Project project budget generation method, system, equipment and medium

Abstract

The invention provides a project engineering budget generation method, system and device and a medium. The method comprises the steps of obtaining historical budget data of all engineering projects; determining cost performance indexes of different engineering projects, and performing association analysis through all the cost performance indexes in combination with different engineering characteristics of the engineering projects to obtain cost conversion coefficients of the different engineering characteristics; dividing the target engineering project into a plurality of engineering sub-projects, and determining a feature association relationship of each engineering sub-project through all the cost conversion coefficients; obtaining a cost risk, constructing a risk distribution model of each project sub-project, and further generating a cost hyper-branched rate of each project sub-project at different construction nodes; and determining confidence cost information of each project sub-project according to all the cost hyperbranched rates and all the feature association relationships, and further updating a project budget table of the target project. According to the scheme, the project budget can be dynamically adjusted along with the change of the construction progress.

Description

Technical Field

[0001] This application relates to the technical field of budget estimate generation. More specifically, this application relates to a method, system, device, and medium for generating a project engineering budget estimate. Background Art

[0002] Budget estimate generation is a technology based on big data analysis and intelligent algorithms, which is widely used in fields such as engineering projects, manufacturing, and financial forecasting; by analyzing historical data, existing conditions, and project requirements, it quickly estimates key indicators such as project budgets, costs, and resource requirements; traditional budget estimate generation relies on manual experience and cumbersome manual calculations, with low efficiency and prone to errors, while modern budget estimate generation technologies combine cutting-edge technologies such as machine learning, artificial intelligence, and data mining, and can provide more accurate and reliable estimation results in a very short time.

[0003] In project engineering management, budget estimate generation obtains the preliminary budget of a project quickly for the project manager by inputting basic information of the project, such as construction plans, quantities of work, equipment requirements, etc., and combining with the use of historical project data and algorithm models for calculation; its purpose is to efficiently and accurately generate budget estimate data for engineering projects to support investment decisions and budget control; the generation of project engineering budget estimates not only improves the efficiency and accuracy of engineering cost estimation, but also provides data support for the whole life cycle cost management of the project, helps to reduce investment risks, and improves the scientificity and controllability of project management; in the existing project engineering budget estimate generation process, a statistical regression model is usually used to form a cost prediction formula through regression analysis of historical project data, and then budget estimate generation is realized. However, this method is based on the assumption that engineering costs increase according to a fixed relationship, so the generated budget estimate information lacks a dynamic adjustment mechanism for construction progress (for example, if bad weather or material shortages are encountered during construction, this method cannot adjust the cost estimate according to the actual situation). Therefore, how to dynamically adjust the project engineering budget estimate according to the change of construction progress has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides a method, system, device, and medium for generating a project engineering budget estimate, which can dynamically adjust the project engineering budget estimate according to the change of construction progress.

[0005] In a first aspect, this application provides a method for generating a project engineering budget estimate, including the following steps: Obtain the historical budget estimate data of all engineering projects; Determine the cost performance indices of different engineering projects based on the historical budget estimate data, and then conduct correlation analysis through all the cost performance indices combined with different engineering characteristics of the engineering projects to obtain the cost conversion coefficients under different engineering characteristics during construction; Divide the target engineering project into multiple engineering sub - projects based on the tree - structure management model, and determine the characteristic correlation relationship between each engineering sub - project and the engineering cost through all cost conversion coefficients; Obtain the cost risks during engineering construction, construct the risk distribution model of each engineering sub - project according to the distribution probability of cost risks in each engineering sub - project, and then generate the cost over - run rate of each engineering sub - project at different construction nodes in combination with the construction progress of different construction nodes; Determine the confidence cost information of each engineering sub - project according to the cost over - run rate of the engineering cost of each engineering sub - project at different construction nodes and the characteristic correlation relationship between each engineering sub - project and the engineering cost, and then update the engineering budget statement of the target engineering project at different construction nodes in real - time through all the confidence cost information.

[0006] In some embodiments, determining the cost performance index of different engineering projects based on the historical budget data specifically includes: Obtain the budget cost and actual cost of each engineering project from the historical budget data; Determine the cost performance index of each engineering project through the budget cost and the actual cost.

[0007] In some embodiments, performing correlation analysis by combining all cost performance indices with different engineering characteristics of the engineering project to obtain the cost conversion coefficients under different engineering characteristics during construction specifically includes: Obtain the engineering characteristic information of all engineering projects under all engineering characteristics; Determine the characteristic influence degree between each engineering characteristic and the engineering cost through all engineering characteristic information and all cost performance indices; Determine the cost conversion coefficients under different engineering characteristics during construction through all characteristic influence degrees.

[0008] In some embodiments, determining the characteristic correlation relationship between each engineering sub - project and the engineering cost through all cost conversion coefficients specifically includes: Obtain the budget cost range of each engineering sub - project; Determine the cost deviation range of each engineering sub - project through all cost conversion coefficients and the budget cost range of each engineering sub - project; Determine the characteristic correlation relationship between each engineering sub - project and the engineering cost through all cost deviation ranges.

[0009] In some embodiments, constructing the risk distribution model of each engineering sub - project according to the distribution probability of cost risks in each engineering sub - project, and then generating the cost over - run rate of each engineering sub - project at different construction nodes in combination with the construction progress of different construction nodes specifically includes: Determine the distribution probability curve of cost risks at different construction nodes for each engineering sub - project; Construct the risk distribution model for each engineering sub - project according to the distribution probability curve; Generate the cost fluctuation range of each engineering sub - project at different construction nodes through the risk distribution model; Generate the cost over - run rate of each engineering sub - project at different construction nodes based on the cost fluctuation range of each engineering sub - project at different construction nodes and the construction progress of different construction nodes.

