CN118070095A

CN118070095A - Method and device for predicting power emergency capacity of power grid enterprise and computer equipment

Info

Publication number: CN118070095A
Application number: CN202410174505.3A
Authority: CN
Inventors: 朱永兴; 柯伟; 洪巧章; 邹学通; 曾宪伟; 韦明鸣; 袁太平
Original assignee: China Southern Power Grid Co Ltd; Energy Development Research Institute of China Southern Power Grid Co Ltd
Current assignee: China Southern Power Grid Co Ltd; Energy Development Research Institute of China Southern Power Grid Co Ltd
Priority date: 2024-02-07
Filing date: 2024-02-07
Publication date: 2024-05-24

Abstract

The application relates to a power grid enterprise electric power emergency capability prediction method, a device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring index data of a power grid enterprise to be analyzed; clustering the index data to obtain an index data set of the power grid enterprise to be analyzed; respectively inputting the feature vectors corresponding to the index data sets into a first emergency capacity fraction prediction model of each index data set to obtain predicted electric power emergency capacity fractions of each index data set; the predicted power emergency capacity scores of the index data sets are input into a second emergency capacity score prediction model to be subjected to fusion processing, so that the target power emergency capacity score of the power grid enterprise to be analyzed is obtained; and determining the power emergency capacity grade of the power grid enterprise to be analyzed according to the target power emergency capacity score of the power grid enterprise to be analyzed. By adopting the method, the determination accuracy of the power emergency capacity of the power grid enterprise can be improved.

Description

Method and device for predicting power emergency capacity of power grid enterprise and computer equipment

Technical Field

The application relates to the technical field of power grids, in particular to a power emergency capability prediction method, a device, computer equipment, a storage medium and a computer program product for a power grid enterprise.

Background

In power grid enterprises, the power emergency capacity of the power grid enterprises is accurately evaluated, and the power emergency capacity of the power grid enterprises is extremely important to construction and improvement.

In the traditional technology, when evaluating the power emergency capacity of a power grid enterprise, a manual evaluation method is usually the main method; however, the manual evaluation method has subjective factors, errors are easy to occur, and the determination accuracy of the power emergency capacity of the power grid enterprise is low.

Disclosure of Invention

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

In a first aspect, the application provides a method for predicting power emergency capability of a power grid enterprise, which comprises the following steps:

Responding to a power emergency capability prediction request aiming at a power grid enterprise to be analyzed, and acquiring index data of the power grid enterprise to be analyzed under a preset power grid enterprise power emergency capability index;

clustering the index data to obtain an index data set corresponding to the power grid enterprise to be analyzed;

Respectively inputting the feature vectors corresponding to the index data sets into a first emergency capacity fraction prediction model corresponding to the index data sets to obtain predicted electric power emergency capacity fractions corresponding to the index data sets;

inputting the predicted power emergency capacity scores corresponding to the index data sets into a second emergency capacity score prediction model for fusion processing to obtain target power emergency capacity scores corresponding to the power grid enterprises to be analyzed;

And determining the power emergency capacity grade of the power grid enterprise to be analyzed according to the target power emergency capacity score of the power grid enterprise to be analyzed.

In one embodiment, the obtaining, in response to a power emergency capability prediction request for a power grid enterprise to be analyzed, index data of the power grid enterprise to be analyzed under a preset power grid enterprise power emergency capability index includes:

Determining an enterprise type of a power grid enterprise to be analyzed in response to a power emergency capability prediction request for the power grid enterprise to be analyzed;

identifying an electric power emergency capacity index corresponding to the enterprise type from preset electric power emergency capacity indexes of the electric power grid enterprise as the electric power emergency capacity index corresponding to the electric power grid enterprise to be analyzed;

And acquiring index data of the electric power emergency capacity index corresponding to the electric power enterprise to be analyzed, and taking the index data of the electric power emergency capacity index of the electric power enterprise to be analyzed as the index data of the electric power emergency capacity index of the preset electric power enterprise.

In one embodiment, the clustering processing is performed on the index data to obtain an index data set corresponding to the power grid enterprise to be analyzed, including:

acquiring index data characteristics corresponding to the index data;

extracting key data features in the index data features;

according to key data characteristics in the index data characteristics, carrying out initial clustering treatment on the index data to obtain an initial index data set corresponding to a power grid enterprise to be analyzed;

and updating the initial index data set according to the distance between the key data features in the index data features and the clustering center of the initial index data set to obtain an updated index data set serving as the index data set corresponding to the power grid enterprise to be analyzed.

In one embodiment, before the feature vectors corresponding to the index data sets are respectively input into the first emergency power score prediction model corresponding to the index data sets to obtain the predicted power emergency power score corresponding to the index data sets, the method further includes:

identifying index data set identifiers of the index data sets;

Verifying the index data set identifiers of the index data sets;

And under the condition that the index data set identifiers of all the index data sets pass verification, inquiring the corresponding relation between the index data set identifiers and the first emergency capacity fraction prediction model according to the index data set identifiers of all the index data sets, and obtaining the first emergency capacity fraction prediction model corresponding to all the index data sets.

Acquiring characteristic vectors of index data in each index data set;

respectively inputting the feature vectors of the index data in each index data set into a weight prediction model to obtain weights corresponding to the index data in each index data set;

and carrying out fusion processing on the feature vectors of the index data in each index data set according to the weight corresponding to the index data in each index data set to obtain the feature vector corresponding to each index data set.

