Precise checking method, system and equipment for cost range based on geographic region characteristics, and medium

Abstract

The invention relates to the technical field of project cost, and discloses a method, a system, equipment and a medium for precisely checking a cost range based on geographic region characteristics, and the method comprises the steps: collecting project engineering data, and carrying out the data preprocessing; performing feature extraction based on the project engineering data to obtain project geographic features and engineering cost features, and performing feature analysis; constructing a project construction cost model, and calculating to obtain a project construction cost prediction range; and comparing the construction cost with a preset construction cost range to check the construction cost, judging whether the construction cost exceeds the preset construction cost range or not, and adjusting and optimizing the project construction cost if the construction cost exceeds the preset construction cost range. According to the method, the cost range of various engineering projects in different geographic areas can be predicted, the prediction precision is improved, through comparison with actual cost data, the prediction accuracy is evaluated by adopting a statistical method, the high accuracy of the final cost range is ensured, and a visual and comprehensive decision basis can be provided for a decision maker according to a cost check result.

Description

Technical Field

[0001] This invention relates to the field of engineering cost technology, and in particular to a method, system, equipment and medium for accurate verification of cost range based on geographical regional characteristics. Background Technology

[0002] Accurate project cost estimates are crucial for the smooth implementation of engineering projects. Geographical characteristics have a significant impact on project costs; natural conditions and engineering costs in different regions can all lead to differences in project costs.

[0003] Traditional cost verification methods primarily rely on historical data and empirical formulas, typically estimating costs based on cost indicators from similar projects, combined with the current project's scale, function, and other characteristics. They also consider common influencing factors such as material prices and labor costs.

[0004] Traditional cost verification relies heavily on the experience and subjective judgment of cost estimators. Due to differences in professional competence, practical experience, and individual thinking styles among cost estimators, the results obtained by different individuals for the same cost project often vary significantly. This subjectivity, lacking unified standards and norms, greatly reduces the reliability and stability of cost verification results, failing to guarantee objectivity and accuracy. Geographical characteristics have a crucial impact on costs, including raw material prices, labor costs, geological conditions, and climate conditions in different regions. However, traditional cost verification methods fail to fully consider these differences in geographical factors. This severely limits the applicability of the methods when verifying costs for projects in different regions, making it impossible to accurately reflect the actual cost situation of projects in different geographical areas and easily leading to cost estimation errors.

[0005] While modern cost estimation systems excel in improving work efficiency, they suffer from significant shortcomings in considering geographical regional characteristics. During the design and development process, insufficient attention has been paid to cost differences across different geographical regions, and there is a lack of functional modules and algorithm optimizations tailored to the specific characteristics of different areas. This makes it impossible to accurately adjust the calculation model according to local conditions when handling cost verification for projects in different geographical regions, thus affecting the accuracy of cost calculations. Furthermore, the data update speed for cost management is too slow, failing to keep pace with market changes. Cost data is influenced by various market factors, making it difficult to obtain the latest data in a timely manner. This results in data used in cost verification processes that may be outdated and unable to accurately reflect the current cost situation, thereby affecting the reliability of cost results. Summary of the Invention

[0006] In view of the aforementioned existing problems, this invention is proposed. Therefore, this invention provides a method for accurately verifying the cost range based on geographical regional characteristics to solve the above problems.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0008] In a first aspect, the present invention provides a method for accurate verification of cost range based on geographical regional characteristics, including: collecting project engineering data and performing data preprocessing;

[0009] Feature extraction is performed based on the project engineering data to obtain the project's geographical features and engineering cost features, and feature analysis is then conducted.

[0010] Based on the feature analysis results of the project's geographical features and engineering cost features, a project engineering cost model is constructed, and the predicted cost range of the project is calculated.

[0011] Based on the project's predicted cost range, the cost is checked by comparing it with the preset cost range, and it is determined whether the cost exceeds the preset cost range. If the cost exceeds the cost range, the project cost is adjusted and optimized.

[0012] As a preferred embodiment of the method for accurate cost range verification based on geographical region characteristics described in this invention, the following steps are included: collecting project engineering data and performing data preprocessing:

[0013] Collect project engineering data, which includes completed projects and projects under construction. Classify the project engineering data into project type, engineering cost data, basic engineering information data, geographical environment data, and engineering cost data.

