current influencing factor data of the enterprise; inputs the current influencing factor data into the cost evaluation model to obtain the predicted total cost C1; determines the benchmark cost C0 and the benchmark electricity price P0, and calculates the enterprise's electricity price sensitivity coefficient using the formula (C1‑C0) / (P1‑P0); if the electricity price sensitivity coefficient is greater than the preset threshold, an alarm is issued. The present application not only provides real-time electricity price risk monitoring, but also provides intelligent decision-making support for enterprises, helping enterprises optimize their cost structure and reduce the adverse effects of electricity price changes.

Description

Technical Field

[0001] The present application relates to the field of enterprise management, and in particular to a method, device, storage medium and computer equipment for evaluating the electricity price sensitivity of high-energy-consuming enterprises. Background Art

[0002] In my country's economic system, high-energy-consuming industries occupy a pivotal position, not only providing a strong impetus for the sustained growth of the national economy, but also maintaining a wide range of employment opportunities and social stability. These industries usually cover a number of key areas such as steel, cement, non-ferrous metals, and chemicals, and play an irreplaceable role in promoting infrastructure construction, promoting industrial upgrading, and meeting people's living needs.

[0003] High-energy-consuming industries are facing unprecedented challenges. On the one hand, affected by multiple factors such as limited resources, rising production costs and stricter environmental protection regulations, high-energy-consuming industries are gradually showing a trend of shifting and agglomerating to specific provinces or regions to adapt to new requirements for resource distribution, cost-effectiveness and environmental capacity. Although this geographical reconstruction has alleviated environmental pressure in some areas to a certain extent, it has also exacerbated the problem of resource consumption in the receiving areas.

[0004] On the other hand, many high-energy-consuming enterprises are standing at the crossroads of transformation and upgrading, facing urgent tasks such as technological innovation, energy efficiency improvement, and product structure adjustment to cope with increasingly stringent environmental standards and changes in market demand. In this process, a key factor that cannot be ignored is the operating cost of the enterprise, especially the electricity cost. Due to the production characteristics of high-energy-consuming enterprises, electricity consumption is huge, and electricity expenses often constitute an important part of the total cost of the enterprise. Therefore, any fluctuations in electricity prices may directly affect the profitability and market competitiveness of the enterprise, and even threaten the survival and development of the enterprise.

[0005] How to accurately assess the specific impact of electricity price changes on the costs of high-energy-consuming enterprises, and timely discover and effectively respond to the resulting production and operation risks has become a focus of widespread concern within and outside the industry. Therefore, developing effective assessment models and methods to scientifically quantify the impact of electricity price fluctuations on corporate costs is of great significance for guiding high-energy-consuming enterprises to reasonably adjust production strategies, optimize cost structures, and promote energy conservation and emission reduction. Summary of the invention

[0006] The embodiments of the present application provide a method, device, storage medium and computer equipment for evaluating the electricity price sensitivity of high-energy-consuming enterprises, which can solve the problem of how to accurately evaluate the impact of electricity prices on high-energy-consuming enterprises in the prior art. The technical solution is as follows:

[0007] In a first aspect, an embodiment of the present application provides a method for evaluating the sensitivity of a high energy-consuming enterprise to electricity prices, the method comprising:

[0008] Collecting multiple pieces of operation data of the enterprise at different time points within a historical time interval, and generating a data set based on the collected operation data; wherein each operation data in the data set includes: total cost and influencing factor data, and the influencing factor data includes: electricity price, product price, product output, raw material price, raw material consumption, and industry type code;

[0009] Dividing the data set into a training set and a test set;

[0010] A cost evaluation model is obtained by performing model training and model verification using the training set and the test set;

[0011] Monitoring the current impact factor data of the enterprise; wherein the electricity price in the current impact factor data is P1;

[0012] Inputting the current impact factor data into the cost evaluation model to obtain the predicted total cost C1;

[0013] Determine the benchmark cost C0 and the benchmark electricity price P0, and calculate the electricity price sensitivity coefficient of the enterprise using the formula (C1-C0) / (P1-P0);

[0014] If the electricity price sensitivity coefficient is greater than a preset threshold, an alarm is issued.

