Engineering cost data calculation management system and method

Abstract

The invention relates to the technical field of project management, in particular to a project cost data calculation management system and method.The project cost data calculation management system comprises a data acquisition module, a data modeling module, a data fusion and optimization module, a dynamic analysis and early warning module, a cost analysis module and a data storage module; a global cost prediction model is established through standardized processing of acquired multi-dimensional data, and real-time data is dynamically analyzed in a project implementation process to generate a cost control report and an adjustment suggestion. And after the project is completed, the system comprehensively analyzes all cost data and generates a multi-dimensional cost analysis report. The security and expandability of data are guaranteed by adopting a distributed storage technology, and the confidentiality and integrity of the data are ensured through a multi-user authority management function. According to the invention, the accuracy, real-time performance and safety of engineering cost management can be effectively improved, and comprehensive support is provided for cost control and optimization of an engineering project.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering management, and in particular to an engineering cost data calculation management system and method. Background Art

[0002] In the field of construction engineering, project cost management is one of the important links for project success. As the scale and complexity of projects increase, accurately predicting and controlling project costs becomes increasingly critical. Traditional project cost management usually relies on manual calculations and empirical judgments, involving the extraction of information from multidimensional data such as design drawings, bills of quantities, market material prices, and comprehensive analysis. However, this manual method is not only time-consuming and labor-intensive, but also prone to data errors, leading to budget overruns or waste of project funds. At the same time, with the development of information technology, more and more engineering projects have begun to use BIM models, CAD drawings, and project management systems to assist in cost management and forecasting. These digital tools provide new data sources and a higher level of automation for project cost management.

[0003] However, the existing technologies still have some obvious technical problems in engineering cost management. First, due to the diversity of data sources and non-uniform formats, data integration is difficult, which in turn affects the accuracy of cost forecasting. Secondly, the existing cost forecasting model lacks flexibility and adaptability, and cannot dynamically adjust model parameters and weights to cope with the ever-changing actual situation during the project. In addition, traditional systems also have shortcomings in data storage and security management, and it is difficult to cope with the security requirements of large-scale data storage and the collaborative management requirements of multiple users. These technical problems make it difficult to implement engineering cost management efficiently in practice, which restricts the effect of project cost control and optimization. Summary of the invention

[0004] The invention provides a system and method for calculating and managing engineering cost data.

[0005] A method for calculating and managing engineering cost data comprises the following steps: S1, data collection and processing: collect multi-dimensional data through various data source interfaces related to the project, including project planning, design drawings, market labor prices, bills of quantities and market material prices. The data sources include BIM models, CAD drawings, project management systems and market databases. Format and standardize the collected multi-dimensional data, and use data cleaning technology to remove redundant data and outliers; S2, data modeling and correlation analysis: Based on the processed multidimensional data, a global cost prediction model is established, which includes a construction quantity model, a material cost model, a labor cost model, and a time cost model. A multidimensional data analysis algorithm is used to perform correlation analysis on the data between different models, identify cost driving factors and potential risks, and thus generate a prediction result for the overall cost of the engineering project; S3, data fusion and optimization calculation: Based on the global cost prediction model constructed in S2, data fusion technology is used to comprehensively process data from different sources to improve the accuracy and robustness of the data. During the data fusion process, machine learning algorithms are used to train historical data to further optimize the global cost prediction model, automatically adjust parameters and weights to meet the needs of different types of projects, and update them in real time; S4, dynamic cost control and early warning: Based on the optimized global cost prediction model, the real-time data during the project implementation is dynamically analyzed to generate real-time cost control reports, predict future cost change trends, and set multiple cost early warning thresholds in combination with cost control goals. When the actual cost approaches or exceeds the preset threshold, the system automatically triggers an early warning and provides specific adjustment suggestions; S5, cost analysis and report generation: After the project is completed, the system conducts a comprehensive analysis of all cost data and generates a multi-dimensional cost analysis report, including overall project cost analysis, cost distribution at each stage, and budget deviation analysis; S6, Data Storage and Management: All generated data and reports are stored in a cloud database, using distributed storage technology to ensure data security and scalability.

