CN118014425A - Emergency system electric power emergency capacity prediction method and device and computer equipment - Google Patents

Abstract

The application relates to an emergency system power emergency capability prediction method, an emergency system power emergency capability prediction device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: identifying index data corresponding to an electric power emergency capacity index of a preset emergency system from system data of the emergency system to be predicted; performing feature extraction processing on the index data to obtain feature vectors corresponding to the index data; inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data; and determining a power emergency capacity prediction result of the emergency system to be predicted according to the prediction emergency score and the weight. By adopting the method, the determination accuracy of the electric power emergency capacity of the emergency system can be improved.

Description

Emergency system electric power emergency capacity prediction method and device and computer equipment

Technical Field

The application relates to the technical field of power grids, in particular to a method, a device, computer equipment, a storage medium and a computer program product for predicting electric power emergency capacity of an emergency system.

Background

In an emergency system, the electric power emergency capacity of the emergency system is accurately evaluated, and the electric power emergency capacity of the emergency system is extremely important to construction and improvement.

In the prior art, when the emergency power capability of an emergency system is evaluated, a manual evaluation method is usually the main method; however, the manual evaluation method has subjective factors, is easy to error, and has low determination accuracy of the electric power emergency capability of the emergency system.

Disclosure of Invention

In view of the foregoing, it is desirable to provide an emergency system power emergency capability prediction method, apparatus, computer device, computer readable storage medium, and computer program product that can improve the accuracy of determination of an emergency system power emergency capability.

In a first aspect, the present application provides a method for predicting an electric power emergency capability of an emergency system, including:

Identifying index data corresponding to an electric power emergency capacity index of a preset emergency system from system data of the emergency system to be predicted;

performing feature extraction processing on the index data to obtain feature vectors corresponding to the index data;

inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data;

And determining a power emergency capacity prediction result of the emergency system to be predicted according to the prediction emergency score and the weight.

In one embodiment, the identifying, from the system data of the emergency system to be predicted, index data corresponding to an electric emergency capability index of the preset emergency system includes:

Preprocessing system data of an emergency system to be predicted to obtain preprocessed system data;

Identifying a data identifier corresponding to the preprocessing system data;

And identifying system data, corresponding to the data identification, matched with the preset emergency system power emergency capacity index from the preprocessing system data, as index data corresponding to the preset emergency system power emergency capacity index.

In one embodiment, the performing feature extraction processing on the index data to obtain a feature vector corresponding to the index data includes:

Screening key index data from the index data;

determining a feature extraction model corresponding to the key index data according to the data type of the key index data;

Inputting the key index data into a corresponding feature extraction model to perform feature extraction processing to obtain feature vectors corresponding to the key index data;

Inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data, wherein the method comprises the following steps:

And inputting the feature vector corresponding to the key index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the key index data and a weight corresponding to the key index data.

In one embodiment, the pre-trained power emergency capability prediction model includes an emergency score prediction network and an attention mechanism network;

Inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data, wherein the method comprises the following steps:

performing feature extraction processing on the feature vector corresponding to the index data through the emergency score prediction network to obtain a first target feature vector corresponding to the index data, and performing emergency prediction processing on the first target feature vector corresponding to the index data to obtain a predicted emergency score corresponding to the index data;

And performing feature extraction processing on the feature vector corresponding to the index data through the attention mechanism network to obtain a second target feature vector corresponding to the index data, and performing attention mechanism processing on the second target feature vector corresponding to the index data to obtain a weight corresponding to the index data.

In one embodiment, the pre-trained power emergency capability prediction model is trained by:

Acquiring sample index data corresponding to a preset emergency system power emergency capacity index in a sample emergency system;

performing feature extraction processing on the sample index data to obtain feature vectors corresponding to the sample index data;

inputting the feature vector corresponding to the sample index data into a power emergency capacity prediction model to be trained to obtain a prediction emergency score corresponding to the sample index data and a weight corresponding to the sample index data;

determining a power emergency capacity prediction result of the sample emergency system according to the prediction emergency score corresponding to the sample index data and the weight corresponding to the sample index data;

And carrying out iterative training on the electric power emergency capacity prediction model to be trained according to the difference between the electric power emergency capacity prediction result of the sample emergency system and the electric power emergency capacity actual result of the sample emergency system, so as to obtain the pre-trained electric power emergency capacity prediction model.

In one embodiment, the determining the power emergency capability prediction result of the emergency system to be predicted according to the prediction emergency score and the weight includes:

Clustering the index data through a pre-trained clustering model to obtain an index data set;

Performing fusion processing on the prediction emergency score corresponding to the index data in each index data set to obtain the prediction emergency score corresponding to each index data set, and performing fusion processing on the weight corresponding to the index data in each index data set to obtain the weight corresponding to each index data set;

And carrying out fusion processing on the prediction emergency score corresponding to each index data set and the weight corresponding to each index data set to obtain a power emergency capability prediction result of the emergency system to be predicted.

In a second aspect, the present application also provides an emergency system power emergency capability prediction apparatus, including:

The index data identification module is used for identifying index data corresponding to the electric power emergency capacity index of the preset emergency system from the system data of the emergency system to be predicted;

The feature vector extraction module is used for carrying out feature extraction processing on the index data to obtain feature vectors corresponding to the index data;

The index data prediction module is used for inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data;

And the prediction result determining module is used for determining the power emergency capacity prediction result of the emergency system to be predicted according to the prediction emergency score and the weight.

