Intelligent operation plan risk management method and system based on digital model

Abstract

The invention discloses an intelligent operation plan risk management method and system based on a digital model, and relates to the field of electric power operation risk management, and the method comprises the steps: automatically exporting an operation plan from a power grid management system, and carrying out the refining and screening of the exported data; training a risk assessment model according to the historical risk data; inputting the refined and screened data into a risk assessment model, setting an automatic trigger mechanism, and automatically performing risk assessment on the data; and automatically generating a report according to an evaluation result, and automatically compiling and distributing a risk report according to risk levels and departments. According to the method, the operation plan is automatically exported from the power grid management system, a large amount of manual data processing work is omitted, the automatic data refining and screening steps ensure the quality and correlation of the data, and reliable input is provided for risk assessment. A digital model based on historical data, such as historical risk levels, environmental factors (humidity and power loads), and the number of personnel configurations, provides accurate risk predictions.

Description

Technical Field

[0001] The present invention relates to the field of power operation risk management, and in particular to an intelligent operation plan risk management method and system based on a digital model. Background Art

[0002] At present, the idea of ​​1+N operation risk control has been continuously valued by various industries. With the continuous expansion of the scale of the power grid, higher requirements are put forward for the safety of power operations. The planned operation risk control for power operations has now achieved full coverage in the power grid, and the spirit of "no operation without plan, no operation without video, and no operation without file" has also been deeply rooted in the hearts of the people. However, with the comprehensiveness of control measures, the corresponding system operation, data application, and plan analysis results appear.

[0003] For planning work, we generally adopt the idea of ​​annual disclosure, monthly analysis, weekly warning, and daily verification to carry out work. Next, we need to review the daily, weekly, monthly, and annual plans and conduct comprehensive analysis and warning, so as to monitor the entire process of operational risk management. Every day, the collection, summary, comprehensive analysis, and warning of the daily plan consume an average of 2 hours of work per day. Compared with the same period last year, the time consumed is basically doubled, and the planned data volume is large, with many analysis dimensions and levels, which may cause problems such as inadequate analysis and warning, data errors, and missing content.

[0004] Therefore, the present invention uses intelligent operation plan risk management based on digital models to solve the problems of inaccurate and incomplete manual analysis and early warning and rapid changes in power grid management systems.

[0005] The present invention aims at the problems of difficult early warning and analysis of risk control of relay operation plan in power system, deepens the informatization and data interaction between various business functions of power grid management platform, and forms a set of intelligent operation plan risk technology management system that can be replicated and promoted.

[0006] The present invention is expected to develop a set of intelligent operation plan risk management tools based on digital models, realize one-stop analysis of operation plans, realize the "three excess warnings" of operation plans, and realize intelligent, modular and systematic operation plan risk management and control. Improve work efficiency, reduce operation risks, and improve operation risk management methods and lean management levels. Summary of the invention

[0007] In view of the above-mentioned problems, the present invention is proposed.

[0008] Therefore, the problem to be solved by the present invention is: Key problem point 1: First, the analysis and processing of data. Due to the influence of multiple plans, multiple departments, multiple types of operations, risk levels and other influencing factors, the data needs to be classified, processed and counted, and the processing time of the algorithm model needs to be efficient, and the processing results need to be accurate.

[0009] Key point 2: For the intelligent processing of job plans, the idea of ​​modularization is added, and the analysis results must be accurate enough in the algorithm to avoid erroneous analysis results.

[0010] Key issue point three: Operation plan query needs to be queried in the maintenance and repair module of the power grid management platform. Currently, the data cannot be automatically read.

[0011] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent operation plan risk management method based on a digital model, which includes automatically exporting the operation plan from the power grid management system and refining and screening the exported data; training a risk assessment model based on historical risk data; inputting the refined and screened data into the risk assessment model, setting an automatic trigger mechanism, and automatically performing risk assessment on the data; automatically generating a report based on the assessment results, and automatically compiling and distributing the risk report according to the risk level and department.