In one embodiment, the inputting the feature vectors corresponding to the index data sets into the first emergency power score prediction model corresponding to the index data sets to obtain the predicted power emergency power score corresponding to the index data sets includes:

Respectively inputting the feature vectors corresponding to the index data sets into a first emergency capacity fraction prediction model corresponding to the index data sets to obtain the prediction probability of the index data sets under each preset electric power emergency capacity fraction;

And screening the preset power emergency capacity fraction with the maximum prediction probability from the preset power emergency capacity fractions according to each index data set, and taking the preset power emergency capacity fraction with the maximum prediction probability as the predicted power emergency capacity fraction corresponding to each index data set.

In a second aspect, the present application further provides a power emergency capability prediction apparatus for a power grid enterprise, including:

The system comprises an index data acquisition module, a power emergency capacity prediction module and a power emergency capacity prediction module, wherein the index data acquisition module is used for responding to a power emergency capacity prediction request for a power grid enterprise to be analyzed and acquiring index data of the power grid enterprise to be analyzed under a preset power emergency capacity index of the power grid enterprise;

the index data clustering module is used for carrying out clustering processing on the index data to obtain an index data set corresponding to the power grid enterprise to be analyzed;

The first score prediction module is used for respectively inputting the feature vectors corresponding to the index data sets into a first emergency capacity score prediction model corresponding to the index data sets to obtain predicted power emergency capacity scores corresponding to the index data sets;

The second score prediction module is used for inputting the predicted power emergency capacity score corresponding to each index data set into a second emergency capacity score prediction model for fusion processing to obtain a target power emergency capacity score corresponding to the power grid enterprise to be analyzed;

And the capacity grade determining module is used for determining the electric power emergency capacity grade of the electric power enterprise to be analyzed according to the target electric power emergency capacity score of the electric power enterprise to be analyzed.

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:

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:

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:

According to the power grid enterprise power emergency capacity prediction method, the device, the computer equipment, the storage medium and the computer program product, firstly, index data of the power grid enterprise to be analyzed under the preset power grid enterprise power emergency capacity index is obtained in response to a power emergency capacity prediction request of the power grid enterprise to be analyzed, then the index data are clustered to obtain index data sets corresponding to the power grid enterprise to be analyzed, then feature vectors corresponding to the index data sets are respectively input into a first emergency capacity score prediction model corresponding to the index data sets to obtain predicted power emergency capacity scores corresponding to the index data sets, then the predicted power emergency capacity scores corresponding to the index data sets are input into a second emergency capacity score prediction model to be subjected to fusion processing to obtain target power emergency capacity scores corresponding to the power grid enterprise to be analyzed, and finally, the power emergency capacity grade of the power grid enterprise to be analyzed is determined according to the target power emergency capacity scores of the power grid enterprise to be analyzed. When the electric power emergency capacity of the electric power grid enterprise is predicted, index data sets are obtained by clustering the index data of the electric power grid enterprise to be analyzed, and each index data set is predicted by utilizing the two emergency capacity fraction prediction models, so that the predicted electric power emergency capacity fraction of the electric power grid enterprise to be analyzed is more accurate, the determination accuracy of the electric power emergency capacity grade of the electric power grid enterprise to be analyzed is improved, the determination accuracy of the electric power emergency capacity of the electric power grid enterprise is improved, manual intervention is not needed in the whole process, and the defect that the error occurs easily in manual evaluation, and the determination accuracy of the electric power emergency capacity of an 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 chart of a method for predicting power emergency capability of a power grid enterprise in one embodiment;

FIG. 2 is a schematic diagram of presetting power emergency capability indicators of a power grid enterprise in one embodiment;

FIG. 3 is a flowchart illustrating steps for obtaining index data of a power grid enterprise to be analyzed under a preset power grid enterprise power emergency capability index according to an embodiment;

FIG. 4 is a flowchart illustrating steps for obtaining an index data set corresponding to a grid enterprise to be analyzed according to an embodiment;

FIG. 5 is a flowchart illustrating steps for obtaining a first emergency capacity score prediction model corresponding to each index data set in one embodiment;

FIG. 6 is a flowchart illustrating a step of obtaining feature vectors corresponding to each index data set according to one embodiment;

FIG. 7 is a flowchart illustrating steps for obtaining predicted power emergency capability scores corresponding to respective index data sets according to one embodiment;

FIG. 8 is a flowchart of a method for predicting power emergency capability of a power grid enterprise according to another embodiment;

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

Fig. 10 is an internal structural view of a computer device in one 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, a power emergency capability prediction method of a power grid enterprise is provided, and the embodiment is exemplified by applying the method to a server; 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, in response to a power emergency capability prediction request for a power grid enterprise to be analyzed, index data of the power grid enterprise to be analyzed under a preset power grid enterprise power emergency capability index is obtained.

The power grid enterprise to be analyzed refers to a power grid enterprise needing to be analyzed.

The power emergency capability prediction request refers to a request for predicting the power emergency capability of a power grid enterprise to be analyzed.

The preset power grid enterprise power emergency capacity index refers to a preset emergency system power emergency capacity index.

For example, referring to fig. 2, the grid enterprise 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 rebuilding capability; the prevention and emergency preparation capability indexes can have 8 secondary indexes, such as regulation system, emergency planning and implementation, emergency organization, emergency plan, emergency training and exercise, emergency team, emergency command center and emergency guarantee capability; 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 response and early treatment, emergency command, emergency rescue, information report and release, public opinion guiding, adjustment and ending; there may be 3 secondary indicators under the post-recovery and reconstruction capability indicators, such as post-treatment, emergency treatment assessment, recovery reconstruction.