In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

Identifying index data corresponding to an electric power emergency capacity index of a preset emergency system from system data of the emergency system to be predicted;

performing feature extraction processing on the index data to obtain feature vectors corresponding to the index data;

inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data;

And determining a power emergency capacity prediction result of the emergency system to be predicted according to the prediction emergency score and the weight.

In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

Identifying index data corresponding to an electric power emergency capacity index of a preset emergency system from system data of the emergency system to be predicted;

performing feature extraction processing on the index data to obtain feature vectors corresponding to the index data;

inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data;

And determining a power emergency capacity prediction result of the emergency system to be predicted according to the prediction emergency score and the weight.

In a fifth aspect, the application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of:

Identifying index data corresponding to an electric power emergency capacity index of a preset emergency system from system data of the emergency system to be predicted;

performing feature extraction processing on the index data to obtain feature vectors corresponding to the index data;

inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data;

And determining a power emergency capacity prediction result of the emergency system to be predicted according to the prediction emergency score and the weight.

According to the emergency system power emergency capacity prediction method, the device, the computer equipment, the storage medium and the computer program product, firstly, index data corresponding to a preset emergency system power emergency capacity index are identified from system data of an emergency system to be predicted, then feature extraction processing is carried out on the index data to obtain feature vectors corresponding to the index data, then the feature vectors corresponding to the index data are input into a pre-trained power emergency capacity prediction model to obtain prediction emergency scores corresponding to the index data and weights corresponding to the index data, and finally a power emergency capacity prediction result of the emergency system to be predicted is determined according to the prediction emergency scores and the weights. When the electric power emergency capacity of the emergency system is predicted, the system data of the emergency system to be predicted are recognized and extracted, and then the recognized and extracted result is input into the pre-trained electric power emergency capacity prediction model to be predicted, so that the electric power emergency capacity prediction result of the emergency system to be predicted is more accurate, the determination accuracy of the electric power emergency capacity of the emergency system is improved, manual intervention is not needed in the whole process, and the defect that the evaluation result is one-sided due to manual evaluation, and the determination accuracy of the electric power emergency capacity of the emergency system is lower is avoided.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for those skilled in the art.

FIG. 1 is a flow diagram of a method for predicting power emergency capability of an emergency system in one embodiment;

FIG. 2 is a schematic diagram of a preset emergency system power emergency capability index in one embodiment;

FIG. 3 is a flowchart illustrating steps for identifying index data corresponding to a preset emergency system power emergency capability index in one embodiment;

FIG. 4 is a flowchart illustrating steps for obtaining feature vectors corresponding to index data according to an embodiment;

FIG. 5 is a flowchart illustrating steps for obtaining predicted emergency scores and weights corresponding to index data in one embodiment;

FIG. 6 is a flow chart of steps for deriving a pre-trained power emergency capability prediction model in one embodiment;

FIG. 7 is a flowchart illustrating steps for obtaining a power emergency capability prediction result for an emergency system to be predicted in one embodiment;

FIG. 8 is a flow chart of a method for predicting power emergency capability of an emergency system according to another embodiment;

FIG. 9 is a block diagram of an emergency system power emergency capability prediction device in one embodiment;

FIG. 10 is an internal block diagram of a computer device in one embodiment;

Fig. 11 is an internal structural view of a computer device in another embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are both information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to meet the related regulations.

In an exemplary embodiment, as shown in fig. 1, there is provided a method for predicting power emergency capability of an emergency system, where the method is applied to a server for illustration; it will be appreciated that the method may also be applied to a terminal, and may also be applied to a system comprising a terminal and a server, and implemented by interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones and tablet computers; the server may be implemented as a stand-alone server or as a server cluster composed of a plurality of servers. In this embodiment, the method includes the steps of:

step S101, identifying index data corresponding to a preset emergency system power emergency capability index from system data of an emergency system to be predicted.

The emergency system may be referred to herein as a government system.

The emergency system to be predicted refers to an emergency system which needs to be predicted.

The system data of the emergency system to be predicted refers to data in the emergency system to be predicted, and can refer to population data, economic data and the like.

The preset emergency system power emergency capability index refers to a preset emergency system power emergency capability index.

For example, referring to fig. 2, the emergency system power emergency capability indicators may include 4 power emergency capability assessment primary indicators, such as prevention and emergency readiness capability, monitoring and early warning capability, emergency disposal and rescue capability, and post-hoc recovery and reconstruction capability; the system comprises a prevention and emergency preparation capacity index, a control system, a resource guarantee system, an information reporting and information release system, an emergency linkage foundation and a risk assessment, wherein the prevention and emergency preparation capacity index can have 6 secondary indexes; 3 secondary indexes can be arranged under the monitoring and early warning capability indexes, such as monitoring and early warning capability, event monitoring and early warning management; the emergency treatment and rescue capability indexes can have 6 secondary indexes, such as command decision capability, information communication and sharing capability, emergency rescue capability, emergency guarantee capability, emergency control capability and linkage processing capability; the post-disaster recovery and reconstruction capability index can have 4 secondary indexes, such as emergency guarantee capability, electric power emergency loss evaluation capability, post-disaster recovery and reconstruction capability and post-disaster linkage capability.

