Market behavior evaluation method and device, equipment, storage medium and program product

Abstract

The invention relates to a market behavior evaluation method and device, equipment, a storage medium and a program product. The method comprises the steps of constructing a market behavior evaluation model based on historical behavior data of an electricity market and a Bayesian network constructed based on an evaluation index system, obtaining to-be-evaluated market behavior data of the electricity market, and determining a market behavior evaluation result of the to-be-evaluated market behavior data based on the market behavior evaluation model, therefore, market behavior evaluation results under different evaluation indexes can be comprehensively considered based on the Bayesian network structure, the influence of uncertain factors of the electricity market on the market behavior evaluation results is reduced, and the accuracy and reliability of market behavior evaluation are improved.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a market behavior evaluation method, device, equipment, storage medium and program product. Background Art

[0002] The power generation side is an important participant in the operation of the electricity market. The market behaviors of power generation entities such as quotation and quantity reporting are directly related to the efficiency and quality of market operation. Therefore, evaluating the market behavior of power generation entities based on evaluation indicators is of great significance for predicting the direction of market development, judging the efficiency of market operation, and helping market operating institutions and other participants to make optimal decisions.

[0003] At present, market behavior evaluation is usually based on methods such as hierarchical analysis method, TOPSIS comprehensive evaluation method, fuzzy comprehensive evaluation method, etc. However, these methods only evaluate market behavior based on a single evaluation indicator, resulting in low accuracy of market behavior evaluation results. Summary of the invention

[0004] Based on this, it is necessary to provide a market behavior evaluation method, device, equipment, storage medium and program product that can improve the accuracy of market behavior evaluation results in response to the above technical problems.

[0005] In a first aspect, the present application provides a market behavior evaluation method. The method comprises:

[0006] A market behavior evaluation model is constructed based on historical behavior data of the power market and a Bayesian network; the Bayesian network is constructed based on an evaluation index system, and the evaluation index system includes multiple first-level evaluation indicators and second-level evaluation indicators corresponding to each of the first-level evaluation indicators;

[0007] Obtain the market behavior data to be evaluated in the electricity market;

[0008] Based on the market behavior evaluation model, a market behavior evaluation result of the market behavior data to be evaluated is determined.

[0009] In one embodiment, determining the market behavior evaluation result of the market behavior data to be evaluated based on the market behavior evaluation model includes:

[0010] Based on the market behavior evaluation model, determining a first market behavior evaluation result of the market behavior data to be evaluated under each of the first-level evaluation indicators;

[0011] Determine a second market behavior evaluation result of the market behavior data to be evaluated according to each of the first market behavior evaluation results and the weight coefficient corresponding to each of the first-level evaluation indicators;

[0012] The market behavior evaluation result includes the first market behavior evaluation result and the second market behavior evaluation result.

[0013] In one embodiment, based on the market behavior evaluation model, determining the first market behavior evaluation result of the market behavior data to be evaluated under each of the first-level evaluation indicators includes:

[0014] For each of the first-level evaluation indicators, based on the market behavior evaluation model, determine the probability of each market behavior level of the market behavior data to be evaluated under the first-level evaluation indicator;

[0015] The market behavior level corresponding to the maximum probability is used as the first market behavior evaluation result of the market behavior data to be evaluated under the first-level evaluation indicator.

[0016] In one embodiment, the market behavior evaluation model is constructed based on the historical behavior data of the electricity market and the Bayesian network, including:

[0017] Construct an evaluation index system based on the historical behavior data;

[0018] The Bayesian network is constructed based on the evaluation index system; the nodes of the Bayesian network are used to represent the indicators in the evaluation index system, and the edges of the Bayesian network are used to represent the dependency relationship between the indicators;

[0019] Based on the expectation maximization algorithm, the parameters of the Bayesian network are determined according to the historical behavior data to obtain the market behavior evaluation model.

[0020] In one embodiment, the parameter of the Bayesian network is determined based on the historical behavior data based on the expectation maximization algorithm, including:

[0021] Obtain the initial parameters of the Bayesian network;

[0022] Determining the expected probability distribution of each latent variable in the Bayesian network according to the Bayesian network, the initial parameters, and the historical behavior data;

[0023] The parameters of the Bayesian network are determined based on the maximum probability distribution expectation.

[0024] In one embodiment, obtaining the market behavior data to be evaluated in the power market includes:

[0025] Obtaining initial market behavior data of the electricity market;

[0026] Based on the regression interpolation method, the missing values ​​and outliers in the initial market behavior data are corrected to obtain the intermediate market behavior data;

[0027] determining the maximum and minimum values ​​in the intermediate market behavior data;

[0028] The intermediate market behavior data is standardized according to the maximum value, the minimum value, and the numerical value of the intermediate market behavior data to obtain the market behavior data to be evaluated.

[0029] In a second aspect, the present application also provides a market behavior evaluation device. The device comprises:

[0030] A model building module is used to build a market behavior evaluation model based on historical behavior data of the power market and a Bayesian network; the Bayesian network is built based on an evaluation index system, and the evaluation index system includes multiple first-level evaluation indicators and second-level evaluation indicators corresponding to each of the first-level evaluation indicators;

[0031] An acquisition module, used for acquiring the market behavior data to be evaluated in the power market;

[0032] The determination module is used to determine the market behavior evaluation result of the market behavior data to be evaluated based on the market behavior evaluation model.

[0033] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when executed by a processor.

[0035] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of any of the above methods when executed by a processor.