The index data of the power grid enterprise to be analyzed under the preset power grid enterprise power emergency capacity index refers to data corresponding to the preset emergency system power emergency capacity index in the power grid enterprise to be analyzed, for example, the index data of the power grid enterprise to be analyzed under the emergency team index is 10 emergency expert teams and 5 emergency rescue teams.

The server, in response to a power emergency capability prediction request for the power grid enterprise to be analyzed, recognizes a power emergency capability index corresponding to the power grid enterprise to be analyzed from preset power grid enterprise power emergency capability indexes, and then obtains index data of the power emergency capability index corresponding to the power grid enterprise to be analyzed from a database as index data of the power grid enterprise to be analyzed under the preset power grid enterprise power emergency capability index.

And step S102, clustering is carried out on the index data to obtain an index data set corresponding to the power grid enterprise to be analyzed.

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.

For example, referring to fig. 2, after the clustering, the index data such as regulation system, emergency planning and implementation, emergency organization, emergency plan, emergency training and exercise, emergency team, emergency command center and emergency guarantee capability are clustered as one index data set.

The server obtains index data characteristics corresponding to the index data, performs initial clustering processing on the index data according to the index data characteristics to obtain an initial index data set corresponding to the power grid enterprise to be analyzed, and updates the initial index data set according to the distance between the index data characteristics in the index data characteristics and the clustering center of the initial index data set to obtain an updated index data set serving as the index data set corresponding to the power grid enterprise to be analyzed.

Step S103, respectively inputting the feature vectors corresponding to the index data sets into a first emergency capacity fraction prediction model corresponding to the index data sets to obtain predicted power emergency capacity fractions corresponding to the index data sets.

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

The first emergency capacity fraction prediction model is a network model corresponding to the predicted power emergency capacity fraction corresponding to each index data set, which can be obtained by using feature vectors corresponding to each index data set.

The first emergency capacity score prediction model is obtained through training in the following mode: the method comprises the steps that a server obtains sample index data of a sample power grid enterprise under a preset power emergency capacity index of the power grid enterprise, and then clusters the sample index data to obtain a sample index data set corresponding to the sample power grid enterprise; then, the server respectively inputs the feature vectors corresponding to the sample index data sets into a to-be-trained first emergency capacity score prediction model corresponding to the sample index data sets, and predicts through the to-be-trained first emergency capacity score prediction model to obtain predicted electric emergency capacity scores corresponding to the sample index data sets; then, the server inputs the predicted power emergency capacity scores corresponding to the index data sets of the samples into a second emergency capacity score prediction model for fusion processing to obtain target power emergency capacity scores corresponding to the sample power grid enterprises; then, determining the predicted power emergency capacity grade of the sample power grid enterprise according to the target power emergency capacity score corresponding to the sample power grid enterprise; then, the server obtains a loss value according to the difference between the predicted power emergency capacity level of the sample power grid enterprise and the actual power emergency capacity level of the sample power grid enterprise; and then, the server adjusts model parameters of the first emergency capacity fraction prediction model to be trained according to the loss value, retrains the first emergency capacity fraction prediction model after the model parameters are adjusted until the loss value obtained by the trained first emergency capacity fraction prediction model is smaller than a loss value threshold value, and stops training and takes the trained first emergency capacity fraction prediction model as a pre-trained first emergency capacity fraction prediction model.

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

The server inputs the feature vectors corresponding to the index data sets into a first emergency capacity fraction prediction model corresponding to the index data sets, performs feature extraction processing on the feature vectors corresponding to the index data sets through the first emergency capacity fraction prediction model to obtain feature vectors after feature extraction processing, and then classifies the feature vectors after feature extraction processing to obtain predicted power emergency capacity fractions corresponding to the index data sets.

And step S104, the predicted power emergency capacity scores corresponding to the index data sets are input into a second emergency capacity score prediction model for fusion processing, and the target power emergency capacity scores corresponding to the power grid enterprises to be analyzed are obtained.

The second emergency capacity fraction prediction model is a network model capable of obtaining a target power emergency capacity fraction corresponding to a power grid enterprise to be analyzed by using the predicted power emergency capacity fraction corresponding to each index data set.

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

The target power emergency capacity score refers to a comprehensive score of the target power emergency capacity corresponding to the power grid enterprise to be analyzed.

The server inputs the predicted power emergency capacity score corresponding to each index data set into a second emergency capacity score prediction model, obtains the prediction probability under each preset weight corresponding to each index data set through the second emergency capacity score prediction model, and then respectively screens out the preset weight with the maximum prediction probability from the prediction probability under each preset weight to serve as the weight corresponding to each index data set; then, the server performs fusion processing on the predicted power emergency capacity scores corresponding to the index data sets and the corresponding weights to obtain target power emergency capacity scores corresponding to the power grid enterprises to be analyzed; for example, the server performs weighting processing on the predicted power emergency capacity score corresponding to each index data set and the corresponding weight to obtain the target power emergency capacity score corresponding to the power grid enterprise to be analyzed.

Further, the weight corresponding to each index data set may also be determined by: the server obtains index variability and index conflict corresponding to each index data set through CRITIC (objective weighting method) weighting method, and respectively performs fusion processing on the index variability and the index conflict corresponding to each index data set to obtain the weight corresponding to each index data set.