[0012] As a preferred solution of the intelligent job planning risk management method based on digital model described in the present invention, the refined and screened data includes job name, job start time and end time, job type, preliminary estimated risk level, department name, historical risk data, current environmental data and personnel configuration; the historical risk data includes historical risk level and historical job data, and the historical risk level ranges from 1 to 5.

[0013] As a preferred solution of the intelligent operation plan risk management method based on digital model described in the present invention, wherein: the screening model for refined screening includes: using the screening mode of key features step by step to build a screening model, setting 1 to retain data, 0 to remove data, and preliminarily determining the operation name S of any operation plan N It is expressed as,

[0014]

[0015] When S N When the operation time is 1, S T Judgment, the formula is expressed as,

[0016]

[0017] When S T When the number of people is 1, S P Judgment, the formula is expressed as,

[0018]

[0019] When S P When it is 1, the risk level S is preliminarily estimatedH Judgment, the formula is expressed as,

[0020]

[0021] Among them, "key" represents the keyword, len(n) represents the number of keywords, e Represents the job end time, t s represents the start time of the operation, p represents the number of personnel configured for the current operation, and h represents the preliminary estimated risk level for the current operation; when S N , S T , S P , S H When the judgment results are all 1, the operation plan data of this time is added to the refined and filtered data set D.

[0022] As a preferred solution of the intelligent operation plan risk management method based on digital model described in the present invention, the historical operation data includes the number of personnel configurations and environmental data during the historical operation; the risk assessment model includes setting a preliminary risk level according to the historical risk level of any operation type, and the formula of the preliminary risk level R0 is expressed as:

[0023]

[0024] Where n represents the number of previous jobs of the current job type, H i It is represented as the historical risk level of the past i-th operation of the current operation type. The number of personnel configurations of historical operations is integrated using the harmonic mean method to obtain the number threshold T, which is expressed as:

[0025]

[0026] Among them, p i It is represented by the number of staffing for the past i-th job of the current job type; the staffing number influence term ΔR is constructed based on the number of staffing thresholds and expressed as,

[0027]

[0028] The environmental data includes humidity data and power load data. A composite function F(G,L) is constructed based on the humidity data and power load data of historical operations and is expressed as:

[0029]

[0030] Where G represents the current operating humidity data, L(g) represents the correlation function between the power load and humidity of the historical operation, and L iIt is represented by the power load data of the past i-th operation of the current operation type, L0 is represented as the basic power load, α and λ are represented as model parameters, which are used to adjust the sensitivity and attenuation speed of humidity influence. gi It is represented by the humidity data of the past i-th operation of the current operation type; the environmental factor influencing term E is constructed based on the composite function and expressed as:

[0031]

[0032] Where K is a normalization constant.

[0033] As a preferred solution of the intelligent operation plan risk management method based on digital model described in the present invention, the risk assessment model also includes constructing a risk assessment model H based on the preliminary risk level R0, the personnel configuration number influence term ΔR and the environmental factor influence term E. z It is expressed as,

[0034] H z =W1R0+W2ΔR+W3E

[0035] Among them, W1, W2, and W3 represent weight coefficients.

[0036] As a preferred solution of the intelligent operation plan risk management method based on digital model described in the present invention, the automatic trigger mechanism includes dividing the operation tasks into daily tasks, weekly tasks, monthly tasks and annual tasks according to the start time and end time of the operation, and automatically performing evaluation and processing in the order of priority daily tasks > weekly tasks > monthly tasks > annual tasks.

[0037] As a preferred solution of the intelligent operation plan risk management method based on digital model described in the present invention, wherein: the evaluation result includes: when H z When the output value is 1, it is judged as low risk and the task is executed normally; z When the output value is 2 or 3, it is judged as medium risk, and additional personnel are assigned to the original task until the risk assessment model output is 1; when H z When the output value is 4 or 5, it is judged as high risk, and the current task is reset, and resources, staffing and task duration are reallocated to meet the assessment risk level of 1.