[0010] In some embodiments, determining the confidence cost information of each engineering sub - project according to the cost over - run rate of the engineering cost of each engineering sub - project at different construction nodes and the characteristic correlation relationship between each engineering sub - project and the engineering cost specifically includes: Determine the characteristic cost of each engineering sub - project through the characteristic correlation relationship between each engineering sub - project and the engineering cost; Determine the confidence cost information of each engineering sub - project according to the cost over - run rate of the engineering cost of each engineering sub - project at different construction nodes and all characteristic costs.

[0011] In some embodiments, the tree - structure management model adopts the work breakdown structure.

[0012] In a second aspect, the present application provides a project engineering budget generation system, including: An acquisition module, configured to acquire the historical budget data of all engineering projects; A processing module, configured to determine the cost performance index of different engineering projects according to the historical budget data, and then perform correlation analysis by combining all cost performance indexes with different engineering characteristics of the engineering projects to obtain the cost conversion coefficient under different engineering characteristics during construction; The processing module is further configured to divide the target engineering project into multiple engineering sub - projects based on the tree - structure management model, and determine the characteristic correlation relationship between each engineering sub - project and the engineering cost through all cost conversion coefficients; The processing module is further configured to obtain the cost risk during engineering construction, construct the risk distribution model of each engineering sub - project according to the distribution probability of the cost risk in each engineering sub - project, and then generate the cost over - run rate of each engineering sub - project at different construction nodes in combination with the construction progress of different construction nodes; An execution module, configured to determine the confidence cost information of each engineering sub - project according to the cost over - run rate of the engineering cost of each engineering sub - project at different construction nodes and the characteristic correlation relationship between each engineering sub - project and the engineering cost, and then update the engineering budget table of the target engineering project at different construction nodes in real - time through all the confidence cost information.

[0013] In a third aspect, the present application provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned project engineering budget generation method are implemented.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned project engineering budget generation method are implemented.

[0015] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects: In the project engineering budget generation method, system, device, and medium provided by the present application, historical budget data of all engineering projects are obtained; cost performance indices of different engineering projects are determined based on the historical budget data, and then correlation analysis is performed by combining all the cost performance indices with different engineering characteristics of the engineering projects to obtain cost conversion coefficients under different engineering characteristics during construction; the target engineering project is divided into multiple engineering sub-projects based on a tree structure management model, and the characteristic correlation relationship between each engineering sub-project and the project cost is determined through all the cost conversion coefficients; the cost risk during project construction is obtained, and a risk distribution model for each engineering sub-project is constructed according to the distribution probability of the cost risk in each engineering sub-project, and then the cost overrun rate of each engineering sub-project at different construction nodes is generated by combining the construction progress of different construction nodes; the confidence cost information of each engineering sub-project is determined according to the cost overrun rate of the project cost of each engineering sub-project at different construction nodes and the characteristic correlation relationship between each engineering sub-project and the project cost, and then the engineering budget table of the target engineering project at different construction nodes is updated in real time through all the confidence cost information.

[0016] It can be seen that in this application, first, historical budgetary estimate data of all engineering projects are obtained; after determining the cost control efficiency of different engineering projects based on the historical budgetary estimate data (i.e., cost performance index), the cost conversion coefficients under different engineering characteristics during construction are then determined. Through the cost conversion coefficients, the historical cost data under different engineering characteristics are converted into cost estimate values applicable to the current project, thereby ensuring that the budgetary estimate can be dynamically adjusted with the change of the construction progress. Subsequently, the characteristic correlation relationship between each engineering sub-project and the project cost is determined through all the cost conversion coefficients, so as to clarify how the cost of the engineering sub-project changes with specific engineering characteristics (such as structural type, construction method, geographical conditions, etc.). Then, when the construction process changes (such as the project is adjusted to a steel structure instead of a concrete structure), the system can quickly adjust the budgetary estimate to match the new characteristics. Then, after constructing the risk distribution model of each engineering sub-project through cost risks, the cost overrun rate of each engineering sub-project at different construction nodes is generated in combination with the construction progress of different construction nodes, thereby quantifying the cost deviation at different construction nodes. Through constructing the cost risk distribution model of each sub-project, the system can continuously predict future cost deviations according to the progress of the construction (for example, when the construction period is delayed due to weather impact at a certain construction node, the system can calculate the possible impact of the delay on the subsequent labor cost and reflect this change in the budgetary estimate in advance). Finally, the confidence cost information of each engineering sub-project is determined according to the cost overrun rate of the project cost of each engineering sub-project at different construction nodes and the characteristic correlation relationship between each engineering sub-project and the project cost, that is, by calculating the cost overrun rate of each sub-project at different construction nodes and combining historical data and the current construction situation to reflect the most likely actual cost at a certain construction node. Then, the engineering budgetary estimate table of the target engineering project at different construction nodes is updated in real time through all the confidence cost information. In summary, by adopting the solution of this application, the engineering budgetary estimate can be dynamically adjusted with the change of the construction progress. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic flow chart of a method for generating a project engineering budgetary estimate according to some embodiments of the present application; Figure 2 is a schematic flow chart of determining a cost conversion coefficient according to some embodiments of the present application; Figure 3 is a schematic structural diagram of a hierarchical structure according to some embodiments of the present application; Figure 4 is a schematic structural diagram of a project engineering budgetary estimate generation system according to some embodiments of the present application; Figure 5 is an internal structural diagram of a computer device for implementing the method for generating a project engineering budgetary estimate according to some embodiments of the present application. Specific Embodiments

[0018] To better understand the technical solutions in this embodiment, the technical solutions in this embodiment will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0019] Refer to Figure 1 , which is a schematic flowchart of a method for generating a project engineering budget estimate according to some embodiments of the present application. The method 100 for generating a project engineering budget estimate mainly includes the following steps: In step 101, historical budget estimate data of all engineering projects is obtained.

