Power construction management operation system and operation method thereof

Abstract

The invention relates to the technical field of power management, and discloses a power construction management operation system and an operation method thereof, and the method comprises the following steps: a project team uploads a power construction project plan task and team information to a management operation system through a cloud system, according to the actual construction condition, automatically loading plan project information of the power construction project; the project team inputs an optimization target through the cloud system; the cloud system carries out calculation through the optimization target and outputs an optimization result, and the optimization result comprises optimization task allocation, construction progress arrangement, total project cost and a pipeline sequence of electric power construction projects; the cloud system feeds back an optimization result to a project manager, and the project manager arranges a project team for construction according to the optimization result; according to the invention, automatic optimization of the electric power construction project is realized by providing a comprehensive processing model, and the method has the characteristics of short system updating period, fast information feedback speed, high execution efficiency and the like, and enables manpower distribution to be more reasonable.

Description

Technical Field

[0001] The present invention relates to the field of power management, and more specifically, to a power construction management operation system and an operation method thereof. Background Art

[0002] During the process of power construction, how to reasonably and efficiently manage the quality, progress, and cost of construction projects is an important task. Traditional project management is often dominated by manual work, and it is often difficult to take into account all project information simultaneously. In project management, how to use advanced computer technologies and intelligent algorithms to manage projects intelligently has become an important requirement in power construction project management;

[0003] Projects usually require multiple team members or teams to collaborate to complete. Different team members or teams have specific capabilities and resources. Therefore, reasonably allocating the tasks of power construction projects, maximizing the capabilities of the project team, and improving team efficiency are also important tasks for optimizing the management of construction projects.

[0004] Power construction project management usually includes aspects such as project planning, resource allocation, schedule control, cost management, quality control, risk management, and data visualization. The multi-objectives, multi-tasks, and complexity of power construction projects make their management complex and time-consuming. It is often difficult to take into account all project information simultaneously by manual processing, and intelligent management is particularly important in improving the management ability and efficiency of power construction projects.

[0005] Currently, the process of power construction project management is cumbersome and complex, lacking automated and intelligent tools, and it is difficult to meet the increasingly complex requirements. For example: there is currently no suitable method or tool to efficiently manage power construction projects as a whole. There are deficiencies in many aspects such as resource allocation, schedule control, and cost management of power construction projects, which affect the project management ability and level.

[0006] Most current project management systems rely on manual decision-making, with a low level of intelligence, and cannot achieve automatic optimization and adjustment. The power construction project management method needs to optimize task allocation, construction sequence, etc. according to the project characteristics, which requires a large amount of calculation. Manual calculation is time-consuming and laborious. The existing technologies generally use a single algorithm, and the complexity of power construction projects is high. A single algorithm is prone to limitations and cannot meet the diverse needs of power construction projects. Summary of the Invention

[0007] The present invention provides a power construction management operation system and an operation method thereof, which solve the deficiencies in the process optimization and intelligent design of the project management operation method in the related art, including optimizing task allocation, construction sequence, etc., which require a large amount of calculations, and optimize the power construction project management method through intelligent algorithms to improve the efficiency of project execution and the management level of technical problems.

[0008] The present invention provides an operation method for a power construction management operation system, including the following steps:

[0009] Step 101, the project team uploads the power construction project plan tasks and team information to the management operation system through the cloud system, and automatically loads the planned project information of the power construction project according to the actual construction situation;

[0010] Step 102, the project team inputs the optimization objectives through the cloud system, and the optimization objectives include the objective of minimizing the total cost and the objective of minimizing the total construction progress duration;

[0011] Step 103, the cloud system calculates through the optimization objectives and outputs the optimization results, and the optimization results include optimized task allocation, construction progress arrangement, project total cost, and the flow sequence of the power construction project;

[0012] Step 104, the cloud system feeds back the optimization results to the project manager, and the project manager arranges the project team to carry out construction according to the optimization results.

