CN115713239B

CN115713239B - Operation and maintenance risk prediction method, device, computer equipment and storage medium

Info

Publication number: CN115713239B
Application number: CN202211564074.9A
Authority: CN
Inventors: 郑武略; 张富春; 张鑫; 郑晓; 梁伟昕; 吴阳阳; 宋丹; 刘楠; 王瑞显; 袁文俊; 翁珠奋; 石延辉; 杨洋; 赵航航; 王宁; 周震震; 汪豪; 陈庆鹏; 范敏; 丁红涛
Original assignee: Guangzhou Bureau of Extra High Voltage Power Transmission Co
Current assignee: Guangzhou Bureau of Extra High Voltage Power Transmission Co
Priority date: 2022-12-07
Filing date: 2022-12-07
Publication date: 2024-04-02
Anticipated expiration: 2042-12-07
Also published as: CN115713239A

Abstract

The application relates to an operation and maintenance risk prediction method, an operation and maintenance risk prediction device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring operation and maintenance data corresponding to the operation and maintenance information of the power grid; inputting the operation and maintenance data into a pre-constructed risk prediction model to obtain the risk level of the operation and maintenance information of the power grid; the pre-constructed risk prediction model is obtained by constructing the risk prediction model according to the risk data corresponding to the historical operation and maintenance information; the risk level is used for representing the risk level generated by the power grid under the condition of carrying out operation and maintenance according to the operation and maintenance information of the power grid; and updating the power grid operation and maintenance information according to the risk level of the power grid operation and maintenance information. By adopting the method, the reliability of the operation and maintenance risk prediction result can be improved.

Description

Operation and maintenance risk prediction method, device, computer equipment and storage medium

Technical Field

The present application relates to the field of power grid technologies, and in particular, to an operation and maintenance risk prediction method, an operation and maintenance risk prediction apparatus, a computer device, a storage medium, and a computer program product.

Background

In the actual operation process of the power system, the influence of the outside on the power system, such as natural disasters and meteorological factors, cannot be avoided; therefore, the power system needs to be operated and maintained regularly. In the operation and maintenance process, the possible risk of the operation and maintenance strategy needs to be predicted in consideration of the external influence.

In the traditional technology, the operation and maintenance strategy is usually analyzed by combining manual work with previous experience, so that the possible risk of the operation and maintenance strategy is predicted; however, according to the operation and maintenance risk prediction method based on the conventional technology, not only is massive data required to be analyzed, but also subjective influence exists, so that reliability of an operation and maintenance risk prediction result is low.

Disclosure of Invention

In view of the foregoing, it is desirable to provide an operation and maintenance risk prediction method, apparatus, computer device, computer-readable storage medium, and computer program product that can improve the reliability of operation and maintenance risk prediction results.

In a first aspect, the present application provides an operation and maintenance risk prediction method. The method comprises the following steps:

acquiring operation and maintenance data corresponding to the operation and maintenance information of the power grid; the operation and maintenance data comprise correction data corresponding to the compensation of environmental influence, correction data corresponding to the compensation of system defects and operation data corresponding to technical overhaul in the power grid operation and maintenance information;

inputting the operation and maintenance data into a pre-constructed risk prediction model to obtain the risk level of the power grid operation and maintenance information; the pre-constructed risk prediction model is obtained by constructing risk data corresponding to historical operation and maintenance information; the risk data comprise result data corresponding to the compensation of environmental influence, result data corresponding to the compensation of system defects and result data corresponding to technical overhaul in the historical operation and maintenance information; the risk level is used for representing the risk level generated by the power grid under the condition of carrying out operation and maintenance according to the power grid operation and maintenance information;

And updating the power grid operation and maintenance information according to the risk level of the power grid operation and maintenance information.

In one embodiment, the pre-constructed risk prediction model is constructed by:

classifying the risk data corresponding to the historical operation and maintenance information to obtain the result data for compensating the environmental influence, the result data for compensating the system defect and the result data for technical overhaul;

for each historical operation and maintenance information, according to the distribution condition of the result data for compensating the environmental influence, confirming the first score, the second score and the third score of the result data for compensating the environmental influence, according to the distribution condition of the result data for compensating the system defect, confirming the first score, the second score and the third score of the result data for compensating the system defect, and according to the distribution condition of the result data for technical overhaul, confirming the first score, the second score and the third score of the result data for technical overhaul; the first score is used for representing possibility information of occurrence of power grid accidents; the second score is used for representing frequent information of personnel exposed to the power grid accident environment; the third score is used for representing result information generated by the power grid accident;

For each environmental impact-compensating result data, confirming a first risk value of the environmental impact-compensating result data according to the first score, the second score and the third score of the environmental impact-compensating result data, and for each system defect-compensating result data, confirming a second risk value of the system defect-compensating result data according to the first score, the second score and the third score of the system defect-compensating result data, and for each technical overhaul result data, confirming a third risk value of the technical overhaul result data according to the first score, the second score and the third score of the technical overhaul result data;

respectively carrying out fusion processing on a first risk value, a second risk value and a third risk value corresponding to each piece of historical operation and maintenance information to obtain risk values of each piece of historical operation and maintenance information;

and constructing the risk prediction model according to the first risk value, the second risk value, the third risk value and the risk value of the historical operation and maintenance information.

In one embodiment, the inputting the operation and maintenance data into a pre-constructed risk prediction model to obtain the risk level of the grid operation and maintenance information includes:

Comparing the operation and maintenance data with the risk data through a pre-constructed risk prediction model to obtain a first risk value, a second risk value and a third risk value corresponding to the operation and maintenance data;

carrying out fusion processing on the first risk value, the second risk value and the third risk value corresponding to the operation and maintenance data to obtain the risk value of the operation and maintenance information of the power grid;

and inquiring a mapping relation between the risk value and the risk level to obtain a risk level corresponding to the risk value of the power grid operation and maintenance information, wherein the risk level is used as the risk level of the power grid operation and maintenance information.