[0014] The project engineering data is preprocessed, including data cleaning, data encoding, and standardization.

[0015] As a preferred embodiment of the method for accurate cost range verification based on geographical region features described in this invention, the following features are extracted based on the project engineering data to obtain the project's geographical features and engineering cost features:

[0016] Based on the project engineering data, the geographical regional characteristic factors affecting the project cost are extracted to obtain the project geographical characteristics, which include topographic features, geological risk features, hydrological features and climate features.

[0017] Based on the project engineering data, the engineering cost characteristic factors affecting the project cost are extracted to obtain the engineering cost characteristics, which include labor cost characteristics, material cost characteristics, transportation cost characteristics, and land cost characteristics.

[0018] As a preferred embodiment of the method for accurate cost range verification based on geographical regional characteristics described in this invention, the feature analysis of the project's geographical features and engineering cost features includes:

[0019] A linear regression model is constructed, and the collected project engineering data is used to train the linear regression model. The values ​​of the regression coefficients are determined by minimizing the loss function, and the trained linear regression model is evaluated by the model evaluation index.

[0020] Using the preprocessed project geographical features and engineering cost features as independent variables and the project cost as the dependent variable, and substituting them into the linear regression model, the linear relationship between each project geographical feature, engineering cost feature and project cost is obtained.

[0021] As a preferred embodiment of the method for accurate cost range verification based on geographical region characteristics described in this invention, the project cost model is expressed as follows:

[0022]

[0023] Where Z represents the total project cost, F j Let α represent the geographic feature adjustment factor for the j-th project. j Let x represent the coefficient of the geographical feature adjustment factor for the j-th project, and D represent the benchmark cost. k Let β represent the cost characteristic of the k-th project. k The coefficient represents the engineering cost characteristic coefficient, where m and n represent the quantity of geographical features and engineering cost characteristics of the project, respectively, and ∈ represents the error term.

[0024] As a preferred embodiment of the method for accurate cost range verification based on geographical region characteristics described in this invention, the cost verification based on the project's predicted cost and by comparing it with the cost range includes:

[0025] Compare the predicted cost range with the preset cost range to determine whether the predicted cost range of the project is within the preset cost range;

[0026] The preset cost range is a cost confidence interval generated based on historical engineering data, geographical features, and cost indicators. The boundary of the preset cost range is calibrated in real time using real-time data.

[0027] As a preferred embodiment of the method for accurate cost range verification based on geographical region characteristics described in this invention, the adjustment and optimization of project engineering costs includes:

[0028] If the predicted cost range exceeds the preset cost range, calculate the quantitative value of the deviation between the predicted cost range and the preset cost range, as well as the contribution of geographical features;

[0029] The corresponding cost verification deviation level is determined based on the deviation quantification value. Based on the cost verification deviation level and the comparison results of the contribution of geographical features and the threshold of the contribution of geographical features, the risk level of the project cost is determined.

[0030] Based on the risk level, the project cost is adjusted to generate a cost adjustment plan, which includes adjustments to the project design, optimization of the construction plan, and adjustments to the project materials.

[0031] Secondly, the present invention provides a cost range accurate verification system based on geographical regional characteristics, including: a data acquisition module for collecting project engineering data and performing data preprocessing;

[0032] The feature extraction module is used to extract features based on the project engineering data to obtain the project's geographical features and engineering cost features, and to perform feature analysis.

[0033] The model building module is used to construct a project cost model based on the feature analysis results of the project's geographical features and engineering cost features, and to calculate the predicted cost range of the project.

[0034] The verification module is used to verify the project cost based on the project's predicted cost range by comparing it with a preset cost range, and to determine whether the project cost exceeds the preset cost range. If it exceeds the cost range, the project cost is adjusted and optimized.

[0035] Thirdly, the present invention provides a computer device, comprising:

[0036] Memory and processor;

[0037] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the method for accurately verifying the cost range based on geographical region features.

[0038] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for accurately verifying the cost range based on geographical region features.