[0013] In a preferred embodiment, the calculation formula of the objective function optimized by the cloud system is:

[0014] minF 1 =αX 1 +βX 2 +θX 3

[0015] Among them, F 1 represents the project expenditure amount, and X 1 , X 2 , X 3 respectively represent the actual project expenditure amount, the project budget amount, and the project progress impact coefficient, and 1≥α, β, θ.

[0016] In a preferred embodiment, the constraint conditions optimized by the cloud system include:

[0017] First, each task can only be assigned to one worker for execution;

[0018]

[0019] Among them, Z ij represents the number of workers assigned to task j in the i-th stage;

[0020] II. Each task can only start after its prerequisite task is completed. If there is a prerequisite task, then:

[0021]

[0022] where P j represents the prerequisite task of task j, and X i represents the start date of the i-th stage, represents the completion time of the prerequisite task P j .

[0023] III. The number of people starting and ending work during the task period is equal;

[0024]

[0025] where C i represents the number of people participating in work at the start of the i-th stage, and D represents the upper limit of the number of people engaged in work at the end of each stage;

[0026] IV. A worker can only be engaged in one task at any given moment;

[0027]

[0028] where B ijk represents whether worker k performs task j in the i-th stage, B ij ∈{0, 1}. If the worker performs task j in the i-th stage, then B ij = 1; otherwise, B ij = 0.

[0029] In a preferred embodiment, the method for the cloud system to calculate through an optimization objective and output an optimization result includes the following steps:

[0030] Step 201: Input the project team involved in the power construction project into the comprehensive processing model, and the comprehensive processing model outputs the team processing capacity coefficient;

[0031] Step 202: Input the project parameters involved in the power construction project into the comprehensive processing model, and the comprehensive processing model outputs the start date, end date, end date of each stage, and planned number of days for each construction stage of the power construction project schedule. The project parameters include construction requirements, construction site, construction materials, and team processing capacity coefficient;

[0032] Step 203: Input the project parameters involved in the power construction project into the comprehensive processing model, and the comprehensive processing model outputs the optimal allocation plan for the tasks of the power construction project;

[0033] Step 204: Input the flow construction plan into the comprehensive processing model, and the comprehensive processing model outputs the optimal flow construction sequence of the power construction project.

[0034] In a preferred embodiment, the comprehensive processing model includes a neural network architecture, a genetic algorithm optimization architecture, and a graph theory optimization architecture; the encoded project team information vector is input into the neural network architecture, and the neural network architecture outputs the team processing ability coefficient of the project team; the encoded project parameters of the power construction project and the team processing ability coefficient output by the neural network architecture are input into the genetic algorithm optimization architecture, and the genetic algorithm optimization architecture outputs the optimal allocation plan of the power construction project; the encoded project task set, task dependencies, and the optimal allocation plan output by the genetic algorithm optimization architecture are input into the graph theory optimization architecture, and the graph theory optimization architecture outputs the execution sequence of each project task in the power construction project.

[0035] In a preferred embodiment, the neural network architecture includes an input layer, a hidden layer, and an output layer;

[0036] Input layer:

[0037] The input data x = (x 1 , x 2 , …, x 18 ), where x 1 , x 2 , …, x 18 respectively represent the working years of the project manager, the number of engineering and technical personnel, the average experience level of engineering and technical personnel, the average experience level of engineering and technical personnel, the average experience level of the schedule planner, the number of procurement personnel, the average experience level of procurement personnel, the number of safety supervisors, the average experience level of safety supervisors, the number of quality supervisors, the average experience level of quality supervisors, the number of cost controllers, the average experience level of cost controllers, the total project budget, the expected project duration, the total number of project tasks, the technical difficulty score of the project, and the weather condition parameters;

[0038] The calculation formula of the hidden layer is:

[0039] z (1) = W (1) x + b (1)