[0015] In a second aspect, an embodiment of the present application provides a device for evaluating the sensitivity of electricity prices of high energy-consuming enterprises, the device comprising:

[0016] A collection unit, used to collect multiple pieces of operation data of the enterprise at different time points within a historical time interval, and generate a data set based on the collected operation data; wherein each operation data in the data set includes: total cost and influencing factor data, and the influencing factor data includes: electricity price, product price, product output, raw material price, raw material consumption, and industry type code;

[0017] A partitioning unit, used for partitioning the data set into a training set and a test set;

[0018] A training unit, used to obtain a cost evaluation model by performing model training and model verification using the training set and the test set;

[0019] A monitoring unit, used for monitoring the current impact factor data of the enterprise; wherein the electricity price in the current impact factor data is P1;

[0020] An evaluation unit, configured to input the current impact factor data into the cost evaluation model to obtain a predicted total cost C1;

[0021] A calculation unit, used to determine a base cost C0 and a base electricity price P0, and to calculate the electricity price sensitivity coefficient of the enterprise using the formula (C1-C0) / (P1-P0);

[0022] The alarm unit is used to issue an alarm if the electricity price sensitivity coefficient is greater than a preset threshold.

[0023] In a third aspect, an embodiment of the present application provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0024] In a fourth aspect, an embodiment of the present application provides a computer device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0025] The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

[0026] By collecting the company's historical operating data and building a cost assessment model, accurate cost forecasting is achieved. The model can quickly calculate the predicted total cost based on the current influencing factor data, and effectively measure the impact of electricity price changes on corporate costs, that is, the electricity price sensitivity coefficient. When the electricity price sensitivity coefficient exceeds the preset threshold, the system will immediately issue an alarm to indicate electricity price risks. This solution not only provides real-time electricity price risk monitoring, but also provides intelligent decision-making support for enterprises, helping them optimize their cost structure and reduce the adverse effects of electricity price changes. Through accurate forecasting, effective monitoring and intelligent decision-making, this technical solution has significantly improved the company's operating efficiency, enhanced its market competitiveness, and laid a solid foundation for the company's steady development. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 It is a schematic diagram of the network architecture provided by the embodiment of the present application;

[0029] Figure 2 It is a flow chart of a method for evaluating the sensitivity of electricity prices of high energy-consuming enterprises provided in an embodiment of the present application;

[0030] Figure 3 It is a schematic diagram of a trend diagram of electricity price adjustment provided in an embodiment of the present application;

[0031] Figure 4 It is a schematic diagram of a trend change diagram of the electricity price sensitivity coefficient provided in an embodiment of the present application;

[0032] Figure 5 It is a structural schematic diagram of an electricity price sensitivity assessment device for high energy consumption enterprises provided by the present application;

[0033] Figure 6 It is a structural schematic diagram of a computer device provided by this application. DETAILED DESCRIPTION

[0034] In order to make the objectives, technical solutions and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0035] It should be noted that the electricity price sensitivity assessment method for high-energy-consuming enterprises provided in the present application is generally executed by a computer device, and accordingly, the electricity price sensitivity assessment device for high-energy-consuming enterprises is generally set in the computer device.

[0036] Figure 1 An exemplary system architecture of an electricity price sensitivity assessment method or an electricity price sensitivity assessment device for a high energy consumption enterprise that can be applied to the present application is shown.

[0037] like Figure 1 As shown, the system architecture may include: a computer device 101 and a server 102. The computer device 101 and the server 102 may communicate via a network, and the network is used as a medium for providing communication links between the above-mentioned units. The network may include various types of wired communication links or wireless communication links, for example: a wired communication link includes an optical fiber, a twisted pair or a coaxial cable, etc., and a wireless communication link includes a Bluetooth communication link, a wireless fidelity (WIreless-FIdelity, Wi-Fi) communication link or a microwave communication link, etc.

[0038] The server 102 stores the historical operation data of the enterprise. The computer device 101 collects the historical operation data in the server 102 to train a cost evaluation model, and uses the success evaluation model to perform cost evaluation and electricity price sensitivity analysis on the current influencing factor data.