[0039] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention uses big data analysis tools for preprocessing and in-depth mining to reveal the specific impact of engineering characteristics on engineering costs. Based on historical project data and feature analysis results, a model is constructed to predict the cost range of various engineering projects in different geographical regions. The model continuously optimizes cost estimation through iterative training, improving prediction accuracy. Based on cost prediction, statistical methods are used to evaluate prediction accuracy by comparing with actual cost data, and model parameters are fine-tuned accordingly to ensure high accuracy of the final cost range. A cost model parameter library is established, containing weight coefficients and adjustment factors for various features. These parameters are dynamically adjusted according to the actual situation of the specific project location, making the cost model more in line with local realities and improving the model's adaptability and accuracy. Based on cost verification results, it can provide decision-makers with intuitive and comprehensive decision-making basis. Based on cost estimation results, project budgets are rationally allocated to ensure optimal allocation of funds, materials, and human resources. At the same time, resource allocation schemes are dynamically adjusted according to the actual situation during project implementation to improve resource utilization efficiency. Attached Figure Description

[0040] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a schematic diagram of the overall process of a method for accurately verifying the cost range based on geographical region characteristics, as described in one embodiment of the present invention. Detailed Implementation

[0042] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0043] Reference Figure 1 As an embodiment of the present invention, a method for accurately verifying the cost range based on geographical region characteristics is provided, comprising:

[0044] S101, Collect project engineering data and perform data preprocessing;

[0045] S102, Based on the project engineering data, feature extraction is performed to obtain the project's geographical features and engineering cost features, and feature analysis is then conducted;

[0046] S103. Based on the feature analysis results of the project's geographical features and engineering cost features, construct the project engineering cost model and calculate the predicted range of the project engineering cost.

[0047] S104. Based on the project's predicted cost range, the cost is checked by comparing it with the preset cost range, and it is determined whether the cost exceeds the preset cost range. If the cost exceeds the cost range, the project cost is adjusted and optimized.

[0048] It should be noted that the present invention mainly includes four main steps: data collection and processing, feature extraction and analysis, cost model construction, and precise verification and adjustment. By collecting and analyzing engineering project data from different geographical regions, the geographical features and engineering cost features of the projects are extracted, a cost model suitable for different regions is constructed, and precise verification and adjustment are performed to determine the standard cost range.

[0049] In a preferred embodiment, collecting project engineering data and performing data preprocessing includes:

[0050] Collect project engineering data, including completed projects and projects under construction. Classify the project engineering data into project type, engineering cost data, basic engineering information data, geographical environment data, and engineering cost data.

[0051] Data preprocessing is performed on project engineering data, including data cleaning, data coding, and standardization.

[0052] In one alternative implementation, engineering project data is collected from various channels, including data on completed or under-construction projects. This extensive collection of various types of engineering project data provides sufficient data support for subsequent analysis and modeling. By utilizing web crawling technology, database queries, and other means, engineering project data is collected from channels such as government departments, industry associations, and enterprise databases. It also includes geographical environmental data of the project location, such as climate conditions and topography.

[0053] In another alternative implementation, another method for collecting engineering cost data can be used, namely, a combination of manual and automatic data collection. By analyzing this data, the extent to which the characteristics of different regions affect engineering costs can be understood.

[0054] In one optional implementation, the collected project engineering data, specifically the basic engineering information data, may include information such as project name, location, scale, construction time, cost, material usage, and construction technology. Among these, the scale can be automatically calculated by a parametric model, the cost can be linked to Glodon through the IFC standard, and the quota (such as concrete quantity × unit price) can be matched according to the component code to dynamically generate the budget, the material usage can be calculated by the Building Information Modeling (BIM) quantity calculation tool, the construction technology can be simulated in 4D using Synchro to optimize resource allocation, and the project type (such as super high-rise) can be matched with the specification library through classification codes and calibrated in combination with historical data.

[0055] In one alternative implementation, the collected project engineering data can be classified and stored according to project type, geographical region, etc. Then, data cleaning is performed to remove duplicate, erroneous, and incomplete data. Finally, the organized data is stored in a database for subsequent analysis and modeling.

[0056] In one alternative implementation, data cleaning may include:

[0057] Check the collected data for missing, erroneous, or outlier values. For missing values, select an appropriate imputation method based on the data distribution, such as mean imputation, median imputation, or imputation based on a regression model. For erroneous and outlier values, correct or remove them to ensure data quality.