In one embodiment, the comparing the operation and maintenance data with the risk data through a pre-constructed risk prediction model to obtain a first risk value, a second risk value and a third risk value corresponding to the operation and maintenance data includes:

classifying the operation data through a pre-constructed risk prediction model to obtain the correction data for compensating the environmental influence, the correction data for compensating the system defects and the operation data for technical overhaul;

among the risk data, the result data of the compensation environmental impact with the highest similarity with the correction data of the compensation environmental impact is taken as first target data, the result data of the compensation system defect with the highest similarity with the correction data of the compensation system defect is taken as second target data, and the result data of the technical overhaul with the highest similarity with the operation data of the technical overhaul is taken as third target data;

The first risk value of the first target data is used as the first risk value corresponding to the operation and maintenance data, the second risk value of the second target data is used as the second risk value corresponding to the operation and maintenance data, and the second risk value of the third target data is used as the third risk value corresponding to the operation and maintenance data.

In one embodiment, the updating the grid operation and maintenance information according to the risk level of the grid operation and maintenance information includes:

under the condition that the risk level of the power grid operation and maintenance information is larger than a risk level threshold value, selecting reference operation and maintenance information from historical operation and maintenance information of which the corresponding risk level is smaller than the risk level threshold value;

and updating the power grid operation and maintenance information according to the target result data corresponding to the compensation of the environmental influence, the target result data corresponding to the compensation of the system defect and the target result data corresponding to the technical overhaul in the reference operation and maintenance information, and the correction data corresponding to the compensation of the environmental influence, the correction data corresponding to the compensation of the system defect and the operation data corresponding to the technical overhaul.

In one embodiment, after updating the grid operation and maintenance information according to the risk level of the grid operation and maintenance information, the method further includes:

Operating and maintaining the power grid according to the updated power grid operation and maintenance information to obtain risk data corresponding to the updated power grid operation and maintenance information;

and updating the pre-constructed risk prediction model according to the risk data corresponding to the updated power grid operation and maintenance information.

In a second aspect, the present application further provides an operation and maintenance risk prediction apparatus. The device comprises:

the operation and maintenance data acquisition module is used for acquiring operation and maintenance data corresponding to the operation and maintenance information of the power grid; the operation and maintenance data comprise correction data corresponding to the compensation of environmental influence, correction data corresponding to the compensation of system defects and operation data corresponding to technical overhaul in the power grid operation and maintenance information;

the risk level confirmation module is used for inputting the operation and maintenance data into a pre-constructed risk prediction model to obtain the risk level of the power grid operation and maintenance information; the pre-constructed risk prediction model is obtained by constructing risk data corresponding to historical operation and maintenance information; the risk data comprise result data corresponding to the compensation of environmental influence, result data corresponding to the compensation of system defects and result data corresponding to technical overhaul in the historical operation and maintenance information; the risk level is used for representing the risk level generated by the power grid under the condition of carrying out operation and maintenance according to the power grid operation and maintenance information;

And the operation and maintenance information updating module is used for updating the power grid operation and maintenance information according to the risk level of the operation and maintenance information.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:

In a fourth aspect, the present application also provides a computer-readable storage medium. The 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 present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:

The operation and maintenance risk prediction method, the device, the computer equipment, the storage medium and the computer program product firstly acquire operation and maintenance data corresponding to the operation and maintenance information of the power grid; the operation and maintenance data comprise correction data corresponding to the compensation of environmental influence, correction data corresponding to the compensation of system defects and operation data corresponding to technical overhaul in the power grid operation and maintenance information; then inputting the operation and maintenance data into a pre-constructed risk prediction model to obtain the risk level of the operation and maintenance information of the power grid; the pre-constructed risk prediction model is obtained by constructing risk data corresponding to historical operation and maintenance information; the risk data comprises historical operation and maintenance information, and corresponds to result data for compensating environmental influence, result data for compensating system defects and result data for technical overhaul; the risk level is used for representing the risk level generated by the power grid under the condition of carrying out operation and maintenance according to the operation and maintenance information of the power grid; and finally, updating the power grid operation and maintenance information according to the risk level of the power grid operation and maintenance information. In this way, the risk prediction model constructed according to the risk data corresponding to the historical operation and maintenance information can confirm the risk level of the operation and maintenance information of the power grid according to the correction data corresponding to the compensation of environmental influence, the correction data corresponding to the compensation of system defects and the operation data corresponding to technical overhaul in the operation and maintenance information of the power grid, so that the risk level possibly faced by the power grid under the condition of operation and maintenance according to the operation and maintenance information of the power grid is predicted, the risk level possibly faced by the power grid is fed back to the operation and maintenance information of the power grid, the operation and maintenance information of the power grid is updated, massive data is not needed to be analyzed in the whole process, and subjective influence is avoided, so that the defect that the reliability of the operation and maintenance risk prediction result obtained by the traditional method is low is avoided, and the reliability of the operation and maintenance risk prediction result is improved.

Drawings

FIG. 1 is a flow chart of a method for predicting operation and maintenance risk according to an embodiment;

FIG. 2 is a flow chart illustrating steps for constructing a pre-constructed risk prediction model in one embodiment;

FIG. 3 is a flowchart illustrating a step of inputting operation and maintenance data into a pre-constructed risk prediction model to obtain a risk level of grid operation and maintenance information in one embodiment;

FIG. 4 is a flowchart of another embodiment of an operation risk prediction method;

FIG. 5 is a block diagram of an operation and maintenance risk prediction apparatus in one embodiment;

fig. 6 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

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

In an exemplary embodiment, as shown in fig. 1, an operation and maintenance risk prediction method is provided, and this embodiment is illustrated 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 server and a terminal, and implemented by interaction between the server and the terminal. The server may be implemented by an independent server or a server cluster formed by a plurality of servers, and the terminal may be, but is not limited to, a personal computer, a notebook computer, a smart phone, a tablet computer, etc. of a power grid operation and maintenance person. In this embodiment, the method includes the steps of:

Step S102, operation and maintenance data corresponding to the operation and maintenance information of the power grid are obtained.