The index data corresponding to the preset emergency system power emergency capacity index refers to data corresponding to the preset emergency system power emergency capacity index, for example, 50 full-time emergency personnel, 10 emergency expert teams, 3 emergency training times and the like exist in the resource guarantee system index.

The server responds to the emergency system power emergency capability prediction instruction, acquires system data of an emergency system to be predicted from a database, identifies a data identifier corresponding to the system data of the emergency system to be predicted, and identifies system data, matched with a preset emergency system power emergency capability index, from the system data of the emergency system to be predicted as index data corresponding to the preset emergency system power emergency capability index.

Step S102, performing feature extraction processing on the index data to obtain feature vectors corresponding to the index data.

The feature extraction processing of the index data may refer to a processing procedure of converting the index data into feature vectors.

The feature vector corresponding to the index data is a feature vector obtained by performing feature extraction processing on the index data.

The server determines a feature extraction model corresponding to the index data according to the data type of the index data, and inputs the index data into the corresponding feature extraction model to perform feature extraction processing to obtain feature vectors corresponding to the index data.

Step S103, inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data.

The power emergency capacity prediction model is a network model which can obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data by utilizing the feature vector corresponding to the index data.

The predicted emergency score corresponding to the index data refers to a predicted value of the emergency score corresponding to the index data.

The weight corresponding to the index data refers to a predicted value of the weight corresponding to the index data, and is used for representing the importance degree corresponding to the index data.

The server inputs the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model, predicts the feature vector corresponding to the index data through the power emergency capacity prediction model to obtain the prediction probability under each preset emergency score and the prediction probability under each preset weight respectively, and then screens out the preset emergency score and the preset weight with the maximum prediction probability from the prediction probability under each preset emergency score and the prediction probability under each preset weight respectively to serve as the prediction emergency score corresponding to the index data and the weight corresponding to the index data.

And step S104, determining a power emergency capacity prediction result of the emergency system to be predicted according to the prediction emergency score and the weight.

The electric power emergency capacity prediction result of the emergency system to be predicted refers to a prediction value of the electric power emergency capacity result of the emergency system to be predicted.

Illustratively, the server performs fusion processing, such as weighted summation processing, on the predicted emergency score corresponding to the index data and the weight corresponding to the index data; and then, the server takes the result obtained after the fusion processing as a power emergency capability prediction result of the emergency system to be predicted.

In the emergency system power emergency capacity prediction method, firstly, index data corresponding to a preset emergency system power emergency capacity index is identified from system data of an emergency system to be predicted, then feature extraction processing is carried out on the index data to obtain feature vectors corresponding to the index data, then the feature vectors corresponding to the index data are input into a pre-trained power emergency capacity prediction model to obtain a predicted emergency score corresponding to the index data and a weight corresponding to the index data, and finally a power emergency capacity prediction result of the emergency system to be predicted is determined according to the predicted emergency score and the weight. When the electric power emergency capacity of the emergency system is predicted, the system data of the emergency system to be predicted are recognized and extracted, and then the recognized and extracted result is input into the pre-trained electric power emergency capacity prediction model to be predicted, so that the electric power emergency capacity prediction result of the emergency system to be predicted is more accurate, the determination accuracy of the electric power emergency capacity of the emergency system is improved, manual intervention is not needed in the whole process, and the defect that the evaluation result is one-sided due to manual evaluation, and the determination accuracy of the electric power emergency capacity of the emergency system is lower is avoided.

In an exemplary embodiment, as shown in fig. 3, the step S101 identifies, from the system data of the emergency system to be predicted, index data corresponding to a preset emergency system power emergency capability index, and specifically includes the following steps:

Step S301, preprocessing system data of an emergency system to be predicted to obtain preprocessed system data.

Step S302, a data identifier corresponding to the preprocessing system data is identified.

Step S303, identifying the system data matched with the preset emergency system power emergency capacity index from the preprocessing system data as index data corresponding to the preset emergency system power emergency capacity index.

The preprocessing of the system data of the emergency system to be predicted refers to preprocessing of the system data of the emergency system to be predicted, such as checking whether missing values and abnormal values exist in the system data of the emergency system to be predicted, filling the system data with the missing values, deleting the system data with the abnormal values, and the like.

The preprocessing system data refers to the preprocessed system data of the emergency system to be predicted.

The data identifier corresponding to the preprocessing system data refers to a data category corresponding to the preprocessing system data, such as command decision capability, emergency rescue capability and the like.

The server preprocesses the system data of the emergency system to be predicted, for example, checking whether the system data of the emergency system to be predicted has a missing value and an abnormal value, filling the system data with the missing value, deleting the system data with the abnormal value, and the like, so as to obtain the preprocessed system data of the emergency system to be predicted, and taking the preprocessed system data as preprocessed system data; then, the server identifies the data identification corresponding to the preprocessing system data, then obtains the matching degree between the data identification corresponding to the preprocessing system data and the preset emergency system power emergency capacity index, and screens out the system data with the matching degree larger than the preset matching degree from the preprocessing system data as index data corresponding to the preset emergency system power emergency capacity index.

In the embodiment, the system data of the emergency system to be predicted is preprocessed, so that the accuracy and the reliability of the system data are improved; and the system data matched with the preset emergency system power emergency capacity index is identified, so that the data conforming to the preset index can be obtained, and the subsequent analysis of the emergency system power emergency capacity is facilitated.

