Key process optimization method based on burden value

Abstract

The invention discloses a key process optimization method based on a burden value, and the method comprises the steps: collecting data related to a key process, including construction period related data, cost related data and resource related data; respectively calculating a construction period burden value, a cost burden value and a resource burden value of the key process according to the collected data; calculating a comprehensive burden value of the key process by adopting a weighted average method, and constructing a comprehensive burden value dynamic adjustment model in a scene which reflects that the construction period, the cost and the resource consumption change along with time in real time; and carrying out identification and statistics on the key process load value based on the dynamic adjustment model, determining the change trend of the key process load value with a high load value in the whole process of the engineering project, and providing a basis for optimization decision making. Through the method, the influence of the key process on the construction period, cost and resource consumption of the engineering project can be comprehensively evaluated, and the project management efficiency and the resource allocation rationality can be conveniently improved through an optimization strategy. The method is suitable for the crossing field of engineering management and intelligent optimization.

Description

Technical Field

[0001] The invention belongs to the technical field of engineering project management, and in particular relates to a key process optimization method based on burden value. Background Art

[0002] In engineering project management, the optimization of key processes is crucial to the success of the project. Traditional critical path method (CPM) and project evaluation and review technique (PERT) are mainly based on the critical path evaluation of the construction period in order to predict the time and key tasks of project completion. However, these methods usually ignore other important factors, such as cost and resource constraints and their dynamic changes in the overall impact on the project. Existing technologies have shortcomings in the following aspects:

[0003] (1) Insufficient multi-dimensional comprehensive evaluation capabilities: Existing methods usually only focus on construction period optimization and fail to fully consider the comprehensive impact of multi-dimensional factors such as cost and resources. This single-dimensional analysis method is difficult to quantify the comprehensive impact of key processes on the overall multi-faceted goals of the project, resulting in limitations in decision-making results.

[0004] (2) Poor dynamic adaptability: During the implementation of engineering projects, construction period, cost and resource consumption are constantly changing as the project progresses. However, traditional methods are mostly based on static data and analysis of a single time node, and are unable to capture in real time the impact of dynamic changes in key processes on the overall project goals. At the same time, these methods lack a policy framework that can support dynamic adjustments, resulting in insufficient real-time control capabilities for complex projects.

[0005] (3) Lack of intelligence: Traditional methods rely on experience and static data and fail to make full use of modern data analysis and intelligent technologies, showing obvious disadvantages in data-driven optimization and automatic adjustment capabilities.

[0006] With the increasing complexity of engineering projects and the increasingly significant constraints on construction period, cost and resources, the shortcomings of traditional methods in multi-dimensional comprehensive analysis, dynamic adaptability and intelligence have become bottlenecks restricting the efficiency and success rate of engineering project management. Therefore, in order to overcome these limitations, there is an urgent need for a key process optimization method that can comprehensively consider multi-dimensional factors such as construction period, cost and resources. This method should have the following characteristics:

[0007] (1) Through the quantitative evaluation of burden values, the comprehensive impact of key processes in multiple dimensions is comprehensively measured;

[0008] (2) Dynamically capture the real-time changing trends of key processes in relation to the overall project objectives and support adjustments as the project progresses;

[0009] (3) Combine modern intelligent technologies (such as machine learning) to extract influencing factors and weights from historical data to achieve data-driven optimization and automatic adjustment. Summary of the invention

[0010] In view of this, the present invention proposes a key process optimization method based on burden value, which is used to comprehensively evaluate the impact of key processes on the construction period, cost and resource consumption of engineering projects, so as to facilitate the staff to improve the project management efficiency and rationality of resource allocation through optimization strategies. This method is applicable to the intersection of engineering management and intelligent optimization.