The operation and maintenance data comprise correction data corresponding to the compensation of environmental influence, correction data corresponding to the compensation of system defects and operation data corresponding to technical overhaul in the power grid operation and maintenance information; correction data for compensating for environmental influences, which means data for adjusting the operation of a power grid in order to cope with the influence of external environments on the power grid; correction data for compensating the defects of the system, namely data which need to adjust the operation of the power grid in order to overcome faults generated in the power grid system; the technical overhaul operation data refer to operation data generated by operation staff in the operation and maintenance overhaul process.

It can be understood that the operation and maintenance information of the power grid is essentially an operation and maintenance scheme aiming at the power grid, and various data and various text information are arranged in the operation and maintenance information of the power grid, so that the operation and maintenance information of the power grid needs to be converted into system coding data which can be identified by a computer, and then the corresponding operation and maintenance data are obtained by analyzing the system coding data.

Specifically, the server extracts data of classification nodes containing correction data for compensating for environmental influence, correction data for compensating for system defects and operation data for technical overhaul from system coding data through a data classification algorithm, such as a naive Bayesian classification algorithm, so as to obtain operation and maintenance data corresponding to operation and maintenance information of the power grid.

And step S104, inputting the operation and maintenance data into a pre-constructed risk prediction model to obtain the risk level of the operation and maintenance information of the power grid.

The pre-constructed risk prediction model is constructed according to risk data corresponding to historical operation and maintenance information, and is a model for predicting risk levels of operation and maintenance information of a power grid, such as a neural network model, a deep learning model and the like. The risk data comprises historical operation and maintenance information, and corresponds to result data for compensating environmental influence, result data for compensating system defects and result data for technical overhaul; it can be understood that the risk data is the result data obtained after the operation and maintenance is performed according to the executed historical operation and maintenance information, and the operation and maintenance data is the operation data in the operation and maintenance information of the power grid to be executed. The risk level is used for representing the risk level generated by the power grid under the condition of carrying out operation and maintenance according to the operation and maintenance information of the power grid, such as low risk, medium risk, higher risk, high risk and the like.

Specifically, the server inputs operation and maintenance data into a pre-constructed risk prediction model, and the risk prediction model compares correction data for compensating for environmental influence, correction data for compensating for system defects and operation data for technical overhaul in the operation and maintenance data with result data for compensating for environmental influence, result data for compensating for system defects and result data for technical overhaul in the risk data to obtain the risk level of the operation and maintenance information of the power grid to be executed.

For example, it is assumed that by means of a pre-constructed risk prediction model, the correction data for compensating the environmental influence, the correction data for compensating the system defect and the operation data for technical overhaul in the operation and maintenance data are compared with the result data for compensating the environmental influence, the result data for compensating the system defect and the result data for technical overhaul in the risk data, so that the risk level of the operation and maintenance information of the power grid to be executed is high, and if the operation and maintenance of the power grid are performed according to the operation and maintenance information of the power grid to be executed, the probability of risk occurrence is high, and the operation and maintenance information of the power grid to be executed needs to be adjusted, so that the risk is reduced.

And S106, updating the grid operation and maintenance information according to the risk level of the grid operation and maintenance information.

Specifically, the server judges whether the risk level of the power grid operation and maintenance information is too high, and updates the power grid operation and maintenance information under the condition that the risk level is too high; and under the condition of proper risk level, the power grid is operated and maintained according to the operation and maintenance information of the power grid, so that the normal operation of the power grid system is ensured.

In the operation and maintenance risk prediction method, a server firstly acquires operation and maintenance data corresponding to operation and maintenance information of a power grid; then inputting the operation and maintenance data into a pre-constructed risk prediction model to obtain the risk level of the operation and maintenance information of the power grid; and finally, updating the power grid operation and maintenance information according to the risk level of the power grid operation and maintenance information. In this way, the server can confirm the risk level of the grid operation and maintenance information according to the correction data corresponding to the compensation environment influence, the correction data corresponding to the compensation system defect and the operation data corresponding to the technical overhaul in the grid operation and maintenance information by constructing the risk prediction model according to the risk data corresponding to the historical operation and maintenance information, so that the risk level possibly faced by the grid under the condition of carrying out operation and maintenance according to the grid operation and maintenance information is predicted, the risk level possibly faced by the grid is fed back to the grid operation and maintenance information, the grid operation and maintenance information is updated, the massive data is not required to be analyzed in the whole process, and subjective influence is avoided, so that the defect of lower reliability of the operation and maintenance risk prediction result obtained by the traditional method is avoided, and the reliability of the operation and maintenance risk prediction result is improved.

In an exemplary embodiment, as shown in fig. 2, in step S104, a pre-constructed risk prediction model is constructed by:

step S202, classifying the risk data corresponding to the historical operation and maintenance information to obtain result data for compensating the environmental influence, result data for compensating the system defects and result data for technical overhaul.

Step S204, for each historical operation and maintenance information, confirming the first score, the second score and the third score of the result data for compensating the environmental influence according to the distribution condition of the result data for compensating the environmental influence, confirming the first score, the second score and the third score of the result data for compensating the system defect according to the distribution condition of the result data for compensating the system defect, and confirming the first score, the second score and the third score of the result data for technical overhaul according to the distribution condition of the result data for technical overhaul.

Step S206, confirming a first risk value of the result data of the environmental impact according to the first score, the second score and the third score of the result data of the environmental impact, confirming a second risk value of the result data of the system defect according to the first score, the second score and the third score of the result data of the system defect, confirming a third risk value of the result data of the technical overhaul according to the first score, the second score and the third score of the result data of the technical overhaul, and confirming the third risk value of the result data of the technical overhaul according to the first score, the second score and the third score of the result data of the technical overhaul.

