Power transmission line loss rate prediction method and system based on electric quantity and machine account information

Abstract

The invention discloses a power transmission line loss rate prediction method based on electric quantity and ledger information, and the method comprises the steps: obtaining the electric quantity data and ledger information of a power transmission line, and carrying out the preprocessing, and obtaining an original feature set related to the line loss rate; performing feature selection on the original feature set through correlation analysis to obtain key features; training the time convolution network through the key features and the line loss rate to obtain a trained prediction model; and predicting the line loss rate of the power transmission line through the trained prediction model. By fusing various data sources such as the electric quantity data and the machine account information, the prediction robustness is improved, and high prediction accuracy can be kept even under the condition that historical data is incomplete.

Description

Technical Field

[0001] The present invention relates to transmission line loss prediction in the field of electric power grid, and in particular to a transmission line line loss rate prediction method and system based on electric quantity and ledger information. Background Art

[0002] The existing technology for obtaining transmission line losses includes theoretical calculation methods, actual measurement methods, and prediction methods. Theoretical calculations are based on the physical parameters of the line (such as resistance, reactance, etc.) and operating data (such as voltage, current, etc.). This method requires accurate line parameters and operating data, but in reality these data may not be completely accurate or difficult to obtain.

[0003] Actual measurement method: Use an electric energy meter or other equipment to measure the difference in power input and output of the transmission line, and then calculate the line loss rate. This method is subject to the influence of equipment accuracy and environmental factors, and is difficult to monitor in real time.

[0004] Prediction method based on historical data: Use historical data to predict line loss rate. This method usually uses statistical methods or machine learning techniques, such as regression analysis, neural networks, etc., to model historical data to predict future line loss rates. For example, the line loss prediction method based on BP neural network established a line loss prediction model by learning from historical data.

[0005] Prediction method based on grid parameters and electricity growth rate: This method considers whether the number of grid lines and components in the grid forecast year has changed. If not, the line loss rate is predicted based on the electricity growth rate in the grid forecast year, the grid parameters in the grid base year, and the relationship between these parameters. If the grid structure has changed, it is necessary to consider the changes in the variable loss rate and / or fixed loss rate.

[0006] Existing technical methods are highly dependent on the quality and completeness of historical data. If historical data is missing or inaccurate, the reliability of the forecast results will be greatly reduced. Existing forecasting methods often have difficulty adapting well to changes in the grid structure, especially when the grid structure changes, and additional adjustments and parameter updates are required. Traditional statistical methods and simple machine learning models may not be able to capture complex time series patterns, especially in terms of nonlinear relationships and long-term dependencies. Existing methods lack real-time performance, comprehensiveness of forecasts, and accuracy. Summary of the invention

[0007] Purpose of the invention: In view of the above shortcomings, the present invention provides a method and system for predicting transmission line line loss rate based on electricity quantity and ledger information, which improves the comprehensiveness and accuracy of the prediction.

[0008] Technical solution: To solve the above problems, the present invention adopts a method for predicting the line loss rate of a transmission line based on power and ledger information, comprising the following steps:

[0009] Obtain the power data and ledger information of the transmission line, and perform preprocessing to obtain the original feature set related to the line loss rate;

[0010] Perform feature selection on the original feature set through correlation analysis to obtain key features;

[0011] The temporal convolutional network is trained by using key features and line loss rates, and the temporal convolutional network introduces a gated linear unit to obtain a trained prediction model;

[0012] The line loss rate of the transmission line is predicted through the trained prediction model.

[0013] Furthermore, the ledger information includes the line length, material type, load conditions, power supply area, whether it is a rural power grid, and the multiplier of the transmission line; the electricity data includes electricity sales, line loss rate, total capacity of public transformers, total capacity of special transformers, public transformer electricity sales, special transformer electricity sales, high supply and low metering capacity, high supply and low metering electricity sales, and special transformer electricity.

[0014] Further, the preprocessing includes:

[0015] Data cleaning: remove duplicate data, process missing values, and handle outliers;

[0016] Data integration: merging data from multiple data sources;

[0017] Data transformation: normalize, standardize, discretize and construct features of data;

[0018] Feature extraction: select the most informative feature subset;

[0019] Encoding categorical variables: Encoding the variables into a format that can be processed by machine learning algorithms;

[0020] Time series data preprocessing: Differencing, smoothing, or decomposing time series data to extract trend and seasonal components.