[0020] Specifically, the historical budget estimate data of all engineering projects can be obtained from the project management system; it should be noted that the present application performs data interaction with the project management system through an API interface, so as to automatically obtain the budget estimate information of all engineering projects, and then use the set composed of the budget estimate information of all engineering projects in the project management system as the historical budget estimate data in the present application. In addition, the historical budget estimate data refers to the estimated data based on the budget and cost estimation experience of previous similar projects during the project execution process, and it includes the budget estimate cost, actual cost, and other relevant expense details of the engineering project.

[0021] In step 102, the cost performance index of different engineering projects is determined based on the historical budget estimate data, and then correlation analysis is performed by combining all the cost performance indexes with different engineering characteristics of the engineering projects to obtain the cost conversion coefficient under different engineering characteristics during construction.

[0022] In some embodiments, the determination of the cost performance index of different engineering projects based on the historical budget estimate data can be implemented by the following steps: Obtain the budget estimate cost and actual cost of each engineering project from the historical budget estimate data; Determine the cost performance index of each engineering project through the budget estimate cost and the actual cost.

[0023] In specific implementation, determining the cost performance index of each engineering project based on the estimated cost and the actual cost can be achieved in the following manner, that is: taking the ratio of the estimated cost to the actual cost of each engineering project as the cost performance index of the corresponding engineering project. In other embodiments, other methods can also be used for determination, which are not limited herein. It should be noted that the estimated cost referred to in this application means the total estimated cost predicted and calculated based on factors such as the design, scale, and resource allocation of the engineering project before the start of the engineering project; the actual cost means the sum of all incurred costs during the implementation of the engineering project, which includes materials, labor, equipment, management, and other direct or indirect costs at each stage of the project. In addition, the cost performance index is an indicator used to evaluate the effect of project cost control. The cost control efficiency of the corresponding engineering project can be measured by the cost performance index. The larger the cost performance index, the higher the cost control efficiency of the corresponding engineering project; the smaller the cost performance index, the lower the cost control efficiency of the corresponding engineering project.

[0024] In some embodiments, with reference to Figure 2 As shown, this figure is a schematic flowchart of determining the cost conversion coefficient shown in some embodiments of this application. Obtaining the cost conversion coefficient under different engineering characteristics during construction through correlation analysis of all cost performance indices in combination with different engineering characteristics of the engineering project can be achieved through the following steps: First, in 1021, obtain the engineering characteristic information of all engineering projects under all engineering characteristics. Then, in 1022, determine the characteristic influence degree between each engineering characteristic and the engineering cost through all the engineering characteristic information and all the cost performance indices. Finally, in 1023, determine the cost conversion coefficient under different engineering characteristics during construction through all the characteristic influence degrees.

[0025] It should be noted that the engineering characteristic refers to the key variables describing the target engineering project. The engineering characteristics in this application include: project scale, engineering type, construction environment, construction difficulty, and resource allocation. In addition, the engineering characteristic information refers to the relevant information that quantifies the above engineering characteristics in the form of data. As a preferred embodiment, the one-hot encoding technology in the prior art can be used to quantify all the engineering characteristics of each engineering project into the corresponding engineering characteristic information. Among them, one-hot encoding is a method of converting categorical variables (such as categorical data) into a binary format. For example: a feature (engineering characteristic) with multiple original categories is converted into a vector (engineering characteristic information) composed of multiple binary bits (0 or 1). Therefore, the engineering characteristic information includes the engineering characteristic values of each engineering characteristic of the corresponding engineering project. In other embodiments, other methods can also be used for acquisition, which are not limited herein.

[0026] When specifically implemented, the feature influence degree between each engineering feature and the engineering cost can be determined by all engineering feature information and all cost performance indexes in the following way: First, select an engineering feature, and obtain the engineering feature values of this engineering feature in all engineering projects from all engineering feature information. Then, select an engineering project as the selected engineering project, determine the feature fluctuation amount of the selected engineering project under this engineering feature through the engineering feature values of this engineering feature in all engineering projects, determine the performance fluctuation amount of the selected engineering project through the cost performance indexes of all engineering projects, continue to determine the feature fluctuation amounts and performance fluctuation amounts of the remaining engineering projects, and finally, take the sum of the products of the feature fluctuation amounts and performance fluctuation amounts of all engineering projects; determine the square root of the product of the sum of the squares of the feature fluctuation amounts of all engineering projects and the sum of the squares of the performance fluctuation amounts of all engineering projects, and take the value obtained by comparing the above results as the feature influence degree between this engineering feature and the engineering cost. Repeat the above steps to determine the feature influence degrees between the remaining engineering features and the engineering cost; where, when specifically implemented, the feature fluctuation amount of the selected engineering project under this engineering feature can be determined through the engineering feature values of this engineering feature in all engineering projects in the following way: Determine the average value of all engineering feature values of this engineering feature, and then take the difference between the engineering feature value of the selected engineering project and the average value of all engineering feature values as the feature fluctuation amount of the selected engineering project under this engineering feature; when specifically implemented, the performance fluctuation amount of the selected engineering project can be determined through the cost performance indexes of all engineering projects in the following way: Determine the average value of the cost performance indexes of all engineering projects, and then take the difference between the cost performance index of the selected engineering project and the average value of all cost performance indexes as the performance fluctuation amount of the selected engineering project.