[0036] The above-mentioned market behavior evaluation method, device, equipment, storage medium and program product construct a market behavior evaluation model based on the historical behavior data of the electricity market and the Bayesian network constructed based on the evaluation index system, obtain the market behavior data to be evaluated in the electricity market, and determine the market behavior evaluation results of the market behavior data to be evaluated based on the market behavior evaluation model, so as to comprehensively consider the market behavior evaluation results under different evaluation indicators based on the Bayesian network structure, reduce the impact of the uncertainty factors of the electricity market itself on the market behavior evaluation results, and improve the accuracy and reliability of the market behavior evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] FIG1 is an internal structure diagram of a computer device provided in an embodiment of the present application;

[0038] FIG2 is a flow chart of a market behavior evaluation method provided in an embodiment of the present application;

[0039] FIG3 is a flow chart of a method for determining a market behavior evaluation result provided in an embodiment of the present application;

[0040] FIG4 is a flow chart of a method for determining a first market behavior evaluation result provided in an embodiment of the present application;

[0041] FIG5 is a flow chart of a method for obtaining a market behavior evaluation model provided in an embodiment of the present application;

[0042] FIG6 is a flow chart of a parameter determination method provided in an embodiment of the present application;

[0043] FIG7 is a flow chart of a method for obtaining market behavior data to be evaluated provided in an embodiment of the present application;

[0044] FIG8 is a schematic flow chart of a method for evaluating the behavior of a power generation entity based on a Bayesian network according to an embodiment of the present application;

[0045] FIG9 is a curve diagram of a market node electricity price provided in an embodiment of the present application;

[0046] FIG10 is a curve diagram of quotations of various power generation entities provided in an embodiment of the present application;

[0047] FIG. 11 is a structural block diagram of a market behavior evaluation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] The power generation side is an important participant in the operation of the electricity market. The market behaviors of power generation entities such as quotation and quantity reporting are directly related to the efficiency and quality of market operation. Therefore, evaluating the market behavior of power generation entities based on evaluation indicators is of great significance for predicting the direction of market development, judging the efficiency of market operation, and helping market operating institutions and other participants to make optimal decisions.

[0050] At present, market behavior evaluation is usually based on methods such as hierarchical analysis method, TOPSIS comprehensive evaluation method, fuzzy comprehensive evaluation method, etc. However, these methods only evaluate market behavior based on a single evaluation indicator, resulting in low accuracy of market behavior evaluation results.

[0051] The market behavior evaluation method provided in the embodiment of the present application can be applied in the application environment as shown in Figure 1. Figure 1 is an internal structure diagram of a computer device provided in the embodiment of the present application. The computer device can be a server, and its internal structure diagram can be as shown in Figure 1. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a market behavior evaluation method is implemented.

[0052] Those skilled in the art will understand that the structure shown in FIG. 1 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0053] In one embodiment, as shown in FIG. 2 , FIG. 2 is a flow chart of a market behavior evaluation method provided in an embodiment of the present application, which can be applied to the computer device in FIG. 1 , and includes the following steps:

[0054] S201, build a market behavior evaluation model based on the historical behavior data of the electricity market and Bayesian network.

[0055] Among them, the Bayesian network is constructed based on an evaluation index system, and the evaluation index system includes multiple first-level evaluation indicators and second-level evaluation indicators corresponding to each first-level evaluation indicator.

[0056] Optionally, the historical behavior data of the electricity market may include, for example, historical data such as the bid line-reaching rate, capacity retention ratio, and market share of power generation entities in the electricity spot market.

[0057] In one embodiment, an evaluation index system can be established based on the historical behavior data of the power market, the nodes of the Bayesian network can be determined according to the evaluation indexes in the evaluation index system, and the directed edges of the Bayesian network can be determined according to the dependency relationship between the evaluation indexes to construct the Bayesian network. Then, the parameters of the Bayesian network are determined based on the maximum likelihood estimation (MLE) algorithm or the expectation maximum (EM) algorithm to obtain a market behavior evaluation model.

[0058] For example, the first-level evaluation indicators may include market power, market behavior, etc. The second-level evaluation indicators corresponding to market power may include market concentration, Top-m index, etc., and the second-level evaluation indicators corresponding to market behavior may include power generation company retention ratio, quotation limit rate, etc.

[0059] Among them, market concentration is the sum of the squares of the market shares of each power generation enterprise, which depends on the number of market participants and the size of the market share of each participant. The fewer market members, the more concentrated the allocation of market resources. The Top-m index is the sum of the market shares of the top m power generation enterprises in terms of market share. The power producer retention ratio measures competitive behavior from the perspective of the power generation capacity of the power generation enterprises, reflecting the degree of control of the power generation enterprises over the market supply and demand, and is a manifestation of the power generation enterprises' mobilization of market power. The bid limit rate refers to the proportion of the number of times the power generation enterprises' bids reach the bid upper limit to the total number of times.

[0060] S202, obtaining market behavior data to be evaluated in the power market.

[0061] Optionally, the market behavior data to be evaluated in the power market may include, for example, real market behavior data generated during the power market operation process. Alternatively, the market behavior data to be evaluated in the power market may also include simulated market behavior data obtained based on simulation experiments. The simulation experiment is used to simulate the power market operation process.

[0062] In one embodiment, the initial market behavior data to be evaluated can be obtained, the data outliers and missing values ​​in the initial market behavior data can be detected, and the data outliers and missing values ​​in the initial market behavior data can be corrected based on the regression interpolation method to obtain the intermediate market behavior data. Then, the intermediate market behavior data can be standardized, and the standardized intermediate market behavior data can be used as the market behavior data to be evaluated.

[0063] S203: Determine the market behavior evaluation result of the market behavior data to be evaluated based on the market behavior evaluation model.