[0021] Furthermore, the filling method is used for missing values ​​in electricity data and ledger information; the value with the highest frequency of occurrence is used to fill the missing parts of the three data sets of power supply area, whether it is a rural power grid, and multiple; for the power supply radius, 1 / 2 of the corresponding total wire length is used to fill the missing part; for the empty value of line loss rate, the adjacent value filling method is used to fill it.

[0022] Furthermore, after the temporal convolutional network is trained, the trained model is tested using a test set, and the mean square error (MSE) is used to evaluate the effectiveness of the test set prediction results. The calculation formula of MSE is as follows:

[0023]

[0024] Among them, n is the number of samples in the test set, x i is the true value of the i-th sample, y i is the prediction model for x i is the predicted value of the i-th sample.

[0025] The present invention also adopts a transmission line line loss rate prediction system based on power and ledger information, comprising:

[0026] The data acquisition module is used to obtain the power data and ledger information of the transmission line, and perform preprocessing to obtain the original feature set related to the line loss rate;

[0027] The key feature selection module is used to select the original feature set through correlation analysis to obtain key features;

[0028] A prediction model building module is used to train a temporal convolutional network through key features and line loss rates, wherein the temporal convolutional network introduces a gated linear unit to obtain a trained prediction model;

[0029] The prediction module is used to predict the line loss rate of the transmission line through the trained prediction model.

[0030] The present invention also adopts a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0031] The present invention also adopts a computer-readable storage medium on which a computer program is stored, and the computer program implements the steps of the above method when executed by a processor.

[0032] Beneficial effects: Compared with the prior art, the significant advantage of the present invention is that by integrating multiple data sources such as electricity data and ledger information, the robustness of the prediction is improved, and even when the historical data is incomplete, a high prediction accuracy can be maintained, reducing the reliance on high-quality historical data. The effective integration of various types of heterogeneous data such as electricity data and ledger information can effectively process multi-source heterogeneous data and improve the comprehensiveness and accuracy of the prediction. By adopting advanced algorithms such as temporal convolutional networks (TCN), the impact of changes in the grid structure on the line loss rate can be better captured, thereby improving the adaptability of the prediction model. By utilizing the powerful processing power of the temporal convolutional network, complex time series patterns can be captured, especially in terms of nonlinear relationships and long-term dependencies, thereby improving the prediction accuracy. By optimizing the data processing process and algorithm design, the data processing time can be shortened and the real-time performance of the prediction can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic diagram of the flow of the method for predicting the line loss rate of a transmission line in the present invention.

[0034] Figure 2 A heat map drawn for feature correlation analysis in the present invention.

[0035] Figure 3 This is a schematic diagram of the temporal convolutional network structure in the present invention. DETAILED DESCRIPTION

[0036] Example 1

[0037] like Figure 1 As shown, in this embodiment, a method for predicting transmission line line loss rate based on power and ledger information includes the following steps:

[0038] Step 1: Obtain the power data and ledger information of the transmission line, and preprocess them to obtain the original feature set related to the line loss rate.

[0039] By desensitizing and exporting the power data, we can obtain the source data in CSV format to be analyzed. We use the Pandas library in Python to read the source data in CSV format. For the data set to be predicted, we perform data preprocessing.

[0040] Data preprocessing is a crucial step that directly affects the performance and accuracy of the model. The following are some common data preprocessing schemes and measures:

[0041] (1) Data cleaning: 1. Remove duplicate data: delete or merge duplicate records; 2. Use mathematical methods to handle missing values: handle missing data by deletion, filling (such as using mean, median, mode or prediction model) or interpolation methods; 3. Outlier detection: identify and handle outliers based on common sense, possibly through statistical methods or visualization means.

[0042] (2) Data integration: Merge multiple data sources to solve data redundancy and inconsistency problems.

[0043] (3) Data transformation: 1. Normalization / standardization: scaling the data to a small, specified range, such as 0 to 1 (normalization) or with zero mean and unit variance (standardization); 2. Normalization: scaling the data proportionally so that they have the same scale, such as Min-Max Scaling or Robust Scaling; 3. Discretization: converting continuous variables into categorical variables; 4. Feature construction: creating new features or modifying existing features to improve model performance.

[0044] (4) Feature selection and extraction: Select the most informative feature subset to reduce dimensionality and improve model performance. Extract important features from the raw data, such as principal component analysis (PCA) for dimensionality reduction.

[0045] (5) Encoding categorical variables: Convert categorical variables into a format that can be processed by machine learning algorithms, such as using One-Hot Encoding or Label Encoding.

