Power enterprise development quality prediction method and system

Abstract

The invention discloses a power enterprise development quality prediction method and system, and the method comprises the following steps: constructing a simulation index system of the power enterprise development quality according to the characteristics of the enterprise development in six aspects: performance growth, management improvement, reform and innovation, output quality, open sharing and sustainable development; determining a simulation index value according to the power enterprise production data; standardizing the original data matrix to obtain a standardized matrix; determining the comprehensive weight of each simulation index by using an analytic hierarchy process in combination with the standardized matrix, and performing weighted summation on the index values to obtain a target layer score based on historical data; according to the method, a long-short-term memory time sequence model is constructed and trained, the trained long-short-term memory time sequence model is used for predicting the score of a power enterprise development target layer in future time, a simulation index system is constructed from multiple aspects, and a comprehensive index score is obtained in combination with an analytic hierarchy process. And the precision of power enterprise development quality simulation prediction is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of digital management of electric power enterprises, and in particular relates to a method for predicting the development quality of electric power enterprises. Background Art

[0002] In the field of business forecasting for power companies, traditional forecasting methods often focus on single-dimensional data analysis, either focusing on financial data such as profit, cost and revenue, or focusing on operational indicators such as power generation, power sales, customer satisfaction, etc. Although this fragmented perspective can provide in-depth insights in each field, it lacks a comprehensive perspective and cannot effectively integrate business and financial data to build a comprehensive indicator system.

[0003] Building a comprehensive indicator system is crucial for the business forecasting of power companies. It not only helps the company's management to review the company's operating conditions from multiple perspectives, but also promotes communication and collaboration between the business department and the financial department, so as to make more informed strategic decisions. However, in actual operation, there are many challenges, such as how to quantify and integrate indicators of different natures, how to balance short-term interests and long-term development, and how to adapt to the ever-changing market environment and technological progress.

[0004] In addition, with the continuous development of the power industry and technological innovation, emerging factors such as new energy generation and smart grids have gradually become important variables affecting the operation of power companies. The addition of these factors has further increased the complexity of business forecasting, requiring power companies to be forward-looking when building an indicator system that can promptly reflect industry development trends and market demand changes.

[0005] In the face of these challenges, it is particularly important to use advanced data analysis technology and simulation prediction tools. For example, big data analysis technology can be used to process and integrate massive amounts of business and financial data, and machine learning algorithms can be used to explore the deep relationships behind the data to build a more accurate prediction model. At the same time, with the help of simulation prediction tools, the operating conditions of the enterprise can be simulated under different assumptions, and the effectiveness of various strategies can be evaluated, thereby providing a scientific basis for the enterprise's strategic planning and decision-making. Summary of the invention

[0006] In order to solve the problems existing in the prior art, the present invention provides a method for predicting the development quality of electric power enterprises. Aiming at the comprehensive simulation of the integration of business and finance of electric power enterprises, an index system for simulation prediction of the development quality of electric power enterprises is proposed based on high-quality development from six aspects: performance growth, management improvement, reform and innovation, output quality, open sharing, and sustainable development. Based on the hierarchical analysis method, the two data types of business and finance are comprehensively considered to obtain the weight of the comprehensive index, and the simulation prediction is carried out by constructing a time series prediction model LSTM. Compared with the simulation prediction method that only considers one aspect, the simulation accuracy of this method is effectively improved, which can make the simulation results more objective and reasonable.

[0007] In order to achieve the above-mentioned object, in a first aspect, the present invention provides a method for predicting the development quality of an electric power enterprise, comprising the following steps:

[0008] According to the six characteristics of enterprise development, namely, performance growth, management improvement, reform and innovation, output quality, open sharing and sustainable development, a simulation index system for the development quality of power enterprises is constructed, and the simulation index values ​​are determined according to the production data of power enterprises;

[0009] Constructing an original data matrix according to the simulation index value, and performing standardization processing on the original data matrix to obtain a standardized matrix;

[0010] Combined with the standardized matrix, the analytic hierarchy process is used to determine the comprehensive weight of each simulation indicator, and the indicator value is weighted and summed according to the comprehensive weight of each simulation indicator to obtain the target layer score based on historical data;

[0011] Construct and train a long short-term memory time series model, take the historical production data of power companies and the target layer scores of historical data as input, and use the trained long short-term memory time series model to predict the target layer scores of power companies in the future.