[0038] Another object of the present invention is to provide an intelligent operation plan risk management system based on a digital model, which can automatically conduct risk assessment on operation projects and generate reports to be sent to relevant departments.

[0039] To solve the above technical problems, the present invention provides the following technical solutions: a system for an intelligent operation plan risk management method based on a digital model, comprising: a data screening module, an evaluation module and a reporting module; the data screening module automatically exports the operation plan from the power grid management system, and performs refined screening on the exported data; the evaluation module trains a risk assessment model based on historical risk data, inputs the refined and screened data into the risk assessment model, sets an automatic trigger mechanism, and automatically performs risk assessment on the data; the reporting module automatically generates a report based on the evaluation results, and automatically compiles and distributes risk reports according to risk levels and departments.

[0040] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned intelligent operation plan risk management method based on a digital model are implemented.

[0041] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned intelligent operation plan risk management method based on a digital model.

[0042] The beneficial effects of the present invention are as follows: based on the idea of ​​digitization, the present invention performs lean processing on the exported work plan, extracts the information that needs attention, and formats the content in a simple manner without losing the key content.

[0043] The present invention saves a lot of manual data processing work by automatically exporting the operation plan from the power grid management system. The automated data refinement and screening steps ensure the quality and relevance of the data, providing a reliable input for risk assessment.

[0044] The invention provides accurate risk predictions using digital models based on historical data, such as historical risk levels, environmental factors (humidity and power load), and staffing numbers. The model is able to generate customized risk assessments for each job type by taking into account different environmental and operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0046] Figure 1 This is a scenario diagram of an intelligent operation plan risk management method and system based on a digital model in Example 1.

[0047] Figure 2 This is a structural diagram of an intelligent operation plan risk management method and system based on a digital model in Example 3. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Example 1, reference Figure 1 , which is the first embodiment of the present invention, and which provides a method for intelligent operation plan risk management based on a digital model, including: Figure 1 As shown:

[0051] Step 1: Automatically export the operation plan from the power grid management system and refine and screen the exported data.

[0052] The refined and filtered data includes job name, job start and end time, job type, preliminary estimated risk level, department name, historical risk data, current environment data and staffing.

[0053] Historical risk data includes historical risk levels and historical operation data. The historical risk levels range from 1 to 5.

[0054] The present invention adopts a step-by-step key feature screening mode to construct a screening model, setting 1 to retain data and 0 to remove data, and preliminarily determining the job name S for any job plan. N It is expressed as,

[0055]

[0056] When S N When it is 1, the operation time S T Judgment, the formula is expressed as,

[0057]

[0058] When S T When the number of people is 1, S P Judgment, the formula is expressed as,

[0059]

[0060] When S PWhen it is 1, the risk level S is preliminarily estimated H Judgment, the formula is expressed as,

[0061]

[0062] Among them, "key" represents the keyword, len(n) represents the number of keywords, e Represents the job end time, t s It represents the start time of the operation, p represents the number of personnel configured for the current operation, and h represents the preliminary estimated risk level for the current operation.

[0063] Threshold explanation: According to regulations, most operations that generally last less than 1 hour are temporary and simple operations. In order to reduce the burden on the system, such operations are not considered; based on the curve drawn based on historical accident data, when the number of personnel is less than four, there will be a huge turning point, and the accident rate will increase exponentially. This is because operations with a small number of people are generally not equipped with safety officers, which leads to an increase in the incidence of accidents. Therefore, the present invention re-evaluates operations with less than four people, and maintains the initial estimated risk level for operations with a larger number of people; the present invention judges operations with a risk level of 1 as low-risk operations, which generally do not need to be re-evaluated, but especially those operations with high risk levels and a small number of people need to be re-evaluated.