[0006] Optionally, the S1 specifically includes: S11. Establishment of data source interface: interface connection of various data sources related to the project; S12. Multidimensional data collection: Collect multidimensional data from various data sources through established interfaces; S13. Data formatting: formatting the collected multidimensional data; S14. Data standardization: Standardize the formatted data to facilitate subsequent analysis and calculation.

[0007] Optionally, the S2 specifically includes: S21, Engineering quantity model: Based on the processed multidimensional data, a linear regression algorithm is used to establish an engineering quantity model to predict the various engineering quantities required in the project; S22, material cost model: Based on the collected market material price data and the output of the engineering quantity model, a material cost model is established using the weighted average method to estimate the cost of different materials; S23, labor cost model: Based on the collected project planning and market labor price data, a labor cost model is established using a multivariate linear regression algorithm to estimate the labor cost required in the project; S24, time cost model: Based on the project planning data, a time cost model is established using the time series analysis method to evaluate the time cost required for the project; S25, multidimensional data analysis and correlation analysis: using multidimensional data analysis algorithms, correlation analysis is performed on the output data of the engineering quantity model, material cost model, labor cost model, and time cost model, and principal component analysis is used to identify the main cost drivers; S26, Potential Risk Identification: Based on the correlation of multi-dimensional data, use correlation analysis and regression analysis to identify potential cost risks; S27, comprehensive generation of a global cost prediction model: Integrate the output results of the engineering quantity model, material cost model, labor cost model and time cost model to generate a global cost prediction model.

[0008] Optionally, the S3 specifically includes: S31, multi-source data fusion: the multi-dimensional data in S1 that has been cleaned, formatted and standardized is fused using the weighted average method; S32, training of machine learning algorithms: using the random forest algorithm to train and optimize historical data, and enhancing the accuracy of the global cost prediction model through cross-validation and hyperparameter adjustment; SS33, real-time update and optimization: using incremental learning and real-time feedback mechanisms to dynamically adjust model parameters and weights to ensure the continued adaptability and accuracy of the global cost forecasting model in different projects.

[0009] Optionally, the S4 specifically includes: S41, real-time data monitoring and collection: collect real-time data during project implementation, including material usage, labor input, equipment usage and progress; S42, Dynamic Analysis and Cost Control Report Generation: Based on the optimized global cost prediction model, dynamic analysis is performed on real-time data to generate a cost control report containing current costs and future cost trends; S43, cost warning threshold setting: according to the cost control target of the project, set and adjust the cost warning threshold in real time to ensure the flexibility of the warning mechanism; S44, early warning triggering and adjustment suggestion generation: When the actual cost reaches or exceeds the early warning threshold, the system automatically triggers an early warning and generates adjustment suggestions.

[0010] Optionally, the S5 specifically includes: S51, Cost data collation: Summarize and collate all cost data after the project is completed to ensure that the data is complete and free of anomalies, providing a basis for subsequent analysis; S52, Multi-dimensional Cost Analysis: Multi-dimensional analysis of the aggregated cost data, including overall project cost analysis, cost distribution analysis at each stage, and budget deviation analysis; S53, cost analysis report generation: Generate a comprehensive cost analysis report, use visualization technology to display the analysis results, and support output and archiving in multiple formats.

[0011] Optionally, the S6 includes: S61, Data storage: Design and configure a cloud database to categorize and store the generated cost data and reports to ensure orderly management and fast retrieval of data; S62, Storage Structure: Apply distributed storage technology to ensure data security, high availability and scalability through data redundancy, encryption and automatic expansion.

[0012] Optionally, the S6 includes data backup and recovery functions. The cloud database is configured with a regular automatic backup strategy to ensure that data can be restored in time in the event of an accident. The backup data is stored in an independent disaster recovery center. A disaster recovery plan is formulated and implemented, including data recovery priority and recovery time objectives, to ensure that data and services can be restored in the event of data loss or system failure.

[0013] Optionally, the S6 includes a multi-user authority management function, which defines different user roles according to the structure and responsibilities of the project team, such as project manager, data analyst, engineer, auditor, etc. Each role defines a different scope of authority, and the operation authority covers data access, editing, exporting and deletion. It also supports real-time dynamic adjustment of user authority according to the progress of the project and changes in the responsibilities of team members, ensuring the flexibility and adaptability of authority allocation.