Further, the weight corresponding to each index data set may also be determined by: the server generates importance degree investigation tasks corresponding to the index data sets according to the index data sets, extracts result data corresponding to the results of the importance degree investigation tasks according to the results of the importance degree investigation tasks, and determines weights corresponding to the index data sets according to the result data and the analytic hierarchy process.

Step S105, determining the power emergency capacity grade of the power grid enterprise to be analyzed according to the target power emergency capacity score of the power grid enterprise to be analyzed.

The electric power emergency capacity grade refers to a grade which is classified according to the electric power emergency capacity of an electric network enterprise.

The server queries the corresponding relation between the electric power emergency capacity score and the electric power emergency capacity grade according to the target electric power emergency capacity score of the electric power enterprise to be analyzed, and determines the electric power emergency capacity grade corresponding to the target electric power emergency capacity score as the electric power emergency capacity grade of the electric power enterprise to be analyzed.

In the power grid enterprise power emergency capacity prediction method, firstly, index data of a power grid enterprise to be analyzed under a preset power grid enterprise power emergency capacity index is obtained in response to a power emergency capacity prediction request of the power grid enterprise to be analyzed, then the index data are clustered to obtain index data sets corresponding to the power grid enterprise to be analyzed, then feature vectors corresponding to the index data sets are input into a first emergency capacity score prediction model corresponding to the index data sets respectively to obtain predicted power emergency capacity scores corresponding to the index data sets, then the predicted power emergency capacity scores corresponding to the index data sets are input into a second emergency capacity score prediction model to be subjected to fusion processing to obtain target power emergency capacity scores corresponding to the power grid enterprise to be analyzed, and finally the power emergency capacity grade of the power grid enterprise to be analyzed is determined according to the target power emergency capacity scores of the power grid enterprise to be analyzed. When the electric power emergency capacity of the electric power grid enterprise is predicted, index data sets are obtained by clustering the index data of the electric power grid enterprise to be analyzed, and each index data set is predicted by utilizing the two emergency capacity fraction prediction models, so that the predicted electric power emergency capacity fraction of the electric power grid enterprise to be analyzed is more accurate, the determination accuracy of the electric power emergency capacity grade of the electric power grid enterprise to be analyzed is improved, the determination accuracy of the electric power emergency capacity of the electric power grid enterprise is improved, manual intervention is not needed in the whole process, and the defect that the error occurs easily in manual evaluation, and the determination accuracy of the electric power emergency capacity of an emergency system is lower is avoided.

In an exemplary embodiment, as shown in fig. 3, step S101, in response to a power emergency capability prediction request for a power grid enterprise to be analyzed, acquires index data of the power grid enterprise to be analyzed under a preset power grid enterprise power emergency capability index, and specifically includes the following steps:

step S301, determining an enterprise type of the grid enterprise to be analyzed in response to the power emergency capability prediction request for the grid enterprise to be analyzed.

In step S302, from the preset power grid enterprise power emergency capability indexes, a power emergency capability index corresponding to the enterprise type is identified as a power emergency capability index corresponding to the power grid enterprise to be analyzed.

Step S303, index data of the electric power emergency capacity index corresponding to the electric power enterprise to be analyzed is obtained and is used as index data of the electric power emergency capacity index of the electric power enterprise to be analyzed under the preset electric power enterprise.

The enterprise type may refer to an enterprise scale, and is generally classified into an extra-large enterprise, a medium-sized enterprise, a small enterprise, and the like.

The power emergency capacity index refers to an index divided according to the power emergency capacity of a power grid enterprise.

The power emergency capability index corresponding to the enterprise type refers to the power emergency capability index corresponding to the enterprise type.

For example, referring to fig. 2, the power emergency capability index includes 4 power emergency capability evaluation primary indexes, which are a preventive and emergency preparation capability, a monitoring and early warning capability, an emergency treatment and rescue capability, and a post-hoc recovery and reconstruction capability, respectively. The electric power emergency capacity indexes corresponding to the oversized enterprise are prevention and emergency preparation capacity, monitoring and early warning capacity, emergency treatment and rescue capacity and post-recovery and reconstruction capacity; the electric power emergency capacity indexes corresponding to the large enterprises are prevention and emergency preparation capacity, monitoring and early warning capacity and emergency treatment and rescue capacity; the corresponding power emergency capacity indexes of the medium-sized enterprises are prevention and emergency preparation capacity and monitoring and early warning capacity; the corresponding power emergency capability index of the small enterprise is the preventive and emergency preparation capability.

The power emergency capacity index corresponding to the power grid enterprise to be analyzed refers to a power emergency capacity index matched with the power grid enterprise to be analyzed.

For example, referring to fig. 2, if the grid enterprise to be analyzed belongs to an oversized enterprise, the corresponding power emergency capability indicators are prevention and emergency preparation capability, monitoring and early warning capability, emergency disposal and rescue capability, and post-recovery and reconstruction capability.

The index data of the power emergency capacity index corresponding to the power grid enterprise to be analyzed refers to related data of the power emergency capacity index corresponding to the power grid enterprise to be analyzed.