[0040] where z (1) represents the project team output feature vector of the hidden layer, x represents the project team information vector, W (1) represents the weight matrix of the hidden layer, and b (1) represents the bias vector of the hidden layer;

[0041] The activation function of the hidden layer is:

[0042] a (1) = f(z (1) )

[0043] where a (1) represents the activation output vector of the hidden layer, f represents the RELU activation function, and z (1) represents the item team output feature vector of the hidden layer;

[0044] The calculation formula of the output layer is:

[0045] z (2) = W (2) a (1) + b (2)

[0046] where z (2) represents the linear combination output vector of the output layer, a (1) represents the activation output vector of the hidden layer, W (2) represents the weight matrix of the output layer, and b (2) represents the bias vector of the output layer;

[0047] The activation function of the output layer is:

[0048] y = softmax(z (2) )

[0049] where y represents the team processing ability coefficient of the project team, and z (2) represents the linear combination output vector of the output layer, and softmax represents the softmax activation function.

[0050] In a preferred embodiment, the fitness function of the genetic algorithm optimization architecture is:

[0051]

[0052] where F(S) represents the fitness value corresponding to the task assignment scheme S, S ij = 1 means that task t i is assigned to worker ω j , otherwise S ij = 0, and CB ij represents the cost of task t i being assigned to worker ω j , m represents the number of project tasks, and k represents the number of workers in the project team.

[0053] In a preferred embodiment, the graph theory optimization architecture uses Kahn's algorithm or depth - first search to determine the execution order of each project task.

[0054] A power construction management operation system includes the following modules:

[0055] A cloud system initialization module, which is used to receive and store the power construction project plan tasks and team information uploaded by the project team;

[0056] An optimization requirement input module, which is used for the project team to input optimization goals through the cloud system, including the goal of minimizing the total cost and the goal of minimizing the total construction progress duration;

[0057] An intelligent algorithm optimization module, which conducts multi-faceted optimizations based on neural networks, genetic algorithms, and graph theory, predicts the team processing ability coefficient, optimized task allocation, and construction sequence of the project team, and generates an optimal construction plan;

[0058] An optimization result feedback module, which is used to feedback the optimization result to the project manager and provide a visual optimization result and construction plan.

[0059] A computer storage medium is used to store computer-readable instructions, and these computer-readable instructions can execute the steps in the operation method of the above-mentioned power construction management operation system when executed by a computer system.

[0060] The beneficial effects of the present invention are as follows: The management operation method provided by the present invention conducts intelligent optimization on construction projects, and through the management operation system, it can carry out progress and management supervision during the project process, which can accelerate the completion of power construction projects, save the total project cost, and improve construction efficiency; and through providing a comprehensive processing model, it realizes automatic optimization of power construction projects, with characteristics such as a short system update cycle, fast information feedback speed, high execution efficiency, and more reasonable manpower allocation. Brief Description of the Drawings

[0061] Figure 1 is a flowchart of the operation method of the present invention.

[0062] Figure 2 is a flowchart of the method for processing the cloud system of the present invention. Detailed Embodiments

[0063] Now, the subject matter described herein will be discussed with reference to exemplary embodiments. It should be understood that discussing these embodiments is only to enable those skilled in the art to better understand and thus implement the subject matter described herein. Without departing from the protection scope of the content of this specification, changes can be made to the functions and arrangements of the elements discussed. Each example can omit, substitute, or add various processes or components as needed. Additionally, the features described relative to some examples can also be combined in other examples.