[0064] In one embodiment, market behavior can be graded based on historical behavior data to obtain multiple market behavior grades. Then, for each first-level evaluation indicator in the evaluation indicator system, based on the market behavior evaluation model, the probability of each market behavior grade of the market behavior data to be evaluated under the first-level evaluation indicator is determined, and the market behavior grade corresponding to the largest probability is used as the first market behavior evaluation result of the market behavior data to be evaluated under the first-level evaluation indicator.

[0065] For example, assuming that there are market behavior grades, namely, Grade A, Grade B, and Grade C, and there are two first-level evaluation indicators, namely, market power and market behavior, in the evaluation indicator system, the probability that the market behavior data to be evaluated is at Grade A, Grade B, and Grade C respectively under the market power indicator can be determined, and the probability that the market behavior data to be evaluated is at Grade A, Grade B, and Grade C respectively under the market behavior indicator can be determined. If the probability that the market behavior data to be evaluated is at Grade A under the market power indicator is 99.79%, the probability that it is at Grade B is 0.15%, and the probability that it is at Grade C is 0.06%, and the probability that the market behavior data to be evaluated is at Grade A under the market behavior indicator is 0.31%, the probability that it is at Grade B is 6.90%, and the probability that it is at Grade C is 92.79%, then the first market behavior evaluation result of the market behavior data to be evaluated under the market power indicator is Grade A, and the first market behavior evaluation result under the market behavior indicator is Grade C.

[0066] Optionally, the second market behavior evaluation result of the market behavior data to be evaluated can also be determined according to the weight coefficients corresponding to the first market behavior evaluation results and the first-level evaluation indicators, and the second market behavior evaluation result is the overall evaluation result. Then, the first market behavior evaluation result and the second market behavior evaluation result can be used as the market behavior evaluation results of the market behavior data to be evaluated.

[0067] In an embodiment of the present application, a market behavior evaluation model is constructed based on historical behavior data of the electricity market and a Bayesian network constructed based on an evaluation index system, market behavior data to be evaluated in the electricity market is obtained, and market behavior evaluation results of the market behavior data to be evaluated are determined based on the market behavior evaluation model, thereby being able to comprehensively consider market behavior evaluation results under different evaluation indicators based on the Bayesian network structure, reducing the impact of uncertainty factors of the electricity market itself on the market behavior evaluation results, and improving the accuracy and reliability of market behavior evaluation.

[0068] Referring to FIG. 3 , FIG. 3 is a flow chart of a method for determining a market behavior evaluation result provided by an embodiment of the present application. This embodiment relates to a possible implementation method of how to determine a market behavior evaluation result of market behavior data to be evaluated based on a market behavior evaluation model. In the above S203, the following steps are included:

[0069] S301, based on the market behavior evaluation model, determining the first market behavior evaluation result of the market behavior data to be evaluated under each primary evaluation indicator.

[0070] In one embodiment, market behavior can be graded based on historical behavior data to obtain multiple market behavior grades. Then, for each first-level evaluation indicator in the evaluation indicator system, based on the market behavior evaluation model, the probability of each market behavior grade of the market behavior data to be evaluated under the first-level evaluation indicator is determined, and the market behavior grade corresponding to the largest probability is used as the first market behavior evaluation result of the market behavior data to be evaluated under the first-level evaluation indicator.

[0071] For example, assuming that there are market behavior grades, namely, Grade A, Grade B, and Grade C, and there are two first-level evaluation indicators, namely, market power and market behavior, in the evaluation indicator system, the probability that the market behavior data to be evaluated is at Grade A, Grade B, and Grade C respectively under the market power indicator can be determined, and the probability that the market behavior data to be evaluated is at Grade A, Grade B, and Grade C respectively under the market behavior indicator can be determined. If the probability that the market behavior data to be evaluated is at Grade A under the market power indicator is 99.79%, the probability that it is at Grade B is 0.15%, and the probability that it is at Grade C is 0.06%, and the probability that the market behavior data to be evaluated is at Grade A under the market behavior indicator is 0.31%, the probability that it is at Grade B is 6.90%, and the probability that it is at Grade C is 92.79%, then the first market behavior evaluation result of the market behavior data to be evaluated under the market power indicator is Grade A, and the first market behavior evaluation result under the market behavior indicator is Grade C.

[0072] S302: Determine a second market behavior evaluation result of the market behavior data to be evaluated according to each first market behavior evaluation result and a weight coefficient corresponding to each primary evaluation indicator.

[0073] Among them, the market behavior evaluation results include a first market behavior evaluation result and a second market behavior evaluation result.

[0074] In one embodiment, the weight coefficient corresponding to each first-level evaluation indicator can be determined based on factors such as the importance of each first-level evaluation indicator in evaluating market behavior, and then the second market behavior evaluation result of the market behavior data to be evaluated can be determined based on the first market behavior evaluation results and the weight coefficient corresponding to each first-level evaluation indicator using a weighted average method.

[0075] In an embodiment of the present application, based on the market behavior evaluation model, the first market behavior evaluation result of the market behavior data to be evaluated under each first-level evaluation indicator is determined, and the second market behavior evaluation result of the market behavior data to be evaluated is determined according to the weight coefficients corresponding to each first-level evaluation result and each first-level evaluation indicator. Therefore, the overall evaluation result for the market behavior data to be evaluated can be determined based on the first market behavior evaluation results, and the market behavior evaluation results under different evaluation indicators are comprehensively considered, thereby reducing the impact of the uncertainty factors of the electricity market itself on the market behavior evaluation results, and improving the accuracy and reliability of the market behavior evaluation.