[0039] It should be noted that the computer device 101 and the server 102 can be hardware or software. When the computer device 101 and the server 102 are hardware, they can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the computer device 101 and the server 102 are software, they can be implemented as multiple software or software modules (for example, for providing distributed services), or as a single software or software module, which is not specifically limited here.

[0040] Various communication client applications can be installed on the computer device of the present application, such as: video recording applications, video playback applications, voice interaction applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0041] The computer device may be hardware or software. When the computer device is hardware, it may be various computer devices with a display screen, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers. When the computer device is software, it may be installed in the computer devices listed above. It may be implemented as multiple software or software modules (for example, to provide distributed services), or it may be implemented as a single software or software module, which is not specifically limited here.

[0042] When the computer device is hardware, a display device and a camera may be installed thereon. The display device may be any device capable of realizing a display function, and the camera is used to collect video streams; for example, the display device may be a cathode ray tube display (CR), a light-emitting diode display (LED), an electronic ink screen, a liquid crystal display (LCD), a plasma display panel (PDP), etc. The user may use the display device on the computer device to view displayed text, pictures, videos and other information.

[0043] It should be understood that Figure 1 The number of computer devices, networks and servers in the embodiment is only for illustration. Any number of computer devices, networks and servers may be used as required.

[0044] The following will be combined with the attached Figure 2 , the electricity price sensitivity evaluation method for high energy-consuming enterprises provided in the embodiment of the present application is described in detail. Among them, the electricity price sensitivity evaluation device for high energy-consuming enterprises in the embodiment of the present application can be Figure 1 Computer equipment shown.

[0045] See also Figure 2 , which is a flow chart of a method for evaluating the sensitivity of electricity prices of high energy-consuming enterprises provided in the present application embodiment. Figure 2 As shown, the method of the embodiment of the present application may include the following steps:

[0046] S201. Collect multiple pieces of operation data of the enterprise at different time points within a historical time period, and generate a data set based on the collected operation data.

[0047] Among them, the computer equipment first sets the historical time interval, such as the past 24 months or 36 months. Through the enterprise's internal ERP system, database management system (DBMS) or dedicated operation data platform, use API interface, database query statement (such as SQL) or data export function to batch obtain operation data at different time points. Preprocess the collected raw data, including removing duplicate data, processing missing values ​​(such as using mean, median to fill or delete records with missing values), correcting outliers (such as setting a reasonable range, and data outside the range is considered abnormal and processed). Integrate the cleaned data into a data set in a unified format. Each record contains fields such as total cost, electricity price, product price, product output, raw material price, raw material usage, and industry type code. Add a timestamp to each record for subsequent analysis and time series modeling.

[0048] Further, in the embodiments of the present application, the data collection sources include: corporate financial statements, ERP systems, production systems, and power marketing bills, etc. Corporate financial statements: Collect financial data such as cost, revenue, and profit from the company's financial statements. These statements usually include balance sheets, income statements, cash flow statements, etc., and are important bases for evaluating the economic status of the company. ERP system: The enterprise resource planning (ERP) system is an information system used within the enterprise to integrate various business modules (such as finance, procurement, production, sales, etc.). Detailed operational data such as raw material procurement, production plans, inventory, sales orders, etc. can be obtained from the ERP system. Production system: Directly obtain real-time data in the production process from the company's production system, such as product output, production hours, equipment utilization, energy consumption, etc. These data are crucial for evaluating production efficiency and costs. Power marketing bill: Collect power consumption data such as electricity prices, electricity consumption, and electricity charges from the marketing bills provided by power suppliers. These data are key indicators for evaluating the impact of electricity prices on corporate costs. Computer equipment uses API interfaces: If the above system supports API interfaces, you can call the API interface by writing a program to obtain data in real time or regularly. If the data is stored in a database, you can use SQL or other database query languages ​​to write query statements to obtain the data. If the data is stored in the form of files (such as Excel, CSV, etc.), you can use data import tools or write programs to import the data into the database. Computer equipment integrates data collected from different sources into a unified format of data sets. Clean the data, including removing duplicate data, processing missing values, correcting outliers, etc. Add a timestamp to each record for subsequent analysis and time series modeling.