[0064] Such as Figure 1As shown in the figure, an operation method of an electric power construction management operation system, the method includes cloud system initialization, optimization requirement input, intelligent algorithm optimization and optimization result feedback, and the method includes the following steps:

[0065] Step 101, the project team uploads the electric power construction project plan tasks and team information to the management operation system through the cloud system, and automatically loads the planned project information of the electric power construction project according to the actual construction situation;

[0066] It should be noted that the initialization parameters optimized by the cloud system include construction requirements, construction site, construction materials, and team processing ability coefficient;

[0067] Step 102, the project team inputs optimization goals through the cloud system, and the optimization goals include the goal of minimizing the total cost and the goal of minimizing the total construction progress duration;

[0068] It should be noted that the project teams involved in the electric power construction project include project managers, on-site engineering and technical personnel, schedule planners, procurement personnel, safety supervisors, quality supervisors, and cost controllers;

[0069] The electric power construction enterprises involved in the electric power construction project include enterprise departments and construction enterprises;

[0070] The application systems involved in the electric power construction project include project management applications, cost control applications, and data visualization applications;

[0071] The intelligent algorithms involved in the electric power construction project include predicting the team processing ability coefficient with neural networks, optimizing the team task allocation with genetic algorithms, and optimizing the project flow construction sequence with graph theory;

[0072] The calculation formula of the objective function optimized by the cloud system is:

[0073] minF 1 =αX 1 +βX 2 +θX 3

[0074] Among them, F 1 represents the project cost amount, and X 1 , X 2 , X 3 respectively represent the actual project cost amount, the project budget amount, and the project schedule impact coefficient, and 1≥α, β, θ;

[0075] The constraint conditions for cloud system optimization include:

[0076] V. Each task can only be assigned to one worker for execution;

[0077]

[0078] Among them, Z ij represents the number of workers assigned to task j in the i-th stage;

[0079] VI. Each task can only start after its preceding task is completed. If there is a preceding task, then:

[0080]

[0081] Among them, P j represents the preceding task of task j, X i represents the start date of the i-th stage, represents the completion time of the preceding task P j ;

[0082] VII. The number of people starting and ending work during the task period is equal;

[0083]

[0084] Among them, C i represents the number of people participating in work at the start of the i-th stage, and D represents the upper limit of the number of people put into work at the end of each stage;

[0085] VIII. A worker can only be engaged in one task at any given moment;

[0086]

[0087] Among them, B ijk represents whether worker k performs task j in the i-th stage. B ij ∈{0, 1}. If the worker performs task j in the i-th stage, then B ij = 1; otherwise, B ij = 0;

[0088] In an embodiment of the present invention, the optimization objective of power construction project management is to minimize the total cost. The total project cost consists of three parts: project fixed cost, project processing cost, and project planning cost; since the project fixed cost is fixed and cannot be changed, the focus of optimization is on reducing the processing cost and planning cost.

[0089] To achieve this goal, the following three intelligent algorithms are combined:

[0090] 1. Neural network to predict the project processing capacity coefficient;

[0091] 2. Genetic algorithm to optimize project task allocation;

[0092] 3. Graph theory to optimize the project construction sequence.

[0093] Step 103, the cloud system calculates based on the optimization objectives and outputs the optimization results, which include the optimized task allocation, construction schedule arrangement, total project cost, and the flow sequence of the power construction project;

[0094] The method for the cloud system to calculate based on the optimization objectives and output the optimization results includes the following steps:

[0095] Step 201, input the project teams involved in the power construction project into the comprehensive processing model, and the comprehensive processing model outputs the team processing ability coefficient;

[0096] The project teams include project managers, on-site engineering and technical personnel, schedule planners, procurement personnel, safety supervisors, quality supervisors, and cost controllers;

[0097] Step 202, input the project parameters involved in the power construction project into the comprehensive processing model, and the comprehensive processing model outputs the start date, end date, end date of each stage, and planned days of each construction stage of the power construction project schedule. The project parameters include construction requirements, construction site, construction materials, and team processing ability coefficient;

[0098] Step 203, input the project parameters involved in the power construction project into the comprehensive processing model, and the comprehensive processing model outputs the optimal allocation plan for the tasks of the power construction project;

[0099] Step 204, input the flow construction plan into the comprehensive processing model, and the comprehensive processing model outputs the optimal flow construction sequence of the power construction project;