[0014] A construction cost data calculation management system, used to implement the above-mentioned construction cost data calculation management method, includes the following modules: Data collection module: used to collect multi-dimensional data including project planning, design drawings, bill of quantities and market material prices through various data source interfaces related to engineering projects, and to format, standardize and clean the collected multi-dimensional data; Data modeling module: used to establish a global cost prediction model based on the processed multi-dimensional data. The global cost prediction model includes a construction quantity model, a material cost model, a labor cost model, and a time cost model, and to perform correlation analysis on the data between different models to identify key cost drivers and potential risks, and generate prediction results for the overall cost of the project; Data fusion and optimization module: It is used to comprehensively process data from different sources using data fusion technology based on the global cost prediction model, and train historical data through machine learning algorithms to optimize the global cost prediction model, automatically adjust parameters and weights to meet the needs of different types of projects, and achieve real-time updates; Dynamic analysis and early warning module: It is used to dynamically analyze the real-time data during the project implementation process based on the optimized global cost prediction model, generate real-time cost control reports, predict future cost change trends, set multiple cost early warning thresholds, and automatically trigger early warnings and provide specific adjustment suggestions when the actual cost approaches or exceeds the predetermined threshold; Cost analysis module: used to conduct a comprehensive analysis of all cost data after the project is completed and generate a multi-dimensional cost analysis report, including overall project cost analysis, cost distribution at each stage, and budget deviation analysis; Data storage module: used to store all generated data and reports in the cloud database, and adopts distributed storage technology to ensure data security and scalability.

[0015] Beneficial effects of the present invention: The present invention, through a systematic data collection and processing module, can collect multidimensional data from multiple sources (such as BIM models, CAD drawings, project management systems and market databases), and format, standardize and clean them. This process ensures the accuracy and consistency of input data, effectively reduces calculation errors caused by inconsistent data formats or abnormal values, and thus improves the accuracy and reliability of subsequent cost forecasts.

[0016] The present invention uses historical data to train and optimize the global cost prediction model through data modeling, data fusion and optimization modules, and adjusts the model parameters and weights in real time to meet the needs of different types of projects. This mechanism enables the system to dynamically respond to real-time data changes during project implementation, generate real-time cost control reports, and predict future cost trends. At the same time, the system's early warning function can trigger early warnings and make adjustment suggestions in a timely manner when cost overrun risks are detected, thereby ensuring the timeliness and effectiveness of project cost management.

[0017] The present invention, by adopting distributed storage technology and multi-user authority management functions, not only ensures the secure storage and high availability of project data, but also protects the confidentiality and integrity of data through fine-grained authority control. The system supports hierarchical access and operation authority management for different user roles, enabling project teams to collaborate flexibly and effectively while ensuring data security, and provides audit logs and monitoring functions to ensure the traceability of operations and the transparency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A schematic diagram of a method flow of an embodiment of the present invention; Figure 2 Schematic diagram of a system flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0021] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0022] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0023] like Figure 1 As shown, a method for calculating and managing engineering cost data includes the following steps: S1, data collection and processing: collect multi-dimensional data through various data source interfaces related to the project. The multi-dimensional data includes project planning, design drawings, market labor prices, bills of quantities and market material prices. The data sources include BIM models, CAD drawings, project management systems and market databases. The collected multi-dimensional data are formatted and standardized, and data cleaning technology is used to remove redundant data and outliers. S2, data modeling and correlation analysis: Based on the processed multi-dimensional data, a global cost prediction model is established. The global cost prediction model includes the engineering quantity model, material cost model, labor cost model and time cost model. The multi-dimensional data analysis algorithm is used to perform correlation analysis on the data between different models, identify cost driving factors and potential risks, and thus generate prediction results for the overall cost of the engineering project; S3, data fusion and optimization calculation: Based on the global cost prediction model constructed in S2, data fusion technology is used to comprehensively process data from different sources to improve the accuracy and robustness of the data. During the data fusion process, machine learning algorithms are used to train historical data to further optimize the global cost prediction model, automatically adjust parameters and weights to meet the needs of different types of projects, and update them in real time; S4, dynamic cost control and early warning: Based on the optimized global cost prediction model, the real-time data during the project implementation is dynamically analyzed to generate real-time cost control reports, predict future cost change trends, and set multiple cost early warning thresholds in combination with cost control goals. When the actual cost approaches or exceeds the preset threshold, the system automatically triggers an early warning and provides specific adjustment suggestions; S5, cost analysis and report generation: After the project is completed, the system conducts a comprehensive analysis of all cost data and generates a multi-dimensional cost analysis report, including overall project cost analysis, cost distribution at each stage, and budget deviation analysis; S6, Data Storage and Management: All generated data and reports are stored in a cloud database, using distributed storage technology to ensure data security and scalability.