[0011] In order to achieve the above object, the present invention provides the following technical solutions:

[0012] A preferred method for optimizing key processes based on burden values ​​provided by the present invention includes:

[0013] Collect data related to key processes, including duration-related data, cost-related data, and resource-related data;

[0014] According to the collected data, the duration burden value, cost burden value and resource burden value of the key process are calculated respectively; the burden value refers to the proportion of the duration / cost / resources of the key process to the total duration / total cost / total resources of the project;

[0015] The weighted average method is used to calculate the comprehensive burden value of key processes, and a dynamic adjustment model for the comprehensive burden value is constructed to reflect the changes in construction period, cost and resource consumption over time in real time;

[0016] Based on the dynamic adjustment model, the burden values ​​of key processes are identified and counted to determine the changing trends of the burden values ​​of key processes with high burden values ​​in the overall process of the project, providing a basis for optimizing decisions.

[0017] Preferably, the data related to the key process, including the construction period related data, cost related data and resource related data, includes:

[0018] The machine learning model is used to collect and extract the weight coefficients and influencing factors of the duration, cost and resources of key processes from historical data, including:

[0019] Construction period related data: Construction period T of key processes task 、The total duration of the project is T totak , the weight coefficient W of the construction period burden value duration And the impact factor I of the construction period burden value duration ;

[0020] Cost-related data: cost of key processes C task 、The total cost of the project C total , the weight coefficient W of the cost burden value cost And the impact factor of cost burden value I cost ;

[0021] Resource-related data: resource consumption of key processes R task , the total resource consumption of the project R total , the weight coefficient W of resource burden value resource And the impact factor of resource burden value I resource ;

[0022] Among them, weights and impact factors are quantitatively obtained through machine learning.

[0023] Preferably, according to the collected data, respectively calculating the duration burden value, cost burden value and resource burden value of the key process includes:

[0024] The duration burden value of the key process is calculated by the following formula:

[0025]

[0026] Among them, B duration Indicates the duration burden value, which is used to indicate the proportion of the key process duration in the total project duration and its impact on the project;

[0027] The cost burden value of the key process is calculated by the following formula:

[0028]

[0029] Among them, B cost Indicates the cost burden value, which is used to indicate the proportion of key process cost to total cost and its impact on the project;

[0030] The resource burden value of the key process is calculated by the following formula:

[0031]

[0032] Among them, B resource Indicates the resource burden value, which is used to indicate the proportion of key process resource consumption in the total resource consumption and its impact on the project.

[0033] Preferably, the weighted average method is used to calculate the comprehensive burden value of the key process, including the formula:

[0034] B total =αB duration +βB cost +γB resource

[0035] Among them, α, β, and γ are weight coefficients set according to project management requirements;

[0036] The dynamic adjustment model of comprehensive burden value is expressed as:

[0037] ai (t) = a i , 0 ―r a ·t·C task ·R task

[0038] Among them, a i (t) represents the comprehensive burden value of the i-th key process at time t, a i，0 represents the initial burden value of the i-th key process, r a Indicates the decay rate of the burden value over time.

[0039] Preferably, identifying and counting the burden values ​​of key processes based on the dynamic adjustment model includes:

[0040] According to the dynamic adjustment model, the dynamic data of key processes are collected in real time and standardized, where the dynamic data includes construction period, cost, resource consumption and corresponding burden value;

[0041] The standardized dynamic data is used as training data (x i ,y i ), establish the support vector machine regression model:

[0042]

[0043] Among them, x i is the input feature vector, f(x) is the function output, and its goal is to fit the training data (x) as much as possible. i ,y i ), y i is the target burden value, a i is the Lagrange multiplier, K(x i , x) is the RBF kernel function, b is the bias term, where:

[0044]

[0045] Among them, σ is the width parameter of the kernel function;

[0046] Optimization objectives for establishing support vector machine regression models:

[0047] Among them, ‖w‖ 2 represents the regularization term of model complexity, C is the regularization parameter used to balance model complexity and fitting error, ξ i represents the i-th slack variable used to process the error of the data point, and n represents the total number of slack variables selected;

[0048] Using the training data (x i ,y i) training the support vector machine regression model, optimizing the objective function and solving the Lagrange multiplier and the bias term to obtain a trained support vector machine regression model;

[0049] For the updated key process data x new , use the trained support vector machine regression model for prediction:

[0050]

[0051] Among them, y new is the predicted burden value;

[0052] Use the trained support vector machine regression model to dynamically update the burden value, count the burden value change trends of key processes, identify high-burden value processes, and mark them as high-burden value processes when the predicted burden value exceeds the preset threshold;

[0053] Analyze the changing trend of burden values, such as continuous increase or decrease, to provide a basis for optimizing decisions.