[0049] S202, dividing the data set into a training set and a test set.

[0050] Among them, a random number generator is used to randomly assign records in the data set to the training set and the test set. The common division ratio is 80% for training and 20% for testing. If there is a class imbalance problem in the data set (such as less data for some raw materials), a stratified sampling method is used to ensure that the proportion of each category in the training set and the test set is consistent with the original data set.

[0051] S203, after model training and model verification using the training set and the test set, a cost evaluation model is obtained.

[0052] Among them, according to domain knowledge and data correlation analysis, select features that have a significant impact on cost prediction, such as electricity prices, raw material prices, etc. Select a suitable machine learning algorithm (such as multivariate linear regression, random forest, gradient boosting tree, etc.), and use the data in the training set to train the model. The training process includes adjusting model parameters (such as learning rate, number of trees, depth, etc.) to minimize the prediction error. During the training process, K-fold cross validation (such as K = 5 or 10) is used to evaluate the generalization ability of the model and avoid overfitting. Use the test set to verify the trained model, calculate the error between the predicted total cost and the actual cost (such as mean square error MSE, mean absolute error MAE, etc.), and evaluate the prediction accuracy of the model.

[0053] S204. Monitor the current impact factor data of the enterprise.

[0054] The current impact factor data is obtained in real time or periodically (such as every hour or every day) through an API interface or database query. The acquired data is preprocessed as necessary, such as format conversion, unit unification, etc. The electricity price in the current impact factor data is recorded as P1.

[0055] S205 , input the current impact factor data into the cost evaluation model to obtain the predicted total cost C1.

[0056] The preprocessed current impact factor data is used as input and passed to the trained cost evaluation model. The model calculates and outputs the predicted total cost C1 based on the input data.

[0057] In some embodiments of the present application, a computer device uses the cost assessment model to calculate the predicted total cost corresponding to each of n electricity prices to obtain n predicted total costs; wherein n is an integer greater than 1, and the n electricity prices increase incrementally at a preset step size; and generates and displays an electricity price adjustment change trend chart based on the n electricity prices and the n predicted total costs.

[0058] Among them, the electricity price range and step size are set: determine an electricity price range (such as ±20% of the current electricity price), and set a step size for the electricity price increase (such as 0.01 yuan / kWh). For each electricity price within the electricity price range (a total of n, where n is an integer greater than 1), keep other influencing factors unchanged, only change the electricity price, input the adjusted influencing factor data into the cost evaluation model, and calculate the corresponding predicted total cost. Take each electricity price and its corresponding predicted total cost as data points for drawing. Use a chart library (such as Matplotlib, ECharts, etc.) to draw a trend chart of electricity price adjustment changes. The chart should clearly show the relationship between the electricity price (horizontal axis) and the predicted total cost (vertical axis). Display the generated electricity price adjustment trend chart on the screen of the computer device, or share it with relevant personnel through emails, reports, etc.

[0059] For example, referring to the electricity price adjustment trend chart shown in 3, the horizontal axis is the electricity price, the vertical axis is the calculated predicted total cost, n=4, and the four electricity prices are 1.5 times, 2 times, 3 times and 4 times the original price (ie, the benchmark electricity price).

[0060] S206: Determine the benchmark cost C0 and the benchmark electricity price P0, and calculate the enterprise's electricity price sensitivity coefficient using the formula (C1-C0) / (P1-P0).

[0061] Among them, a benchmark cost C0 and a benchmark electricity price P0 are set according to historical data or corporate strategy. The benchmark cost can be the average cost in the past period of time, and the benchmark electricity price can be the average electricity price in the same period of time. The electricity price sensitivity coefficient is calculated using the formula (C1-C0) / (P1-P0), where C1 is the predicted total cost and P1 is the current electricity price.