The server responds to a power emergency capability prediction request for the power grid enterprise to be analyzed, determines enterprise information of the power grid enterprise to be analyzed, acquires enterprise types of the power grid enterprise to be analyzed from the enterprise information of the power grid enterprise to be analyzed, acquires preset power grid enterprise power emergency capability indexes, and then identifies power emergency capability indexes corresponding to the enterprise types from the preset power grid enterprise power emergency capability indexes as power emergency capability indexes corresponding to the power grid enterprise to be analyzed; then, the server acquires data of the power grid enterprise to be analyzed from the database, and then screens out index data of the power emergency capacity index corresponding to the power grid enterprise to be analyzed from the data of the power grid enterprise to be analyzed, and the index data of the power emergency capacity index of the power grid enterprise to be analyzed is used as index data of the power grid enterprise to be analyzed under the preset power grid enterprise power emergency capacity index.

In this embodiment, by determining the type of enterprise of the power grid enterprise to be analyzed, the power emergency capability index corresponding to the type of enterprise is identified from the preset power grid enterprise power emergency capability indexes, and is used as the power emergency capability index corresponding to the power grid enterprise to be analyzed, so that the matched power emergency capability index can be selected for different types of enterprises, and the accuracy and pertinence of the power grid enterprise analysis are improved.

In an exemplary embodiment, as shown in fig. 4, step S102, the clustering process is performed on the index data to obtain an index data set corresponding to the power grid enterprise to be analyzed, and specifically includes the following steps:

Step S401, obtaining index data characteristics corresponding to the index data.

Step S402, extracting key data features in the index data features.

Step S403, performing initial clustering processing on the index data according to key data features in the index data features to obtain an initial index data set corresponding to the power grid enterprise to be analyzed.

Step S404, updating the initial index data set according to the distance between the key data feature in each index data feature and the clustering center of the initial index data set, and obtaining an updated index data set serving as an index data set corresponding to the power grid enterprise to be analyzed.

Wherein, the index data feature refers to feature information related to the index data. For example, the number of emergency expert teams in the emergency team index data is 10, and the number of emergency rescue teams is 5.

The key data features are index data features with higher importance degree extracted from the index data features. For example, the present application uses, as the key data feature, the index data feature having the importance degree larger than the preset importance degree (such as the number of emergency specialist teams, etc.).

The initial clustering process refers to a first clustering process of the index data according to key data features in the index data features.

The initial index data set is an index data set obtained after initial clustering.

The clustering center of the initial index data set refers to the center point of all key data features in the initial index data set.

Wherein the distance may refer to euclidean distance.

Wherein, updating the initial index data set refers to the process of adjusting the original index data set according to the distance.

The updated index data set refers to an index data set obtained by updating the initial index data set.

The server performs feature extraction processing on the index data to obtain index data features corresponding to the index data, and extracts the index data features meeting preset conditions from the index data features to serve as key data features; for example, the server determines the importance degrees corresponding to the index data features, extracts index data features with the importance degrees greater than a preset importance degree from the index data features, and takes the index data features as key data features; then, the server inputs key data features in the index data features into a clustering model (such as a self-organizing map neural network model), and the index data is subjected to initial clustering treatment, so that an index data set obtained after the initial clustering treatment is used as an initial index data set corresponding to a power grid enterprise to be analyzed; then, the server determines a clustering center of the initial index data set according to key data features in the initial index data set; for example, the server acquires feature vectors corresponding to key data features in the initial index data set, performs average processing on the feature vectors corresponding to the key data features, and uses the feature vectors obtained by the average processing as a clustering center of the initial index data set; then, the server acquires the distance between each key data feature and the clustering center of the initial index data set, and screens out the index data set with the minimum distance from the initial index data set, and the index data set screened for each key data feature is correspondingly used as a new index data set corresponding to each key data feature; then, the server determines a clustering center of the new index data set according to key data features in the new index data set; when the new index data set meets the preset clustering condition (for example, the objective function is converged), the new index data set meeting the preset clustering condition is used as the index data set corresponding to the power grid enterprise to be analyzed.

In the embodiment, by extracting the key data features, index data features with higher importance degree can be screened out, the data volume required by subsequent clustering can be greatly reduced, and the efficiency of clustering is improved; in addition, the clustering effect of the index data set is more accurate through continuous updating in the clustering process, and the method is beneficial to improving the determination accuracy of the index data set.

In an exemplary embodiment, as shown in fig. 5, the step S103, before inputting the feature vectors corresponding to the index data sets into the first emergency power score prediction model corresponding to the index data sets to obtain the predicted power emergency power score corresponding to the index data sets, specifically includes the following steps:

in step S501, an index data set identifier of each index data set is identified.

Step S502, verifying the index data set identifier of each index data set.

Step S503, under the condition that the index data set identifiers of all the index data sets pass verification, inquiring the corresponding relation between the index data set identifiers and the first emergency ability score prediction model according to the index data set identifiers of all the index data sets, and obtaining the first emergency ability score prediction model corresponding to all the index data sets.

Wherein the index data set identification may refer to a primary index name, such as preventive and contingency readiness.

Verification may refer to checking the index data set identifier, for example, checking whether the index data set identifier has the same or wrong identifier.

Wherein, the verification passes the index data set identification which can be each index data set to meet the corresponding standard.

The corresponding relation between the index data set identifier and the first emergency capacity fraction prediction model refers to the association information between the index data set identifier and the first emergency capacity fraction prediction model. For example, an emergency capability score prediction model a corresponding to emergency preparation capability, an emergency capability score prediction model b corresponding to early warning capability, and an emergency treatment and rescue capability score prediction model c corresponding to emergency treatment and rescue capability are prevented.