[0076] Referring to FIG. 4 , FIG. 4 is a flow chart of a method for determining a first market behavior evaluation result provided by an embodiment of the present application. This embodiment relates to a possible implementation method of how to determine the first market behavior evaluation result of the market behavior data to be evaluated under each primary evaluation indicator based on the market behavior evaluation model. In the above S301, the following steps are included:

[0077] S401, for each first-level evaluation indicator, based on the market behavior evaluation model, determine the probability of each market behavior level of the market behavior data to be evaluated under the first-level evaluation indicator.

[0078] For example, assuming that there are market behavior levels, namely A, B, and C, and there are two first-level evaluation indicators, namely market power and market behavior, in the evaluation indicator system, then the probability that the market behavior data to be evaluated is at level A, level B, and level C under the market power indicator can be determined, as well as the probability that the market behavior data to be evaluated is at level A, level B, and level C under the market behavior indicator can be determined.

[0079] S402, taking the market behavior level corresponding to the maximum probability as the first market behavior evaluation result of the market behavior data to be evaluated under the first-level evaluation index.

[0080] For example, if the probability that the market behavior data to be evaluated is at Grade A under the market power index is 99.79%, the probability that it is at Grade B is 0.15%, and the probability that it is at Grade C is 0.06%, and the probability that the market behavior data to be evaluated is at Grade A under the market behavior index is 0.31%, the probability that it is at Grade B is 6.90%, and the probability that it is at Grade C is 92.79%, then the first market behavior evaluation result of the market behavior data to be evaluated under the market power index is Grade A, and the first market behavior evaluation result under the market behavior index is Grade C.

[0081] In an embodiment of the present application, for each first-level evaluation indicator, based on the market behavior evaluation model, the probability of each market behavior level of the market behavior data to be evaluated under the first-level evaluation indicator is determined, and the market behavior level corresponding to the maximum probability is used as the first market behavior evaluation result of the market behavior data to be evaluated under the first-level evaluation indicator, thereby comprehensively considering the market behavior evaluation results under different evaluation indicators, reducing the impact of the uncertainty factors of the electricity market itself on the market behavior evaluation results, and improving the accuracy and reliability of the market behavior evaluation.

[0082] Referring to FIG. 5 , FIG. 5 is a flow chart of a method for obtaining a market behavior evaluation model provided in an embodiment of the present application. This embodiment relates to a possible implementation method of how to construct a market behavior evaluation model based on historical behavior data of the power market and a Bayesian network. In the above S201, the following steps are included:

[0083] S501, construct an evaluation index system based on historical behavior data.

[0084] Optionally, the historical behavior data of the power market can be obtained, and then the quality of the historical behavior data can be tested to determine the abnormal values ​​and missing values ​​in the historical behavior data, and the abnormal values ​​and missing values ​​in the historical behavior data can be corrected using the regression interpolation method. The corrected historical behavior data can then be standardized, and an evaluation index system can be constructed based on the standardized historical behavior data.

[0085] In one embodiment, the primary evaluation indicators and the secondary evaluation indicators corresponding to each primary evaluation indicator can be determined according to the historical behavior data, and then an evaluation indicator system can be constructed according to each primary evaluation indicator and the secondary evaluation indicators corresponding to each primary evaluation indicator.

[0086] S502, constructing a Bayesian network based on the evaluation index system.

[0087] The nodes of the Bayesian network are used to represent the indicators in the evaluation index system, and the edges of the Bayesian network are used to represent the dependency relationship between the indicators.

[0088] In one embodiment, the nodes of the Bayesian network may be determined according to the evaluation indicators in the evaluation indicator system, and the directed edges of the Bayesian network may be determined according to the dependency relationship between the evaluation indicators to construct the Bayesian network.

[0089] For example, if node A represents the first-level evaluation indicator market power, and node B represents the second-level evaluation indicator market concentration, then a directed edge between node A and node B can be determined.

[0090] S503, based on the expectation maximization algorithm, determine the parameters of the Bayesian network according to the historical behavior data to obtain a market behavior evaluation model.

[0091] In one embodiment, a conditional probability table can be defined for each node in the Bayesian network, and then an initial value (i.e., initial parameter) is assigned to each parameter of the Bayesian network (i.e., the probability value in the conditional probability table). Step E (expectation step): Calculate the probability distribution expectation of each hidden variable based on the initial parameter calculation and historical behavior data. Step M (maximization step): Redetermine the parameters of the Bayesian network based on the probability distribution expectation in step E. Repeat the above steps E and M until the convergence condition is reached to obtain the optimal parameters of the Bayesian network. Finally, a market behavior evaluation model is constructed based on the parameters of the optimal Bayesian network.

[0092] Optionally, the initial parameters of the Bayesian network can be random or estimated based on prior knowledge.

[0093] In an embodiment of the present application, an evaluation index system is constructed based on historical behavior data, a Bayesian network is constructed based on the evaluation index system, and the parameters of the Bayesian network are determined based on the historical behavior data based on the expectation maximization algorithm to obtain a market behavior evaluation model, thereby being able to comprehensively consider the market behavior evaluation results under different evaluation indicators based on the Bayesian network structure, reducing the impact of the uncertainty factors of the electricity market itself on the market behavior evaluation results, and improving the accuracy and reliability of the market behavior evaluation.

[0094] Referring to Figure 6, Figure 6 is a flow chart of a parameter determination method provided in an embodiment of the present application. This embodiment relates to a possible implementation method of how to determine the parameters of a Bayesian network based on historical behavior data based on an expected maximum algorithm. In the above S503, the following steps are included:

[0095] S601, obtaining initial parameters of the Bayesian network.