Step S208, fusion processing is carried out on the first risk value, the second risk value and the third risk value corresponding to each piece of historical operation and maintenance information respectively, so that the risk value of each piece of historical operation and maintenance information is obtained.

Step S210, constructing a risk prediction model according to each first risk value, each second risk value, each third risk value and each risk value of the historical operation and maintenance information.

The pre-constructed risk prediction model is constructed based on LEC (Likelihood, exposure, consequence, possibility of accident occurrence, how frequently personnel are exposed to dangerous environments, and consequences possibly caused by accident once the accident occurs) evaluation method, so that the first score is used for representing possibility information of power grid accident occurrence, namely the possibility of power grid accident occurrence; the second score is used for representing frequent information of exposure of personnel to the power grid accident environment, namely the frequent degree of exposure of power grid personnel to the power grid dangerous environment; the third score is used to characterize the outcome information of the grid incident, i.e., the severity of the consequences that may be caused by the grid incident. The method for calculating the risk value based on the LEC evaluation method can be represented by a formula d=lec, wherein D is a risk value, L is a probability score of occurrence of an accident, E is a frequency score of exposure of power grid staff to a dangerous environment of the power grid, and D is a severity score of a possible consequence of occurrence of the power grid accident. The score values in the LEC evaluation method are shown in the following tables 1, 2 and 3:

Table 1 table of likelihood score for accident occurrence

Possibility of accident L	Score value
		Can be completely expected	10
Quite possibly	6
		Infrequently, but possibly	3
At all, it is very unlikely that	1
		It is conceivable, but very unlikely	0.5
Very unlikely to be	0.2
		In practice it is impossible	0.1

Table 2 table of how frequently a grid worker is exposed to a grid hazardous environment

How frequently a grid worker is exposed to a dangerous environment of the grid E	Score value
		Continuous exposure to hazard event environments	10
Daily exposure during working hours	6
		Once a week or accidentally exposed	3
Once a month exposure	2
		Several occurrences each year in a hazard event environment	1
Very rarely exposed to	0.5

Table 3 severity score table for possible consequences of grid accident

Severity C of consequences of grid accidents	Score value
		Big disaster (many people die)	100
Disaster (death of several people)	40
		Very serious (death of one person)	15
Serious (serious injury)	7
		Great (disability)	3
Eye-catching (for rescue)	1

Specifically, the step of constructing the risk prediction model by the server is as follows: firstly, classifying risk data corresponding to historical operation and maintenance information to obtain a plurality of result data for compensating environmental influence, a plurality of result data for compensating system defects and a plurality of result data for technical overhaul; then, according to the distribution of the result data for compensating the environmental influence, obtaining a first score for compensating the probability of the occurrence of the accident, a second score for the frequency of the exposure of the power grid staff to the dangerous environment of the power grid and a third score for the severity of the consequences possibly caused by the occurrence of the power grid accident; according to the distribution of the result data for compensating the system defects, a first score for compensating the probability of the occurrence of the accident, a second score for the frequency of the exposure of the power grid staff to the dangerous environment of the power grid and a third score for the severity of the consequences possibly caused by the occurrence of the power grid accident are obtained; and obtaining a first score of technical overhaul result data corresponding to the possibility of accident occurrence, a second score of frequency of exposure of power grid staff to a power grid dangerous environment and a third score of severity of consequences possibly caused by power grid accident occurrence according to distribution of the technical overhaul result data; next, according to formula d=lec, calculating a first risk value of each of the result data compensating for the environmental impact, a second risk value of each of the result data compensating for the system defect, and a third risk value of each of the result data of the technical overhaul; and finally, carrying out fusion processing on the first risk value, the second risk value and the third risk value, such as a weighted summation fusion processing mode, so as to obtain risk values corresponding to each piece of historical operation and maintenance information, and constructing a risk prediction model according to each first risk value, each second risk value, each third risk value and each risk value. Wherein, the first score, the second score and the third score are obtained by looking up tables 1, 2 and 3 according to the distribution condition.

For example, assuming that the probability of occurrence of an accident corresponding to the result data of compensating the environmental impact is quite probable in a certain risk data, the corresponding first score is 6, the corresponding frequency of exposure of the power grid staff to the dangerous environment of the power grid is once per week or accidentally, the corresponding second score is 3, the severity of the possible consequences of the occurrence of the power grid accident is serious (disability), the corresponding third score is 3, and thus the first risk value of the result data of compensating the environmental impact is:

D＝LEC＝6×3×3＝54

in the same way, it is assumed that in the obtained risk data, the second risk value of the result data for compensating the system defect is 36, the third risk value of the result data for technical overhaul is 3, and the fusion formula of the risk values is as follows:

wherein D is a risk value of the risk data, w _n Weight of the nth risk value, D _n For the nth risk value, if w _n = {0.2,0.4,0.7}, then the risk value that can get this risk data is:

D＝0.2×54+0.4×36+0.7×3＝27.3

in this embodiment, the server calculates the first score, the second score, and the third score corresponding to the result data for compensating the environmental impact, the result data for compensating the system defect, and the result data for technical overhaul, respectively, and obtains the result data for compensating the environmental impact, the result data for compensating the system defect, and the first risk value, the second risk value, and the third risk value corresponding to the result data for technical overhaul based on the LEC evaluation method, and then performs fusion processing on the first risk value, the second risk value, and the third risk value to obtain the risk value of the corresponding historical operation and maintenance information, and constructs a risk prediction model based on the above information, so as to provide a prediction basis for the risk value of the grid operation and maintenance information to be executed, thereby improving the reliability of the operation and maintenance risk prediction result.