[0024] S1 specifically includes: S11. Establishment of data source interface: Interface connection of various data sources related to the project, including: BIM model interface: extract 3D building information model data from BIM software through API or plug-in; CAD drawing interface: extract 2D design drawing data from CAD files through file parsing or data conversion tools; Project management system interface: access the project management system through database query or API to obtain project planning and bill of quantities data; Market database interface: obtain market material price data through API or data crawling tools, and update it regularly; S12. Multidimensional data collection: Collect multidimensional data from various data sources through established interfaces, including: Project planning data: Obtain project master plan and project schedule from the project management system, such as project duration and time cost rate; Design drawing data: Extract design drawing data of architecture, structure, electromechanical and other disciplines from CAD drawings, such as dimensions in the design drawings; Bill of Quantities data: Extract the bill of quantities from the project management system, including the quantity and unit price information of each sub-item, such as the number of components and the type of building materials; Market material price data: obtain the price information of major building materials in the current market from the market database, covering the prices of materials of different brands and specifications; Market labor price: including labor type, working hours and unit price of work; S13. Data formatting: Format the collected multi-dimensional data to ensure that data from different data sources can be used uniformly, including: Data field mapping: Map fields in various data sources and unify naming conventions, for example, matching material identifiers in CAD drawings with material codes in market databases; Data type conversion: unify data types from different sources into a format that the system can recognize, such as converting dates in text format into a standard date format, and converting engineering quantities in different units into a unified measurement unit; Data structure normalization: storing data according to a predetermined structure, such as converting 2D CAD data into a database table format recognizable by the system, including geometric information and attribute information of building components; S14. Data standardization: Standardize the formatted data for subsequent analysis and calculation, including: Numerical data standardization: Use the z-score standardization method to process numerical data, expressed as: ; in, is the standardized value, is the original data value, is the mean of the data set, is the standard deviation of the data set; Data consistency check: ensure that the same data fields from different data sources are consistent. For example, the material information in the BIM model should be consistent with the material price information in the market database. By establishing data source interfaces, collecting multi-dimensional data, formatting data, standardizing data, and applying data cleaning technology, the integrity, consistency, and accuracy of the data are ensured, laying a solid foundation for the accurate calculation of project costs.