[0064] When S N , S T , S P , S H When the judgment results are all 1, the operation plan data of this time is added to the refined and filtered data set D.

[0065] Step 2: Train a risk assessment model based on historical risk data.

[0066] The historical operation data includes the number of personnel and environmental data when the operation was performed historically.

[0067] According to the historical risk level of any operation type, a preliminary risk level is set. The formula of the preliminary risk level R0 is expressed as:

[0068]

[0069] Where n represents the number of previous jobs of the current job type, and H i It is represented by the historical risk level of the i-th operation of the current operation type in the past.

[0070] The harmonic mean method is used to integrate the number of personnel configurations for historical operations to obtain the number threshold T, which is expressed as:

[0071]

[0072] Among them, p i It represents the number of staffing for the past i-th job of the current job type.

[0073] According to the number of people threshold, the staffing number influence term ΔR is expressed as:

[0074]

[0075] The environmental data includes humidity data and power load data. A composite function F(G,L) is constructed based on the humidity data and power load data of historical operations and is expressed as:

[0076]

[0077] Where G represents the current operating humidity data, L(g) represents the correlation function between the power load and humidity of the historical operation, and L i It is represented by the power load data of the past i-th operation of the current operation type, L0 is represented as the basic power load, α and λ are represented as model parameters, which are used to adjust the sensitivity and attenuation speed of humidity influence. gi Represents the humidity data of the past i-th operation of the current operation type.

[0078] The environmental factor influencing term E based on the composite function is expressed as:

[0079]

[0080] Where K is a normalization constant.

[0081] In the design, the value of the constant K needs to be determined according to the specific data range and the required output range. In order to ensure that the output of the environmental factor E is between 0 and 5, the setting of K should make the maximum theoretical or actual value of F(G,L) mapped to a value close to 1 after normalization, so that the maximum value of E is 5. The choice here depends on the analysis of humidity and power load data.

[0082] Steps to determine K: First, you need to collect enough historical data points for humidity G and power load L, and analyze these data points to determine their maximum possible values ​​and typical values.

[0083] Simulate the maximum value of F(G,L): Assume the maximum rate of change of humidity g(t) and the maximum value of power load under extreme conditions. Calculate F(G,L) for these extreme values.

[0084] For example, if the humidity changes rapidly from very low to very high and the power load peaks at the same time, this will be an extreme case of F(G,L).

[0085] Choose K: K should be chosen so that Close to 0, so Close to 1. If F max is the calculated value of F(G,L) in extreme cases, we can assume K≈F max .

[0086] Example calculation: We know the maximum values ​​of humidity G and power load L from historical data. Let g max and L max Represent the maximum possible rate of change and maximum value of humidity and power load respectively.

[0087] The calculation of the extreme value of F(G,L) is expressed as,

[0088]

[0089] Among them, G max It is represented as the maximum duration of humidity change and m is the number of measurement points of the power load.

[0090] Assume h max =10% per hour, L max =5000 units, the measurement period is one day, i.e. 24 hours.

[0091] Humidity integral:

[0092]

[0093] The square root of the sum of the squares of the power load:

[0094]

[0095] Calculate F max :

[0096]

[0097] Select the normalization constant K. In order to make the value of E close to 5, we need to choose a suitable K so that Close to 0. A simple approach is to set K equal to F max , or slightly larger than F max .

[0098] Select K:

[0099] K=F max =1031.46.

[0100] Based on the preliminary risk level R0, the staffing number influencing term ΔR and the environmental factor influencing term E, the risk assessment model H is constructed. z It is expressed as,

[0101] H z =W1R0+W2ΔR+W3E

[0102] Among them, W1, W2, and W3 represent weight coefficients.

[0103] Step 3: Input the refined and screened data into the risk assessment model, set up an automatic trigger mechanism, and automatically perform risk assessment on the data.