[0054] The present invention has achieved at least the following beneficial effects:

[0055] 1. The present invention comprehensively evaluates the impact of key processes on the construction period, cost and resource consumption of engineering projects, and improves project management efficiency and rationality of resource allocation through optimization strategies.

[0056] 2. The present invention can quantify the comprehensive impact of key processes on the overall project duration, cost and resources in multiple dimensions, overcoming the limitations of single-dimensional analysis of traditional methods.

[0057] 3. Through the dynamic adjustment mechanism, rapid response to real-time changes can be achieved, enhancing the adaptability of project management.

[0058] 4. Combine machine learning technology to provide intelligent optimization strategies, reducing reliance on experience-based decisions.

[0059] 5. Ultimately, it significantly improves project management efficiency, reduces construction delays, cost overruns and resource waste, and is applicable to a variety of scenarios in complex engineering project management.

[0060] Other advantages, objectives and features of the present invention will be described in the following description and will be apparent to those skilled in the art to some extent, or those skilled in the art may be taught from the practice of the present invention. The objectives and other advantages of the present invention may be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to make the purpose, technical solution and beneficial effects of the present invention clearer, the present invention provides the following drawings for illustration:

[0062] Figure 1 The present invention is a flowchart of a method for optimizing a key process based on burden values ​​in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0064] The burden value is the core concept of this method, which is used to quantify the impact of key processes on the overall project goals in multiple dimensions such as duration, cost and resources. The burden value reflects the burden and importance of key processes on project management by comprehensively evaluating the proportion of key processes in different dimensions and their influencing factors. Specifically, it includes dimensions such as duration burden value, cost burden value and resource burden value, which respectively represent the impact of key processes on the total duration, total cost and total resource consumption. The characteristics of burden value are multidimensionality, dynamics and relativity, which provide a quantitative basis for the formulation of subsequent optimization strategies.

[0065] The preferred key process optimization method based on burden value provided by the present invention is as follows: Figure 1 ,include:

[0066] Collect data related to key processes, including duration-related data, cost-related data, and resource-related data;

[0067] According to the collected data, the duration burden value, cost burden value and resource burden value of the key process are calculated respectively; the burden value refers to the proportion of the duration / cost / resources of the key process to the total duration / total cost / total resources of the project;

[0068] The weighted average method is used to calculate the comprehensive burden value of key processes, and a dynamic adjustment model for the comprehensive burden value is constructed to reflect the changes in construction period, cost and resource consumption over time in real time;

[0069] Based on the dynamic adjustment model, the burden values ​​of key processes are identified and counted to determine the changing trends of the burden values ​​of key processes with high burden values ​​in the overall process of the project, providing a basis for optimizing decisions.

[0070] The working principle and beneficial effects of the above technical solution are as follows: the key process optimization method based on burden value of the present invention extracts the weight coefficients and influencing factors of the duration, cost and resources of the key process from historical data through a machine learning model, calculates the burden values ​​of the duration, cost, resources and other dimensions respectively, and uses the weighted average method to calculate the comprehensive burden value. At the same time, a dynamic adjustment formula is introduced so that the comprehensive burden value can be updated in real time as the project progresses, reflecting the dynamic changes of the impact of the key process on the overall project. Based on this, high burden value processes are identified and optimization strategies are formulated, including resource priority allocation and execution order adjustment, so as to achieve dynamic optimization of key processes. The present invention can quantify the comprehensive impact of the key process on the duration, cost and resources of the overall project in multiple dimensions, overcoming the limitations of single-dimensional analysis of traditional methods; through a dynamic adjustment mechanism, a rapid response to real-time changes is achieved, and the adaptability of project management is enhanced; combined with machine learning technology, an intelligent optimization strategy is provided, reducing the reliance on experience-based decision-making; ultimately significantly improving project management efficiency, reducing construction delays, cost overruns and resource waste, and is suitable for a variety of scenarios of complex engineering project management.