[0058] In one alternative implementation, data encoding and standardization may include:

[0059] Encode some categorical variables so that they can be used in the model. At the same time, standardize all variables (including geographical environment data, engineering cost data, etc.), for example, convert the data into a standard normal distribution with a mean of 0 and a standard deviation of 1. This can avoid the influence of the difference in the units of different variables on the model results.

[0060] It should be noted that cost verification based on the natural and cost characteristics of different regions is a key aspect of this invention, and the impact of the natural environment on project costs cannot be ignored. In earthquake-prone areas, engineering construction needs to consider higher seismic resistance requirements, which will increase the design difficulty of building structures and material costs. For example, in some earthquake-prone areas of Sichuan, the seismic fortification intensity of building projects is high, requiring the use of special seismic-resistant structures and materials, such as increasing the amount of steel reinforcement and using concrete with better seismic performance, which will undoubtedly increase project costs. In flood-prone areas, the foundation design and drainage system of the project need to be more robust and complete to prevent flood damage. In mountainous areas, due to complex terrain and inconvenient transportation, material transportation costs will increase significantly. In addition, different regional climatic conditions will also affect project costs; for example, cold regions require insulation measures, while hot regions require ventilation and heat insulation measures. Regional cost composition is affected by multiple factors.

[0061] Regarding project costs, firstly, labor costs are directly affected by the supply and demand of the labor market in different regions, with wages for construction workers in first-tier cities generally being higher. Secondly, material costs are determined by the distance from the production site and market supply and demand; if materials are sourced far from economically developed areas, procurement costs increase significantly. Thirdly, transportation costs are strongly correlated with geographical location and transportation conditions; in some central and western regions, inconvenient transportation leads to significantly higher material transportation costs. Some projects also require the use of environmentally friendly materials and technologies, further increasing project costs; and fourthly, there are equipment rental costs, among other expenses.

[0062] In a preferred embodiment, feature extraction based on project engineering data yields project geographical features and engineering cost features, including:

[0063] Based on project engineering data, the geographical regional characteristic factors affecting project cost are extracted to obtain the project geographical characteristics, which include topographic features, geological risk features, hydrological features and climate features.

[0064] Based on project engineering data, the engineering cost characteristics that affect the project cost are extracted, resulting in engineering cost characteristics, which include labor cost characteristics, material cost characteristics, transportation cost characteristics, and land cost characteristics.

[0065] In one alternative implementation, the geographical features of the project include, but are not limited to, topographic features, geological risk features, hydrological features, and climate features. When extracting the geographical features of the project, multi-source remote sensing data and AI model optimization schemes can be combined. High-precision topographic features (such as elevation, slope, and rock layer distribution) can be obtained through satellite remote sensing and UAV oblique photography, and underground structures (such as karst cave risk) can be detected using ground-penetrating radar.

[0066] In another alternative implementation, when extracting the geographical features of a project, a graph neural network (GNN) can be used to model the geographical-cost correlation and dynamically extract key factors affecting the cost, thereby improving the effectiveness of manual statistics.

[0067] In one optional implementation, in the early stages of the project, the range of project cost can be preliminarily determined by analyzing the regional geographical environment and engineering costs. When determining the range of project cost in the early stages of the project, it is necessary to systematically classify and quantify the natural environment through multi-dimensional technical means. Among them, the geographical environment classification includes four types of elements: topography (slope, elevation), geological risks (rock and soil type, seismic intensity), hydrological conditions (groundwater level, flood control level), and climate and meteorology (extreme precipitation, temperature difference). These can be identified through GIS spatial analysis (generating slope classification maps and rock and soil distribution heat maps based on digital elevation models). The conversion of analysis results into cost parameters can be combined with the setting of threshold rules in engineering specifications: for example, when the terrain slope is >25%, the earthwork excavation cost is adjusted according to the "Technical Specification for Slope Construction of Building Engineering" according to the rule that "for every 5% increase in slope, the mechanical efficiency reduction coefficient increases by 1.2 times"; when the groundwater level is <2m, the high-pressure jet grouting pile support scheme is used; and in areas with seismic intensity ≥7 degrees, the seismic resistance measure fee is added at 20%-30% of the structural cost.