[0104] The automatic trigger mechanism includes: dividing the job tasks into daily tasks, weekly tasks, monthly tasks and annual tasks according to the start time and end time of the job, and automatically evaluating and processing them in the order of priority daily tasks > weekly tasks > monthly tasks > annual tasks.

[0105] Step 4: Automatically generate reports based on the assessment results, and automatically prepare and distribute risk reports by risk level and department.

[0106] The evaluation results are as follows: z When the output value is 1, it is judged as low risk and the job task is executed normally.

[0107] When H z When the output value is 2 or 3, it is judged as medium risk, and additional personnel are assigned to the original task until the risk assessment model output is 1.

[0108] When H z When the output value is 4 or 5, it is judged as high risk, and the current task is reset, and resources, staffing and task duration are reallocated to meet the assessment risk level of 1.

[0109] Embodiment 2, the second embodiment of the present invention, is different from the first embodiment in that: a method for intelligent operation plan risk management based on a digital model also includes: in order to verify and illustrate the technical effects adopted in this method, this embodiment adopts a traditional technical solution and the method of the present invention for comparative testing, and compares the test results by means of scientific argumentation to verify the real effect of this method.

[0110] This embodiment compares the experimental data obtained by loading the method invented by our party into the system with the experimental data obtained by the traditional manual analysis and early warning technical solution. The comparison indicators are as follows:

[0111] Risk Identification Accuracy: Evaluate the accuracy of both methods in correctly identifying and assessing the risk level of the operation.

[0112] Response time: Compare the total time from data input to risk warning output.

[0113] Processing capability: Evaluate the processing efficiency and stability of the two methods when faced with large amounts of data.

[0114] Data transfer: the time it takes for data to reach the terminal of relevant departments after being analyzed and evaluated.

[0115] The comparison results of the experimental data are shown in Table 1:

[0116] Table 1: Experimental data comparison table

[0117]

[0118] Accuracy of risk identification: By integrating deep learning and statistical analysis techniques, the method of the present invention can more accurately analyze and predict potential risks, significantly improving the accuracy of risk identification compared with traditional methods.

[0119] Response time: Automated and digitalized processing significantly reduces the time from receiving data to generating warnings, making risk management faster and more efficient.

[0120] Processing capability: This method can process a large amount of data input at the same time and is suitable for large-scale operation scenarios, while manual methods are prone to bottlenecks when the amount of data increases.

[0121] Example 3, reference Figure 2 , which is the third embodiment of the present invention, and is different from the previous two embodiments in that: a system of an intelligent operation plan risk management method based on a digital model, including a data screening module, an evaluation module and a reporting module; the data screening module automatically exports the operation plan from the power grid management system, and refines and screens the exported data; the evaluation module trains a risk assessment model based on historical risk data, inputs the refined and screened data into the risk assessment model, sets an automatic trigger mechanism, and automatically performs risk assessment on the data; the reporting module automatically generates a report based on the evaluation results, and automatically compiles and distributes risk reports according to risk levels and departments.

[0122] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0123] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0124] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0125] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0126] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent operation plan risk management method based on a digital model, characterized by: include, Automatically export the operation plan from the power grid management system and refine and filter the exported data; Train a risk assessment model based on historical risk data; Input the refined and screened data into the risk assessment model, set up an automatic trigger mechanism, and automatically conduct risk assessment on the data; Automatically generate reports based on assessment results, and automatically prepare and distribute risk reports by risk level and department.

2. The method for intelligent operation plan risk management based on digital model as claimed in claim 1, characterized in that: The refined and screened data includes the job name, job start time and end time, job type, preliminary estimated risk level, department name, historical risk data, current environment data and staffing; The historical risk data includes historical risk levels and historical operation data, and the historical risk levels range from 1 to 5.