Illustratively, the server identifies index data set identifiers of each index data set according to the index data of each index data set, and verifies the index data set identifiers of each index data set; under the condition that the index data set identifiers of all the index data sets are not verified, the server re-identifies the index data set identifiers of all the index data sets to obtain new index data set identifiers of all the index data sets, and verifies the new index data set identifiers of all the index data sets until verification is passed; and under the condition that the index data set identifiers of all the index data sets pass verification, inquiring the corresponding relation between the index data set identifiers and the first emergency capacity score prediction model according to the index data set identifiers of all the index data sets to obtain the first emergency capacity score prediction model corresponding to all the index data sets.

In this embodiment, by verifying the index data set identifier of each index data set, accuracy and reliability of the index data set identifier can be further ensured; and the index data set identification and the first emergency capacity score prediction model are queried to obtain the first emergency capacity score prediction model corresponding to each index data set, and the matched emergency capacity score prediction model can be selected for different index data sets, so that the accuracy rate of emergency capacity score prediction is improved.

In an exemplary embodiment, as shown in fig. 6, the step S103, before inputting the feature vectors corresponding to the index data sets into the first emergency power score prediction model corresponding to the index data sets to obtain the predicted power emergency power score corresponding to the index data sets, specifically includes the following steps:

In step S601, feature vectors of index data in each index data set are acquired.

In step S602, feature vectors of the index data in each index data set are input into the weight prediction model, so as to obtain weights corresponding to the index data in each index data set.

Step S603, performing fusion processing on the feature vectors of the index data in each index data set according to the weights corresponding to the index data in each index data set, to obtain the feature vectors corresponding to each index data set.

The feature vector of the index data in each index data set may be a feature vector obtained by performing feature extraction processing on the index data in each index data set.

The weight prediction model is a network model that can obtain weights corresponding to index data in each index data set by using feature vectors of the index data in each index data set. Such as a transducer model.

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

The feature vector corresponding to each index data set is a feature vector obtained by fusing feature vectors of index data in each index data set.

Illustratively, the server performs feature extraction processing on the index data in each index data set, and takes a feature vector obtained by the feature extraction processing as a feature vector of the index data in each index data set; then, the server respectively inputs the characteristic vectors of the index data in each index data set into a weight prediction model, predicts the characteristic vectors of the index data in each index data set through the weight prediction model, and respectively obtains the prediction probability under each preset weight; then, the server respectively screens out the preset weight with the maximum prediction probability from the prediction probabilities under each preset weight, and the preset weight is used as the weight corresponding to the index data in each index data set; then, according to the weight corresponding to the index data in each index data set, carrying out fusion processing on the feature vector of the index data in each index data set, and taking the feature vector obtained after the fusion processing as the feature vector corresponding to each index data set; for example, the server performs a weighting process on the feature vectors of the index data in each index data set according to the weights corresponding to the index data in each index data set, and uses the feature vectors obtained after the weighting process as the feature vectors corresponding to each index data set.

In this embodiment, the weight prediction model is used to obtain the weight corresponding to the index data in each index data set, and the feature vector corresponding to each index data set is obtained by performing fusion processing on the feature vector of the index data in each index data set according to the weight. Therefore, the importance degrees corresponding to the index data can be comprehensively considered, and more accurate feature vectors can be obtained.

In an exemplary embodiment, as shown in fig. 7, the step S103 inputs feature vectors corresponding to each index data set into a first emergency power score prediction model corresponding to each index data set to obtain a predicted power emergency power score corresponding to each index data set, and specifically includes the following steps:

Step S701, respectively inputting the feature vectors corresponding to the index data sets into a first emergency capacity score prediction model corresponding to each index data set to obtain the prediction probability of each index data set under each preset electric power emergency capacity score.

Step S702, for each index data set, a preset power emergency capacity score with the largest prediction probability is screened out from the preset power emergency capacity scores and is used as the predicted power emergency capacity score corresponding to each index data set.

The preset power emergency capacity score refers to a preset power emergency capacity score, for example, 70 score, 80 score, 90 score, etc.

The prediction probability of each index data set under each preset power emergency capacity score represents the probability of each index data set under each preset power emergency capacity score, for example, the probability of index data set a under each preset power emergency capacity score is 20%, the probability of index data set a under each preset power emergency capacity score is 50% and the probability of index data set a under each preset power emergency capacity score is 30%.

The server respectively inputs the feature vectors corresponding to the index data sets into a first emergency capacity fraction prediction model corresponding to the index data sets, and predicts the feature vectors through the first emergency capacity fraction prediction model to obtain the prediction probability of the index data sets under each preset electric emergency capacity fraction; then, the server screens out the preset power emergency capacity fraction with the largest prediction probability from the preset power emergency capacity fractions aiming at each index data set, and the preset power emergency capacity fraction is used as the predicted power emergency capacity fraction corresponding to each index data set.

In this embodiment, the prediction probability of each index data set under each preset power emergency capacity score is obtained through the first emergency capacity score prediction model, and then the most probable power emergency capacity score is screened out according to the prediction probability, so that the prediction accuracy of the power emergency capacity score corresponding to each index data set is improved, manual intervention is not required in the whole process, and the defect that the prediction accuracy of the power emergency capacity score is low due to the fact that errors are easy to occur in manual evaluation is avoided.

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

Step S801, determining an enterprise type of the grid enterprise to be analyzed in response to the power emergency capability prediction request for the grid enterprise to be analyzed.