[0027] It should be noted that the feature influence degree in this application is an index that measures the relationship strength between a certain engineering feature (such as project scale, engineering type, construction environment, etc.) and the engineering cost. The greater the feature influence degree, the higher the relationship strength between the corresponding engineering project and the engineering cost. The smaller the feature influence degree, the lower the relationship strength between the corresponding engineering project and the engineering cost. The feature fluctuation amount is used to measure the change degree of a certain engineering feature in different engineering projects, and can reflect the influence degree of the fluctuation of the corresponding engineering feature on the engineering cost performance through the feature fluctuation amount. The greater the feature fluctuation amount, the higher the influence degree of the fluctuation of the corresponding engineering feature on the engineering cost performance. The smaller the feature fluctuation amount, the lower the influence degree of the fluctuation of the corresponding engineering feature on the engineering cost performance. The performance fluctuation amount measures the fluctuation degree of the cost performance index of each engineering project relative to the average cost performance index of all engineering projects, and can reflect the change degree of the cost performance index through the performance fluctuation amount. The greater the performance fluctuation amount, the higher the change degree of the cost performance index. The smaller the performance fluctuation amount, the lower the change degree of the cost performance index.

[0028] In specific implementation, the cost conversion coefficient under different engineering features during construction can be determined through all feature influence degrees in the following way: First, select an engineering feature, determine the result after taking the feature influence degree of this engineering feature as the exponent of the natural constant e, and then take the reciprocal of the above result as the cost conversion coefficient under this engineering feature during construction. Repeat the above steps to determine the cost conversion coefficient under the remaining engineering features. It should be noted that the cost conversion coefficient in this application refers to the coefficient adjusted based on the relationship between the engineering feature and the engineering cost, and can reflect the adjustment range of the cost under the corresponding engineering feature through the cost conversion coefficient. The greater the cost conversion coefficient, the greater the adjustment range of the cost under the corresponding engineering feature. The smaller the cost conversion coefficient, the smaller the adjustment range of the cost under the corresponding engineering feature.

[0029] In step 103, based on the tree - shaped structure management model, the target engineering project is divided into multiple engineering sub - projects, and the feature association relationship between each engineering sub - project and the engineering cost is determined through all cost conversion coefficients.

[0030] It should be noted that the tree structure management model described in this application adopts the Work Breakdown Structure (WBS); in specific implementation, dividing the target engineering project into multiple engineering sub-projects based on the tree structure management model can be achieved in the following manner, that is: First, set the hierarchical structure of the target engineering project, then, define the engineering sub-projects in each level of the hierarchical structure; finally, establish a tree structure diagram, and then generate multiple engineering sub-projects of the target engineering project; preferably, the hierarchical structure of the target engineering project can be set as the top layer, the middle layer, and the bottom layer. Refer to Figure 3 As shown, this figure is a schematic structural diagram of the hierarchical structure shown in some embodiments of this application. Among them, the top layer, that is: the entire target engineering project, represents the overall of the project. The middle layer, that is: each main engineering module or stage, is usually the key part after disassembling the project as a whole; for example, the design stage, the construction stage, the equipment installation stage, etc. The bottom layer, that is: specific sub-projects or tasks, are usually more refined specific work units, such as civil engineering construction, equipment procurement, on-site installation, etc.

[0031] It should be noted that each level in the tree structure corresponds to engineering tasks or sub-projects with different granularities; according to the complexity of the target engineering project, the engineering sub-projects can be further divided into more small units. Therefore, in specific implementation, defining the engineering sub-projects in each level can be achieved in the following manner, that is: First, determine the scope, objectives, resource allocation, etc. of the target engineering project, and then, decompose the target engineering project into multiple large categories of tasks or modules, and these modules represent the main components of the project (such as design, construction, equipment installation, etc.). Finally, refine each large category of tasks into smaller tasks or sub-projects. For example, the construction stage can be divided into sub-projects such as civil engineering construction, structural construction, electrical construction, etc.; in addition, as a preferred embodiment, establishing a tree structure diagram and then generating multiple engineering sub-projects of the target engineering project can be achieved in the following manner, that is: First, in the Microsoft Project software, select "New Project" to create a blank project file, and then, enter the start date, end date, and working calendar of the project in the basic settings of the project. You can select "Project Information" in the "Project" menu to set the start and end times of the project. Subsequently, in the "Task" view, enter the main tasks (parent nodes) of the project. For example, the engineering project can be decomposed into several main stages, such as the "design stage", the "construction stage", the "acceptance stage", etc. Then, under each main task, continue to enter more specific sub-tasks or sub-projects to form a tree structure. For example, the "construction stage" can be divided into "civil engineering construction", "equipment installation", etc. In other embodiments, other methods can also be used to generate it, which are not limited here.

[0032] In some embodiments, the characteristic association relationship between each engineering sub - project and the engineering cost can be determined by all cost conversion factors through the following steps: Obtain the budget cost range of each engineering sub - project; Determine the cost deviation range of each engineering sub - project through all cost conversion factors and the budget cost range of each engineering sub - project; Determine the characteristic association relationship between each engineering sub - project and the engineering cost through all cost deviation ranges.