3. The method for intelligent operation plan risk management based on digital model as claimed in claim 2, characterized in that: The screening model for refined screening includes: constructing a screening model using a step-by-step key feature screening mode, setting 1 to retain data and 0 to remove data, and preliminarily determining the job name S for any job plan. N It is expressed as, When S N When it is 1, the operation time S T Judgment, the formula is expressed as, When S T When the number of people is 1, S P Judgment, the formula is expressed as, When S P When it is 1, the risk level S is preliminarily estimated H Judgment, the formula is expressed as, Among them, "key" represents the keyword, len(n) represents the number of keywords, e Represents the job end time, t s It represents the start time of the operation, p represents the number of personnel under the current operation, and h represents the preliminary estimated risk level under the current operation; When S N , S T , S P , S H When the judgment results are all 1, the operation plan data of this time is added to the refined and filtered data set D.

4. The method for intelligent operation plan risk management based on digital model as claimed in claim 3, characterized in that: The historical operation data includes the number of personnel configurations and environmental data during the historical operations; The risk assessment model includes setting a preliminary risk level according to the historical risk level of any operation type. The formula of the preliminary risk level R0 is expressed as: Where n represents the number of previous jobs of the current job type, and H i It is represented by the historical risk level of the past i-th operation of the current operation type; The harmonic mean method is used to integrate the number of personnel configurations for historical operations to obtain the number threshold T, which is expressed as: Among them, p i It represents the number of staffing for the past i-th job of the current job type; According to the number of people threshold, the staffing number influence term ΔR is expressed as: The environmental data includes humidity data and power load data. A composite function F(G,L) is constructed based on the humidity data and power load data of historical operations and is expressed as: Where G represents the current operating humidity data, L(g) represents the correlation function between the power load and humidity of the historical operation, and L i It is represented by the power load data of the past i-th operation of the current operation type, L0 is represented as the basic power load, α and λ are represented as model parameters, which are used to adjust the sensitivity and attenuation speed of humidity influence. gi It represents the humidity data of the past i-th operation of the current operation type; The environmental factor influencing term E based on the composite function is expressed as: Where K is a normalization constant.

5. The method for intelligent operation plan risk management based on digital model as claimed in claim 4, characterized in that: The risk assessment model also includes constructing a risk assessment model H based on the preliminary risk level R0, the staffing number influence term ΔR and the environmental factor influence term E. z It is expressed as, H z =W1R0+W2ΔR+W3E Among them, W1, W2, and W3 represent weight coefficients.

6. The method for intelligent operation plan risk management based on digital model as claimed in claim 5, characterized in that: The automatic trigger mechanism includes dividing the operation tasks into daily tasks, weekly tasks, monthly tasks and annual tasks according to the start time and end time of the operation, and automatically performing evaluation and processing in the order of priority daily tasks > weekly tasks > monthly tasks > annual tasks.

7. The method for intelligent operation plan risk management based on digital model as claimed in claim 6, characterized in that: The evaluation results include: z When the output value is 1, it is judged as low risk and the task is executed normally; When H z When the output value is 2 or 3, it is judged as medium risk, and additional personnel are assigned to the original task until the risk assessment model output is 1; When H z When the output value is 4 or 5, it is judged as high risk, and the current task is reset, and resources, staffing and task duration are reallocated to meet the assessment risk level of 1.

8. A system using a digital model-based intelligent operation plan risk management method as claimed in any one of claims 1 to 7, characterized in that: It includes data screening module, evaluation module and reporting module; The data screening module automatically exports the operation plan from the power grid management system and performs refined screening on the exported data; The assessment module trains a risk assessment model based on historical risk data, inputs the refined and screened data into the risk assessment model, sets an automatic trigger mechanism, and automatically performs risk assessment on the data; The reporting module automatically generates reports based on the assessment results, and automatically compiles and distributes risk reports by risk level and department.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent operation plan risk management method based on a digital model described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a digital model-based intelligent operation plan risk management method according to any one of claims 1 to 7 are implemented.

Images