[0068] In one alternative implementation, the engineering cost parameters are determined as follows:

[0069] The unit price of labor is calculated by weighting the regional quota price with the job shortage index (e.g., skilled worker's daily wage = benchmark price × (1 + regional adjustment coefficient + 0.2 × shortage index)); the material price adopts a time-varying parameter model, with the China Steel Price Index as the benchmark and futures volatility added (e.g., rebar purchase price = benchmark price × (1 + 0.7 × futures monthly change)); the machine shift fee is adjusted for utilization rate based on GPS monitoring data (actual machine shift fee = quota price × (1 - idle rate / 3)).

[0070] It should be noted that by constructing multi-disciplinary 3D models (architecture, structure, MEP, etc.) using BIM technology, integrating geographic data and design parameters, and utilizing tools such as Revit and Navisworks to achieve automatic extraction of quantities, clash detection, and dynamic cost correlation, accurate bill of quantities can be generated in real time. Furthermore, by simulating construction plans, costs can be optimized, ultimately reducing human error and improving the efficiency of cost calculation.

[0071] In another optional implementation, after extracting the project's geographical features and engineering cost features, data statistics and visualization analysis can be performed. Data features and trends can be displayed intuitively through methods such as average value analysis, ratio analysis, and trend analysis, as well as in the form of bar charts, line charts, and pie charts, providing a basis for cost verification. Furthermore, cluster analysis can be used to classify the cost structure of different regions, providing a more accurate basis for engineering cost verification.

[0072] In a preferred embodiment, feature analysis of the project's geographical characteristics and engineering cost characteristics includes:

[0073] A linear regression model is constructed, and the collected project engineering data is used to train the linear regression model. The value of the regression coefficient is determined by minimizing the loss function so that the model can best fit the data. The trained linear regression model is evaluated by the model evaluation index.

[0074] By substituting the preprocessed project geographical features and engineering cost features as independent variables and the project cost as the dependent variable into the linear regression model, the linear relationships between each project geographical feature, engineering cost feature and project cost are obtained.

[0075] In one alternative implementation, a multiple linear regression model is constructed, expressed as:

[0076] Y = β0 + β1X1 + β2X2 + ... + β n X n +∈

[0077] Where Y is the project cost, β0 is the intercept, and β i The independent variable is the geographical feature or engineering cost feature of the project. i The regression coefficient, ∈, is the error term, and the regression coefficient β i It reflects the degree of influence of each characteristic factor on the project cost. A positive regression coefficient indicates that the factor is positively correlated with the project cost, that is, when the value of the factor increases, the project cost also increases; a negative regression coefficient indicates a negative correlation. The absolute value of the regression coefficient indicates the importance of the factor's influence on the project cost. The larger the absolute value, the more significant the influence.

[0078] In one alternative implementation, by performing a significance test on the regression coefficients (such as a t-test or an F-test), it can be determined whether the impact of each characteristic factor on the project cost is significant. If the regression coefficient of a certain factor passes the significance test (usually ρ≤0.05 is used as the standard), it indicates that the factor has a significant impact on the project cost and is of great significance in the model; conversely, if the ρ value is greater than 0.05, the factor can be considered to be removed from the model.

[0079] In another alternative implementation, other regression models can be used to obtain the linear relationship between the geographical features and engineering cost features of each project and the project cost, such as linear regression models, multinomial regression models, etc.

[0080] In another alternative implementation, if the relationship between project features and engineering costs is complex, a nonlinear regression model can be considered, preferably support vector regression, neural network regression, etc. Furthermore, automated feature engineering and regression can be considered, using automated machine learning tools to automatically generate feature interaction terms (such as "slope × rainfall") and transformations (such as unique thermal encoding of geological types).

[0081] In one alternative implementation, a suitable evaluation metric can be used to evaluate the model's performance, wherein the evaluation metric includes the coefficient of determination R. 2 Adjusted R 2 Mean squared error (MSE), mean absolute error (MAE), etc., R 2 The value indicates how well the model fits the data; the closer the value is to 1, the better the model fits. MSE and MAE measure the magnitude of the error between the model's predicted values ​​and the actual values; the smaller the value, the better. In addition, methods such as cross-validation can be used to further evaluate the model's stability and generalization ability.