[0025] S2 specifically includes: S21, Engineering quantity model: Based on the processed multidimensional data, a linear regression algorithm is used to establish an engineering quantity model to predict various engineering quantities required in the project (such as earthwork, concrete, steel bar weight, etc.), including: (1) Data preparation: Extracting input data related to engineering quantities from the processed multidimensional data, such as dimensions and component quantities in the design drawings; (2) Feature selection: Select key features related to quantity prediction, such as the geometric properties of components (length, width, height) and the type of building materials, and construct a dataset; (3) Target variable: Set the engineering quantity (such as earthwork volume, concrete volume, steel bar weight, etc.) as the output target of the model; (4) Model establishment: The engineering quantity model is established using the linear regression algorithm, which is suitable for the linear relationship between input variables and output quantities. The model is expressed as: ; in, For the predicted engineering quantity, is the input feature variable, is the intercept term, is the regression coefficient, is the error term; (5) Model training: Divide the data set into a training set (80%) and a test set (20%), and use the training set data to train the model; (6) Model verification: Use test set data to verify model performance and ensure that the model can accurately predict engineering quantities; S22, Material cost model: Based on the collected market material price data and the output of the engineering quantity model, a material cost model is established using the weighted average method to estimate the cost of different materials, including: (1) Data collection: extracting market material price data, engineering quantity data predicted by the engineering quantity model, and project planning data, including the market unit price, specifications, and quantity of different materials; (2) Feature selection: Select the main features that affect material costs, such as material type, market unit price, and predicted engineering quantity; (3) Target variable: Set the total material cost as the output target of the model; (4) Model establishment: Use the weighted average method to establish a material cost model and calculate the total cost of different materials. The model is expressed as: ; in, is the total material cost, For the The quantity of materials, For the The market price of the material, is the number of material types; (4) Model optimization: adjust the weights of different materials according to their influence on the total cost so that the model can more accurately reflect the actual material cost; (5) Model evaluation and verification: Use material cost data from historical projects to verify the model, check the model's prediction error, analyze the source of the model's prediction error, and make necessary weight adjustments; S23, Labor cost model: Based on the collected project planning and market labor price data, a labor cost model is established using a multivariate linear regression algorithm to estimate the labor cost required in the project, including: (1) Data collection: extract relevant data such as labor type, working hours, unit price of work type, etc. from project planning data and market labor price data; (2) Feature selection: Select key features that affect labor costs, such as type of work, working hours, and task complexity; (3) Target variable: Set total labor cost as the output target of the model; (4) Model establishment: Use the multivariate linear regression algorithm to establish a labor cost model to predict the labor cost of each type of work. The model is expressed as: ; in, is the total labor cost, The time input for each type of work, is the intercept term, is the regression coefficient, is the error term; (5) Model training and optimization: The regression coefficients are optimized through the least squares method to ensure that the model can accurately predict labor costs. To avoid overfitting of the model, L1 regularization or L2 regularization is used to constrain the regression model. (6) Model evaluation and validation: Use historical labor cost data to validate the model, check the difference between the predicted results and the actual costs, and adjust the model parameters to improve the prediction accuracy based on the model evaluation results; S24, time cost model: Based on the project planning data, a time cost model is established using the time series analysis method to evaluate the time cost required for the project, including: (1) Data collection: extract relevant information from the project schedule, such as project duration and time cost rate; (2) Feature selection: Select key factors that affect time cost, such as task duration, delay risk, resource utilization, etc. (3) Target variable: Set the total time cost as the output target of the model; (4) Model establishment: Use time series analysis to establish a time cost model to predict the time cost required for the project. Consider the time dependence of historical data. The model is expressed as: ; in, is the total time cost, It is the key node time in the project schedule. is the intercept term, is the regression coefficient, is the error term; (5) Model training and optimization: Optimize the parameters of the time cost model to improve the prediction accuracy of the time cost. The parameters include the autoregressive order, the difference order, and the moving average order. Seasonal factors (such as the difficulty of construction in the rainy season) are introduced into the model to adjust the time cost prediction results. (6) Model evaluation and validation: Use time cost data from historical projects to validate the model, evaluate its accuracy at different project stages, analyze prediction errors, and adjust model parameters to improve its applicability in future projects; S25, multidimensional data analysis and correlation analysis: Use multidimensional data analysis algorithms to conduct correlation analysis on the output data of the engineering quantity model, material cost model, labor cost model, and time cost model, and use principal component analysis to identify the main cost driving factors. The specific steps include: (1) Data standardization: standardize the data output by the model; (2) Covariance matrix calculation: Calculate the covariance matrix between each cost variable; (3) Eigenvalue decomposition: Perform eigenvalue decomposition on the covariance matrix and extract the first few principal components; (4) Principal component analysis: select the main cost drivers based on their contribution rates; S26, potential risk identification: Based on the correlation of multidimensional data, correlation analysis and regression analysis are used to identify potential cost risks. The correlation between variables is calculated using the Pearson correlation coefficient, which is expressed as: ; in, For variables and The correlation coefficient between is the corresponding model output value, are their respective means; S27, comprehensive generation of a global cost prediction model: Integrate the output results of the engineering quantity model, material cost model, labor cost model and time cost model to generate a global cost prediction model. The global cost prediction model is obtained by calculating the weighted sum of the outputs of the engineering quantity model, material cost model, labor cost model and time cost model. The expression is: ; in, The overall cost forecast result of the project. is the material cost, For labor costs, For time cost, For the engineering quantity, The weights of the engineering quantity model, material cost model, labor cost model and time cost model are dynamically adjusted according to the results of the association analysis; By establishing engineering quantity models, material cost models, labor cost models and time cost models, and conducting multi-dimensional data analysis and correlation analysis, we ultimately generated a comprehensive global cost forecasting model that can accurately identify cost drivers and potential risks, providing a scientific basis for the overall cost forecast of engineering projects.