In an exemplary embodiment, as shown in fig. 3, the step S104 inputs the operation and maintenance data into a pre-constructed risk prediction model to obtain a risk level of the operation and maintenance information of the power grid, and specifically includes the following steps:

step S302, comparing the operation and maintenance data with the risk data through a pre-constructed risk prediction model to obtain a first risk value, a second risk value and a third risk value corresponding to the operation and maintenance data.

And step S304, carrying out fusion processing on the first risk value, the second risk value and the third risk value corresponding to the operation and maintenance data to obtain the risk value of the operation and maintenance information of the power grid.

Step S306, inquiring a mapping relation between the risk value and the risk level to obtain the risk level corresponding to the risk value of the grid operation and maintenance information, wherein the risk level is used as the risk level of the grid operation and maintenance information.

The mapping relationship between the risk value and the risk level may be specifically set according to the actual situation, and the example illustrated in this embodiment is shown in table 4:

table 4 relationship between risk value and risk level

Specifically, the server compares the operation and maintenance data with the risk data through the risk prediction model constructed in steps S202 to S210 to obtain a first risk value, a second risk value and a third risk value corresponding to the operation and maintenance information of the power grid, performs fusion processing on the first risk value, the second risk value and the third risk value of the operation and maintenance information of the power grid according to a method for calculating the risk value of the historical operation and maintenance information, obtains the risk value of the operation and maintenance information of the power grid, and then queries the table 4 according to the risk value to obtain a risk level corresponding to the risk value, thereby obtaining the risk level of the operation and maintenance information of the power grid. The definition and division of the risk level can be adjusted according to actual needs.

For example, assuming that the server obtains, through a pre-constructed risk prediction model, a first risk value of 180, a second risk value of 30, and a third risk value of 420 corresponding to the grid operation and maintenance information, the risk value after the fusion processing is 342, and it can be known through looking up table 4 that the risk level corresponding to the risk value of 342 is very high risk, and the operation needs to be stopped. The risk of the operation and maintenance information of the power grid is very high, the operation and maintenance operation needs to be stopped immediately, the operation and maintenance information of the power grid is adjusted, and the risk level is reduced.

In this embodiment, the server can predict the risk value of the grid operation and maintenance information to be executed based on the actual risk value of the historical operation and maintenance information by using the pre-constructed risk prediction model, and determine the risk level of the grid operation and maintenance information based on the risk value, thereby improving the reliability of the operation and maintenance risk prediction result.

In an exemplary embodiment, step S302, comparing the operation and maintenance data with the risk data through a pre-constructed risk prediction model, obtains a first risk value, a second risk value and a third risk value corresponding to the operation and maintenance data, which specifically includes the following contents: classifying the operation data through a pre-constructed risk prediction model to obtain correction data for compensating the environmental influence, correction data for compensating the system defects and operation data for technical overhaul; in the risk data, the result data of compensating the environmental influence, which has the highest similarity with the correction data of compensating the environmental influence, is taken as first target data, the result data of compensating the system defect, which has the highest similarity with the correction data of compensating the system defect, is taken as second target data, and the result data of technical overhaul, which has the highest similarity with the operation data of technical overhaul, is taken as third target data; the first risk value of the first target data is used as the first risk value corresponding to the operation data, the second risk value of the second target data is used as the second risk value corresponding to the operation data, and the second risk value of the third target data is used as the third risk value corresponding to the operation data.

It should be noted that, the result data of the compensation environmental impact with the highest similarity to the correction data of the compensation environmental impact, the result data of the compensation system defect with the highest similarity to the correction data of the compensation system defect, and the result data of the technical overhaul with the highest similarity to the operation data of the technical overhaul do not necessarily belong to the same historical operation and maintenance information.

Specifically, the server firstly divides operation and maintenance data of the operation and maintenance information of the power grid into correction data for compensating for environmental influence, correction data for compensating for system defects and operation data for technical overhaul through a pre-constructed risk prediction model; then according to the classification result, respectively comparing the corrected data for compensating the environmental influence with the result data for compensating the environmental influence in the risk prediction model to obtain first target data with highest similarity with the corrected data for compensating the environmental influence, comparing the corrected data for compensating the system defect with the result data for compensating the system defect, obtaining second target data with highest similarity with the corrected data for compensating the system defect, and comparing the operation data for technical overhaul with the result data for technical overhaul to obtain third target data with highest similarity with the operation data for technical overhaul; and then taking the first risk value of the first target data as the first risk value of the correction data for compensating the environmental influence, taking the second risk value of the second target data as the second risk value of the correction data for compensating the system defect, and taking the third risk value of the third target data as the third risk value of the operation data for technical overhaul, thereby obtaining the first risk value, the second risk value and the third risk value of the operation and maintenance data.

For example, assuming that the server is obtained by query and comparison of a pre-constructed risk prediction model, the first risk value of the result data of the compensation environment with the highest similarity to the correction data of the compensation environment is 180, the second risk value of the result data of the compensation system with the highest similarity to the correction data of the compensation system defect is 30, and the third risk value of the result data of the technical overhaul with the highest similarity to the operation data of the technical overhaul is 420, the first risk value of 180, the second risk value of 30, and the third risk value of 420 corresponding operation data can be confirmed.

In this embodiment, the server obtains the first risk value, the second risk value and the third risk value corresponding to the operation and maintenance data through the first risk value of the first target data, the second risk value of the second target data and the third risk value of the third target data, which have the highest similarity with the operation and maintenance data, so that the risk value corresponding to the operation and maintenance information of the power grid and the risk level of the operation and maintenance information of the power grid are predicted conveniently obtained through subsequent fusion processing.

In an exemplary embodiment, the step S106 updates the grid operation and maintenance information according to the risk level of the grid operation and maintenance information, which specifically includes the following contents: under the condition that the risk level of the power grid operation and maintenance information is larger than a risk level threshold value, selecting reference operation and maintenance information from historical operation and maintenance information of which the corresponding risk level is smaller than the risk level threshold value; and updating the power grid operation and maintenance information according to the target result data corresponding to the compensation of the environmental influence, the target result data corresponding to the compensation of the system defect and the target result data corresponding to the technical overhaul in the reference operation and maintenance information, and the correction data corresponding to the compensation of the environmental influence, the correction data corresponding to the compensation of the system defect and the operation data corresponding to the technical overhaul.