[0082] It should be noted that the influence of engineering characteristic factors on engineering cost can be explained based on the regression coefficients and significance test results. For example, if the regression coefficient of the topographic complexity variable of a certain region is significantly positive, it means that the more complex the topography, the higher the engineering cost, because complex terrain requires more construction measures and costs. At the same time, the interaction terms in the model can be analyzed to further understand the impact of the interaction between different characteristic factors on engineering cost.

[0083] In a preferred embodiment, the project cost model is expressed as follows:

[0084]

[0085] Where Z represents the total project cost, F j Let α represent the geographic feature adjustment factor for the j-th project. j Let x represent the coefficient of the geographical feature adjustment factor for the j-th project, and D represent the benchmark cost. k Let β represent the cost characteristic of the k-th project. k The coefficient represents the engineering cost characteristic coefficient, where m and n represent the quantity of geographical features and engineering cost characteristics of the project, respectively, and ∈ represents the error term.

[0086] It should be noted that, based on the results of feature analysis, cost models applicable to different geographical regions can be constructed. These models can be adjusted according to the differences in characteristics of different geographical regions (such as terrain complexity (plains / hills / mountains), climate (humid / arid / frigid zones), and geological risks (karst / permafrost / earthquake zones)) and the actual project conditions. This can improve the accuracy and applicability of the model. For example, if the climate conditions of the project location are special, the weight of climate factors in the model can be adjusted according to the actual situation. Through parameter adjustment, the cost model can more accurately reflect the actual situation of a specific project.

[0087] In a preferred embodiment, cost verification based on the project's projected cost and by comparing it with the cost range includes:

[0088] Compare the predicted cost range with the preset cost range to determine whether the predicted cost range of the project is within the preset cost range;

[0089] The preset cost range is based on historical engineering data, geographical features, and cost indicators, generating a cost confidence interval. The boundaries of the preset cost range are calibrated in real time using real-time data to ensure timeliness.

[0090] In an alternative implementation, statistical methods (such as Monte Carlo simulation, interval estimation, etc.) can be used to generate cost confidence intervals. For example, based on the distribution of historical project data, a confidence level (preferably 90%) is set, and the corresponding cost interval is calculated. This interval is the preset cost range.

[0091] In a preferred embodiment, adjusting and optimizing the project cost includes:

[0092] If the predicted cost range exceeds the preset cost range, calculate the quantitative value of the deviation between the predicted cost range and the preset cost range, as well as the contribution of geographical features;

[0093] The corresponding cost verification deviation level is determined based on the deviation from the quantitative value. Based on the cost verification deviation level and the comparison results between the contribution of geographical features and the threshold of the contribution of geographical features, the risk level of the project cost is determined.

[0094] Based on the risk level, the project cost is adjusted to generate a cost adjustment plan, which includes adjustments to the project design, optimization of the construction plan, and adjustments to the project materials.

[0095] In one optional implementation, calculating the deviation quantification value between the predicted cost range and the preset cost range includes:

[0096] The absolute value of the difference between the upper limit of the predicted cost range and the upper limit of the preset cost range, plus the absolute value of the difference between the lower limit of the predicted cost range and the lower limit of the preset cost range, is divided by the difference between the upper and lower limits of the preset cost range to obtain the deviation quantification value between the predicted cost range and the preset cost range, with a value range of [0,1].

[0097] In one alternative implementation, calculating the contribution of geographic features includes:

[0098] To establish a model of the relationship between geographical features and cost deviation, methods such as multiple linear regression can be used. Geographical features are used as independent variables, and cost deviation (i.e., the difference between the predicted cost and the preset cost) is used as the dependent variable to obtain regression coefficients. The contribution of geographical features to cost deviation is obtained by multiplying the geographical features and the regression coefficients and dividing by the cost deviation.

[0099] In one optional implementation, based on the actual application scenario, a deviation quantification value range corresponding to each cost verification deviation level is set. The corresponding cost verification deviation level (which can be set to level 1-3) is determined according to the calculated deviation quantification value, and the risk level is determined. The geographical feature contribution threshold can also be set according to the actual application scenario (e.g., 30%).