[0062] Further, in some embodiments of the present application, the computer device calculates the difference between the n electricity prices and the benchmark electricity price to obtain n electricity price differences;

[0063] Calculating the differences between the n predicted total costs and the benchmark cost to obtain n total cost differences;

[0064] Calculating n electricity price sensitivity coefficients according to the n total cost differences and the n electricity price differences;

[0065] An electricity price sensitivity coefficient trend change graph is generated according to the n electricity price sensitivity coefficients, the n electricity price differences and the n electricity price sensitivity coefficients.

[0066] Among them, the computer equipment uses the cost evaluation model to calculate the predicted total cost corresponding to each of n electricity prices (increasing in a preset step size) to obtain n predicted total costs. For each electricity price (a total of n), calculate the difference between it and the benchmark electricity price to obtain n electricity price differences. For each predicted total cost (a total of n), calculate the difference between it and the benchmark cost to obtain n total cost differences. Use the formula "electricity price sensitivity coefficient = total cost difference / electricity price difference" to calculate the electricity price sensitivity coefficient corresponding to each electricity price, and obtain n electricity price sensitivity coefficients.

[0067] The computer device uses n electricity price differences, n total cost differences and n electricity price sensitivity coefficients as data points for plotting. Use a chart library (such as Matplotlib, ECharts, etc.) to plot the trend change chart of the electricity price sensitivity coefficient, see Figure 4 As shown, a schematic diagram of the trend change graph of the electricity price sensitivity coefficient is shown. The chart should clearly show the relationship between the electricity price difference (horizontal axis, which can be an absolute difference or a relative percentage) and the electricity price sensitivity coefficient (vertical axis), and different total cost differences can be distinguished by different colors or marks. Display the generated electricity price sensitivity coefficient trend change graph on the screen of the computer device, or share it with relevant personnel through emails, reports, etc. Observe the electricity price sensitivity coefficient trend change graph and analyze the impact trend of electricity price changes on cost sensitivity. If the electricity price sensitivity coefficient increases significantly with the increase of the electricity price difference, it means that the impact of electricity price changes on costs is greater, and the company may need to take corresponding measures to reduce electricity price sensitivity.

[0068] S207: If the electricity price sensitivity coefficient is greater than a preset threshold, an alarm is issued.

[0069] Among them, a reasonable threshold of the electricity price sensitivity coefficient is set according to the enterprise's risk tolerance, cost control objectives, etc. The calculated electricity price sensitivity coefficient is compared with the preset threshold. If the sensitivity coefficient is greater than the threshold, an alarm is triggered. Alarm notifications are sent to the company's managers, financial departments, production departments and other relevant personnel through e-mails, text messages, internal corporate communication tools, etc., reminding them to pay attention to the impact of electricity price changes on costs and suggesting corresponding measures.

[0070] In some embodiments of the present application, the method for determining the preset threshold is:

[0071] Selecting an operation data from the data set as the benchmark operation data, wherein the electricity price of the benchmark operation data is the benchmark electricity price P0, and the cost is the benchmark cost C0;

[0072] Eliminating the operation data whose electricity price is equal to the benchmark electricity price P0 from the data set;

[0073] Calculating the electricity price sensitivity coefficients between the remaining operating data and the benchmark operating data to obtain multiple electricity price sensitivity coefficients,

[0074] The preset threshold value is obtained by averaging the multiple electricity price sensitivity coefficients.

[0075] Among them, a representative operating data is selected from the data set as the benchmark operating data. This data should be typical data of the enterprise under normal operating conditions, with its electricity price recorded as the benchmark electricity price P0 and its cost recorded as the benchmark cost C0. Eliminate data with the same electricity price: Eliminate operating data with an electricity price equal to the benchmark electricity price P0 in the data set to avoid the situation where the denominator is zero when calculating the electricity price sensitivity coefficient and ensure the diversity of data. Calculate the electricity price sensitivity coefficient: For each remaining operating data, calculate the electricity price sensitivity coefficient between it and the benchmark operating data. This usually involves calculating the difference between the electricity price of each operating data and the benchmark electricity price P0 (electricity price difference), and the difference between the cost of each operating data and the benchmark cost C0 (cost difference), and then using the formula "electricity price sensitivity coefficient = cost difference / electricity price difference" for calculation. Calculate the average value to obtain the preset threshold value: The multiple calculated electricity price sensitivity coefficients are averaged, and the result obtained is the preset threshold value. This preset threshold value will be used in subsequent steps to determine whether the impact of electricity price changes on costs is significant. Computer equipment can more accurately determine the preset threshold and conduct a more sophisticated analysis of the impact of electricity price changes on costs based on the threshold. This helps companies better understand their cost structure and develop more reasonable electricity price risk management strategies.