[0100] The comprehensive processing model includes a neural network architecture, a genetic algorithm optimization architecture, and a graph theory optimization architecture; the encoded project team information vector is input into the neural network architecture, and the neural network architecture outputs the team processing ability coefficient of the project team; the encoded project parameters of the power construction project and the team processing ability coefficient output by the neural network architecture are input into the genetic algorithm optimization architecture, and the genetic algorithm optimization architecture outputs the optimal allocation plan for the power construction project; the encoded project task set, task dependencies, and the optimal allocation plan output by the genetic algorithm optimization architecture are input into the graph theory optimization architecture, and the graph theory optimization architecture outputs the execution order of each project task in the power construction project.

[0101] I. The neural network architecture includes an input layer, a hidden layer, and an output layer;

[0102] Input layer:

[0103] The input data x = (x 1 , x 2 , …, x 18 ), where x 1 , x2 , …, x 18 respectively represent the working years of the project manager, the number of engineering and technical personnel, the average experience level of engineering and technical personnel, the average experience level of engineering and technical personnel, the average experience level of the schedule planner, the number of procurement personnel, the average experience level of procurement personnel, the number of safety supervisors, the average experience level of safety supervisors, the number of quality supervisors, the average experience level of quality supervisors, the number of cost controllers, the average experience level of cost controllers, the total project budget, the estimated project duration, the total number of tasks of the project, the technical difficulty score of the project, and the weather condition parameters;

[0104] The calculation formula for the hidden layer is:

[0105] z (1) = W (1) x + b (1)

[0106] Among them, z (1) represents the output feature vector of the project team of the hidden layer, x represents the project team information vector, and W (1) represents the weight matrix of the hidden layer, and b (1) represents the bias vector of the hidden layer;

[0107] The activation function of the hidden layer is:

[0108] a (1) = f(z (1) )

[0109] Among them, a (1) represents the activation output vector of the hidden layer, f represents the RELU activation function, and z (1) represents the output feature vector of the project team of the hidden layer;

[0110] The calculation formula for the output layer is:

[0111] z (2) = W (2) a (1) + b (2)

[0112] Among them, z (2) represents the linear combination output vector of the output layer, a (1) represents the activation output vector of the hidden layer, W (2) represents the weight matrix of the output layer, and b (2) represents the bias vector of the output layer;

[0113] The activation function of the output layer is:

[0114] y = softmax(z (2) )

[0115] Among them, y represents the team processing ability coefficient of the project team, and z (2) represents the linear combination output vector of the output layer, and softmax represents the softmax activation function;

[0116] II. Genetic algorithm optimization architecture;

[0117] Input:

[0118] Task set T = {t 1 , t 2 , …, t m};

[0119] Worker set W = {ω 1 , ω 2 , …, ω k};

[0120] Project processing ability coefficient y;

[0121] Output:

[0122] Task assignment plan S. If S ij = 1, it means that task t i is assigned to worker ω j , otherwise S ij = 0;

[0123] The fitness function of the genetic algorithm optimization architecture is:

[0124]

[0125] Among them, F(S) represents the fitness value corresponding to the task assignment plan S. S ij = 1 means that task t i is assigned to worker ω j , otherwise S ij = 0, and CB ij represents the cost of task t i being assigned to worker ω j . m represents the number of project tasks, and k represents the number of workers in the project team;

[0126] It should be noted that in the genetic algorithm optimization architecture, the roulette wheel selection method is used for selection, the single-point crossover or uniform crossover is used for the crossover operation, and the task assignment is randomly changed with a certain probability.

[0127] III. Quasi-graph theory optimization architecture;

[0128] Input:

[0129] Task set T = {t 1 , t 2 , …, tm};

[0130] Task dependency relationship D;

[0131] Task assignment plan S (from the genetic algorithm optimization architecture);

[0132] Output: The execution order O of each project task in the power construction project;

[0133] It should be noted that in the power construction project, the task dependency relationship means that some tasks must start after other tasks are completed. This dependency relationship can be represented by the "precedence -

[0134] successor" relationship in project management and is usually shown using a network diagram (such as a Gantt chart or PERT chart);

[0135] It should be further noted that by discussing with the project manager, engineers, and other project team members, the dependency relationship of each task is determined.