[0071] In a preferred embodiment, collecting data related to key processes, including duration-related data, cost-related data, and resource-related data, includes:

[0072] The machine learning model is used to collect and extract the weight coefficients and influencing factors of the duration, cost and resources of key processes from historical data, including:

[0073] Construction period related data: Construction period T of key processes task 、The total duration of the project is T total , the weight coefficient W of the construction period burden value duration And the impact factor I of the construction period burden value duration ;

[0074] Cost-related data: cost of key processes C task 、The total cost of the project C total , the weight coefficient W of the cost burden value cost And the impact factor of cost burden value I cost ;

[0075] Resource-related data: resource consumption of key processes R task , the total resource consumption of the project R total , the weight coefficient W of resource burden value resource And the impact factor of resource burden value I resource ;

[0076] Among them, weights and impact factors are quantitatively obtained through machine learning.

[0077] The working principle and beneficial effects of the above technical solution are as follows: This technical solution adopts an innovative method to optimize the management of engineering projects, especially the management of the duration, cost and resource consumption of key processes. The core of this method is to use machine learning technology to extract the weight coefficients and influencing factors of the duration, cost and resources of key processes from historical data, and then calculate the burden value of each process. The working principle of this method can be summarized as the following steps: First, we collect detailed data related to key processes, including but not limited to the duration of key processes, the total duration of the project, the cost of key processes, the total cost of the project, and the resource consumption of key processes and the total resource consumption of the project. These data provide us with a quantitative basis for the impact of key processes on the entire project. Next, we use machine learning models to conduct in-depth analysis of these historical data, and statistically extract the weight coefficients and influencing factors of key processes in the three dimensions of duration, cost and resources. This step is achieved by training a machine learning model, which can identify and learn the complex relationships and patterns in the data, thereby providing a quantitative assessment of the importance and influence of each process in different dimensions. With these weight coefficients and influencing factors, we can calculate the duration burden value, cost burden value and resource burden value of each key process. These burden values ​​comprehensively reflect the degree of impact of key processes on the overall project goals, including the impact on total construction period, total cost and total resource consumption. The beneficial effects of this method are multifaceted. First, by quantifying the burden values ​​of key processes, project managers can more clearly identify the processes that are critical to the success of the project, thereby prioritizing the allocation of resources and attention. Secondly, this method can dynamically capture the real-time changing trends of key processes on the overall goals of the project, support adjustments as the project progresses, and enhance the adaptability of project management. In addition, the combination of machine learning technology provides intelligent optimization strategies, reduces dependence on empirical decisions, and improves the scientificity and accuracy of decision-making. Ultimately, this method significantly improves project management efficiency, reduces construction delays, cost overruns and resource waste, is suitable for a variety of scenarios in complex engineering project management, and has broad application prospects and practical value.

[0078] In a preferred embodiment, respectively calculating the duration burden value, cost burden value and resource burden value of the key process according to the collected data includes:

[0079] The duration burden value of the key process is calculated by the following formula:

[0080]

[0081] Among them, B duration Indicates the duration burden value, which is used to indicate the proportion of the key process duration in the total project duration and its impact on the project;

[0082] The cost burden value of the key process is calculated by the following formula:

[0083]

[0084] Among them, B cost Indicates the cost burden value, which is used to indicate the proportion of key process cost to total cost and its impact on the project;

[0085] The resource burden value of the key process is calculated by the following formula:

[0086]

[0087] Among them, B resource Indicates the resource burden value, which is used to indicate the proportion of key process resource consumption in the total resource consumption and its impact on the project.