[0076] The present application specifically includes the following beneficial effects:

[0077] By collecting multiple operational data of enterprises in historical time periods, and building a data set based on these data, a cost assessment model is trained, which can accurately predict the total cost of the enterprise based on the current influencing factor data (such as electricity prices, product prices, product output, etc.). This accurate cost prediction capability helps enterprises better control costs and manage budgets.

[0078] The technical solution proposes to use the formula (C1-C0) / (P1-P0) to calculate the enterprise's electricity price sensitivity coefficient, where C1 is the predicted total cost, C0 is the benchmark cost, P1 is the current electricity price, and P0 is the benchmark electricity price. This calculation method can intuitively reflect the impact of electricity price changes on enterprise costs and provide a scientific basis for enterprises to formulate electricity price risk management strategies.

[0079] By monitoring the company's current influencing factor data, especially electricity price data, and inputting this data into the cost assessment model, the technical solution can calculate the predicted total cost and electricity price sensitivity coefficient in real time. When the electricity price sensitivity coefficient is greater than the preset threshold, the system will automatically issue an alarm to remind the company to pay attention to the cost risks that may be caused by electricity price changes. This real-time electricity price risk monitoring capability helps companies take timely measures to reduce the adverse impact of electricity price changes on costs.

[0080] The technical solution not only provides accurate cost forecasting and electricity price sensitivity coefficient calculation functions, but also provides intelligent decision support based on the calculation results. For example, when the electricity price sensitivity coefficient is high, the system can suggest that the enterprise take energy-saving measures, adjust production plans or procurement strategies, etc., to reduce sensitivity to electricity prices, thereby optimizing the cost structure and improving the profitability of the enterprise.

[0081] By implementing this technical solution, enterprises can more accurately grasp the cost changes and respond to changes in factors such as electricity prices in a timely manner, thereby improving operational efficiency and competitiveness. In addition, this technical solution can also provide enterprises with data support and decision-making basis, helping them better respond to market changes and competitive challenges.

[0082] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0083] See also Figure 5 , which shows a schematic diagram of the structure of an electricity price sensitivity assessment device for high energy consumption enterprises provided by an exemplary embodiment of the present application, hereinafter referred to as device 5. The device 5 can be implemented as all or part of a computer device through software, hardware, or a combination of both. The device 5 includes: a collection unit 501, a division unit 502, a training unit 503, a monitoring unit 504, an evaluation unit 505, a calculation unit 506, and an alarm unit 507.

[0084] The collection unit 501 is used to collect multiple pieces of operation data of the enterprise at different time points within a historical time interval, and generate a data set based on the collected operation data; wherein each operation data in the data set includes: total cost and influencing factor data, and the influencing factor data includes: electricity price, product price, product output, raw material price, raw material consumption, and industry type code;

[0085] A division unit 502, configured to divide the data set into a training set and a test set;

[0086] A training unit 503 is used to obtain a cost evaluation model by performing model training and model verification using the training set and the test set;

[0087] A monitoring unit 504 is used to monitor the current impact factor data of the enterprise; wherein the electricity price in the current impact factor data is P1;

[0088] An evaluation unit 505, configured to input the current impact factor data into the cost evaluation model to obtain a predicted total cost C1;

[0089] A calculation unit 506, used to determine a base cost C0 and a base electricity price P0, and to calculate the electricity price sensitivity coefficient of the enterprise using the formula (C1-C0) / (P1-P0);

[0090] The alarm unit 507 is used to issue an alarm if the electricity price sensitivity coefficient is greater than a preset threshold.