[0136] In an embodiment of the present invention, a topological sorting algorithm (such as Kahn's algorithm or depth - first search) is used to determine the execution order of tasks;

[0137] Critical path method:

[0138] Calculate the earliest start time (ES) and the latest start time (LS) of each task;

[0139] The critical path is the path with the longest total project duration;

[0140] In an embodiment of the present invention, an example is provided:

[0141] Suppose there is a simple power construction project, including three tasks {t 1 , t 2 , t 3}, two workers {ω 1 , ω 2}, and the task dependency relationship D;

[0142] 1. Neural network architecture:

[0143] Input: x = (x 1 , x 2 , …, x 18 ), where x 1 , x 2 , …, x 18 respectively represent the working years of the project manager, engineering and technical personnel;

[0144] Output: The team processing ability coefficient y of the project team;

[0145] 2. Genetic Algorithm Optimization Architecture:

[0146] Input: Tasks {t 1 , t 2 , t 3}, workers {ω 1 , ω 2}, and the team processing capacity coefficient y of the project team;

[0147] Output: Task assignment plan S:

[0148] For example:

[0149] 3. Quasi-Graph Theory Optimization Architecture:

[0150] Input: Tasks {t 1 , t 2 , t 3}, task dependency D, and task assignment plan S;

[0151] Output: Construction sequence O;

[0152] For example: O = [t 1 , t 2 , t 3 ;

[0153] In this way, the present invention constructs a comprehensive processing model that can effectively predict the project processing capacity coefficient, optimize task assignment, and determine the optimal construction sequence.

[0154] Step 104: The cloud system feeds back the optimization result to the project manager, and the project manager arranges the project team to carry out construction according to the optimization result.

[0155] The management operation method provided by the present invention performs intelligent optimization on construction projects. Through the management operation system, the progress and management supervision of the project process can be carried out, which can speed up the completion of power construction projects, save the total project cost, improve construction efficiency; and through providing a comprehensive processing model, the automatic optimization of power construction projects is realized, with characteristics such as a short system update cycle, fast information feedback speed, high execution efficiency, and more reasonable manpower allocation.

[0156] The specific implementation process of the present invention is as follows:

[0157] Upload the project team information, project construction tasks, project construction sites, and project construction materials involved in the power construction project to the system through the cloud system;

[0158] The project team selects a power construction project and inputs optimization requirements, which include minimizing the total cost of the power construction project, shortening the construction period, minimizing the project progress impact coefficient, the project worker handling capacity coefficient, etc.;

[0159] The project manager makes manual allocations based on the project information displayed in the cloud system and then conducts construction according to the power construction project schedule generated by the cloud system. The cloud system will automatically optimize the task allocation, construction arrangement, project cost, etc. of the power construction project. During the construction process, the project team can control the project cost, track the progress, and conduct parameter visualization analysis through the cloud system.

[0160] A power construction management operating system includes the following modules:

[0161] The cloud system initialization module is used to receive and store the power construction project plan tasks and team information uploaded by the project team;

[0162] The optimization requirement input module is used for the project team to input optimization goals through the cloud system, including the goal of minimizing the total cost and the goal of minimizing the total construction progress duration;

[0163] The intelligent algorithm optimization module conducts multi-faceted optimization based on neural networks, genetic algorithms, and graph theory, predicts the team handling capacity coefficient of the project team, optimizes the task allocation and construction sequence, and generates the optimal construction plan.

[0164] The optimization result feedback module is used to feedback the optimization results to the project manager and provide visual optimization results and construction plans.