[0033] It should be noted that the budget cost range mentioned in this application refers to the estimated range of the expected cost of each engineering sub - project in project management. It is usually a total cost estimate range obtained after a detailed analysis of resource requirements, time arrangements, personnel arrangements, etc. in the project planning stage. As a preferred embodiment, the budget cost range of each engineering sub - project can be determined by the three - point estimation method in the prior art. The three - point estimation method is an estimation technique commonly used in project management to predict project costs. It calculates a cost range by considering three possible scenarios (the most optimistic, the most likely, and the most pessimistic scenarios). Specifically, when implementing, the budget cost range of each engineering sub - project is determined by the three - point estimation method in the prior art, that is: First, estimate the most optimistic cost according to the most ideal situation of the project (sufficient resources, no external interference), estimate the most likely cost according to the currently known information and actual situation, and estimate the most pessimistic cost according to the most unfavorable situation (resource shortage, equipment failure). Then, the result of dividing the sum of the most optimistic cost plus 4 times the most likely cost plus the most pessimistic cost by 6 is used as the expected cost of the corresponding engineering sub - project. Subsequently, after determining the result of dividing the difference between the most optimistic cost and the most pessimistic cost by 6 as the cost fluctuation range of the corresponding engineering sub - project, the value obtained by subtracting twice the cost fluctuation range from the expected cost is used as the lower limit of the range, and the value obtained by adding twice the cost fluctuation range to the expected cost is used as the upper limit of the range, thereby obtaining the budget cost range of each engineering sub - project. In other embodiments, other methods can also be used to determine it, which is not limited here.

[0034] In specific implementation, the cost deviation range of each engineering sub - project can be determined by all cost conversion coefficients and the budget cost range of each engineering sub - project in the following way: First, determine the average value of the cost conversion coefficients of each engineering feature. Then, select the budget cost range of an engineering sub - project, multiply the upper limit of the budget cost range by the value of the average value as the new upper limit, multiply the lower limit of the budget cost range by the value of the average value as the new lower limit, and then use the obtained range as the cost deviation range of this engineering sub - project. Repeat the above steps to determine the cost deviation ranges of the remaining engineering sub - projects. It should be noted that in this application, the cost deviation range refers to the new cost deviation interval determined by the product of the budget cost range of each engineering sub - project and the cost conversion coefficient, and the cost deviation interval can reflect the adjustment range of the project cost under different construction conditions.

[0035] Preferably, the characteristic association relationship between each engineering sub - project and the project cost can be determined by all cost deviation ranges through the multiple regression analysis algorithm in the prior art. The multiple regression analysis is a statistical technique used to explore the relationship between a dependent variable (e.g., project cost deviation) and multiple independent variables (e.g., engineering characteristics such as project scale, construction environment, resource allocation, etc.). As a preferred embodiment, first, select an engineering sub - project, use all engineering characteristics as the independent variables of the multiple regression model, and use the cost deviation range of this engineering sub - project as the dependent variable of the multiple regression model, and then construct a multiple regression model. Subsequently, input the multiple regression model into the scikit - learn library in Python, and then use the scikit - learn library to fit the input data combined with the least - squares method to generate all regression coefficients in the multiple regression model, and then use all regression coefficients as the characteristic association relationship between this engineering sub - project and the project cost. Repeat the above steps to determine the characteristic association relationships between the remaining engineering sub - projects and the project cost.

[0036] It should be noted that in this application, the characteristic association relationship refers to a quantitative value describing the influence degree of the engineering characteristics (such as project scale, construction environment, resource allocation, etc.) on the project cost deviation. The larger the characteristic association relationship, the greater the influence degree of the engineering characteristics on the project cost deviation; the smaller the characteristic association relationship, the smaller the influence degree of the engineering characteristics on the project cost deviation.

[0037] In step 104, obtain the cost risk during project construction, construct the risk distribution model of each engineering sub - project according to the distribution probability of the cost risk in each engineering sub - project, and then generate the cost over - run rate of each engineering sub - project at different construction nodes in combination with the construction progress of different construction nodes.

[0038] It should be noted that the cost risk described in this application refers to the factors that cause the cost to deviate from the estimated budget during the implementation of the engineering project, specifically including: resource allocation risk, project management risk, construction site risk, and project external dependence risk.

[0039] In some embodiments, constructing the risk distribution model of each engineering sub-project according to the distribution probability of cost risk in each engineering sub-project, and then generating the cost overrun rate of each engineering sub-project at different construction nodes in combination with the construction progress of different construction nodes can be achieved by the following steps: Determine the distribution probability curve of cost risk in each engineering sub-project at different construction nodes; Construct the risk distribution model of each engineering sub-project according to the distribution probability curve; Generate the cost fluctuation range of each engineering sub-project at different construction nodes through the risk distribution model; Generate the cost overrun rate of each engineering sub-project at different construction nodes based on the cost fluctuation range of each engineering sub-project at different construction nodes and the construction progress of different construction nodes.

[0040] As a preferred embodiment, determining the distribution probability curve of cost risk in each engineering sub-project at different construction nodes can be achieved in the following manner, that is: assume that the distribution probability of the cost risk in all engineering sub-projects is a normal distribution (the distribution probability of the cost risk in each engineering sub-project), describe the distribution probability of the corresponding cost risk in all engineering sub-projects through the normal distribution model, and then generate the distribution probability curve of the cost risk in each engineering sub-project at different construction nodes through the Monte Carlo simulation in the prior art. Specifically, when implementing, after setting the number of simulations in the NumPy software, input the normal distribution model of each cost risk in all engineering sub-projects into the NumPy software, and then perform random sampling on each risk factor, calculate the total cost of each simulation. Subsequently, use the Matplotlib tool to draw the probability distribution diagram of the simulation results of each engineering sub-project, so as to use the probability distribution diagram as the distribution probability curve of the cost risk in the corresponding engineering sub-project at different construction nodes. In other embodiments, other methods can also be used to determine, which is not limited here.