In an exemplary embodiment, as shown in fig. 4, in step S102, feature extraction processing is performed on the index data to obtain feature vectors corresponding to the index data, and the method specifically includes the following steps:

Step S401, screening key index data from the index data.

Step S402, determining a feature extraction model corresponding to the key index data according to the data type of the key index data.

Step S403, inputting the key index data into the corresponding feature extraction model for feature extraction processing to obtain feature vectors corresponding to the key index data.

Then, in step S103, the feature vector corresponding to the index data is input into the pre-trained power emergency capability prediction model to obtain the predicted emergency score corresponding to the index data and the weight corresponding to the index data, including: and inputting the feature vector corresponding to the key index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the key index data and a weight corresponding to the key index data.

The key index data is index data with higher importance degree obtained by screening from the index data. For example, the application uses index data (such as the number of full-time emergency personnel, the number of emergency expert teams, etc.) with an importance degree greater than a preset importance degree in the index data as key index data.

The data type of the key index data may refer to text class data, numerical class data, and the like.

The feature extraction model corresponding to the key index data refers to a feature extraction model matched with the key index data. Such as RNN (Recurrent Neural Network ), CNN (Convolutional Neural Network, convolutional neural network), and transform models.

The feature vector corresponding to the key index data is a feature vector obtained by performing feature extraction processing on the key index data.

The predicted emergency score corresponding to the key index data refers to a predicted value of the emergency score corresponding to the key index data.

The weight corresponding to the key index data refers to a predicted value of the weight corresponding to the key index data, and is used for representing the importance degree corresponding to the key index data.

The server screens out index data meeting preset conditions from the index data as key index data; for example, the server determines the importance degrees corresponding to the index data, screens out index data with the importance degrees greater than a preset importance degree from the index data, and takes the index data as key index data; then, the server acquires the association degree between the data type of the key index data and the feature extraction model, and screens the feature extraction model, which corresponds to the data type of the key index data and has the association degree larger than the preset association degree, from the feature extraction model, and takes the feature extraction model as the feature extraction model corresponding to the key index data; then, the server inputs the key index data into the corresponding feature extraction model to perform feature extraction processing; for example, the server inputs the key index data into the transducer model to perform feature extraction processing, and obtains feature vectors corresponding to the key index data.

In the embodiment, the key index data is screened out from the index data, so that the index data with higher importance degree can be screened out, the data quantity required by the subsequent feature extraction can be greatly reduced, and the feature extraction efficiency is improved; in addition, by selecting a proper feature extraction model according to the data type of the key index data, the extracted features can be ensured to be more in line with the actual requirements, so that the subsequent processing and analysis are convenient.

In one exemplary embodiment, as shown in FIG. 5, the pre-trained power emergency capability prediction model includes an emergency score prediction network and an attention mechanism network.

Then, in step S103, the feature vector corresponding to the index data is input into the pre-trained power emergency capability prediction model to obtain the predicted emergency score corresponding to the index data and the weight corresponding to the index data, and specifically includes the following steps:

Step S501, performing feature extraction processing on feature vectors corresponding to the index data through an emergency score prediction network to obtain first target feature vectors corresponding to the index data, and performing emergency prediction processing on the first target feature vectors corresponding to the index data to obtain predicted emergency scores corresponding to the index data.

Step S502, performing feature extraction processing on feature vectors corresponding to the index data through the attention mechanism network to obtain second target feature vectors corresponding to the index data, and performing attention mechanism processing on the second target feature vectors corresponding to the index data to obtain weights corresponding to the index data.

The emergency score prediction network is a network model which can obtain the prediction emergency score corresponding to the index data by utilizing the feature vector corresponding to the index data.

The attention mechanism network is a network model which can obtain the weight corresponding to the index data by utilizing the feature vector corresponding to the index data.

The first target feature vector is a feature vector obtained by performing feature extraction processing on a feature vector corresponding to the index data through an emergency score prediction network.

The emergency prediction processing refers to a process of classifying a first target feature vector corresponding to the index data to obtain a predicted emergency score corresponding to the index data.

The second target feature vector is a feature vector obtained by performing feature extraction processing on the feature vector corresponding to the index data through the attention mechanism network.

The attention mechanism processing refers to a process of obtaining the weight corresponding to the index data according to the second target feature vector corresponding to the index data.

The server inputs the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model, and performs feature extraction processing on the feature vector corresponding to the index data through an emergency score prediction network in the pre-trained power emergency capacity prediction model to obtain a feature vector after feature extraction processing as a first target feature vector corresponding to the index data; then, the server carries out emergency prediction processing on the first target feature vector corresponding to the index data to obtain a predicted emergency score corresponding to the index data; for example, the server inputs a first target feature vector corresponding to the index data into an FC layer (Fully Connected Layer, full connection layer) in the emergency score prediction network for classification processing to obtain a predicted emergency score corresponding to the index data; then, the server performs feature extraction processing on the feature vector corresponding to the index data through a pre-trained attention mechanism network in the electric power emergency capacity prediction model to obtain a feature vector after the feature extraction processing, and the feature vector is used as a second target feature vector corresponding to the index data; then, the server performs attention mechanism processing on a second target feature vector corresponding to the index data to obtain a weight corresponding to the index data; for example, the server inputs a second target feature vector corresponding to the index data into an Attention module in the Attention mechanism network to perform Attention mechanism processing, so as to obtain a weight corresponding to the index data.