[0091] In one or more possible embodiments, a plurality of operational data at different time points in the past three years are collected from the enterprise's financial statements, ERP system, production system, and electricity marketing bills.

[0092] In one or more possible embodiments, 20% of the data in the data set is divided into a training set, and 80% of the data in the data set is divided into a test set.

[0093] In one or more possible embodiments, it further includes:

[0094] A cleaning unit is used to clean and normalize the data set.

[0095] In one or more possible embodiments, it further includes:

[0096] A statistical unit, used to calculate the predicted total costs corresponding to each of the n electricity prices using the cost evaluation model to obtain n predicted total costs; wherein n is an integer greater than 1, and the n electricity prices are incremented by a preset step size;

[0097] An electricity price adjustment change trend graph is generated and displayed according to the n electricity prices and the n predicted total costs.

[0098] In one or more possible embodiments, the statistical unit is further configured to:

[0099] Calculating the differences between the n electricity prices and the benchmark electricity price to obtain n electricity price differences;

[0100] Calculating the differences between the n predicted total costs and the benchmark cost to obtain n total cost differences;

[0101] Calculating n electricity price sensitivity coefficients according to the n total cost differences and the n electricity price differences;

[0102] An electricity price sensitivity coefficient trend change graph is generated according to the n electricity price sensitivity coefficients, the n electricity price differences and the n electricity price sensitivity coefficients.

[0103] In one or more possible embodiments, the method for determining the preset threshold is:

[0104] Selecting an operation data from the data set as the benchmark operation data, wherein the electricity price of the benchmark operation data is the benchmark electricity price P0, and the cost is the benchmark cost C0;

[0105] Eliminating the operation data whose electricity price is equal to the benchmark electricity price P0 from the data set;

[0106] Calculating the electricity price sensitivity coefficients between the remaining operating data and the benchmark operating data to obtain multiple electricity price sensitivity coefficients,

[0107] The preset threshold value is obtained by averaging the multiple electricity price sensitivity coefficients.

[0108] It should be noted that the device 5 provided in the above embodiment only uses the division of the above functional modules as an example when executing the method for evaluating the sensitivity of electricity prices of high-energy-consuming enterprises. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above functions. In addition, the device for evaluating the sensitivity of electricity prices of high-energy-consuming enterprises provided in the above embodiment and the embodiment of the method for evaluating the sensitivity of electricity prices of high-energy-consuming enterprises belong to the same concept. The implementation process is detailed in the method embodiment, which will not be repeated here.

[0109] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0110] The present application also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor as described above. Figure 2 The method steps of the embodiment shown in the figure can be found in the specific implementation process. Figure 2 The specific description of the illustrated embodiment will not be repeated here.

[0111] The present application also provides a computer program product, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the electricity price sensitivity assessment method for high-energy-consuming enterprises as described in the above embodiments.

[0112] See also Figure 6 , which is a schematic diagram of the structure of a computer device according to an embodiment of the present application. Figure 6As shown, the computer device 600 may include: at least one processor 601 , at least one network interface 604 , a user interface 603 , a memory 605 , and at least one communication bus 602 .

[0113] The communication bus 602 is used to realize the connection and communication between these components.

[0114] The user interface 603 may include a display screen (Display) and a camera (Camera), and the optional user interface 603 may also include a standard wired interface and a wireless interface.

[0115] The network interface 604 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0116] Among them, the processor 601 may include one or more processing cores. The processor 601 uses various interfaces and lines to connect the various parts of the entire computer device 600, and executes various functions and processes data of the computer device 600 by running or executing instructions, programs, code sets or instruction sets stored in the memory 605, and calling data stored in the memory 605. Optionally, the processor 601 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 601 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 601, and it can be implemented separately through a chip.

[0117] Among them, the memory 605 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 605 includes a non-transitory computer-readable storage medium. The memory 605 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 605 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 605 may optionally be at least one storage device located away from the aforementioned processor 601. As Figure 6 As shown, the memory 605 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program.

[0118] exist Figure 6 In the computer device 600 shown in FIG. 1 , the user interface 603 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 601 can be used to call the application program stored in the memory 605 and specifically execute the following steps: Figure 2 The specific process can be referred to Figure 2 As shown, no further description is given here.