[0041] It should be noted that the distribution probability curve described in this application refers to the probability distribution of the cost risk in the engineering sub-project at different construction nodes, which reflects the change probability of cost risk factors (such as resource allocation risk, project management risk, construction site risk, project external dependence risk) at each construction node.

[0042] In specific implementation, constructing the risk distribution model of each engineering sub - project according to the distribution probability curve can be achieved by the following method: First, perform Monte Carlo simulation on the cost risk of each engineering sub - project at each construction node through the distribution probability curve to obtain the corresponding cost risk sample data, and assume that the cost risk sample data follows a standard normal distribution; Subsequently, based on the probability density function of the normal distribution, calculate the probability density values of each sample point (i.e., each construction node of each engineering sub - project), and then construct a risk likelihood function by taking the logarithmic sum of all probability density values; Then, adopt the maximum likelihood estimation method in the prior art to adjust and compare the risk likelihood function values corresponding to different distribution parameter combinations, and then determine the distribution parameter combination that can make the risk likelihood function reach the maximum value as the risk distribution parameter of the corresponding engineering sub - project; Subsequently, substitute the risk distribution parameter into the standard normal distribution model to generate the risk distribution model of each engineering sub - project; As a preferred embodiment, the risk distribution parameter may include the central tendency parameter of the risk distribution and the volatility parameter of the risk distribution, where the central tendency parameter of the risk distribution can be determined by performing arithmetic mean operation on the cost risk sample data, and the volatility parameter of the risk distribution can be determined by performing arithmetic mean operation after squaring the difference between each cost risk sample data and the central tendency parameter. In other embodiments, other methods can also be used to determine it, which is not limited here.

[0043] It should be noted that the function value of the risk likelihood function in this application is used to characterize the overall possibility of observing the current cost risk sample data under different distribution parameter conditions; In addition, the risk distribution model is a model obtained by generating a risk likelihood function from the distribution probability curve and then determining the optimal risk distribution parameter through the maximum likelihood estimation method, and the probability distribution of the cost risk of each engineering sub - project changing with the construction node can be represented by the risk distribution model.

[0044] In specific implementation, the cost fluctuation range of each engineering sub - project at different construction nodes generated by the risk distribution model can be achieved in the following way, that is: First, generate the cost risk rate of the corresponding engineering sub - project at each construction node through the risk distribution model. Then, obtain the mean and standard deviation of the project cost in the risk distribution model. Subsequently, determine the result of multiplying the standard deviation by 2 times the cost risk rate and adding it to the mean as the upper limit of the interval, and determine the mean minus the result of multiplying the standard deviation by 2 times the cost risk rate as the lower limit of the interval. Furthermore, take the numerical range composed of the upper limit and the lower limit of the interval as the cost fluctuation range of the corresponding construction node, so as to obtain the cost fluctuation range of each engineering sub - project at different construction nodes. It should be noted that in this application, the cost fluctuation range refers to the fluctuation range of the project cost at different construction nodes generated according to the risk distribution model.

[0045] In specific implementation, the cost over - run rate of each engineering sub - project at different construction nodes generated based on the cost fluctuation range of each engineering sub - project at different construction nodes and the construction progress at different construction nodes can be achieved in the following way, that is: First, obtain the construction progress of each construction node, select a construction node, and take the negative result of subtracting the construction progress of this construction node from the natural constant 1 as the result of the exponent of the natural constant e as the progress impact factor of this construction node. Then, obtain the budget cost of this construction node, and determine the average cost in the cost fluctuation range of this construction node. Determine the result of dividing the result of subtracting the budget cost from the average cost by the budget cost, and then multiply the result by the progress impact factor as the cost over - run rate of this construction node. Repeat the above steps to determine the cost over - run rates of the remaining construction nodes, so as to obtain the cost over - run rates of each engineering sub - project at different construction nodes. It should be noted that in this application, the cost over - run rate refers to the proportion of the actual cost exceeding the budget cost at a certain construction node, which is usually used to measure the cost control situation of the engineering sub - project at different construction nodes. The larger the cost over - run rate, the worse the cost control situation of the engineering sub - project at the corresponding construction node, and the smaller the cost over - run rate, the better the cost control situation of the engineering sub - project at the corresponding construction node.

[0046] In step 105, determine the confidence cost information of each engineering sub - project according to the cost over - run rate of the engineering cost of each engineering sub - project at different construction nodes and the characteristic correlation relationship between each engineering sub - project and the engineering cost, and then update the engineering budget table of the target engineering project at different construction nodes in real - time through all the confidence cost information.

[0047] In some embodiments, determining the confidence cost information of each engineering sub - project according to the cost over - run rate of the engineering cost of each engineering sub - project at different construction nodes and the characteristic correlation relationship between each engineering sub - project and the engineering cost is implemented by the following steps: Determine the characteristic cost of each engineering sub - project through the characteristic correlation relationship between each engineering sub - project and the engineering cost; Determine the confidence cost information of each engineering sub - project according to the cost over - run rate of the engineering cost of each engineering sub - project at different construction nodes and all the characteristic costs.

[0048] It should be noted that the characteristic correlation relationship corresponds to multiple regression coefficients, and each regression coefficient has a uniquely corresponding engineering characteristic; therefore, in specific implementation, determining the cost information of each engineering sub - project through the characteristic correlation relationship between each engineering sub - project and the engineering cost can be implemented in the following way, that is: First, select an engineering sub - project, obtain the engineering characteristic information of this engineering sub - project, then, after multiplying all the engineering characteristic values in the engineering characteristic information by the corresponding regression coefficients in the characteristic correlation relationship, the value obtained by adding all the results is used as the characteristic cost of this engineering sub - project. Repeat the above steps to determine the characteristic costs of the remaining engineering sub - projects; it should be noted that the characteristic cost in this application is an estimated cost calculated according to the characteristic information (such as project scale, construction environment, resource allocation, etc.) of each engineering sub - project and the regression coefficients in the characteristic correlation relationship.