In the embodiment, the emergency score prediction network and the attention mechanism network in the pre-trained electric power emergency capacity prediction model are used for automatically determining the predicted emergency score corresponding to the index data and the weight corresponding to the index data, and the whole process is free from manual processing, so that the predicted emergency score corresponding to the index data and the weight corresponding to the index data can be accurately determined, and the determination accuracy of the electric power emergency capacity of the emergency system is improved.

In an exemplary embodiment, as shown in fig. 6, the emergency system power emergency capability prediction method provided by the present application further includes a training step of a pre-trained power emergency capability prediction model, and specifically includes the following steps:

Step S601, sample index data corresponding to a preset emergency system power emergency capacity index in a sample emergency system is obtained.

Step S602, performing feature extraction processing on the sample index data to obtain feature vectors corresponding to the sample index data.

Step S603, inputting the feature vector corresponding to the sample index data into a power emergency capacity prediction model to be trained, and obtaining a prediction emergency score corresponding to the sample index data and a weight corresponding to the sample index data.

Step S604, determining a power emergency capacity prediction result of the sample emergency system according to the prediction emergency score corresponding to the sample index data and the weight corresponding to the sample index data.

Step S605, performing iterative training on the electric power emergency capacity prediction model to be trained according to the difference between the electric power emergency capacity prediction result of the sample emergency system and the electric power emergency capacity actual result of the sample emergency system, and obtaining a pre-trained electric power emergency capacity prediction model.

The sample emergency system is used for training an electric emergency capacity prediction model.

The sample index data refers to data corresponding to a preset emergency system power emergency capacity index in the sample emergency system.

The feature vector corresponding to the sample index data is a feature vector obtained by performing feature extraction processing on the sample index data.

The predicted emergency score corresponding to the sample index data refers to a predicted value of the emergency score corresponding to the sample index data.

The weight corresponding to the sample index data refers to a predicted value of the weight corresponding to the sample index data, and is used for representing the importance degree corresponding to the sample index data.

The power emergency capability prediction result of the sample emergency system refers to a prediction value of the power emergency capability result of the sample emergency system.

The actual power emergency capability result of the sample emergency system refers to a true value of the power emergency capability result of the sample emergency system.

The difference may refer to a difference between a predicted result and an actual result of the power emergency capability of the sample emergency system.

The server responds to a training instruction aiming at the electric power emergency capacity prediction model to be trained, acquires system data of the sample emergency system from a database, identifies a data identifier corresponding to the system data of the sample emergency system, and identifies the system data, of which the corresponding data identifier is matched with a preset emergency system electric power emergency capacity index, from the system data of the sample emergency system as sample index data corresponding to the preset emergency system electric power emergency capacity index; then, the server determines a feature extraction model corresponding to the sample index data according to the data type of the sample index data, and then inputs the sample index data into the corresponding feature extraction model to perform feature extraction processing to obtain feature vectors corresponding to the sample index data; then, the server inputs the feature vector corresponding to the sample index data into a power emergency capacity prediction model to be trained, and predicts the feature vector through the power emergency capacity prediction model to be trained to obtain a predicted emergency score corresponding to the sample index data and a weight corresponding to the sample index data; then, the server performs fusion processing, such as weighted summation processing, on the prediction emergency score corresponding to the sample index data and the weight corresponding to the sample index data; then, the server takes the result obtained after fusion processing as a power emergency capability prediction result of the sample emergency system; then, the server obtains a loss value according to the difference between the power emergency capacity prediction result of the sample emergency system and the power emergency capacity actual result of the sample emergency system; and then, the server adjusts model parameters of the power emergency capacity prediction model to be trained according to the loss values, retrains the power emergency capacity prediction model with the model parameters adjusted until the loss values obtained by the trained power emergency capacity prediction model are smaller than the loss value threshold, and stops training and takes the trained power emergency capacity prediction model as a pre-trained power emergency capacity prediction model.

In the embodiment, the electric power emergency capacity prediction model is trained in advance, so that in practical application, after the feature vector corresponding to the index data is determined, the prediction emergency score corresponding to the index data and the weight corresponding to the index data are predicted; in addition, the electric power emergency capacity prediction model receives new data in each round of iteration, improves and optimizes the inside of the model, is convenient for more effectively predicting, and is beneficial to improving the prediction accuracy of the electric power emergency capacity prediction model.

In an exemplary embodiment, as shown in fig. 7, the step S104 determines a power emergency capability prediction result of the emergency system to be predicted according to the predicted emergency score and the weight, and specifically includes the following steps:

Step S701, clustering is carried out on the index data through a pre-trained clustering model, so as to obtain an index data set.

Step S702, performing fusion processing on the prediction emergency score corresponding to the index data in each index data set to obtain the prediction emergency score corresponding to each index data set, and performing fusion processing on the weight corresponding to the index data in each index data set to obtain the weight corresponding to each index data set.

Step S703, performing fusion processing on the prediction emergency score corresponding to each index data set and the weight corresponding to each index data set, to obtain a power emergency capability prediction result of the emergency system to be predicted.

The clustering model refers to a network model capable of carrying out clustering processing on index data, such as a K-means (K mean clustering algorithm) clustering model, a systematic clustering model and the like.