The risk level threshold is a threshold condition set according to actual requirements, and referring to table 4, for example, if the risk level is not expected to be too high, the risk level threshold is set to be medium risk, so long as the risk level of the grid operation and maintenance information reaches or exceeds the medium risk, the grid operation and maintenance information needs to be updated, operation and maintenance data is adjusted, and the risk level is reduced

Specifically, under the condition that the risk level of the power grid operation and maintenance information is greater than a risk level threshold, the server selects one piece of operation and maintenance information from the historical operation and maintenance information with the risk level smaller than the risk level threshold as reference operation and maintenance information according to the record of the historical operation and maintenance information; and according to the target result data of the reference operation and maintenance information, which compensates for the environmental influence, the target result data of the system defect and the target result data of the technical overhaul, correspondingly updating the correction data of the power grid operation and maintenance information, which compensates for the environmental influence, the correction data of the system defect and the operation data of the technical overhaul, obtaining updated power grid operation and maintenance information.

For example, assuming that the risk level threshold is a medium risk and the risk level of the grid operation and maintenance information is a very high risk, the operation and maintenance operation needs to be stopped immediately, and a piece of historical operation and maintenance information with the highest similarity between the external condition and the external condition to be operated is selected as reference operation and maintenance information from the historical operation and maintenance information with the possible risk or acceptable risk of the risk level, and according to the target result data for compensating the environmental influence, the target result data for compensating the system defect and the target result data for technical maintenance in the reference operation and maintenance information, the correction data for compensating the environmental influence, the correction data for compensating the system defect and the operation data for technical maintenance of the grid operation and maintenance are updated correspondingly, so that the risk level of the grid operation and maintenance information is reduced.

In this embodiment, the server determines whether the risk level of the operation and maintenance information of the power grid is greater than a risk level threshold, and determines whether the operation and maintenance information of the power grid needs to be updated; and the power grid operation and maintenance information is updated according to the historical operation and maintenance information with the risk level smaller than the risk level threshold, so that the risk can be timely adjusted when the risk level of the power grid operation and maintenance information is too high, the risk is reduced, and the safe operation and maintenance of the power grid is ensured.

In an exemplary embodiment, in step S106, after updating the grid operation and maintenance information according to the risk level of the grid operation and maintenance information, the method specifically further includes the following: operating and maintaining the power grid according to the updated power grid operation and maintenance information to obtain risk data corresponding to the updated power grid operation and maintenance information; and updating a pre-constructed risk prediction model according to the risk data corresponding to the updated power grid operation and maintenance information.

It can be understood that after the updated grid operation and maintenance information is operated for a period of time, the updated grid operation and maintenance information also becomes a part of historical operation and maintenance information relative to the new grid operation and maintenance information, and the updated grid operation and maintenance information changes the original historical operation and maintenance information, compensates the distribution condition of the result data of environmental influence, compensates the distribution condition of the result data of system defects and the distribution condition of the result data according to technical overhaul; therefore, a pre-constructed risk prediction model needs to be updated at intervals according to the power grid operation and maintenance information in the intervals.

Specifically, assuming that the pre-constructed risk prediction model is updated once every other week, the server obtains corresponding risk data according to the executed grid operation and maintenance information in the week, updates the distribution condition of the result data for compensating the environmental influence, the distribution condition of the result data for compensating the system defect and the distribution condition of the result data for technical overhaul according to the corresponding risk data, and further updates the first risk value corresponding to the result data for compensating the environmental influence, the second risk value corresponding to the result data for compensating the system defect and the third risk value corresponding to the result data for technical overhaul, thereby updating the risk values corresponding to the different historical operation and maintenance information. Based on the above process, the server completes updating the pre-constructed risk prediction model.

In this embodiment, the server updates the pre-constructed risk prediction model, so as to update the prediction standard of the risk level of the operation and maintenance information of the power grid in real time, and optimize the prediction accuracy of the risk level of the operation and maintenance information of the power grid, thereby improving the reliability of the operation and maintenance risk prediction result.

In an exemplary embodiment, as shown in fig. 4, another operation and maintenance risk prediction method is provided, and the method is applied to a server for illustration, and includes the following steps:

Step S401, constructing a risk prediction model based on an LEC evaluation method according to risk data corresponding to the historical operation and maintenance information.

The risk data comprises result data corresponding to the compensation of environmental influence, result data corresponding to the compensation of system defects and result data corresponding to technical overhaul in the historical operation and maintenance information.

Step S402, operation and maintenance data corresponding to the operation and maintenance information of the power grid are obtained.

The operation and maintenance data comprise correction data corresponding to the compensation of environmental influence, correction data corresponding to the compensation of system defects and operation data corresponding to technical overhaul in the power grid operation and maintenance information;

step S403, through a pre-constructed risk prediction model, the first target data with the highest similarity to the correction data for compensating the environmental impact, the second target data with the highest similarity to the correction data for compensating the system defect, and the third target data with the highest similarity to the operation data for technical maintenance are confirmed in the risk data.

The first target data are result data which have the highest similarity with the corrected data for compensating the environmental influence and compensate the environmental influence; the second target data is the result data of compensating the system defect, which has the highest similarity with the correction data of compensating the system defect; the third target data is technical overhaul result data with highest similarity with the technical overhaul operation data.

Step S404, the first risk value of the first target data is used as the first risk value corresponding to the operation data, the second risk value of the second target data is used as the second risk value corresponding to the operation data, and the second risk value of the third target data is used as the third risk value corresponding to the operation data.

And step S405, carrying out fusion processing on the first risk value, the second risk value and the third risk value corresponding to the operation and maintenance data to obtain the risk value of the operation and maintenance information of the power grid.