Step S802, identifying a power emergency capability index corresponding to the enterprise type from preset power grid enterprise power emergency capability indexes, as a power emergency capability index corresponding to the power grid enterprise to be analyzed.

Step 803, obtaining index data of the power emergency capacity index corresponding to the power grid enterprise to be analyzed, wherein the index data is used as index data of the power grid enterprise to be analyzed under the preset power grid enterprise power emergency capacity index.

Step S804, obtaining index data characteristics corresponding to the index data; extracting key data features in the index data features; and carrying out initial clustering treatment on the index data according to key data features in the index data features to obtain an initial index data set corresponding to the power grid enterprise to be analyzed.

Step S805, updating the initial index data set according to the distance between the key data feature in each index data feature and the clustering center of the initial index data set, to obtain an updated index data set, and using the updated index data set as the index data set corresponding to the power grid enterprise to be analyzed.

Step S806, identifying index data set identifiers of the index data sets; and verifying the index data set identification of each index data set.

Step S807, in the case that the index data set identifiers of the index data sets pass the verification, the corresponding relationship between the index data set identifiers and the first emergency ability score prediction model is queried according to the index data set identifiers of the index data sets, and the first emergency ability score prediction model corresponding to the index data sets is obtained.

Step S808, obtaining feature vectors of index data in each index data set; and respectively inputting the feature vectors of the index data in each index data set into a weight prediction model to obtain the weight corresponding to the index data in each index data set.

Step S809, performing fusion processing on the feature vectors of the index data in each index data set according to the weights corresponding to the index data in each index data set, to obtain feature vectors corresponding to each index data set.

Step S810, respectively inputting the feature vectors corresponding to the index data sets into a first emergency capacity score prediction model corresponding to the index data sets to obtain the prediction probability of the index data sets under each preset electric power emergency capacity score.

Step S811, aiming at each index data set, a preset power emergency capacity score with the largest prediction probability is screened out from the preset power emergency capacity scores to be used as the predicted power emergency capacity score corresponding to each index data set.

And step S812, the predicted power emergency capacity scores corresponding to the index data sets are input into a second emergency capacity score prediction model for fusion processing, and the target power emergency capacity scores corresponding to the power grid enterprises to be analyzed are obtained.

Step S813, determining the power emergency capacity grade of the power grid enterprise to be analyzed according to the target power emergency capacity score of the power grid enterprise to be analyzed.

According to the method for predicting the electric power emergency capacity of the electric power grid enterprise, when the electric power emergency capacity of the electric power grid enterprise is predicted, index data sets are obtained through clustering the index data of the electric power grid enterprise to be analyzed, and the two emergency capacity fraction prediction models are utilized to predict each index data set, so that the predicted electric power emergency capacity fraction of the electric power grid enterprise to be analyzed is more accurate, the accuracy of determining the electric power emergency capacity level of the electric power grid enterprise to be analyzed is improved, the accuracy of determining the electric power emergency capacity of the electric power grid enterprise is improved, manual intervention is not needed in the whole process, and the defect that errors are easy to occur in manual evaluation, and the accuracy of determining the electric power emergency capacity of an emergency system is lower is avoided.

In an exemplary embodiment, in order to more clearly illustrate the power emergency capability prediction method of the power grid enterprise provided by the embodiment of the present application, a specific embodiment of the power grid enterprise power emergency capability prediction method is described below in detail. In one embodiment, the application further provides a power emergency capacity evaluation method for the power grid enterprise, when the power emergency capacity of the power grid enterprise is predicted, a plurality of evaluation indexes are obtained by constructing a power emergency capacity index system, weights and scores of all indexes are obtained by building a power safety management evaluation model of the power grid enterprise, an evaluation result is determined according to the weights and scores of all indexes, and further the determination accuracy of the power emergency capacity of the power grid enterprise 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 a power grid enterprise 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 uniformly converting each index into a very large index, then calculating the index variability and index conflict of each index by CRITIC weight method, and further calculating the weight of each index by integrating the index variability and index conflict. 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 electric power emergency capacity of the electric power grid enterprise is predicted, the index data sets are obtained by clustering the index data of the electric power grid enterprise to be analyzed, and the index data sets are predicted by utilizing the two emergency capacity fraction prediction models, so that the predicted electric power emergency capacity fraction of the electric power grid enterprise to be analyzed is more accurate, the determination accuracy of the electric power emergency capacity level of the electric power grid enterprise to be analyzed is improved, the determination accuracy of the electric power emergency capacity of the electric power grid enterprise is improved, manual intervention is not needed in the whole process, and the defect that the error occurs easily in manual evaluation, and the determination accuracy of the electric power emergency capacity of an emergency system is lower is avoided. Meanwhile, the application establishes an evaluation index system of the power emergency of the power grid enterprise, and can completely, comprehensively and systematically reflect the power safety condition of the power grid enterprise so as to find problems and defects existing in emergency capacity in time, thereby guiding the power grid enterprise to perfect the power emergency system.

It should be understood that, although the steps in the flowcharts related to the embodiments described above 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 a power grid enterprise power emergency capability prediction device for realizing the power grid enterprise power emergency capability prediction method. The implementation scheme of the device for solving the problem is similar to that described in the above method, so the specific limitation in the embodiments of the device for predicting the power emergency capability of the power grid enterprise provided below may be referred to the limitation of the method for predicting the power emergency capability of the power grid enterprise hereinabove, and will not be repeated here.