The clustering process refers to a process of classifying index data into different classes according to a specific standard (such as distance or similarity).

Wherein, the index data set refers to a set containing a plurality of index data.

The fusion process may be weighting process, averaging process, or maximum value calculation process.

The predicted emergency score corresponding to each index data set refers to a predicted value of the emergency score corresponding to each index data set.

The weight corresponding to each index data set refers to a predicted value of the weight corresponding to each index data set, and is used for representing the importance degree corresponding to the index data set.

The server performs clustering processing on the index data through a pre-trained clustering model to obtain an index data set; for example, the server performs clustering processing on the index data according to the similarity among the index data through a K-means clustering model trained in advance to obtain an index data set; then, the server performs fusion processing on the predicted emergency scores corresponding to the index data in each index data set, and the predicted emergency scores obtained after the fusion processing are used as the predicted emergency scores corresponding to each index data set; for example, the server screens out the highest predicted emergency score from the predicted emergency scores corresponding to the index data in each index data set, and the highest predicted emergency score is used as the predicted emergency score corresponding to each index data set; then, the server performs fusion processing on weights corresponding to index data in each index data set, and the weights obtained after the fusion processing are used as the weights corresponding to each index data set; for example, the server performs an averaging process on weights corresponding to index data in each index data set, and uses the average weight obtained after the averaging process as the weight corresponding to each index data set; finally, the server performs fusion processing on the prediction emergency score corresponding to each index data set and the weight corresponding to each index data set, and the result obtained after the fusion processing is used as the power emergency capacity prediction result of the emergency system to be predicted; for example, the server performs weighting processing on the prediction emergency score corresponding to each index data set and the weight corresponding to each index data set, and uses the result obtained after the weighting processing as the power emergency capability prediction result of the emergency system to be predicted.

In the embodiment, the index data with high dimensionality can be reduced to the index data set with low dimensionality by carrying out clustering processing on the index data, and similar index data are classified into one type, so that the complexity of the data can be reduced, and the accuracy of a prediction model can be improved; moreover, the importance of a plurality of indexes can be comprehensively considered by fusion processing of the prediction emergency score and the weight of each index data set, so that more accurate prediction results can be obtained.

In an exemplary embodiment, as shown in fig. 8, another emergency system power emergency capability prediction method is provided, and the method is applied to a server for illustration, and includes the following steps:

Step S801, preprocessing system data of an emergency system to be predicted to obtain preprocessed system data.

Step S802, a data identifier corresponding to preprocessing system data is identified; and identifying system data, corresponding to the data identification, matched with the preset emergency system power emergency capacity index from the preprocessing system data, as index data corresponding to the preset emergency system power emergency capacity index.

Step S803, screening key index data from the index data; determining a feature extraction model corresponding to the key index data according to the data type of the key index data; inputting the key index data into the corresponding feature extraction model to perform feature extraction processing, and obtaining feature vectors corresponding to the key index data.

Step S804, performing feature extraction processing on feature vectors corresponding to the key index data through an emergency score prediction network to obtain first target feature vectors corresponding to the key index data, and performing emergency prediction processing on the first target feature vectors corresponding to the key index data to obtain predicted emergency scores corresponding to the key index data.

Step S805, performing feature extraction processing on feature vectors corresponding to the key index data through the attention mechanism network to obtain second target feature vectors corresponding to the key index data, and performing attention mechanism processing on the second target feature vectors corresponding to the key index data to obtain weights corresponding to the key index data.

Step S806, clustering is carried out on the index data through a pre-trained clustering model, and an index data set is obtained.

Step S807, performing fusion processing on the prediction emergency score corresponding to the index data in each index data set to obtain a prediction emergency score corresponding to each index data set, and performing fusion processing on the weight corresponding to the index data in each index data set to obtain a weight corresponding to each index data set.

Step S808, fusion processing is carried out on the prediction emergency score corresponding to each index data set and the weight corresponding to each index data set, so as to obtain the electric power emergency capacity prediction result of the emergency system to be predicted.

According to the emergency system power emergency capacity prediction method, when the emergency system power emergency capacity prediction is carried out, the system data of the emergency system to be predicted are recognized and extracted, and then the recognized and extracted result is input into the pre-trained power emergency capacity prediction model to be predicted, so that the power emergency capacity prediction result of the emergency system to be predicted is more accurate, the determination accuracy of the emergency system power emergency capacity is improved, manual intervention is not needed in the whole process, and the defect that the determination accuracy of the emergency system power emergency capacity is lower due to the fact that the evaluation result is compared on one side due to manual evaluation is avoided.

In an exemplary embodiment, in order to more clearly illustrate the emergency system power emergency capability prediction method provided by the embodiment of the present application, a specific embodiment of the emergency system power emergency capability prediction method is described below in detail. In one embodiment, as shown in fig. 2, the application further provides an emergency system power emergency capability evaluation method, when the emergency system power emergency capability is predicted, a plurality of evaluation indexes are obtained by constructing a power emergency capability index system, weights and scores of all indexes are obtained by establishing an emergency system power safety management evaluation model, an evaluation result is determined according to the weights and scores of all indexes, and further the determination accuracy of the emergency system power emergency capability is improved. The method specifically comprises the following steps:

1. Construction of an electric power emergency capacity index system:

Starting from four aspects of prevention and preparation capability, monitoring and early warning capability, treatment and rescue capability and recovery and reconstruction capability, an electric power emergency capability evaluation index system with the characteristics of an emergency system is formulated, for example, emergency guarantee capability, post-disaster recovery reconstruction capability and post-disaster linkage capability are taken as characteristic recovery and reconstruction capability evaluation indexes, and the detailed view is shown in fig. 2.