[0026] S3 specifically includes: S31, multi-source data fusion: The multi-dimensional data in S1 that has been cleaned, formatted and standardized is fused using the weighted average method to integrate data from different sources and improve the consistency and reliability of the data. The weighted average method is expressed as: ; in, is the fused data value, For the After processing the data from the data source, For the The weight of each data source is dynamically adjusted based on the credibility and historical performance of the data source; S32, training of machine learning algorithms: Use the Random Forest algorithm to train and optimize historical data, and enhance the accuracy of the global cost prediction model through cross-validation and hyperparameter adjustment. The specific steps are as follows: (1) Historical data set construction: Construct a historical data set, including the engineering quantity, material cost, labor cost, and actual cost data of previous projects, to provide a basis for model training; (2) Random forest model training: Use the random forest algorithm to train the historical data set and optimize the global cost prediction model, which is expressed as: ; in, is the predicted value, is the number of decision trees, For the The prediction results of a decision tree; (3) Model optimization: Optimize the parameters of the random forest model through cross-validation and hyperparameter adjustment (such as the number of decision trees, maximum depth, etc.) to ensure the prediction accuracy of the model in different types of projects; S33, real-time update and optimization: using incremental learning and real-time feedback mechanisms, dynamically adjust model parameters and weights to ensure the continuous adaptability and accuracy of the global cost prediction model in different projects. The steps are as follows: (1) Incremental learning: Through incremental learning technology, the model's predictive ability and adaptability are gradually improved by using new project data. The model will continuously absorb new data and update parameters and weights in real time to reflect the latest project conditions. (2) Real-time feedback and dynamic adjustment: The real-time feedback mechanism dynamically adjusts the prediction parameters of the model based on the actual data during the project implementation process to reduce errors. The dynamic weight adjustment mechanism redistributes weights based on new data to optimize the robustness of the model. Through data fusion technology, machine learning algorithm training and optimization, real-time update and feedback mechanism, the accuracy and adaptability of the global cost forecasting model have been further improved, enabling it to provide reliable cost forecasts in different project environments.

[0027] S4 specifically includes: S41, real-time data monitoring and collection: collect real-time data during project implementation, including material usage, labor input, equipment usage and progress; S42, Dynamic Analysis and Cost Control Report Generation: Based on the optimized global cost prediction model, dynamic analysis is performed on real-time data to generate a cost control report containing current costs and future cost trends, including: (1) Real-time dynamic analysis: Based on the optimized global cost prediction model, dynamic analysis algorithms (such as time series analysis) are used to dynamically analyze the real-time data of the project to evaluate the difference between the current cost and the expected cost; (2) Cost control report generation: Generate real-time cost control reports, including: Comparison of current actual costs with budget; analysis of cost overruns or savings; Forecast of future cost change trends; S43, Cost warning threshold setting: According to the cost control objectives of the project, set and adjust the cost warning threshold in real time to ensure the flexibility of the warning mechanism, including: (1) Definition of warning thresholds: According to the project cost control objectives, multiple cost warning thresholds are set. The warning thresholds include: General warning threshold: triggered when actual cost approaches 80% of budget; Warning threshold: triggered when the actual cost approaches 90% of the budget; Emergency warning threshold: triggered when actual cost reaches or exceeds budget; (2) Adaptive early warning: The early warning threshold is adjusted in real time according to the project progress, resource consumption rate and market price fluctuations to ensure the flexibility of the early warning mechanism; S44, early warning triggering and adjustment suggestion generation: When the actual cost reaches or exceeds the early warning threshold, the system automatically triggers an early warning and generates adjustment suggestions, including: (1) Automatic warning trigger: When the actual cost reaches or exceeds the set warning threshold, the system automatically triggers the warning and notifies the relevant person in charge via email, SMS or project management platform; (2) Adjustment suggestion generation: The system generates specific adjustment suggestions based on real-time data and historical project data, including: Project schedule adjustment suggestions: adjust the priority or schedule of tasks based on cost overruns or savings; Resource optimization suggestions: Based on resource usage, it is recommended to reallocate labor or equipment; Procurement and supply chain adjustment suggestions: Based on material price fluctuations, it is recommended to adjust the purchase batch or supplier selection; Through real-time data collection and dynamic analysis, combined with cost control reports, cost early warning mechanisms and adjustment suggestions, we ensure that the project can respond to cost changes in a timely manner during implementation, and effectively control costs through early warning mechanisms and adjustment measures to avoid budget overruns.