In an exemplary embodiment, as shown in fig. 9, there is provided a power emergency capability prediction apparatus for a power grid enterprise, including: an index data acquisition module 901, an index data clustering module 902, a first score prediction module 903, a second score prediction module 904, and a capability level determination module 905, wherein:

The index data obtaining module 901 is configured to obtain index data of a power grid enterprise to be analyzed under a preset power grid enterprise power emergency capability index in response to a power emergency capability prediction request for the power grid enterprise to be analyzed.

And the index data clustering module 902 is used for carrying out clustering processing on the index data to obtain an index data set corresponding to the power grid enterprise to be analyzed.

The first score prediction module 903 is configured to input feature vectors corresponding to each index data set to a first emergency power score prediction model corresponding to each index data set, so as to obtain a predicted power emergency power score corresponding to each index data set.

The second score prediction module 904 is configured to input the predicted power emergency capacity score corresponding to each index data set into a second emergency capacity score prediction model for fusion processing, so as to obtain a target power emergency capacity score corresponding to the power grid enterprise to be analyzed.

The capacity level determining module 905 is configured to determine a power emergency capacity level of the power grid enterprise to be analyzed according to the target power emergency capacity score of the power grid enterprise to be analyzed.

In an exemplary embodiment, the index data obtaining module 901 is further configured to determine an enterprise type of the power grid enterprise to be analyzed in response to the power emergency capability prediction request for the power grid enterprise to be analyzed; identifying an electric power emergency capacity index corresponding to the enterprise type from preset electric power emergency capacity indexes of the electric power network enterprise as the electric power emergency capacity index corresponding to the electric power network enterprise to be analyzed; and acquiring index data of the electric power emergency capacity index corresponding to the electric power enterprise to be analyzed, and taking the index data as the index data of the electric power emergency capacity index of the electric power enterprise to be analyzed under the preset electric power emergency capacity index of the electric power enterprise.

In an exemplary embodiment, the index data clustering module 902 is further configured to obtain index data features corresponding to index data; extracting key data features in the index data features; according to key data characteristics in the index data characteristics, carrying out initial clustering treatment on the index data to obtain an initial index data set corresponding to the power grid enterprise to be analyzed; and updating the initial index data set according to the distance between the key data features in the index data features and the clustering center of the initial index data set to obtain an updated index data set serving as an index data set corresponding to the power grid enterprise to be analyzed.

In an exemplary embodiment, the power grid enterprise power emergency capability prediction device further includes a prediction model determining module, configured to identify an index data set identifier of each index data set; verifying the index data set identifiers of the index data sets; and under the condition that the index data set identifiers of all the index data sets pass verification, inquiring the corresponding relation between the index data set identifiers and the first emergency capacity score prediction model according to the index data set identifiers of all the index data sets to obtain the first emergency capacity score prediction model corresponding to all the index data sets.

In an exemplary embodiment, the power grid enterprise power emergency capability prediction apparatus further includes a feature vector fusion module, configured to obtain feature vectors of the index data in each index data set; respectively inputting the feature vectors of the index data in each index data set into a weight prediction model to obtain weights corresponding to the index data in each index data set; and carrying out fusion processing on the feature vectors of the index data in each index data set according to the weights corresponding to the index data in each index data set to obtain the feature vectors corresponding to each index data set.

In an exemplary embodiment, the first score prediction module 903 is further configured to input feature vectors corresponding to each index data set to a first emergency capability score prediction model corresponding to each index data set, to obtain a prediction probability of each index data set under each preset power emergency capability score; and aiming at each index data set, screening out the preset power emergency capacity fraction with the maximum prediction probability from the preset power emergency capacity fractions, and taking the preset power emergency capacity fraction as the predicted power emergency capacity fraction corresponding to each index data set.

The modules in the power grid enterprise 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, index data sets, electric power emergency capacity scores 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 is configured to implement a method for predicting power emergency capability of a power grid enterprise.

It will be appreciated by those skilled in the art that the structure shown in FIG. 10 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or 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 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 and are described in detail herein without thereby 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

1. A method for predicting power emergency capability of a power grid enterprise, the method comprising:

2. The method according to claim 1, wherein the obtaining, in response to the power emergency capability prediction request for the power grid enterprise to be analyzed, index data of the power grid enterprise to be analyzed under a preset power grid enterprise power emergency capability index includes:

3. The method of claim 1, wherein the clustering the index data to obtain the index data set corresponding to the grid enterprise to be analyzed comprises:

acquiring index data characteristics corresponding to the index data;

extracting key data features in the index data features;

4. The method according to claim 1, further comprising, before inputting the feature vectors corresponding to the respective index data sets to the first emergency power score prediction model corresponding to the respective index data sets, obtaining the predicted power emergency power score corresponding to the respective index data sets:

identifying index data set identifiers of the index data sets;

Verifying the index data set identifiers of the index data sets;

5. The method according to claim 1, further comprising, before inputting the feature vectors corresponding to the respective index data sets to the first emergency power score prediction model corresponding to the respective index data sets, obtaining the predicted power emergency power score corresponding to the respective index data sets:

Acquiring characteristic vectors of index data in each index data set;

6. The method according to any one of claims 1 to 5, wherein the inputting the feature vector corresponding to each of the index data sets into the first emergency power score prediction model corresponding to each of the index data sets to obtain the predicted power emergency power score corresponding to each of the index data sets includes:

7. A power grid enterprise power emergency capability prediction apparatus, the apparatus comprising:

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.