[0012] Furthermore, the simulation index system for the development quality of power enterprises includes 16 types of simulation indicators:

[0013] The performance growth aspect includes three types of simulation indicators: operating quality, economic benefits and asset safety;

[0014] The management improvement level includes three types of simulation indicators: asset efficiency, personnel efficiency and cost efficiency;

[0015] The reform and innovation aspects include three types of simulation indicators: advanced technology, scientific and technological innovation, and digital transformation;

[0016] The output quality aspect includes three types of simulation indicators: power supply quality, service capability and grid security;

[0017] The open sharing aspect includes two types of simulation indicators: international cooperation and industrial chain ecology;

[0018] The sustainable development aspect includes two types of simulation indicators: environmental benefits and social benefits.

[0019] Furthermore, the 16 types of simulation indicators are determined based on statistics of business-finance integration data of power enterprises.

[0020] Furthermore, combined with the standardized matrix, the hierarchical analysis method is used to determine the comprehensive weight of each simulation indicator, including: taking the comprehensive indicators of power enterprise development quality as the target layer, taking the comprehensive indicators of the six major levels as the criterion layer, and all simulation indicators in the sixteen types of simulation indicator systems as the indicator layer. The relative importance of the simulation indicators is given according to the nine-level scaling method, and the relative importance of the simulation indicators is constructed as a judgment matrix, and a consistency test is performed. The weight of each level is calculated, and the comprehensive score of the power enterprise development quality is obtained as follows:

[0021] Z=w1*z1+w2*z2+…+w m *z m

[0022] Where Z is the comprehensive score of the development quality of power enterprises, i is the i-th index of the simulation index system, w i is the indicator z i The weight of , m is the number of simulation indicators.

[0023] Furthermore, the indicators of business quality include: growth rate of main business income, growth rate of total profit and economic added value; the indicators of economic benefits include operating income profit margin, return on total assets and return on net assets; the indicators of asset safety include: asset-liability ratio, operating cash ratio, interest-bearing debt ratio and non-performing asset ratio; the indicators of asset efficiency include total asset turnover rate, unit asset sales volume and power generation equipment utilization rate; the personnel efficiency considers the labor productivity of all employees; the cost efficiency includes indicators: fixed asset operation and maintenance fee per 10,000 yuan and controllable cost rate; the indicators of advanced technology include the proportion of smart substations and the proportion of distribution automation coverage; the indicators of scientific and technological innovation include: R&D funding intensity, proportion of R&D technicians and number of patents per capita; digital transformation considers the digital development index, which is composed of a third-party organization The power supply quality includes indicators such as power supply reliability, failure and outage rate of transmission and transformation equipment, comprehensive voltage qualification rate and power supply service compliance rate; service capacity includes two indicators: power business environment development index and growth rate of electricity users; indicators for power grid safety include the number of responsible accidents and misoperation events of power grid equipment; indicators for international cooperation include the proportion of foreign procurement, the proportion of power transmission and transmission, and investment in major power projects; the industrial chain ecology considers the added value of upstream and downstream industries; indicators for environmental benefits include smoke emission rate, wastewater emission rate, emission rate of polluting gases such as sulfur dioxide and nitrogen oxides, environmental protection investment rate and application rate of advanced energy-saving and emission reduction technologies; indicators for social benefits include the amount of public donations, total tax payment, number of new jobs, social power supply, employee training coverage and employee income growth rate.

[0024] Furthermore, the power enterprise development quality simulation prediction model is constructed in the following ways:

[0025] The input and output data are normalized by MinMax, an LSTM neural network model is constructed, the MAE function is selected as the loss function, the gradient descent method is used for training, the trained neural network is used to simulate the sample data of the test data set, and the prediction results are obtained after denormalization.

[0026] Furthermore, it also includes displaying the historical production data of power companies and the power companies' development target layer scores in the future through visualization tools.

[0027] On the other hand, the present invention provides a power enterprise development quality prediction system, including a data acquisition module, a data analysis calculation and prediction module, and a visualization module;

[0028] The data acquisition module is used to obtain the historical production data of the power enterprise in the simulation indicator system about the development quality of the power enterprise;

[0029] The data analysis, calculation and prediction module includes a simulation index matrix construction unit, a hierarchical analysis calculation unit and a prediction unit.