[0165] In an embodiment of the present invention, the intelligent algorithm optimization module includes a neural network prediction project handling capacity coefficient sub-module, a genetic algorithm optimization task allocation sub-module, and a graph theory optimization construction sequence sub-module; among them, the neural network prediction project handling capacity coefficient sub-module is used to predict the team handling capacity coefficient of the project team through a trained neural network, the genetic algorithm optimization task allocation sub-module is used to optimize the task allocation through the genetic algorithm to find the construction progress plan with the minimum total cost, and the graph theory optimization construction sequence sub-module is used to optimize the construction sequence through graph theory to ensure that tasks are executed in the correct order.

[0166] A computer storage medium is used to store computer-readable instructions, which can execute the steps in the operation method of the above-mentioned power construction management operating system when executed by a computer system.

[0167] The above has described the embodiments of this example, but this example is not limited to the above specific implementation manners. The above specific implementation manners are merely illustrative rather than restrictive. Under the inspiration of this example, those of ordinary skill in the art can also make many forms, all of which fall within the protection scope of this example.

Claims

1. An operating method of an electric power construction management operating system, characterized in that: The following steps are involved: Step 101, the project team uploads the planned tasks and team information of the power construction project to the management operating system through the cloud system, and automatically loads the planned project information of the power construction project according to the actual construction situation; Step 102, the project team inputs optimization goals through the cloud system, and the optimization goals include a total cost minimization goal and a total construction schedule minimization goal; Step 103, the cloud system calculates by optimizing the target and outputs the optimization result, which includes optimizing task allocation, construction schedule, total project cost and flow sequence of the power construction project; Step 104, the cloud system feeds back the optimization results to the project manager, and the project manager arranges the project team to carry out construction according to the optimization results.

2. The operating method of an electric power construction management operating system according to claim 1, characterized in that: The calculation formula of the objective function of cloud system optimization is: minF1=αX1+βX2+θX3 Among them, F1 represents the project expenditure amount, X1, X2, and X3 represent the actual project expenditure amount, the project budget amount, and the project progress impact coefficient, respectively, 1≥α, β, θ.

3. The operating method of an electric power construction management operating system according to claim 2, characterized in that: The constraints for cloud system optimization include:

1. Each task can only be assigned to one worker; Among them, Z ij represents the number of workers assigned to task j in stage i; 2. Each task can only start after its predecessor task is completed. If there is a predecessor task, then: Among them, P j represents the predecessor task of task j, X i represents the start date of the i-th phase, Represents the predecessor task P j completion time; 3. The number of people who start and finish work during the mission is equal; Among them, C i represents the number of people working at the beginning of the i-th stage, and D represents the upper limit of the number of people working at the end of each stage; 4. A worker can only be engaged in one task at any one time; Among them, B ijk Indicates whether worker k performs task j in stage i, B ij ∈{0,1}, if a worker performs task j in stage i, then B ij =1, otherwise, B ij =0.

4. The operating method of the electric power construction management operating system according to claim 3 is characterized in that: The cloud system calculates by optimizing the target, and the method of outputting the optimization result includes the following steps: Step 201, inputting the project team involved in the power construction project into the comprehensive processing model, and the comprehensive processing model outputs the team processing capacity coefficient; Step 202, inputting the project parameters involved in the power construction project into the comprehensive processing model, the comprehensive processing model outputs the start date, end date, end date of each stage and the planned number of days for each construction stage of the power construction project schedule, the project parameters include construction requirements, construction site, construction materials and team processing capacity coefficient; Step 203, inputting the project parameters involved in the power construction project into the comprehensive processing model, and the comprehensive processing model outputs the optimal allocation plan of the power construction project tasks; Step 204, input the flow construction plan into the comprehensive processing model, and the comprehensive processing model outputs the optimal flow construction sequence of the power construction project.