[0096] In one embodiment, a conditional probability table may be defined for each node in the Bayesian network, and then an initial value (ie, initial parameter) may be assigned to each parameter of the Bayesian network (ie, the probability value in the conditional probability table).

[0097] Alternatively, the initial parameters of the Bayesian network may be randomly generated or estimated based on prior knowledge.

[0098] S602, determining the expected probability distribution of each latent variable in the Bayesian network according to the Bayesian network, initial parameters, and historical behavior data.

[0099] For example, the expected probability distribution of each latent variable in the Bayesian network can be determined based on the following formula (1):

[0100] (1)

[0101] In formula (1), is the parameter value of the current iteration (initial parameter value), is the parameter estimate obtained in the previous iteration, is a sample data set, is the current sample set, and Z is the subject behavior event to be studied.

[0102] S603, determining the parameters of the Bayesian network according to the maximum probability distribution expectation.

[0103] For example, the parameters of the Bayesian network can be determined by the following formula (2):

[0104] (2)

[0105] In one embodiment, the above steps S602-S603 may be repeatedly performed until a convergence condition is reached to obtain optimal Bayesian network parameters, and then a market behavior evaluation model is constructed based on the optimal Bayesian network parameters.

[0106] Optionally, the posterior probability distribution of each node can be calculated based on the following formula (3):

[0107] (3)

[0108] In formula (3), For Node The posterior probability of For Node The prior probability of and Is a node The conditional probability of .

[0109] In an embodiment of the present application, the initial parameters of the Bayesian network are obtained, and the probability distribution expectation of each hidden variable in the Bayesian network is determined based on the Bayesian network, the initial parameters, and the historical behavior data. Based on the maximum probability distribution expectation, the parameters of the Bayesian network are determined. This makes it possible to comprehensively consider the market behavior evaluation results under different evaluation indicators based on the Bayesian network structure, reduce the impact of the uncertainty factors of the electricity market itself on the market behavior evaluation results, and improve the accuracy and reliability of the market behavior evaluation.

[0110] Referring to FIG. 7 , FIG. 7 is a flow chart of a method for obtaining market behavior data to be evaluated provided in an embodiment of the present application. This embodiment relates to a possible implementation method of how to obtain market behavior data to be evaluated in the power market. In the above S202, the following steps are included:

[0111] S701, obtaining initial market behavior data of the electricity market.

[0112] Optionally, the initial market behavior data of the power market may include, for example, real market behavior data generated during the power market operation process. Alternatively, the initial market behavior data of the power market may also include simulated market behavior data obtained based on simulation experiments. The simulation experiments are used to simulate the power market operation process.

[0113] S702, correcting missing values ​​and outliers in the initial market behavior data based on a regression interpolation method to obtain intermediate market behavior data.

[0114] In one embodiment, the data outliers and missing values ​​in the initial market behavior data can be detected, and then the average value of several data before and after the outlier data / missing data is determined, and the outlier data / missing data is replaced with the average value to correct the missing values ​​and outliers in the initial market behavior data, and the corrected initial market behavior data is used as the intermediate market behavior data. The outlier refers to a measured value in a group of measured values ​​whose deviation from the average value exceeds two standard deviations.

[0115] For example, the data outliers and missing values ​​in the initial market behavior data can be corrected by the following formula (4):

[0116] (4)

[0117] In formula (4),

[0118] are outliers / missing values ​​in the initial market behavior data, is the first i observations of outliers / missing values ​​in the initial market behavior data, are the first i observations of outliers / missing values ​​in the initial market behavior data.

[0119] S703, determining the maximum value and the minimum value in the intermediate market behavior data.

[0120] In one embodiment, the maximum value and the minimum value of the intermediate market behavior data under each evaluation index may be determined.

[0121] S704, standardizing the intermediate market behavior data according to the maximum value, the minimum value, and the values ​​of the intermediate market behavior data to obtain the market behavior data to be evaluated.

[0122] For example, the intermediate market behavior data may be standardized based on the following formula (5):

[0123] (5)

[0124] In formula (5), represents the standardized value of the i-th group of observation data under the j-th indicator, represents the initial value of the i-th group of observation data under the j-th indicator, , They respectively represent the maximum and minimum values ​​of the intermediate market behavior data under the jth indicator.

[0125] It should be noted that the above steps S701-S704 are steps for preprocessing the market behavior data to be evaluated. In addition to the market behavior data to be evaluated, historical behavior data can also be preprocessed based on the above method.

[0126] In an embodiment of the present application, initial market behavior data of the electricity market is obtained, missing values ​​and outliers in the initial market behavior data are corrected based on the regression interpolation method to obtain intermediate market behavior data, the maximum value and the minimum value in the intermediate market behavior data are determined, and the intermediate market behavior data is standardized according to the maximum value, the minimum value, and the numerical value of the intermediate market behavior data to obtain the market behavior data to be evaluated, thereby achieving preprocessing of the market behavior data to be evaluated, which can eliminate missing values ​​and outliers in the initial market behavior data, improve data quality, improve the accuracy of the market behavior evaluation model, and standardizing the market behavior data can also improve the calculation speed of the market behavior evaluation model.

[0127] Referring to FIG8 , FIG8 is a flow chart of a method for evaluating the behavior of a power generation entity based on a Bayesian network provided in an embodiment of the present application. The method comprises the following steps:

[0128] S801, obtaining historical behavior data, and preprocessing the historical behavior data.

[0129] S802, constructing an evaluation index system based on the processed historical behavior data.

[0130] S803, constructing a Bayesian network based on the evaluation index system.

[0131] S804, based on the expectation maximization algorithm, determine the parameters of the Bayesian network according to the historical behavior data to obtain a market behavior evaluation model.