[0088] The working principle and beneficial effects of the above technical solution are as follows: In this preferred embodiment, an innovative technical solution is proposed, which aims to provide accurate data support and decision-making basis for project management by quantitatively calculating the duration burden value, cost burden value and resource burden value of key processes. The solution first collects detailed data related to key processes, including key indicators such as duration, cost and resource consumption. Then, the machine learning model is used to conduct in-depth analysis of these data to extract the weight coefficients and influencing factors of duration, cost and resources. These weight coefficients and influencing factors are obtained through statistics and learning of historical project data, and can reflect the importance and influence of each process in different dimensions. Based on these extracted weight coefficients and influencing factors, the duration burden value, cost burden value and resource burden value of each key process are calculated respectively. The duration burden value reflects the proportion of the duration of the key process in the total duration of the project and its impact on the project; the cost burden value indicates the proportion of the cost of the key process in the total cost and its impact on the project; the resource burden value indicates the proportion of the resource consumption of the key process in the total resource consumption and its impact on the project. In this way, project managers can more clearly identify the processes that are critical to the success of the project, so as to prioritize the allocation of resources and attention. In addition, this method can dynamically capture the real-time changing trends of key processes in relation to the overall project goals, support adjustments as the project progresses, and enhance the adaptability of project management. It combines machine learning technology to provide intelligent optimization strategies, reduces reliance on empirical decision-making, and improves the scientific nature and accuracy of decision-making. Ultimately, this method significantly improves project management efficiency, reduces construction delays, cost overruns, and waste of resources. It is applicable to a variety of scenarios in complex engineering project management and has broad application prospects and practical value.

[0089] In a preferred embodiment, the weighted average method is used to calculate the comprehensive burden value of the key process, including the formula:

[0090] B total =αB duration +βB cost +γB resource

[0091] Among them, α, β, and γ are weight coefficients set according to project management requirements;

[0092] The dynamic adjustment model of comprehensive burden value is expressed as:

[0093] a i (t) = a i , 0 ―r a ·t·C task ·R task

[0094] Among them, a i (t) represents the comprehensive burden value of the i-th key process at time t, a i，0 represents the initial burden value of the i-th key process, r a Indicates the decay rate of the burden value over time. Combined with the dynamic formula, the comprehensive burden value can be updated in real time, further improving the accuracy of key process impact analysis.

[0095] The working principle and beneficial effects of the above technical solution are as follows: the comprehensive burden value of the key process is calculated by the weighted average method, and a dynamic adjustment model of the comprehensive burden value is introduced to reflect the changes in the burden value of the key process in real time. This method first collects the duration, cost and resource consumption data of the key process and uses these data to calculate the respective burden values. Then, the weighted average method is used to synthesize these burden values ​​into a comprehensive indicator, in which the weight coefficient reflects the relative importance of different burden types to the success of the project. In addition, in order to adapt to the dynamic changes in the project implementation process, this solution also introduces a dynamic adjustment model of the comprehensive burden value, which can update the burden value of the key process in real time to reflect the changes in its impact on the overall project goals. The working principle of this technical solution is to provide accurate data support and decision-making basis for project management through quantitative analysis and dynamic adjustment. The beneficial effects of this method include: Accurate evaluation: By comprehensively considering the duration, cost and resource consumption, a comprehensive process impact assessment is provided to project managers. Dynamic adaptability: The dynamic adjustment model enables project managers to adjust resource allocation and process plans in real time according to the progress of the project and changes in the external environment. Optimized decision-making: The calculation and dynamic adjustment of the comprehensive burden value provide a scientific basis for project optimization decisions, which helps to improve project management efficiency and project success rate. Risk control: By real-time monitoring of the burden value changes of key processes, project managers can promptly identify potential risks and take measures to control them. In short, this method significantly improves the scientificity and adaptability of project management by combining quantitative calculation and dynamic adjustment, which helps to achieve the optimization of project goals and effective control of risks.

[0096] In a preferred embodiment, dynamic evaluation and optimization includes:

[0097] (1) Initial assessment: Calculate the initial burden value based on the formula, identify key processes and their impact on the project, and identify processes with high burden values ​​as optimization targets.