[0049] In specific implementation, determining the confidence cost information of each engineering sub - project according to the cost over - run rate of the engineering cost of each engineering sub - project at different construction nodes and all the characteristic costs can be implemented in the following way, that is: First, select an engineering sub - project, select a construction node of this engineering sub - project as the selected construction node, then, the value obtained by multiplying the characteristic cost of this engineering sub - project by the result of adding 1 to the cost over - run rate of the selected construction node is used as the confidence cost value of this engineering sub - project at the selected construction node. Continue to determine the confidence cost values of this engineering sub - project at the remaining construction nodes, and then the set composed of all the confidence cost values is used as the confidence cost information of this engineering sub - project. Repeat the above steps to determine the confidence cost information of the remaining engineering sub - projects. It should be noted that the confidence cost information in this application is an information set generated by combining the cost over - run rate of each engineering sub - project at different construction nodes and the characteristic cost, representing the cost pre - estimate (confidence cost value) of the engineering sub - project at different construction nodes.

[0050] In specific implementation, the engineering budget sheet of the target engineering project at different construction nodes can be updated in real time through all the confidence cost information, which can be achieved in the following way: First, select a construction node, obtain the confidence cost value of each engineering sub-project at this construction node from all the confidence cost information, and use the result of adding up the confidence cost values of all engineering sub-projects at this construction node as the total cost of the target engineering project at the corresponding construction node. Repeat the above steps to determine the total cost of the target engineering project at the remaining nodes, and then update the total cost of each calculated construction node to the engineering budget sheet of the target engineering project. It should be noted that the engineering budget sheet is a cost estimation form used in project management to summarize and track the costs of each construction node. It records the total costs of all engineering sub-projects under different construction nodes. This application calculates and updates through the confidence cost information of each construction node. The engineering budget sheet provides a comprehensive cost estimate to help project managers track cost changes in real time and adjust the project budget.

[0051] In addition, on the other hand of this application, in some embodiments, this application provides a project engineering budget generation system. Refer to Figure 4 , this figure is a schematic structural diagram of the project engineering budget generation system shown in some embodiments of this application. The project engineering budget generation system 200 includes: The acquisition module 201, the processing module 202, and the execution module 203 are described as follows: The acquisition module 201. In this application, the acquisition module 201 is mainly used to acquire the historical budget data of all engineering projects. The processing module 202. In this application, the processing module 202 is mainly used to determine the cost performance index of different engineering projects based on the historical budget data, and then conduct correlation analysis through all the cost performance indices in combination with different engineering characteristics of the engineering projects to obtain the cost conversion coefficient under different engineering characteristics during construction. In addition, in this application, the processing module 202 is also used to divide the target engineering project into multiple engineering sub-projects based on the tree structure management model, and determine the characteristic correlation relationship between each engineering sub-project and the engineering cost through all the cost conversion coefficients. In addition, in this application, the processing module 202 is also used to obtain the cost risk during engineering construction, construct the risk distribution model of each engineering sub-project according to the distribution probability of the cost risk in each engineering sub-project, and then generate the cost overrun rate of each engineering sub-project at different construction nodes in combination with the construction progress of different construction nodes. Execution module 203. In this application, the execution module 203 is mainly used to determine the confidence cost information of each engineering sub-project according to the cost overrun rate of the engineering cost of each engineering sub-project at different construction nodes and the characteristic correlation relationship between each engineering sub-project and the engineering cost, and then update the engineering budget estimate table of the target engineering project at different construction nodes in real time through all the confidence cost information.

[0052] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned project engineering budget estimate generation method.

[0053] In some embodiments, refer to Figure 5 , this figure is the internal structure diagram of a computer device for implementing the project engineering budget estimate generation method according to some embodiments of this application. The project engineering budget estimate generation method in the above embodiments can be implemented by Figure 5 the computer device shown. The computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0054] The processor 301 can be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the project engineering budget estimate generation method in this application.

[0055] The communication bus 302 is used to transmit information between the above components.

[0056] The memory 303 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), or other types of dynamic storage devices that can store information and instructions. It may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 303 may exist independently and be connected to the processor 301 through the communication bus 302. The memory 303 may also be integrated with the processor 301.

[0057] Among them, the memory 303 is used to store the program code for executing the solution of this application and is controlled by the processor 301 to execute. The processor 301 is used to execute the program code stored in the memory 303. The program code may include one or more software modules. The project engineering budget generation method in the above embodiments may be implemented through one or more software modules in the program code of the processor 301 and the memory 303.

[0058] The communication interface 304 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0059] In a specific implementation, as an embodiment, the computer device may include multiple processors, and each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0060] The above computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0061] In addition, the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above project engineering budget generation method is implemented.

[0062] In summary, in the project engineering budget generation method, system, device, and medium disclosed in the embodiments of the present application, historical budget data of all engineering projects are obtained; cost performance indices of different engineering projects are determined based on the historical budget data, and then correlation analysis is performed by combining all the cost performance indices with different engineering characteristics of the engineering projects to obtain cost conversion coefficients under different engineering characteristics during construction; the target engineering project is divided into multiple engineering sub-projects based on a tree structure management model, and the characteristic correlation relationship between each engineering sub-project and the engineering cost is determined through all the cost conversion coefficients; the cost risk during project construction is obtained, and a risk distribution model of each engineering sub-project is constructed according to the distribution probability of the cost risk in each engineering sub-project, and then the cost overrun rate of each engineering sub-project at different construction nodes is generated by combining the construction progress of different construction nodes; the confidence cost information of each engineering sub-project is determined according to the cost overrun rate of the engineering cost of each engineering sub-project at different construction nodes and the characteristic correlation relationship between each engineering sub-project and the engineering cost, and then the engineering budget table of the target engineering project at different construction nodes is updated in real time through all the confidence cost information; the engineering budget can be dynamically adjusted according to the change of the construction progress.