Step S406, inquiring the mapping relation between the risk value and the risk level to obtain the risk level corresponding to the risk value of the grid operation and maintenance information, and taking the risk level as the risk level of the grid operation and maintenance information.

The risk level is used for representing the risk level generated by the power grid under the condition of carrying out operation and maintenance according to the operation and maintenance information of the power grid.

Step S407, selecting reference operation and maintenance information from the historical operation and maintenance information with the corresponding risk level smaller than the risk level threshold under the condition that the risk level of the operation and maintenance information of the power grid is larger than the risk level threshold, and updating the operation and maintenance information of the power grid according to the reference operation and maintenance information.

And step S408, operating and maintaining the power grid according to the updated power grid operation and maintenance information to obtain risk data corresponding to the updated power grid operation and maintenance information, and updating a pre-constructed risk prediction model according to the risk data corresponding to the updated power grid operation and maintenance information.

In this embodiment, the server can predict the risk value of the grid operation and maintenance information to be executed based on the actual risk value of the historical operation and maintenance information by constructing the risk prediction model according to the risk data corresponding to the historical operation and maintenance information, and determine the risk level of the grid operation and maintenance information based on the risk value, so as to predict the risk level possibly faced by the grid under the condition of performing operation and maintenance according to the grid operation and maintenance information, and feed back the risk level possibly faced to the grid operation and maintenance information to update the grid operation and maintenance information, thereby improving the reliability of the operation and maintenance risk prediction result. In addition, the risk prediction model constructed according to the LEC evaluation method can perform semi-quantitative safety evaluation on the risk source in the potentially dangerous operation environment, so that the risk prediction is performed on the risk level of the power grid operation and maintenance information based on the risk prediction model, and the reliability of an operation and maintenance risk prediction result can be further improved.

In order to more clearly clarify the operation and maintenance risk prediction method provided in the embodiments of the present application, a specific embodiment is described below specifically. In an exemplary embodiment, the application further provides a method for evaluating the differentiated operation and maintenance policy based on risk assessment, which specifically includes the following steps:

Step 1: and classifying the risk grades according to the risk data.

Firstly, sorting and classifying risk data, and then, dividing risk grades based on an LEC evaluation method according to the sorted and classified risk data to establish a risk prediction model.

Step 2: and analyzing the operation and maintenance information to obtain operation and maintenance data.

And converting the operation and maintenance information into system coding data which can be identified by the server, and extracting the operation and maintenance data from the system coding data based on a naive Bayesian classification algorithm.

Step 3: and predicting the risk level of the operation and maintenance information according to the risk prediction model.

And (3) inputting the operation and maintenance data output in the step (2) into a risk prediction model, comparing the operation and maintenance data with the risk data in the risk prediction model, and calculating a risk value of the operation and maintenance information.

Step 4: judging the risk level of the operation and maintenance information in the implementation possible process according to the risk value of the operation and maintenance information output in the step 3, and carrying out feedback modification on the operation and maintenance information according to the obtained risk level to finally obtain perfect operation and maintenance information.

In this embodiment, the server may perform risk calculation on the analyzed operation and maintenance data, automatically compare the calculated risk value with the set risk level, and convert the data into different risk levels, so as to facilitate further improvement on the operation and maintenance information according to the risk level, thereby automatically completing risk assessment of the operation and maintenance information, avoiding trouble caused by the operation and maintenance information in the implementation process, and improving reliability of the operation and maintenance risk prediction result.

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 an operation and maintenance risk prediction device for realizing the above related operation and maintenance risk prediction method. The implementation of the solution provided by the apparatus is similar to the implementation described in the above method, so the specific limitation in the embodiments of the operation and maintenance risk prediction apparatus provided below may be referred to the limitation of the operation and maintenance risk prediction method hereinabove, and will not be described herein.

In an exemplary embodiment, as shown in fig. 5, there is provided an operation and maintenance risk prediction apparatus, including: an operation and maintenance data acquisition module 502, a risk level confirmation module 504, and an operation and maintenance information update module 506, wherein:

the operation and maintenance data acquisition module 502 is configured to acquire operation and maintenance data corresponding to operation and maintenance information of the power grid; the operation data comprise correction data corresponding to the compensation of environmental influence, correction data corresponding to the compensation of system defects and operation data corresponding to technical overhaul in the operation and maintenance information of the power grid.

The risk level confirmation module 504 is configured to input the operation and maintenance data into a pre-constructed risk prediction model to obtain a risk level of the operation and maintenance information of the power grid; the pre-constructed risk prediction model is obtained by constructing the risk prediction model according to the risk data corresponding to the historical operation and maintenance information; the risk data comprises historical operation and maintenance information, and corresponds to result data for compensating environmental influence, result data for compensating system defects and result data for technical overhaul; the risk level is used for representing the risk level generated by the power grid under the condition of operation and maintenance according to the power grid operation and maintenance information.

And the operation and maintenance information updating module 506 is configured to update the grid operation and maintenance information according to the risk level of the operation and maintenance information.

In an exemplary embodiment, the operation and maintenance risk prediction device further includes a risk prediction model construction module, configured to perform classification processing on risk data corresponding to the historical operation and maintenance information, to obtain result data for compensating for environmental effects, result data for compensating for system defects, and result data for technical overhaul; for each historical operation and maintenance information, confirming a first score, a second score and a third score of the result data for compensating the environmental influence according to the distribution condition of the result data for compensating the environmental influence, confirming the first score, the second score and the third score of the result data for compensating the system defect according to the distribution condition of the result data for compensating the system defect, and confirming the first score, the second score and the third score of the result data for technical overhaul according to the distribution condition of the result data for technical overhaul; the first score is used for representing possibility information of occurrence of the power grid accident; the second score is used for representing frequent information of personnel exposed to the power grid accident environment; the third score is used for representing result information generated by the power grid accident; confirming a first risk value of the result data for compensating the environmental influence according to the first score, the second score and the third score of the result data for compensating the environmental influence, confirming a second risk value of the result data for compensating the system defect according to the first score, the second score and the third score of the result data for compensating the system defect according to the result data for compensating the system defect, and confirming a third risk value of the result data for technical overhaul according to the first score, the second score and the third score of the result data for technical overhaul according to the result data for technical overhaul; respectively carrying out fusion processing on the first risk value, the second risk value and the third risk value corresponding to each piece of historical operation and maintenance information to obtain the risk value of each piece of historical operation and maintenance information; and constructing a risk prediction model according to each first risk value, each second risk value, each third risk value and the risk value of each historical operation and maintenance information.