[0098] (2) Dynamic monitoring: As the project progresses, the initial burden value, decay rate, resources, and cost data are updated in real time. The burden value is dynamically calculated and the changing trend is analyzed.

[0099] (3) Optimization suggestions: Resource reallocation: Prioritize resources for high-burden value processes to reduce their overall impact on the project. Process adjustment: Optimize the execution order or method of high-burden value processes.

[0100] In a preferred embodiment, identifying and counting the key process burden values ​​based on the dynamic adjustment model includes:

[0101] According to the dynamic adjustment model, the dynamic data of key processes are collected in real time and standardized, where the dynamic data includes construction period, cost, resource consumption and corresponding burden value;

[0102] The standardized dynamic data is used as training data (x i ,y i ), establish the support vector machine regression model:

[0103]

[0104] Among them, x i is the input feature vector, f(x) is the function output, and its goal is to fit the training data (x) as much as possible. i ,y i ), y i is the target burden value, a i is the Lagrange multiplier, K(x i , x) is the RBF kernel function, b is the bias term, where:

[0105]

[0106] Among them, σ is the width parameter of the kernel function;

[0107] Optimization objectives for establishing support vector machine regression models:

[0108] Among them, ‖w‖ 2 represents the regularization term of model complexity, C is the regularization parameter used to balance model complexity and fitting error, ξ i represents the i-th slack variable used to process the error of the data point, and n represents the total number of slack variables selected;

[0109] Using the training data (x i ,y i ) training the support vector machine regression model, optimizing the objective function and solving the Lagrange multiplier and the bias term to obtain a trained support vector machine regression model;

[0110] For the updated key process data x new , use the trained support vector machine regression model for prediction:

[0111]

[0112] Among them, y new is the predicted burden value;

[0113] Use the trained support vector machine regression model to dynamically update the burden value, count the burden value change trends of key processes, identify high-burden value processes, and mark them as high-burden value processes when the predicted burden value exceeds the preset threshold;

[0114] Analyze the changing trend of burden values, such as continuous increase or decrease, to provide a basis for optimizing decisions.

[0115] The working principle and beneficial effects of the above technical solution are as follows: In this preferred embodiment, a method based on a dynamic adjustment model is proposed to identify and count the burden values ​​of key processes. The method first collects dynamic data such as the construction period, cost, resource consumption, etc. of the key processes in real time, and standardizes these data. Then, a support vector machine regression (SVR) model is trained using these standardized data. The goal of the model is to fit the training data to predict the burden value of the process. Through training, an optimized SVR model is obtained, which can predict new key process data, thereby dynamically updating the burden value. In addition, the model can also count the burden value change trend of the key process and identify high burden value processes, that is, those processes whose predicted burden values ​​exceed the preset threshold. By analyzing the burden value change trend of these processes, whether it is continuously increasing or decreasing, it can provide a basis for optimizing decision-making for project management. The working principle of this method is to use machine learning technology to dynamically predict and adjust the burden value of the key process, thereby realizing refined control of project management. The beneficial effect of this method is that it can reflect the impact of the key process on the overall goal of the project in real time, and improve the adaptability and intelligence level of project management. By timely discovering and marking high-burden value processes, project managers can take corresponding optimization measures, such as adjusting resource allocation or improving execution strategies, to reduce construction delays, cost overruns, and resource waste. This not only improves the efficiency of project management, but also helps to increase the success rate of projects, and has important practical value for complex engineering project management.

[0116] Finally, it should be noted that the above preferred 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 through the above preferred embodiments, those skilled in the art should understand that various changes can be made in form and details without departing from the scope defined by the claims of the present invention.