[0030] The simulation index matrix construction unit constructs an original data matrix according to the simulation index value, and performs standardization processing on the original data matrix to obtain a standardized matrix;

[0031] The hierarchical analysis calculation unit is used to combine the standardized matrix and use the hierarchical analysis method to determine the comprehensive weight of each simulation indicator, and the indicator value is weighted and summed according to the comprehensive weight of each simulation indicator to obtain the target layer score based on historical data;

[0032] The prediction unit is used to construct and train a long short-term memory time series model, taking the historical production data of the power enterprise and the target layer scores of the historical data as input, and using the trained long short-term memory time series model to predict the target layer scores of the power enterprise development in the future;

[0033] The visualization unit displays the historical production data of the power enterprise and the power enterprise development target layer scores in the future by calling the visualization plug-in.

[0034] In addition, the present invention can also provide a computer device, including a processor and a memory, the memory is used to store a computer executable program, the processor reads the computer executable program from the memory and executes it, and when the processor executes the computer executable program, it can implement the power enterprise development quality prediction method described in the present invention.

[0035] At the same time, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the method for predicting the development quality of electric power enterprises described in the present invention can be implemented.

[0036] Compared with the prior art, the present invention has at least the following beneficial effects: the power enterprise development quality simulation index system proposed in the present invention takes high-quality development as the starting point, comprehensively considers business and financial factors, and constructs 45 simulation indicators including main business income growth rate, total profit growth rate, economic added value, operating income profit margin, total asset return rate, and net asset return rate as a simulation index system from six aspects: performance growth, management improvement, reform and innovation, output quality, open sharing, and sustainable development; the comprehensive prediction method proposed in the present invention utilizes the hierarchical analysis method, which can calculate the comprehensive index value of high-quality development based on business and financial integration data, and uses a time series prediction model for simulation prediction. Compared with the traditional business activity prediction that only considers finance or business unilaterally, this method can effectively improve the simulation prediction accuracy for the high-quality development of enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1It is a flow chart of a method for predicting the development quality of an electric power enterprise described in an embodiment of the present invention.

[0038] Figure 2 It is a schematic diagram of the power enterprise development quality simulation prediction index system.

[0039] Figure 3 It is to partially simulate the prediction results by using the prediction method described in the present invention. DETAILED DESCRIPTION

[0040] The purpose of this invention is to solve the problem of incomplete construction of the traditional power enterprise operation simulation prediction index system. At the same time, the index system is constructed from the financial and business aspects of the high-quality development of the enterprise, and a method for predicting the development quality of the power enterprise is provided, which can help to realize the scientific simulation prediction of the development quality of the power enterprise.

[0041] See also Figure 1 The method for predicting the development quality of a power enterprise described in an embodiment of the present invention comprises the following steps:

[0042] Step 1. Based on the six characteristics of high-quality development, namely performance growth, management improvement, reform and innovation, output quality, open sharing, and sustainable development, a simulation indicator system for the development quality of power enterprises is constructed. Relevant managers can input simulation indicator values ​​into the simulation system based on the internal ERP, financial, and business system data of the power enterprises.

[0043] It should be noted that the reference Figure 2 The simulation index system of the power enterprise development quality described in step 1 includes 45 simulation indicators, as shown in Table 1:

[0044] Table 1

[0045]

[0046]

[0047] Step 2: Use the analytic hierarchy process to determine the indicator weights of each criterion layer and indicator layer simulation indicator in step 1.

[0048] Specifically include: constructing a judgment matrix, two factors i and j, A = (a ij )n×n, where a ij Indicates the importance of the i-th factor compared to the j-th factor. The fuzzy judgment matrix a of any two elements on the criterion layer ij It can be expressed as the meaning of the importance scale, where the values ​​of the membership values ​​of the importance of the two elements can be referred to the table below to check whether the established fuzzy matrix is ​​consistent, refer to Table 2.

[0049] Table 2

[0050]

[0051] Normalize the judgment matrix by column, that is, normalize each column of the judgment matrix A:

[0052]

[0053] Add row by row to get the sum vector:

[0054]

[0055] Normalizing the obtained sum vector, we can get the indicator weight vector:

[0056]

[0057] Calculate the largest eigenvalue λ max :

[0058]

[0059] Perform consistency check and introduce random consistency index RI:

[0060]

[0061] When CR<0.1, the consistency of the judgment matrix is ​​considered acceptable, otherwise the judgment matrix should be modified until the consistency of the judgment matrix is ​​acceptable.