In an exemplary embodiment, the risk level confirmation module 504 is further configured to compare the operation and maintenance data with the risk data through a pre-constructed risk prediction model, to obtain a first risk value, a second risk value, and a third risk value corresponding to the operation and maintenance data; carrying out fusion processing on the first risk value, the second risk value and the third risk value corresponding to the operation and maintenance data to obtain the risk value of the operation and maintenance information of the power grid; and inquiring the mapping relation between the risk value and the risk level to obtain the risk level corresponding to the risk value of the power grid operation and maintenance information, and taking the risk level as the risk level of the power grid operation and maintenance information.

In an exemplary embodiment, the risk level confirmation module 504 is further configured to classify the operation data through a pre-constructed risk prediction model, to obtain correction data for compensating for environmental effects, correction data for compensating for system defects, and operation data for technical maintenance; in the risk data, the result data of compensating the environmental influence, which has the highest similarity with the correction data of compensating the environmental influence, is taken as first target data, the result data of compensating the system defect, which has the highest similarity with the correction data of compensating the system defect, is taken as second target data, and the result data of technical overhaul, which has the highest similarity with the operation data of technical overhaul, is taken as third target data; the first risk value of the first target data is used as the first risk value corresponding to the operation data, the second risk value of the second target data is used as the second risk value corresponding to the operation data, and the second risk value of the third target data is used as the third risk value corresponding to the operation data.

In an exemplary embodiment, the operation and maintenance information updating module 506 is further configured to select, in the case where the risk level of the grid operation and maintenance information is greater than the risk level threshold, the reference operation and maintenance information from the historical operation and maintenance information corresponding to the risk level less than the risk level threshold; and updating the power grid operation and maintenance information according to the target result data corresponding to the compensation of the environmental influence, the target result data corresponding to the compensation of the system defect and the target result data corresponding to the technical overhaul in the reference operation and maintenance information, and the correction data corresponding to the compensation of the environmental influence, the correction data corresponding to the compensation of the system defect and the operation data corresponding to the technical overhaul.

The modules in the operation and maintenance risk prediction device can be implemented in whole or in part 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 an exemplary embodiment, a computer device is provided, which may be a server, and an internal structure thereof may be as shown in fig. 6. 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 risk data, operation and maintenance data 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 is executed by a processor to implement an operation and maintenance risk prediction method.

It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain 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 an 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.

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.) referred to in the present application are 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 comply with the related laws and regulations and standards of the related countries and regions.

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 the various 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), magnetic 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 the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being 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 above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. An operation and maintenance risk prediction method, characterized in that the method comprises:

inputting the operation and maintenance data into a pre-constructed risk prediction model, and obtaining the risk level of the power grid operation and maintenance information based on the risk data corresponding to the historical operation and maintenance information; the pre-constructed risk prediction model is obtained by constructing scores of risk data corresponding to the historical operation and maintenance information under three indexes of probability information of accident occurrence, frequent information of personnel exposure to power grid accident environment and result information generated by power grid accidents; the risk data comprise result data corresponding to the compensation of environmental influence, result data corresponding to the compensation of system defects and result data corresponding to technical overhaul in the historical operation and maintenance information; the risk level is used for representing risk situations of the power grid under three indexes of the possibility information of the accident occurrence, the frequent information of the personnel exposed to the power grid accident environment and the result information generated by the power grid accident under the condition of carrying out operation and maintenance according to the power grid operation and maintenance information;

2. The method of claim 1, wherein the pre-constructed risk prediction model is constructed by:

3. The method according to claim 2, wherein the inputting the operation and maintenance data into a pre-constructed risk prediction model, based on risk data corresponding to historical operation and maintenance information, obtains a risk level of the grid operation and maintenance information, includes:

4. The method according to claim 3, wherein comparing the operation and maintenance data with the risk data by a pre-constructed risk prediction model to obtain a first risk value, a second risk value, and a third risk value corresponding to the operation and maintenance data includes:

5. The method of claim 1, wherein updating the grid operation and maintenance information according to the risk level of the grid operation and maintenance information comprises:

6. The method according to any one of claims 1-5, further comprising, after updating the grid operation and maintenance information according to the risk level of the grid operation and maintenance information:

7. An operation and maintenance risk prediction apparatus, characterized in that the apparatus comprises:

the risk level confirmation module is used for inputting the operation and maintenance data into a pre-constructed risk prediction model and obtaining the risk level of the power grid operation and maintenance information based on the risk data corresponding to the historical operation and maintenance information; the pre-constructed risk prediction model is obtained by constructing scores of risk data corresponding to the historical operation and maintenance information under three indexes of probability information of accident occurrence, frequent information of personnel exposure to power grid accident environment and result information generated by power grid accidents; the risk data comprise result data corresponding to the compensation of environmental influence, result data corresponding to the compensation of system defects and result data corresponding to technical overhaul in the historical operation and maintenance information; the risk level is used for representing risk situations of the power grid under three indexes of the possibility information of the accident occurrence, the frequent information of the personnel exposed to the power grid accident environment and the result information generated by the power grid accident under the condition of carrying out operation and maintenance according to the power grid operation and maintenance information;

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.