[0132] S805, obtaining the market behavior data to be evaluated in the power market.

[0133] S806, based on the market behavior evaluation model, determining the first market behavior evaluation result of the market behavior data to be evaluated under each primary evaluation indicator.

[0134] S807, determining a second market behavior evaluation result of the market behavior data to be evaluated according to each first market behavior evaluation result and a weight coefficient corresponding to each first-level evaluation indicator.

[0135] In order to introduce the embodiments of the present application more clearly, an exemplary description is given here in conjunction with Figures 9-10. Figure 9 is a curve chart of a market node electricity price provided in an embodiment of the present application, and Figure 10 is a curve chart of quotations of various power generation entities provided in an embodiment of the present application. A simulation experiment can be set up in combination with the actual rules of the electricity market. The electricity market simulation experiment adopts a four-unit three-node model. Considering only real-time market clearing, a node electricity price model is adopted, and a unified market clearing mode considering network constraints is adopted. The market clearing price of each node is formed once an hour, and each generator set uses the marginal electricity price of the node for settlement. The experiment includes 4 different generator sets and 2 service terminals. According to the requirements for the evaluation of the behavior of the power generation entity, the system electricity and heat load values ​​are collected, and the historical behavior data such as the line-reaching rate, capacity retention ratio, and market share of the market power generation entity quotation are collected. Then the historical behavior data is preprocessed, and an evaluation index system is constructed based on the historical behavior data. The evaluation index system includes two first-level evaluation indicators: market power and market behavior. Market power includes two second-level evaluation indicators: market concentration and Top-m index. Market behavior indicators include two second-level evaluation indicators: power producer retention ratio and quotation limit rate. A Bayesian network is constructed based on the evaluation index system. Three market behavior levels are determined. Level 1 indicates that the market behavior is well regulated. The higher the level, the less regulated the subject behavior and the lower the market efficiency.

[0136] Based on the Bayesian network, a market behavior evaluation model for power generation entities in the power market is established, and 9 rounds of simulation experiments are carried out, as shown in Table 1 below:

[0137]

[0138] Table 1

[0139] The behavior data of the seventh round of simulation experiments are used as the market behavior data to be evaluated. Based on the market behavior evaluation model, the market behavior evaluation results are determined, as shown in Table 2 below:

[0140]

[0141] Table 2

[0142] Based on the above data, it can be seen that the market behavior evaluation model has the ability to identify and process complex structures, and the evaluation results obtained according to the above market behavior evaluation method are more accurate.

[0143] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0144] Based on the same inventive concept, the embodiment of the present application also provides a market behavior assessment device for implementing the market behavior assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more market behavior assessment device embodiments provided below can refer to the limitations of the market behavior assessment method above, and will not be repeated here.

[0145] In one embodiment, as shown in FIG. 11 , FIG. 11 is a structural block diagram of a market behavior evaluation device provided in an embodiment of the present application, and the device 1100 includes:

[0146] The model building module 1101 is used to build a market behavior evaluation model based on the historical behavior data of the power market and the Bayesian network; the Bayesian network is built based on the evaluation index system, and the evaluation index system includes multiple first-level evaluation indicators and second-level evaluation indicators corresponding to each first-level evaluation indicator.

[0147] The acquisition module 1102 is used to acquire the market behavior data to be evaluated in the power market.

[0148] The determination module 1103 is used to determine the market behavior evaluation result of the market behavior data to be evaluated based on the market behavior evaluation model.

[0149] In one embodiment, the determining module 1103 includes:

[0150] The first determination unit is used to determine the first market behavior evaluation result of the market behavior data to be evaluated under each first-level evaluation indicator based on the market behavior evaluation model.

[0151] The second determining unit is used to determine the second market behavior evaluation result of the market behavior data to be evaluated according to each first market behavior evaluation result and the weight coefficient corresponding to each first-level evaluation index.

[0152] Among them, the market behavior evaluation results include a first market behavior evaluation result and a second market behavior evaluation result.

[0153] In one embodiment, the first determining unit includes:

[0154] The first determination subunit is used to determine the probability of each market behavior level of the market behavior data to be evaluated under the first-level evaluation indicators based on the market behavior evaluation model for each first-level evaluation indicator.

[0155] The second determining subunit is used to use the market behavior level corresponding to the maximum probability as the first market behavior evaluation result of the market behavior data to be evaluated under the first-level evaluation index.

[0156] In one embodiment, the model building module 1101 includes:

[0157] The first construction unit is used to construct an evaluation index system based on historical behavior data.

[0158] The second construction unit is used to construct a Bayesian network based on the evaluation index system; the nodes of the Bayesian network are used to represent the indicators in the evaluation index system, and the edges of the Bayesian network are used to represent the dependency relationship between the indicators.

[0159] The third determination unit is used to determine the parameters of the Bayesian network based on the expectation maximization algorithm and the historical behavior data to obtain a market behavior evaluation model.

[0160] In one embodiment, the third determining unit includes:

[0161] Get subunits for obtaining initial parameters of the Bayesian network.

[0162] The third determination subunit is used to determine the expected probability distribution of each latent variable in the Bayesian network according to the Bayesian network, initial parameters, and historical behavior data.

[0163] The fourth determination subunit is used to determine the parameters of the Bayesian network according to the maximum probability distribution expectation.

[0164] In one embodiment, the acquisition module 1102 includes:

[0165] The acquisition unit is used to acquire initial market behavior data of the power market.

[0166] The correction unit is used to correct the missing values ​​and abnormal values ​​in the initial market behavior data based on the regression interpolation method to obtain the intermediate market behavior data.