[0046] (6) Time series data preprocessing: Differentiate, smooth or decompose the time series data to extract trend and seasonal components.

[0047] (7) Algorithmic imputation: using statistical methods, machine learning models, or domain knowledge to estimate and fill in missing values.

[0048] (8) Use data theory to handle outliers (Outlier Detection): Use methods such as box plots, Z-scores, and Isolation Forest to identify and handle outliers.

[0049] The goal of data preprocessing is to improve the quality of data and make it more suitable for analysis and modeling. Different datasets and projects may require different preprocessing steps, so choosing the right preprocessing method requires a deep understanding of the data and business problem.

[0050] In this embodiment, the data tables of electricity data and ledger information are merged based on the line ID, and the missing values ​​in the line loss related data set can be filled in. According to the data attributes of the power business knowledge and its related fields, it is more reasonable to use the most frequently occurring values ​​to fill in the missing parts of the three fields of "power supply area", "whether it is a rural grid", and "multiplier". For the "power supply radius" field, 1 / 2 of the corresponding "total wire length" is used to fill the missing part. In the training set, there is a null value for the line loss rate. Because the reasonable interval of the line loss rate in the power business is [0,10], values ​​not in this interval are regarded as outliers. In addition, because the transmission line has the characteristics of continuity, the line loss rate of the same section of the line shows a linear change, so the null value of the line loss rate can be filled by the adjacent value filling method.

[0051] Step 2: Perform feature selection on the original feature set through correlation analysis to obtain key features.

[0052] Feature selection is an important step in machine learning, which involves selecting the most relevant and informative feature subset from the original feature set. The significance of feature selection includes: (1) Improving model performance: By removing irrelevant or redundant features, the complexity of the model can be reduced, the generalization ability of the model can be improved, and overfitting can be avoided; (2) Reducing training time and cost: Fewer features means less computing resources and time are required for model training and prediction; (3) Improving model interpretability: Feature selection helps to identify and retain the most important features, making the model's prediction process easier to understand and explain.

[0053] In terms of feature selection, Figure 1 As shown in Table 1, we draw a heat map through correlation analysis to find key features. In order to ensure the integrity of learning, we select the top 75% of the features for training. Figure 1 The power attribute names of the fields in the heat map are:

[0054] Table 1 Power attribute names of fields in the heat map

[0055]

[0056]

[0057] Step 3: Train the temporal convolutional network using key features and line loss rates to obtain a trained prediction model.

[0058] In recent years, deep learning has made great progress in time series data processing, and time series data modeling and prediction have been widely used in many fields, such as signal processing, speech recognition, etc. However, traditional sequence modeling methods (such as RNN recurrent neural network, LSTM long short-term memory network, etc.) need to calculate each moment serially and have a large number of parameters, which limits their performance in parallel computing and training efficiency.

[0059] like Figure 3 As shown in the figure, the temporal convolutional network is a method based on the convolutional neural network structure. Because it can calculate data in all time steps in parallel, has a strong ability to model long-term dependencies and fewer parameters, it has been widely used in various fields of artificial intelligence and machine learning.

[0060] The role of temporal convolutional networks:

[0061] Capturing temporal dependencies: TCN can effectively capture long-term dependencies in time series data, which is crucial for predicting transmission line loss rates because changes in line loss rates are often closely related to patterns in time series data.

[0062] Automatic feature learning: TCN automatically learns features through convolutional layers, without the need for manual feature engineering, reducing preprocessing steps while also improving the robustness and generalization ability of the model.

[0063] Parallel processing capability: TCN is able to process data in parallel, which means it can run efficiently on parallel computing resources such as GPUs, speeding up model training and making real-time predictions possible.

[0064] Advantages compared to similar models:

[0065] Compared to RNN / LSTM: TCN does not have the problem of gradient vanishing / exploding because it does not need to be trained through backpropagation through time like RNN or LSTM. TCN usually shows faster convergence speed in prediction tasks.

[0066] Compared with traditional machine learning models: Traditional machine learning models (such as linear regression, support vector machines, etc.) may not be able to handle high-dimensional time series data well, while TCN has obvious advantages in this regard.

[0067] TCN can automatically learn features and reduce the workload of manual feature engineering.

[0068] Compared with other deep learning models: Some deep learning models (such as ordinary convolutional neural networks (CNNs)) may not be suitable for processing long time series data, while TCN can effectively process long sequence data through techniques such as causal convolution and dilated convolution. In addition, TCN usually has better performance and higher prediction accuracy when processing sequence data.