[0100] In an optional implementation, preferably, a red alert is issued if the cost verification deviation level is greater than or equal to level 2 and the contribution of geographical features to the cost deviation is greater than the contribution threshold of geographical features to the cost deviation; otherwise, a yellow alert is issued. Specifically, red alert projects can use the Analytic Hierarchy Process (AHP) to generate multi-objective optimization schemes (e.g., structural simplification rate ≥ 15% and quality loss ≤ 5%), while yellow alert projects use Bayesian updates to dynamically calibrate geographical feature weights. For data defects (such as terrain modeling errors), high-precision GIS data resampling and BIM simulation verification are forcibly initiated. Simultaneously, Monte Carlo simulation is integrated to evaluate the adjusted cost confidence interval, and a "geographical scene-optimization strategy" mapping knowledge base is constructed through reinforcement learning to achieve model self-iterative optimization.

[0101] It should be noted that this invention utilizes big data analytics tools for preprocessing and in-depth analysis to reveal the specific impact of engineering characteristics on project costs. Based on historical project data and feature analysis results, a model is constructed to predict the cost range of various engineering projects in different geographical regions. Through continuous iterative training, the model achieves continuous optimization of cost estimation, improving prediction accuracy. Based on cost prediction, statistical methods are used to evaluate the accuracy of the prediction by comparing it with actual cost data, and the model parameters are fine-tuned accordingly to ensure high accuracy of the final cost range. A cost model parameter library is established, containing weight coefficients and adjustment factors for various characteristics. These parameters are dynamically adjusted according to the actual situation of the specific project location, making the cost model more aligned with local realities and improving its adaptability and accuracy. Based on the cost verification results, it can provide decision-makers with intuitive and comprehensive decision-making basis. Based on the cost estimation results, the project budget is rationally allocated to ensure optimal allocation of funds, materials, and human resources. At the same time, the resource allocation plan is dynamically adjusted according to the actual situation during project implementation to improve resource utilization efficiency.

[0102] The above is an illustrative scheme of a method for accurately verifying the cost range based on geographical region characteristics, as described in this embodiment. It should be noted that the technical solution of this system for accurately verifying the cost range based on geographical region characteristics belongs to the same concept as the technical solution of the method for accurately verifying the cost range based on geographical region characteristics described above. Details not described in detail in the technical solution of the system for accurately verifying the cost range based on geographical region characteristics in this embodiment can be found in the description of the technical solution of the method for accurately verifying the cost range based on geographical region characteristics described above.

[0103] This embodiment presents a cost range accuracy verification system based on geographical region characteristics, comprising:

[0104] The data acquisition module is used to collect project engineering data and perform data preprocessing.

[0105] The feature extraction module is used to extract features based on project engineering data, obtain project geographical features and engineering cost features, and perform feature analysis.

[0106] The model building module is used to construct a project cost model based on the feature analysis results of the project's geographical features and engineering cost features, and to calculate the predicted cost range of the project.

[0107] The verification module is used to verify the project cost based on the project's predicted cost range by comparing it with the preset cost range, and to determine whether it exceeds the preset cost range. If it exceeds the cost range, the project cost will be adjusted and optimized.

[0108] This embodiment also provides a computer device suitable for accurate cost range verification based on geographical region characteristics, including:

[0109] The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement the method for accurately verifying the cost range based on geographical region features, as proposed in the above embodiments.

[0110] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the method for accurately verifying the cost range based on geographical region features as proposed in the above embodiments.

[0111] The storage medium proposed in this embodiment and the method for accurately verifying the cost range based on geographical region features proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0112] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0113] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for accurately verifying the cost range based on geographical regional characteristics, characterized in that, include: Collect project engineering data and perform data preprocessing; Feature extraction is performed based on the project engineering data to obtain the project's geographical features and engineering cost features, and feature analysis is then conducted. Based on the feature analysis results of the project's geographical features and engineering cost features, a project engineering cost model is constructed, and the predicted cost range of the project is calculated. Based on the project's predicted cost range, the cost is checked by comparing it with the preset cost range, and it is determined whether the cost exceeds the preset cost range. If it exceeds the cost range, the project cost is adjusted and optimized.