2. Establishing an emergency system electric power safety management evaluation model:

Preparing an importance degree questionnaire, extracting data from the questionnaire, and calculating the weight of each index by using algorithms such as a hierarchical analysis method; or determining the relation among the indexes by using the knowledge graph of the indexes, and calculating the weight of each index by using DEMATEL (decision laboratory algorithm) according to the logic relation among the indexes and the direct influence. The score of each index is obtained, such as expert scoring, such as questionnaire score, and the data of each index is input into a pre-trained score evaluation model to output the score of each index. And finally determining an evaluation result by using a weighted average principle to form a report.

According to the embodiment, when the emergency system power emergency capacity prediction is carried out, the system data of the emergency system to be predicted are recognized and extracted, and then the recognized and extracted result is input into the pre-trained power emergency capacity prediction model for prediction, so that the power emergency capacity prediction result of the emergency system to be predicted is more accurate, the determination accuracy of the emergency system power emergency capacity is further improved, manual intervention is not needed in the whole process, and the defect that the evaluation result is compared on one side, and the determination accuracy of the emergency system power emergency capacity is lower is avoided. Meanwhile, the application establishes an evaluation index system of the emergency system power emergency, and can completely, comprehensively and systematically reflect the power safety condition of the emergency system so as to find problems and defects of the emergency capability in time, thereby guiding the emergency system to perfect the power emergency system.

It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides an emergency system power emergency capability prediction device for realizing the emergency system power emergency capability prediction method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the emergency system power emergency capability prediction device or devices provided below may be referred to the limitation of the emergency system power emergency capability prediction method hereinabove, and will not be repeated here.

In one exemplary embodiment, as shown in fig. 9, there is provided an emergency system power emergency capability prediction apparatus, including: an index data identification module 901, a feature vector extraction module 902, an index data prediction module 903, and a prediction result determination module 904, wherein:

The index data identification module 901 is configured to identify index data corresponding to an electric power emergency capability index of a preset emergency system from system data of the emergency system to be predicted.

The feature vector extraction module 902 is configured to perform feature extraction processing on the index data, so as to obtain a feature vector corresponding to the index data.

The index data prediction module 903 is configured to input a feature vector corresponding to the index data into a pre-trained power emergency capability prediction model, so as to obtain a predicted emergency score corresponding to the index data and a weight corresponding to the index data.

The prediction result determining module 904 is configured to determine a power emergency capability prediction result of the emergency system to be predicted according to the prediction emergency score and the weight.

In an exemplary embodiment, the index data identification module 901 is further configured to preprocess system data of an emergency system to be predicted to obtain preprocessed system data; identifying a data identifier corresponding to the preprocessing system data; and identifying system data, corresponding to the data identification, matched with the preset emergency system power emergency capacity index from the preprocessing system data, as index data corresponding to the preset emergency system power emergency capacity index.

In an exemplary embodiment, the feature vector extraction module 902 is further configured to filter key index data from the index data; determining a feature extraction model corresponding to the key index data according to the data type of the key index data; inputting the key index data into the corresponding feature extraction model to perform feature extraction processing, and obtaining feature vectors corresponding to the key index data.

In an exemplary embodiment, the index data prediction module 903 is further configured to perform feature extraction processing on a feature vector corresponding to the index data through the emergency score prediction network to obtain a first target feature vector corresponding to the index data, and perform emergency prediction processing on the first target feature vector corresponding to the index data to obtain a predicted emergency score corresponding to the index data; and performing feature extraction processing on the feature vector corresponding to the index data through the attention mechanism network to obtain a second target feature vector corresponding to the index data, and performing attention mechanism processing on the second target feature vector corresponding to the index data to obtain a weight corresponding to the index data.

In an exemplary embodiment, the emergency system power emergency capability prediction device further includes a prediction model training module, configured to obtain sample index data corresponding to a preset emergency system power emergency capability index in the sample emergency system; performing feature extraction processing on the sample index data to obtain feature vectors corresponding to the sample index data; inputting the feature vector corresponding to the sample index data into a power emergency capacity prediction model to be trained to obtain a prediction emergency score corresponding to the sample index data and a weight corresponding to the sample index data; determining a power emergency capacity prediction result of the sample emergency system according to the prediction emergency score corresponding to the sample index data and the weight corresponding to the sample index data; and carrying out iterative training on the electric power emergency capacity prediction model to be trained according to the difference between the electric power emergency capacity prediction result of the sample emergency system and the electric power emergency capacity actual result of the sample emergency system, so as to obtain a pre-trained electric power emergency capacity prediction model.

In an exemplary embodiment, the prediction result determining module 904 is further configured to perform clustering on the index data through a pre-trained clustering model to obtain an index data set; fusion processing is carried out on the prediction emergency score corresponding to the index data in each index data set to obtain the prediction emergency score corresponding to each index data set, and fusion processing is carried out on the weight corresponding to the index data in each index data set to obtain the weight corresponding to each index data set; and carrying out fusion processing on the prediction emergency score corresponding to each index data set and the weight corresponding to each index data set to obtain a power emergency capacity prediction result of the emergency system to be predicted.