[0069] Temporal convolutional networks are ideal for predicting transmission line loss rates due to their powerful capabilities and advantages in processing time series data. It not only improves prediction accuracy, but also simplifies the feature engineering process and achieves more efficient model training. This method optimizes the temporal convolutional network by combining the gating mechanism. TCN enhances the model's ability to learn complex time dependencies in time series data by introducing gating units. The gating mechanism allows the model to control the flow of information more effectively, so that important time features are retained while ignoring irrelevant information, thereby improving the model's prediction accuracy and generalization ability.

[0070] The mean squared error (MSE) is used to evaluate the effectiveness of the prediction results. MSE is a commonly used loss function in regression tasks, which measures the average square error between the model's predicted value and the actual value. Specifically, the calculation formula of MSE is as follows:

[0071]

[0072] Among them, n is the number of samples in the test set, x i is the true value of the i-th sample, y i is the prediction model for x i is the predicted value of the ith sample. The smaller the value of MSE, the smaller the difference between the model's predicted value and the true value, and the better the model performance. MSE can be regarded as the average of the square of the model's prediction error, so it is sensitive to outliers. If there are outliers in the sample, MSE may be affected by them and cause the model performance to deteriorate. MSE is widely used in tasks such as linear regression and multivariate linear regression. In deep learning, MSE is also used to measure the performance of neural networks in regression tasks and is optimized as a loss function.

[0073] Step 4: Predict the line loss rate of the transmission line using the trained prediction model.

[0074] By using the time convolution network (TCN), the prediction accuracy and efficiency are effectively improved. The details are as follows:

[0075]

[0076] It can be seen from the table above that the MAE obtained using the temporal convolutional network is the lowest among similar algorithms, which proves the application effect of the invention.

[0077] In summary, the transmission line line loss rate prediction method based on power and ledger information of the present invention includes the following effects:

[0078] 1. Improve prediction accuracy: The use of temporal convolutional networks can capture long-term dependencies in sequence data, significantly improving the accuracy of transmission line line loss rate prediction. At the same time, the method in this embodiment combines detailed ledger information (such as line length, material type, load conditions, etc.) to further enhance the generalization ability of the model, so that it can adapt to different types of transmission lines.

[0079] 2. Enhance model robustness: Temporal convolutional networks can automatically learn features, reducing the need for manual feature engineering and making the model more robust. By learning from historical electricity data, the model can better cope with outliers or missing data.

[0080] 3. Realize real-time prediction: Due to the parallel processing characteristics of the temporal convolutional network, the method in this embodiment can complete the training and prediction of large-scale data sets in a short time, supporting the application scenario of real-time line loss prediction.

[0081] 4. Reduce operation and maintenance costs: Accurate line loss prediction helps power companies plan maintenance plans in advance, reduce unnecessary inspections and repairs, and thus reduce operation and maintenance costs. Timely warnings of abnormal line losses can effectively prevent potential failures and avoid the resulting economic losses.

[0082] 5. Improve energy efficiency: Through effective prediction of line losses, power system managers can take measures to optimize the grid structure, reduce energy waste, and improve overall energy efficiency.

[0083] 6. Promote the development of smart grids: High-precision line loss prediction provides an important decision-making basis for smart grids, helps to realize intelligent management and scheduling of power grids, and promotes the development of smart grid technology.

[0084] In summary, the method proposed in the present invention not only improves the accuracy of line loss prediction, but also has strong practicality and flexibility, which is of great significance to the efficient and stable operation of the power system.

[0085] Example 2

[0086] In this embodiment, the encryption system adopts a transmission line line loss rate prediction system based on power and ledger information, including:

[0087] The data acquisition module is used to obtain the power data and ledger information of the transmission line, and perform preprocessing to obtain the original feature set related to the line loss rate;

[0088] The key feature selection module is used to select the original feature set through correlation analysis to obtain key features;

[0089] The prediction model building module is used to train the temporal convolutional network through key features and line loss rates to obtain a trained prediction model;

[0090] The prediction module is used to predict the line loss rate of the transmission line through the trained prediction model.

[0091] Example 3

[0092] An embodiment of the present invention discloses a transmission line line loss rate prediction device based on power quantity and ledger information. The device can be applied in a power system, such as for transmission line line loss rate prediction, etc., which is not limited by the embodiment of the present invention.

[0093] The device may include a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the method described in the above embodiment and can achieve the technical effect consistent with the above method.