5. The operating method of the electric power construction management operating system according to claim 4, characterized in that: The comprehensive processing model includes a neural network architecture, a genetic algorithm optimization architecture and a pseudo-graph theory optimization architecture; the encoded project team information vector is input into the neural network architecture, and the neural network architecture outputs the team processing capacity coefficient of the project team; the encoded project parameters of the power construction project and the team processing capacity coefficient output by the neural network architecture are input into the genetic algorithm optimization architecture, and the genetic algorithm optimization architecture outputs the optimal allocation plan for the power construction project; the encoded project task set, task dependency and the optimal allocation plan output by the genetic algorithm optimization architecture are input into the pseudo-graph theory optimization architecture, and the pseudo-graph theory optimization architecture outputs the execution order of each project task in the power construction project.

6. The method for operating an electric power construction management and operation system according to claim 5, characterized in that: The neural network architecture includes input layer, hidden layer and output layer; Input Layer: Input data x = (x1, x2, ..., x 18 ), where x1, x2, …, x 18 They respectively represent the working experience of the project manager, the number of engineering and technical personnel, the average experience level of engineering and technical personnel, the average experience level of engineering and technical personnel, the average experience level of schedule planners, the number of procurement personnel, the average experience level of procurement personnel, the number of safety managers, the average experience level of safety managers, the number of quality supervisors, the average experience level of quality supervisors, the number of cost controllers, the average experience level of cost controllers, the total project budget, the estimated project duration, the total number of project tasks, the technical difficulty score of the project, and the weather condition parameters; The calculation formula for the hidden layer is: z (1) =W (1) x+b (1) Among them, z (1) represents the project team output feature vector of the hidden layer, x represents the project team information vector, W (1) represents the weight matrix of the hidden layer, b (1) represents the bias vector of the hidden layer; The activation function of the hidden layer is: a (1) =f(z (1) ) Among them, a (1) represents the activation output vector of the hidden layer, f represents the RELU activation function, z (1) The project team output feature vector representing the hidden layer; The calculation formula of the output layer is: z (2) =W (2) a (1) +b (2) Among them, z (2) represents the linear combination output vector of the output layer, a (1) represents the activation output vector of the hidden layer, W (2) represents the weight matrix of the output layer, b (2) Represents the bias vector of the output layer; The activation function of the output layer is: y=softmax(z (2) ) Among them, y represents the team processing capacity coefficient of the project team, z (2) represents the linear combination output vector of the output layer, and softmax represents the softmax activation function.

7. The method for operating an electric power construction management and operation system according to claim 6, characterized in that: The fitness function of the genetic algorithm optimization architecture is: Among them, F(S) represents the fitness value corresponding to the task allocation scheme S, S ij =1 indicates task t i Assigned to worker ω j , otherwise S ij =0,CB ij Represents task t i Assigned to worker ω j cost, m represents the number of project tasks, and k represents the number of workers in the project team.

8. The method for operating an electric power construction management and operation system according to claim 7, characterized in that: The quasi-graph theory optimization architecture uses Kahn's algorithm or depth-first search to determine the execution order of each project task.

9. An electric power construction management operating system for executing the operating method of the electric power construction management operating system according to any one of claims 1 to 8, characterized in that: Includes the following modules: The cloud system initialization module is used to receive and store the power construction project plan tasks and team information uploaded by the project team; The optimization requirement input module is used by the project team to input optimization goals through the cloud system, including the total cost minimization goal and the total construction schedule minimization goal; Intelligent algorithm optimization module, which performs multi-faceted optimization based on neural networks, genetic algorithms and pseudo-graph theory, predicts the team processing capacity coefficient of the project team, optimizes task allocation and construction sequence, and generates the optimal construction plan; The optimization result feedback module is used to feed back the optimization results to the project manager and provide visualized optimization results and construction plans.

10. A computer storage medium for storing computer-readable instructions, characterized in that: When executed by a computer system, the computer-readable instructions are capable of executing the steps in the operating method of an electric power construction management operating system according to any one of claims 1 to 8.

Images