[0062] Table 3 Weight matrix

[0063]

[0064]

[0065] Step 3: Calculate the target layer score based on the indicator weights in step 2.

[0066] The details are as follows: Let A be the target layer score, B i is the criterion layer score, C ij is the index layer score, W i is the criterion layer weight, W ij is the index layer weight, V j is the actual value of the indicator layer, T j is the target value of the indicator layer

[0067] The positive indicator score of the calculation indicator layer is:

[0068] C ij =V j / T j *W ij

[0069] The negative indicator score of the calculation indicator layer is:

[0070] C ij =T j / V j *W ij

[0071] The calculation criteria layer score is:

[0072]

[0073] The target layer score is calculated as:

[0074]

[0075] According to the different importance of different indicators, the following weight matrix is ​​calculated:

[0076] Step 4: Based on the comprehensive score, i.e. the target layer score, a multi-round iterative training method is used to construct a long-term and short-term memory time series model to predict the high-quality development of the enterprise. As an example:

[0077] 1) The dataset construction process is as follows:

[0078] The original data set is described as follows:

[0079]

[0080] The original dataset is partially described as follows:

[0081]

[0082] In order, 70% of the data is used as a training data set to train the model, 20% of the data is used as a validation data set to prevent overfitting, and 10% of the data is used as a test data set to evaluate the quality of model prediction.

[0083] The training process of simulation prediction model using time series prediction model is as follows:

[0084] Set the LSTM model hyperparameters as follows:

[0085]

[0086]

[0087] It is defined that a complete model training process is completed after 30 epochs. The model training is performed three times. The train_loss (MSE) and the vali_loss (MSE) based on the validation data set of each trained model in the last epoch training are as follows:

[0088]

[0089] After each model is trained, the test data set is used to input 90 steps of historical data, predict the next 6 steps of future data, and compare them with the labeled data. The evaluation indicators (MAE, MSE, RMAE) are selected to evaluate the model as follows:

[0090]

[0091] For the original data set, in the three models obtained through training, the values ​​of MAE and MSE are both less than 0.1, which proves that the model training method has the characteristics of low prediction error and stable prediction.

[0092] In order to observe the prediction effect of the model more intuitively, based on the MSE and MAE evaluation indicators, we selected the No. 3 model with better average prediction performance for testing. We input the data of the first 90 days and predicted the data of the last 6 days. The following shows the results of one of the experiments, as shown in the attached figure. Figure 3 As shown, observing the data of the last six days, the blue line is the actual value, and the orange and yellow lines are the predicted values. It can be seen from the figure that the prediction difference is small.

[0093] Based on high-quality development, the present invention comprehensively considers business and financial factors, and constructs 45 simulation indicators including main business income growth rate, total profit growth rate, economic added value, operating income profit margin, total asset return rate, and net asset return rate as a simulation indicator system from six aspects: performance growth, management improvement, reform and innovation, output quality, open sharing, and sustainable development. Refer to Table 1 and Table 2. Based on the hierarchical analysis method, it takes into account the characteristics of business data and financial data, and can minimize the loss of simulation indicator information. Compared with the single-aspect data method, the simulation accuracy of this method is effectively improved, and the simulation results can be more objective and reasonable.

[0095] The present invention can also provide a power enterprise development quality prediction system, including a data acquisition module, a data analysis calculation and prediction module and a visualization module;

[0096] The data acquisition module is used to obtain the historical production data of the power enterprise in the simulation indicator system about the development quality of the power enterprise;

[0097] The data analysis, calculation and prediction module includes a simulation index matrix construction unit, a hierarchical analysis calculation unit and a prediction unit.