[0094] The memory may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the memory may be used to read and write non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). A program / utility having a set (at least one) of program modules may be stored in, for example, the memory, such program modules including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include the implementation of a network environment. The program modules typically perform the functions and / or methods in the embodiments described herein.

[0095] The processor executes various functional applications and data processing by running the program stored in the memory, such as implementing the method provided in the first embodiment of the present invention.

[0096] Example 4

[0097] Embodiment 4 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in the above embodiment are implemented and the technical effect consistent with the above method can be achieved.

[0098] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0099] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0100] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0101] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or combinations thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0102] Of course, the storage medium containing computer executable instructions provided by an embodiment of the present invention, whose computer executable instructions are not limited to the above method operations, can also execute related operations in the method provided by any embodiment of the present invention.

[0103] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for predicting transmission line line loss rate based on power and ledger information, characterized in that: The following steps are involved: Obtain the power data and ledger information of the transmission line, and perform preprocessing to obtain the original feature set related to the line loss rate; Perform feature selection on the original feature set through correlation analysis to obtain key features; The temporal convolutional network is trained by using key features and line loss rates, and the temporal convolutional network introduces a gated linear unit to obtain a trained prediction model; The line loss rate of the transmission line is predicted through the trained prediction model.

2. The method for predicting transmission line line loss rate according to claim 1, characterized in that: The ledger information includes the line length, material type, load conditions, power supply area, whether it is a rural power grid, and the multiplier of the transmission line; the electricity data includes electricity sales, line loss rate, total capacity of public transformers, total capacity of special transformers, public transformer electricity sales, special transformer electricity sales, high supply and low metering capacity, high supply and low metering electricity sales, and special transformer electricity.

3. The method for predicting transmission line line loss rate according to claim 2, characterized in that: The pre-processing comprises: Data cleaning: remove duplicate data, process missing values, and handle outliers; Data integration: merging data from multiple data sources; Data transformation: normalize, standardize, discretize and construct features of data; Feature extraction: select the most informative feature subset; Encoding categorical variables: Encoding the variables into a format that can be processed by machine learning algorithms; Time series data preprocessing: Differencing, smoothing, or decomposing time series data to extract trend and seasonal components.

4. The method for predicting transmission line line loss rate according to claim 3, characterized in that: For missing values ​​in electricity data and ledger information, the filling method is used; The value with the highest frequency of occurrence is used to fill the missing parts of the three data sets: power supply area, whether it is a rural power grid, and multiple; for the power supply radius, 1 / 2 of the corresponding total wire length is used to fill the missing part; for the empty value of the line loss rate, the adjacent value filling method is used to fill it.

5. The method for predicting transmission line line loss rate according to claim 4, characterized in that: After training the temporal convolutional network, the trained model is tested using a test set, and the mean square error (MSE) is used to evaluate the effectiveness of the test set prediction results. The calculation formula of MSE is as follows: Among them, n is the number of samples in the test set, x i is the true value of the i-th sample, y i is the prediction model for x i is the predicted value of the i-th sample.

6. A transmission line line loss rate prediction system based on power and ledger information, characterized in that: include: The data acquisition module is used to obtain the power data and ledger information of the transmission line, and perform preprocessing to obtain the original feature set related to the line loss rate; The key feature selection module is used to select the original feature set through correlation analysis to obtain key features; A prediction model building module is used to train a temporal convolutional network through key features and line loss rates, wherein the temporal convolutional network introduces a gated linear unit to obtain a trained prediction model; The prediction module is used to predict the line loss rate of the transmission line through the trained prediction model.

7. The transmission line line loss rate prediction system based on power and ledger information according to claim 6 is characterized in that: The ledger information includes the line length, material type, load conditions, power supply area, whether it is a rural power grid, and the multiplier of the transmission line; the electricity data includes electricity sales, line loss rate, total capacity of public transformers, total capacity of special transformers, public transformer electricity sales, special transformer electricity sales, high supply and low metering capacity, high supply and low metering electricity sales, and special transformer electricity.

8. The transmission line line loss rate prediction system based on power and ledger information according to claim 6 is characterized in that: For missing values ​​in electricity data and ledger information, the filling method is used; The value with the highest frequency of occurrence is used to fill the missing parts of the three data sets: power supply area, whether it is a rural power grid, and multiple; for the power supply radius, 1 / 2 of the corresponding total wire length is used to fill the missing part; for the empty value of the line loss rate, the adjacent value filling method is used to fill it.

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, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images