[0167] The fourth determining unit is used to determine the maximum value and the minimum value in the intermediate market behavior data.

[0168] The standardization unit is used to standardize the intermediate market behavior data according to the maximum value, the minimum value, and the numerical value of the intermediate market behavior data to obtain the market behavior data to be evaluated.

[0169] Each module in the above market behavior evaluation device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0170] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0171] A market behavior evaluation model is constructed based on the historical behavior data of the power market and the Bayesian network; the Bayesian network is constructed based on the evaluation index system, and the evaluation index system includes multiple first-level evaluation indicators and second-level evaluation indicators corresponding to each first-level evaluation indicator;

[0172] Obtain market behavior data to be evaluated in the electricity market;

[0173] Based on the market behavior evaluation model, the market behavior evaluation results of the market behavior data to be evaluated are determined.

[0174] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0175] Based on the market behavior evaluation model, determine the first market behavior evaluation results of the market behavior data to be evaluated under each first-level evaluation indicator;

[0176] Determine the second market behavior evaluation result of the market behavior data to be evaluated according to each first market behavior evaluation result and the weight coefficient corresponding to each first-level evaluation indicator;

[0177] Among them, the market behavior evaluation results include a first market behavior evaluation result and a second market behavior evaluation result.

[0178] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0179] For each first-level evaluation indicator, based on the market behavior evaluation model, determine the probability of each market behavior level of the market behavior data to be evaluated under the first-level evaluation indicator;

[0180] The market behavior level corresponding to the maximum probability is taken as the first market behavior evaluation result of the market behavior data to be evaluated under the first-level evaluation indicator.

[0181] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0182] Build an evaluation indicator system based on historical behavior data;

[0183] A Bayesian network is constructed based on the evaluation index system; the nodes of the Bayesian network are used to represent the indicators in the evaluation index system, and the edges of the Bayesian network are used to represent the dependency relationship between the indicators;

[0184] Based on the expectation maximization algorithm, the parameters of the Bayesian network are determined according to the historical behavior data to obtain a market behavior evaluation model.

[0185] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0186] Get the initial parameters of the Bayesian network;

[0187] Determine the expected probability distribution of each latent variable in the Bayesian network based on the Bayesian network, initial parameters, and historical behavior data;

[0188] Determine the parameters of the Bayesian network based on the maximum probability distribution expectation.

[0189] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0190] Obtaining initial market behavior data of the electricity market;

[0191] Based on the regression interpolation method, the missing values ​​and outliers in the initial market behavior data are corrected to obtain the intermediate market behavior data;

[0192] Determine the maximum and minimum values ​​in the mid-market behavior data;

[0193] According to the values ​​of the maximum value, the minimum value and the intermediate market behavior data, the intermediate market behavior data is standardized to obtain the market behavior data to be evaluated.

[0194] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0195] A market behavior evaluation model is constructed based on the historical behavior data of the power market and the Bayesian network; the Bayesian network is constructed based on the evaluation index system, and the evaluation index system includes multiple first-level evaluation indicators and second-level evaluation indicators corresponding to each first-level evaluation indicator;

[0196] Obtain market behavior data to be evaluated in the electricity market;

[0197] Based on the market behavior evaluation model, the market behavior evaluation results of the market behavior data to be evaluated are determined.

[0198] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0199] Based on the market behavior evaluation model, determine the first market behavior evaluation results of the market behavior data to be evaluated under each first-level evaluation indicator;

[0200] Determine the second market behavior evaluation result of the market behavior data to be evaluated according to each first market behavior evaluation result and the weight coefficient corresponding to each first-level evaluation indicator;

[0201] Among them, the market behavior evaluation results include a first market behavior evaluation result and a second market behavior evaluation result.

[0202] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0203] For each first-level evaluation indicator, based on the market behavior evaluation model, determine the probability of each market behavior level of the market behavior data to be evaluated under the first-level evaluation indicator;

[0204] The market behavior level corresponding to the maximum probability is used as the first market behavior evaluation result of the market behavior data to be evaluated under the first-level evaluation indicator.

[0205] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0206] Build an evaluation indicator system based on historical behavior data;

[0207] A Bayesian network is constructed based on the evaluation index system; the nodes of the Bayesian network are used to represent the indicators in the evaluation index system, and the edges of the Bayesian network are used to represent the dependency relationship between the indicators;

[0208] Based on the expectation maximization algorithm, the parameters of the Bayesian network are determined according to the historical behavior data to obtain a market behavior evaluation model.

[0209] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0210] Get the initial parameters of the Bayesian network;

[0211] Determine the expected probability distribution of each latent variable in the Bayesian network based on the Bayesian network, initial parameters, and historical behavior data;

[0212] Determine the parameters of the Bayesian network based on the maximum probability distribution expectation.

[0213] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0214] Obtaining initial market behavior data of the electricity market;

[0215] Based on the regression interpolation method, the missing values ​​and outliers in the initial market behavior data are corrected to obtain the intermediate market behavior data;

[0216] Determine the maximum and minimum values ​​in the mid-market behavior data;

[0217] According to the values ​​of the maximum value, the minimum value and the intermediate market behavior data, the intermediate market behavior data is standardized to obtain the market behavior data to be evaluated.

[0218] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0219] A market behavior evaluation model is constructed based on the historical behavior data of the power market and the Bayesian network; the Bayesian network is constructed based on the evaluation index system, and the evaluation index system includes multiple first-level evaluation indicators and second-level evaluation indicators corresponding to each first-level evaluation indicator;

[0220] Obtain market behavior data to be evaluated in the electricity market;

[0221] Based on the market behavior evaluation model, the market behavior evaluation results of the market behavior data to be evaluated are determined.