Claims

1. A key process optimization method based on burden value, characterized in that: include: Collect data related to key processes, including duration-related data, cost-related data, and resource-related data; According to the collected data, the duration burden value, cost burden value and resource burden value of the key process are calculated respectively; the burden value refers to the proportion of the duration / cost / resources of the key process to the total duration / total cost / total resources of the project; The weighted average method is used to calculate the comprehensive burden value of key processes, and a dynamic adjustment model for the comprehensive burden value is constructed to reflect the changes in construction period, cost and resource consumption over time in real time; Based on the dynamic adjustment model, the burden values ​​of key processes are identified and counted to determine the changing trends of the burden values ​​of key processes with high burden values ​​in the overall process of the project, providing a basis for optimizing decisions.

2. The key process optimization method based on burden value according to claim 1 is characterized in that: Collect data related to key processes, including duration-related data, cost-related data, and resource-related data, including: The machine learning model is used to collect and extract the weight coefficients and influencing factors of the duration, cost and resources of key processes from historical data, including: Construction period related data: Construction period T of key processes task 、The total duration of the project is T total , the weight coefficient W of the construction period burden value duration And the impact factor I of the construction period burden value duration ; Cost-related data: cost of key processes C task 、The total cost of the project C total , the weight coefficient W of the cost burden value cost And the impact factor of cost burden value I cost ; Resource-related data: resource consumption of key processes R task , the total resource consumption of the project R total , the weight coefficient W of resource burden value resource And the impact factor of resource burden value I resource ; Among them, weights and impact factors are quantitatively obtained through machine learning.

3. The key process optimization method based on burden value according to claim 2 is characterized in that: Based on the collected data, the duration burden value, cost burden value and resource burden value of the key processes are calculated respectively, including: The duration burden value of the key process is calculated by the following formula: Among them, B duration Indicates the duration burden value, which is used to indicate the proportion of the key process duration in the total project duration and its impact on the project; The cost burden value of the key process is calculated by the following formula: Among them, B cost Indicates the cost burden value, which is used to indicate the proportion of key process cost to total cost and its impact on the project; The resource burden value of the key process is calculated by the following formula: Among them, B resource Indicates the resource burden value, which is used to indicate the proportion of key process resource consumption in the total resource consumption and its impact on the project.

4. The key process optimization method based on burden value according to claim 3 is characterized in that: The weighted average method used to calculate the comprehensive burden value of key processes includes the formula: B total =αB duration +βB cost +γB resource Among them, α, β, and γ are weight coefficients set according to project management requirements; The comprehensive burden value dynamic adjustment model is expressed as: a i (t)=a i，0 ―r a ·t·C task ·R task Among them, a i (t) represents the comprehensive burden value of the i-th key process at time t, a i，0 represents the initial burden value of the i-th key process, r a Indicates the decay rate of the burden value over time.

5. The key process optimization method based on burden value according to claim 1 is characterized in that: Identification and statistics of key process burden values ​​based on dynamic adjustment models include: According to the dynamic adjustment model, the dynamic data of key processes are collected in real time and standardized, where the dynamic data includes construction period, cost, resource consumption and corresponding burden value; The standardized dynamic data is used as training data (x i ,y i ), establish the support vector machine regression model: Among them, x i is the input feature vector, f(x) is the function output, and its goal is to fit the training data (x) as much as possible. i ,y i ), y i is the target burden value, a i is the Lagrange multiplier, K(x i , x) is the RBF kernel function, b is the bias term, where: Among them, σ is the width parameter of the kernel function; Optimization objectives for establishing support vector machine regression models: Among them, ‖w‖ 2 represents the regularization term of model complexity, C is the regularization parameter used to balance model complexity and fitting error, ξ i represents the i-th slack variable used to process the error of the data point, and n represents the total number of slack variables selected; Using the training data (x i ,y i ) training the support vector machine regression model, optimizing the objective function and solving the Lagrange multiplier and the bias term to obtain a trained support vector machine regression model; For the updated key process data x new , use the trained support vector machine regression model for prediction: Among them, y new is the predicted burden value; Use the trained support vector machine regression model to dynamically update the burden value, count the burden value change trends of key processes, identify high-burden value processes, and mark them as high-burden value processes when the predicted burden value exceeds the preset threshold; Analyze the changing trend of burden values, such as continuous increase or decrease, to provide a basis for optimizing decisions.

Images