2. The method for accurate cost range verification based on geographical region characteristics as described in claim 1, characterized in that, Collecting project engineering data and performing data preprocessing includes: Collect project engineering data, which includes completed projects and projects under construction. Classify the project engineering data into project type, engineering cost data, basic engineering information data, geographical environment data, and engineering cost data. The project engineering data is preprocessed, including data cleaning, data encoding, and standardization.

3. A method for accurately verifying the cost range based on geographical region characteristics as described in claim 1 or 2, characterized in that, Feature extraction was performed based on the project engineering data to obtain the project's geographical features and engineering cost features, including: Based on the project engineering data, the geographical regional characteristic factors affecting the project cost are extracted to obtain the project geographical characteristics, which include topographic features, geological risk features, hydrological features and climate features. Based on the project engineering data, the engineering cost characteristic factors affecting the project cost are extracted to obtain the engineering cost characteristics, which include labor cost characteristics, material cost characteristics, transportation cost characteristics, and land cost characteristics.

4. The method for accurate cost range verification based on geographical region characteristics as described in claim 3, characterized in that, The feature analysis of the project's geographical features and engineering cost features includes: A linear regression model is constructed, and the collected project engineering data is used to train the linear regression model. The values ​​of the regression coefficients are determined by minimizing the loss function, and the trained linear regression model is evaluated by the model evaluation index. Using the preprocessed project geographical features and engineering cost features as independent variables and the project cost as the dependent variable, and substituting them into the linear regression model, the linear relationship between each project geographical feature, engineering cost feature and project cost is obtained.

5. The method for accurate cost range verification based on geographical region characteristics as described in claim 4, characterized in that, The project cost model is represented as follows: Where Z represents the total project cost, F j α represents the geographic feature adjustment factor for the j-th project. j Let x represent the coefficient of the geographical feature adjustment factor for the j-th project, and D represent the benchmark cost. k Let β represent the cost characteristic of the k-th project. k The coefficient represents the engineering cost characteristic coefficient, where m and n represent the quantity of geographical features and engineering cost characteristics of the project, respectively, and ∈ represents the error term.

6. The method for accurate cost range verification based on geographical region characteristics as described in claim 1, characterized in that, Based on the project's projected cost, cost verification is performed by comparing it with the cost range, including: Compare the predicted cost range with the preset cost range to determine whether the predicted cost range of the project is within the preset cost range; The preset cost range is a cost confidence interval generated based on historical engineering data, geographical features, and cost indicators. The boundary of the preset cost range is calibrated in real time using real-time data.

7. The method for accurate cost range verification based on geographical region characteristics as described in claim 6, characterized in that, Adjustments and optimizations to the project cost include: If the predicted cost range exceeds the preset cost range, calculate the quantitative value of the deviation between the predicted cost range and the preset cost range, as well as the contribution of geographical features; The corresponding cost verification deviation level is determined based on the deviation quantification value. Based on the cost verification deviation level and the comparison results of the contribution of geographical features and the threshold of the contribution of geographical features, the risk level of the project cost is determined. Based on the risk level, the project cost is adjusted to generate a cost adjustment plan, which includes adjustments to the project design, optimization of the construction plan, and adjustments to the project materials.

8. A cost range precision verification system based on geographical region characteristics, employing the cost range precision verification method based on geographical region characteristics as described in any one of claims 1 to 7, characterized in that, include, The data acquisition module is used to collect project engineering data and perform data preprocessing. The feature extraction module is used to extract features based on the project engineering data to obtain the project's geographical features and engineering cost features, and to perform feature analysis. The model building module is used to construct a project cost model based on the feature analysis results of the project's geographical features and engineering cost features, and to calculate the predicted cost range of the project. The verification module is used to verify the project cost based on the project's predicted cost range by comparing it with a preset cost range, and to determine whether the project cost exceeds the preset cost range. If it exceeds the cost range, the project cost is adjusted and optimized.

9. A computer device, characterized in that, include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the method for accurate verification of cost range based on geographical region characteristics as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores computer-executable instructions, which, when executed by a processor, implement the steps of the method for accurate cost range verification based on geographical region characteristics as described in any one of claims 1 to 7.

Images