[0222] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0223] Based on the market behavior evaluation model, determine the first market behavior evaluation results of the market behavior data to be evaluated under each first-level evaluation indicator;

[0224] Determine the second market behavior evaluation result of the market behavior data to be evaluated according to each first market behavior evaluation result and the weight coefficient corresponding to each first-level evaluation indicator;

[0225] Among them, the market behavior evaluation results include a first market behavior evaluation result and a second market behavior evaluation result.

[0226] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0227] For each first-level evaluation indicator, based on the market behavior evaluation model, determine the probability of each market behavior level of the market behavior data to be evaluated under the first-level evaluation indicator;

[0228] The market behavior level corresponding to the maximum probability is taken as the first market behavior evaluation result of the market behavior data to be evaluated under the first-level evaluation indicator.

[0229] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0230] Build an evaluation indicator system based on historical behavior data;

[0231] A Bayesian network is constructed based on the evaluation index system; the nodes of the Bayesian network are used to represent the indicators in the evaluation index system, and the edges of the Bayesian network are used to represent the dependency relationship between the indicators;

[0232] Based on the expectation maximization algorithm, the parameters of the Bayesian network are determined according to the historical behavior data to obtain a market behavior evaluation model.

[0233] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0234] Get the initial parameters of the Bayesian network;

[0235] Determine the expected probability distribution of each latent variable in the Bayesian network based on the Bayesian network, initial parameters, and historical behavior data;

[0236] Determine the parameters of the Bayesian network based on the maximum probability distribution expectation.

[0237] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0238] Obtaining initial market behavior data of the electricity market;

[0239] Based on the regression interpolation method, the missing values ​​and outliers in the initial market behavior data are corrected to obtain the intermediate market behavior data;

[0240] Determine the maximum and minimum values ​​in the mid-market behavior data;

[0241] According to the values ​​of the maximum value, the minimum value and the intermediate market behavior data, the intermediate market behavior data is standardized to obtain the market behavior data to be evaluated.

[0242] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0243] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0244] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A market behavior evaluation method, characterized in that: The method comprises: Constructing a market behavior evaluation model based on historical behavior data of the power market and a Bayesian network; the Bayesian network is constructed based on an evaluation index system, and the evaluation index system includes multiple first-level evaluation indicators and second-level evaluation indicators corresponding to each of the first-level evaluation indicators; Obtaining market behavior data to be evaluated in the electricity market; Based on the market behavior evaluation model, a market behavior evaluation result of the market behavior data to be evaluated is determined.

2. The method according to claim 1, characterized in that Determining the market behavior evaluation result of the to-be-evaluated market behavior data based on the market behavior evaluation model includes: Based on the market behavior evaluation model, determining a first market behavior evaluation result of the market behavior data to be evaluated under each of the first-level evaluation indicators; Determining a second market behavior evaluation result of the market behavior data to be evaluated according to each of the first market behavior evaluation results and a weight coefficient corresponding to each of the first-level evaluation indicators; Among them, the market behavior evaluation result includes the first market behavior evaluation result and the second market behavior evaluation result.

3. The method according to claim 2, characterized in that The determining, based on the market behavior evaluation model, a first market behavior evaluation result of the market behavior data to be evaluated under each of the first-level evaluation indicators comprises: For each of the first-level evaluation indicators, based on the market behavior evaluation model, determine the probability of each market behavior level of the market behavior data to be evaluated under the first-level evaluation indicator; The market behavior level corresponding to the maximum probability is used as the first market behavior evaluation result of the market behavior data to be evaluated under the first-level evaluation indicator.

4. The method according to claim 1, characterized in that: The market behavior evaluation model is constructed based on the historical behavior data of the power market and the Bayesian network, including: Constructing an evaluation index system based on the historical behavior data; The Bayesian network is constructed based on the evaluation index system; the nodes of the Bayesian network are used to represent the evaluation indicators in the evaluation index system, and the edges of the Bayesian network are used to represent the dependency relationship between the evaluation indicators; Based on the expectation maximization algorithm, the parameters of the Bayesian network are determined according to the historical behavior data to obtain the market behavior evaluation model.

5. The method according to claim 4, characterized in that The method of determining the parameters of the Bayesian network based on the historical behavior data based on the expectation maximization algorithm includes: Obtaining initial parameters of the Bayesian network; Determining the expected probability distribution of each latent variable in the Bayesian network according to the Bayesian network, the initial parameters, and the historical behavior data; The parameters of the Bayesian network are determined according to the maximum probability distribution expectation.

6. The method according to any one of claims 1 to 5, characterized in that: The obtaining of the market behavior data to be evaluated in the power market includes: Acquiring initial market behavior data of the electricity market; Correcting missing values ​​and outliers in the initial market behavior data based on regression interpolation method to obtain intermediate market behavior data; determining maximum and minimum values ​​in the intermediate market behavior data; The intermediate market behavior data is standardized according to the maximum value, the minimum value, and the values ​​of the intermediate market behavior data to obtain the market behavior data to be evaluated.

7. A market behavior evaluation device, characterized in that: The device comprises: A model building module, used to build a market behavior evaluation model based on historical behavior data of the power market and a Bayesian network; the Bayesian network is built based on an evaluation index system, and the evaluation index system includes multiple primary evaluation indicators and secondary evaluation indicators corresponding to each of the primary evaluation indicators; An acquisition module, used for acquiring the market behavior data to be evaluated in the power market; A determination module is used to determine the market behavior evaluation result of the market behavior data to be evaluated based on the market behavior evaluation model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. 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 6 are implemented.

10. A computer program product, comprising a computer program, 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 6 are implemented.

Images