[0098] The simulation index matrix construction unit constructs an original data matrix according to the simulation index value, and performs standardization processing on the original data matrix to obtain a standardized matrix;

[0099] The hierarchical analysis calculation unit is used to combine the standardized matrix and use the hierarchical analysis method to determine the comprehensive weight of each simulation indicator, and the indicator value is weighted and summed according to the comprehensive weight of each simulation indicator to obtain the target layer score based on historical data;

[0100] The prediction unit is used to construct and train a long short-term memory time series model, taking the historical production data of the power enterprise and the target layer scores of the historical data as input, and using the trained long short-term memory time series model to predict the target layer scores of the power enterprise development in the future;

[0101] The visualization unit displays the historical production data of the power enterprise and the power enterprise development target layer scores in the future by calling the visualization plug-in.

[0102] Based on the system described in the present invention, the weight values ​​and scores of multiple indicators in six levels, including performance growth, management improvement, reform and innovation, output quality, open sharing, and sustainable development, can be displayed. Based on historical data, a prediction model can be used to obtain annual and monthly prediction results at the six levels, providing a reference for the management and operation of power companies.

[0103] The present invention can also provide a computer device, including a processor and a memory, the memory is used to store a computer executable program, the processor reads the computer executable program from the memory and executes it, and when the processor executes the computer executable program, it can implement the method for predicting the development quality of electric power enterprises described in the present invention.

[0104] On the other hand, the present invention provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method for predicting the development quality of an electric power enterprise described in the present invention can be implemented.

[0105] The computer device may be a laptop computer, a desktop computer or a workstation.

[0106] The processor may be a central processing unit (CPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC) or an off-the-shelf programmable gate array (FPGA). The memory described in the present invention may be an internal storage unit of a laptop computer, a desktop computer or a workstation, such as a memory or a hard disk; an external storage unit may also be used, such as a mobile hard disk or a flash memory card.

[0107] Computer-readable storage media may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer-readable storage media may include: read-only memory (ROM), random access memory (RAM), solid-state drive (SSD) or optical disk, etc. Among them, random access memory may include resistance random access memory (ReRAM) and dynamic random access memory (DRAM).

[0108] Those skilled in the art should recognize that the above embodiments are only used to illustrate the present invention, and are not intended to limit the present invention. As long as they are within the spirit of the present invention, any changes or modifications to the above embodiments will fall within the scope of the claims of the present invention.

Claims

1. A method for predicting the development quality of an electric power enterprise, characterized in that: The following steps are involved: According to the six characteristics of enterprise development, namely, performance growth, management improvement, reform and innovation, output quality, open sharing and sustainable development, a simulation index system for the development quality of power enterprises is constructed, and the simulation index values ​​are determined according to the production data of power enterprises; Constructing an original data matrix according to the simulation index value, and performing standardization processing on the original data matrix to obtain a standardized matrix; Combined with the standardized matrix, the analytic hierarchy process is used to determine the comprehensive weight of each simulation indicator, and the indicator value is weighted and summed according to the comprehensive weight of each simulation indicator to obtain the target layer score based on historical data; Construct and train a long short-term memory time series model, take the historical production data of power companies and the target layer scores of historical data as input, and use the trained long short-term memory time series model to predict the target layer scores of power companies in the future.

2. A method for predicting the development quality of a power enterprise according to claim 1, characterized in that: The simulation index system for the development quality of power enterprises includes 16 types of simulation indicators: The performance growth aspect includes three types of simulation indicators: operating quality, economic benefits and asset safety; The management improvement level includes three types of simulation indicators: asset efficiency, personnel efficiency and cost efficiency; The reform and innovation aspects include three types of simulation indicators: advanced technology, scientific and technological innovation, and digital transformation; The output quality aspect includes three types of simulation indicators: power supply quality, service capability and grid security; The open sharing aspect includes two types of simulation indicators: international cooperation and industrial chain ecology; The sustainable development aspect includes two types of simulation indicators: environmental benefits and social benefits.

3. A method for predicting the development quality of a power enterprise as claimed in claim 2, characterized in that: The 16 types of simulation indicators are determined based on the statistics of the business and financial integration data of the power companies.

4. A method for predicting the development quality of a power enterprise as claimed in claim 2, characterized in that: Combined with the standardized matrix, the comprehensive weight of each simulation indicator is determined by the hierarchical analysis method, including: taking the comprehensive indicators of power enterprise development quality as the target layer, taking the comprehensive indicators of the six major levels as the criterion layer, and all simulation indicators in the sixteen types of simulation indicator systems as the indicator layer. The relative importance of the simulation indicators is given according to the nine-level scaling method, and the relative importance of the simulation indicators is constructed as a judgment matrix, and a consistency test is performed. The weight of each level is calculated, and the comprehensive score of the power enterprise development quality is obtained as follows: Z=w1*w1+w2*w2+…+w m *With m Where Z is the comprehensive score of the development quality of power enterprises, i is the i-th index of the simulation index system, w i is the indicator z i The weight of , m is the number of simulation indicators.