[0063] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0064] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these changes and modifications.

Claims

1. A method for generating a project engineering budget estimate, characterized in that, It includes the following steps: Obtain the historical budget estimate data of all engineering projects; Determine the cost performance indexes of different engineering projects based on the historical budget estimate data, and then conduct correlation analysis by combining all the cost performance indexes with different engineering characteristics of the engineering projects to obtain the cost conversion coefficients under different engineering characteristics during construction; Divide the target engineering project into multiple engineering sub-projects based on the tree structure management model, and determine the characteristic correlation relationship between each engineering sub-project and the project cost through all the cost conversion coefficients; Obtain the cost risks during engineering construction, construct the risk distribution model of each engineering sub-project according to the distribution probability of the cost risks in each engineering sub-project, and then generate the cost overrun rate of each engineering sub-project at different construction nodes in combination with the construction progress of different construction nodes; Determine the confidence cost information of each engineering sub-project according to the cost overrun rate of the engineering cost of each engineering sub-project at different construction nodes and the characteristic correlation relationship between each engineering sub-project and the project cost, and then update the engineering budget estimate table of the target engineering project at different construction nodes in real time through all the confidence cost information.

2. The method according to claim 1, characterized in that, Determining the cost performance indexes of different engineering projects based on the historical budget estimate data specifically includes: Obtain the budgeted cost and actual cost of each engineering project from the historical budget estimate data; Determine the cost performance index of each engineering project through the budgeted cost and the actual cost.

3. The method according to claim 1, wherein Conducting correlation analysis by combining all the cost performance indexes with different engineering characteristics of the engineering projects to obtain the cost conversion coefficients under different engineering characteristics during construction specifically includes: Obtain the engineering characteristic information of all engineering projects under all engineering characteristics; Determine the characteristic influence degree between each engineering characteristic and the project cost through all the engineering characteristic information and all the cost performance indexes; Determine the cost conversion coefficients under different engineering characteristics during construction through all the characteristic influence degrees.

4. The method according to claim 1, characterized in that Determining the characteristic correlation relationship between each engineering sub-project and the project cost through all the cost conversion coefficients specifically includes: Obtain the budget cost range of each engineering sub-project; Determine the cost deviation range of each engineering sub-project through all the cost conversion coefficients and the budget cost range of each engineering sub-project; Determine the characteristic correlation relationship between each engineering sub-project and the project cost through all the cost deviation ranges.

5. The method according to claim 1, characterized in that, Constructing the risk distribution model of each engineering sub-project according to the distribution probability of the cost risks in each engineering sub-project, and then generating the cost overrun rate of each engineering sub-project at different construction nodes in combination with the construction progress of different construction nodes specifically includes: Determine the distribution probability curve of the cost risks in each engineering sub-project at different construction nodes; Construct the risk distribution model of each engineering sub-project according to the distribution probability curve; Generate the cost fluctuation range of each engineering sub-project at different construction nodes through the risk distribution model; Generate the cost overrun rate of each engineering sub-project at different construction nodes based on the cost fluctuation range of each engineering sub-project at different construction nodes and the construction progress of different construction nodes.

6. The method according to claim 1, wherein Determine the confidence cost information of each engineering sub - project according to the cost over - run rate of the engineering cost of each engineering sub - project at different construction nodes and the characteristic correlation relationship between each engineering sub - project and the engineering cost. Specifically, it includes: Determine the characteristic cost of each engineering sub - project through the characteristic correlation relationship between each engineering sub - project and the engineering cost; Determine the confidence cost information of each engineering sub - project according to the cost over - run rate of the engineering cost of each engineering sub - project at different construction nodes and all the characteristic costs.

7. The method according to claim 1, characterized in that, The tree - shaped structure management model adopts the work breakdown structure.

8. A project engineering budget generation system, characterized in that, It includes: An acquisition module, used to acquire the historical budgetary estimate data of all engineering projects; A processing module, used to determine the cost performance index of different engineering projects based on the historical budgetary estimate data, and then conduct correlation analysis through all the cost performance indexes combined with different engineering characteristics of the engineering projects to obtain the cost conversion coefficient under different engineering characteristics during construction; The processing module is also used to divide the target engineering project into multiple engineering sub - projects based on the tree - shaped structure management model, and determine the characteristic correlation relationship between each engineering sub - project and the engineering cost through all the cost conversion coefficients; The processing module is also used to obtain the cost risk during engineering construction, construct the risk distribution model of each engineering sub - project according to the distribution probability of the cost risk in each engineering sub - project, and then generate the cost over - run rate of each engineering sub - project at different construction nodes in combination with the construction progress at different construction nodes; An execution module, used to determine the confidence cost information of each engineering sub - project according to the cost over - run rate of the engineering cost of each engineering sub - project at different construction nodes and the characteristic correlation relationship between each engineering sub - project and the engineering cost, and then update the engineering budget estimate table of the target engineering project at different construction nodes in real - time through all the confidence cost information.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the project engineering budget estimate generation method described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the project engineering budget estimate generation method described in any one of claims 1 to 7.

Images