[0119] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0120] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A method for evaluating the sensitivity of electricity prices of high energy-consuming enterprises, characterized in that: include: Collecting multiple pieces of operation data of the enterprise at different time points within a historical time interval, and generating a data set based on the collected operation data; wherein each operation data in the data set includes: total cost and influencing factor data, and the influencing factor data includes: electricity price, product price, product output, raw material price, raw material consumption, and industry type code; Dividing the data set into a training set and a test set; A cost evaluation model is obtained by performing model training and model verification using the training set and the test set; Monitoring the current impact factor data of the enterprise; wherein the electricity price in the current impact factor data is P1; Inputting the current impact factor data into the cost evaluation model to obtain the predicted total cost C1; Determine the benchmark cost C0 and the benchmark electricity price P0, and calculate the electricity price sensitivity coefficient of the enterprise using the formula (C1-C0) / (P1-P0); If the electricity price sensitivity coefficient is greater than a preset threshold, an alarm is issued.

2. The method according to claim 1, characterized in that: Collect multiple operational data at different time points in the past three years from the company's corporate financial statements, ERP system, production system, and electricity marketing bills.

3. The method according to claim 1 or 2, characterized in that: 20% of the data in the data set is divided into a training set, and 80% of the data in the data set is divided into a test set.

4. The method according to claim 3, characterized in that: Also includes: The data set is cleaned and normalized.

5. The method according to claim 1, 2 or 4, characterized in that: Also includes: The cost evaluation model is used to calculate the predicted total costs corresponding to each of the n electricity prices to obtain n predicted total costs; wherein n is an integer greater than 1, and the n electricity prices are incremented by a preset step size; An electricity price adjustment change trend graph is generated and displayed according to the n electricity prices and the n predicted total costs.

6. The method according to claim 5, characterized in that Also includes: Calculating the differences between the n electricity prices and the benchmark electricity price to obtain n electricity price differences; Calculating the differences between the n predicted total costs and the benchmark cost to obtain n total cost differences; Calculating n electricity price sensitivity coefficients according to the n total cost differences and the n electricity price differences; An electricity price sensitivity coefficient trend change graph is generated according to the n electricity price sensitivity coefficients, the n electricity price differences and the n electricity price sensitivity coefficients.

7. The method according to claim 1 or 2 or 4 or 6, characterized in that: Method for determining the preset threshold: Selecting an operation data from the data set as the benchmark operation data, wherein the electricity price of the benchmark operation data is the benchmark electricity price P0, and the cost is the benchmark cost C0; Eliminating the operation data whose electricity price is equal to the benchmark electricity price P0 from the data set; Calculating the electricity price sensitivity coefficients between the remaining operating data and the benchmark operating data to obtain multiple electricity price sensitivity coefficients, The preset threshold value is obtained by averaging the multiple electricity price sensitivity coefficients.

8. An electricity price sensitivity assessment device for high energy consumption enterprises, characterized in that: include: A collection unit, used to collect multiple pieces of operation data of the enterprise at different time points within a historical time interval, and generate a data set based on the collected operation data; wherein each operation data in the data set includes: total cost and influencing factor data, and the influencing factor data includes: electricity price, product price, product output, raw material price, raw material consumption, and industry type code; A partitioning unit, used for partitioning the data set into a training set and a test set; A training unit, used to obtain a cost evaluation model by performing model training and model verification using the training set and the test set; A monitoring unit, used for monitoring the current impact factor data of the enterprise; wherein the electricity price in the current impact factor data is P1; An evaluation unit, configured to input the current impact factor data into the cost evaluation model to obtain a predicted total cost C1; A calculation unit, used to determine a base cost C0 and a base electricity price P0, and to calculate the electricity price sensitivity coefficient of the enterprise using the formula (C1-C0) / (P1-P0); The alarm unit is used to issue an alarm if the electricity price sensitivity coefficient is greater than a preset threshold.

9. A computer storage medium, characterized in that: The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 7.

10. A computer device, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps as claimed in any one of claims 1 to 7.

Images