5. A method for predicting the development quality of a power enterprise as claimed in claim 2, characterized in that: The indicators of business quality include: growth rate of main business income, growth rate of total profit and economic added value; the indicators of economic benefits include operating income profit margin, return on total assets and return on net assets; the indicators of asset safety include: asset-liability ratio, operating cash ratio, interest-bearing debt ratio and non-performing asset ratio; the indicators of asset efficiency include total asset turnover rate, unit asset sales volume and power generation equipment utilization rate; the personnel efficiency considers the labor productivity of all employees; the cost efficiency includes indicators: fixed asset operation and maintenance fee per 10,000 yuan and controllable cost rate; the indicators of advanced technology include the proportion of smart substations and the proportion of distribution automation coverage; the indicators of scientific and technological innovation include: R&D funding intensity, proportion of R&D technicians and number of patents per capita; digital transformation considers the digital development index, which is implemented by a third-party organization. The power supply quality includes indicators such as power supply reliability, failure and outage rate of transmission and transformation equipment, comprehensive voltage qualification rate and power supply service compliance rate; service capacity includes two indicators: power business environment development index and the growth rate of the number of electricity users; indicators for power grid safety are the number of responsible accidents and misoperation events of power grid equipment; indicators for international cooperation include the proportion of foreign procurement, the proportion of power transmission and transmission, and investment in major power projects; the industrial chain ecology considers the added value indicators of upstream and downstream industries; indicators for environmental benefits include smoke emission rate, wastewater emission rate, emission rate of polluting gases such as sulfur dioxide and nitrogen oxides, environmental protection investment rate, and application rate of advanced energy-saving and emission reduction technologies; indicators for social benefits include the amount of public donations, total tax payment, number of new jobs, social power supply, employee training coverage rate and employee income growth rate.

6. A method for predicting the development quality of a power enterprise according to claim 1, characterized in that: The power enterprise development quality simulation prediction model is constructed in the following ways: The input and output data are normalized by MinMax, an LSTM neural network model is constructed, the MAE function is selected as the loss function, the gradient descent method is used for training, the trained neural network is used to simulate the sample data of the test data set, and the prediction results are obtained after denormalization.

7. A method for predicting the development quality of a power enterprise as claimed in claim 1, characterized in that: It also includes visualization tools to display the historical production data of power companies and the power companies' development target layer scores in the future.

8. A power enterprise development quality prediction system, characterized in that: It includes data acquisition module, data analysis calculation and prediction module and visualization module; The data acquisition module is used to obtain the historical production data of the power enterprise in the simulation indicator system about the development quality of the power enterprise; The data analysis, calculation and prediction module includes a simulation index matrix construction unit, a hierarchical analysis calculation unit and a prediction unit. The simulation index matrix construction unit constructs an original data matrix according to the simulation index value, and performs standardization processing on the original data matrix to obtain a standardized matrix; The hierarchical analysis calculation unit is used to combine the standardized matrix and use the hierarchical analysis method to determine the comprehensive weight of each simulation indicator, and the indicator value is weighted and summed according to the comprehensive weight of each simulation indicator to obtain the target layer score based on historical data; The prediction unit is used to construct and train a long short-term memory time series model, taking the historical production data of the power enterprise and the target layer scores of the historical data as input, and using the trained long short-term memory time series model to predict the target layer scores of the power enterprise development in the future; The visualization unit displays the historical production data of the power enterprise and the power enterprise development target layer scores in the future by calling the visualization plug-in.

9. A computer device, characterized in that: It includes a processor and a memory, the memory is used to store a computer executable program, the processor reads the computer executable program from the memory and executes it, and when the processor executes the computer executable program, it can implement the power enterprise development quality prediction method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored in a computer-readable storage medium, and when the computer program is executed by a processor, the method for predicting the development quality of an electric power enterprise as described in any one of claims 1 to 7 can be implemented.

Images