The modules in the emergency system power emergency capability prediction device can be all or partially realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one exemplary embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 10. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured 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, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing data such as indexes, predicted emergency scores, weights and the like. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a method for predicting power emergency capability of an emergency system.

In an exemplary embodiment, another computer device, which may be a terminal, is provided, and an internal structure diagram thereof may be as shown in fig. 11. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured 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 and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program when executed by a processor implements a method for predicting power emergency capability of an emergency system.

It will be appreciated by those skilled in the art that the structures shown in fig. 10 and 11 are merely block diagrams of portions of structures associated with aspects of the application and are not intended to limit the computer device to which aspects of the application may be applied, and that a particular computer device may include more or fewer components than those shown, or may combine certain components, or may have a different arrangement of components.

In an exemplary embodiment, a computer device is also provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method embodiments described above.

In an exemplary embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magneto-resistive random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims (10)

1. A method for predicting power emergency capability of an emergency system, the method comprising:

Identifying index data corresponding to an electric power emergency capacity index of a preset emergency system from system data of the emergency system to be predicted;

performing feature extraction processing on the index data to obtain feature vectors corresponding to the index data;

inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data;

And determining a power emergency capacity prediction result of the emergency system to be predicted according to the prediction emergency score and the weight.

2. The method according to claim 1, wherein the identifying, from the system data of the emergency system to be predicted, index data corresponding to a preset emergency system power emergency capability index includes:

Preprocessing system data of an emergency system to be predicted to obtain preprocessed system data;

Identifying a data identifier corresponding to the preprocessing system data;

And identifying system data, corresponding to the data identification, matched with the preset emergency system power emergency capacity index from the preprocessing system data, as index data corresponding to the preset emergency system power emergency capacity index.

3. The method of claim 1, wherein the performing feature extraction on the index data to obtain feature vectors corresponding to the index data includes:

Screening key index data from the index data;

determining a feature extraction model corresponding to the key index data according to the data type of the key index data;

Inputting the key index data into a corresponding feature extraction model to perform feature extraction processing to obtain feature vectors corresponding to the key index data;

Inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data, wherein the method comprises the following steps:

And inputting the feature vector corresponding to the key index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the key index data and a weight corresponding to the key index data.

4. The method of claim 1, wherein the pre-trained power emergency capability prediction model comprises an emergency score prediction network and an attention mechanism network;

Inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data, wherein the method comprises the following steps:

performing feature extraction processing on the feature vector corresponding to the index data through the emergency score prediction network to obtain a first target feature vector corresponding to the index data, and performing emergency prediction processing on the first target feature vector corresponding to the index data to obtain a predicted emergency score corresponding to the index data;

And performing feature extraction processing on the feature vector corresponding to the index data through the attention mechanism network to obtain a second target feature vector corresponding to the index data, and performing attention mechanism processing on the second target feature vector corresponding to the index data to obtain a weight corresponding to the index data.

5. The method of claim 1, wherein the pre-trained power emergency capability prediction model is trained by:

Acquiring sample index data corresponding to a preset emergency system power emergency capacity index in a sample emergency system;

performing feature extraction processing on the sample index data to obtain feature vectors corresponding to the sample index data;

inputting the feature vector corresponding to the sample index data into a power emergency capacity prediction model to be trained to obtain a prediction emergency score corresponding to the sample index data and a weight corresponding to the sample index data;

determining a power emergency capacity prediction result of the sample emergency system according to the prediction emergency score corresponding to the sample index data and the weight corresponding to the sample index data;

And carrying out iterative training on the electric power emergency capacity prediction model to be trained according to the difference between the electric power emergency capacity prediction result of the sample emergency system and the electric power emergency capacity actual result of the sample emergency system, so as to obtain the pre-trained electric power emergency capacity prediction model.

6. The method of any one of claims 1 to 5, wherein the determining a power emergency capability prediction result of the emergency system to be predicted from the predicted emergency score and the weight comprises:

Clustering the index data through a pre-trained clustering model to obtain an index data set;

Performing fusion processing on the prediction emergency score corresponding to the index data in each index data set to obtain the prediction emergency score corresponding to each index data set, and performing fusion processing on the weight corresponding to the index data in each index data set to obtain the weight corresponding to each index data set;

And carrying out fusion processing on the prediction emergency score corresponding to each index data set and the weight corresponding to each index data set to obtain a power emergency capability prediction result of the emergency system to be predicted.

7. An emergency system power emergency capability prediction apparatus, the apparatus comprising:

The index data identification module is used for identifying index data corresponding to the electric power emergency capacity index of the preset emergency system from the system data of the emergency system to be predicted;

The feature vector extraction module is used for carrying out feature extraction processing on the index data to obtain feature vectors corresponding to the index data;

The index data prediction module is used for inputting the feature vector corresponding to the index data into a pre-trained power emergency capacity prediction model to obtain a prediction emergency score corresponding to the index data and a weight corresponding to the index data;

And the prediction result determining module is used for determining the power emergency capacity prediction result of the emergency system to be predicted according to the prediction emergency score and the weight.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.