[0028] S5 specifically includes: S51, Cost Data Arrangement: Summarize and sort all cost data after the project is completed to ensure that the data is complete and free of abnormalities, providing a basis for subsequent analysis, including: (1) Data aggregation: After the project is completed, all cost data collected during the project implementation, including engineering quantity, material cost, labor cost and time cost, will be aggregated and stored in the cloud database; (2) Data collation: collate and clean the aggregated data to ensure that the data is complete, non-duplicate, and free of outliers, laying the foundation for subsequent analysis; S52, Multi-dimensional Cost Analysis: Multi-dimensional analysis of the aggregated cost data, including overall project cost analysis, cost distribution analysis at each stage, and budget deviation analysis, including: (1) Overall project cost analysis: Based on the aggregated cost data, the system calculates the total cost of the project and compares it with the initial budget, analyzes the actual implementation of the overall cost, generates a distribution chart of the total cost, and intuitively displays the proportion of each cost in the total budget; (2) Cost distribution analysis at each stage: The system conducts cost analysis at each stage in the project life cycle, evaluates the difference between actual expenditure and expected budget at each stage, generates a phased cost distribution report, and breaks down the cost expenditure in each time period to help management understand the cash flow at each stage; (3) Budget deviation analysis: The system calculates the deviation between the total project cost and the budget to determine whether there is a budget overrun or underrun. It performs deviation analysis on each cost category, identifies the cause of the deviation and generates a corresponding recommendation report, providing targeted adjustment strategies. S53, cost analysis report generation: Generate a comprehensive cost analysis report, use visualization technology to display the analysis results, and support output and archiving in multiple formats, including: (1) Multi-dimensional report generation: Generate a comprehensive analysis report covering the overall project cost, cost distribution at each stage, and budget deviation. The report content includes charts, data tables, and analysis conclusions. The report can be customized according to user needs and supports generating detailed cost analysis views by stage, category, and time period. (2) Visualization of reports: Data visualization technology is used to present cost analysis results in graphical form, including pie charts, bar charts and line charts, which are convenient for users to understand and make decisions. Dynamic interactive report presentation is supported, and users can view detailed analysis results of specific data through click and filter functions. (3) Report output and archiving: The system supports report output in multiple formats, including PDF, Excel, etc., which is convenient for users to save, share and print. The generated cost analysis report will be archived in the cloud database for subsequent review and long-term preservation; By summarizing and organizing cost data, conducting multi-dimensional cost analysis, generating cost analysis reports and visual displays, management can fully understand the cost execution of the project, identify budget deviations and provide a scientific basis for cost control of future projects.

[0029] S6 includes: S61, Data storage: Design and configure a cloud database to categorize and store the generated cost data and reports to ensure orderly management and fast retrieval of data; S62, Storage Structure: Apply distributed storage technology to ensure data security, high availability and scalability through data redundancy, encryption and automatic expansion.

[0030] S6 includes data backup and recovery functions. The cloud database is configured with a regular automatic backup strategy to ensure that data can be restored in time in the event of an accident. The backup data is stored in an independent disaster recovery center. A disaster recovery plan is formulated and implemented, including data recovery priorities and recovery time objectives, to ensure that data and services can be restored in the event of data loss or system failure.

[0031] S6 includes a multi-user permission management function. According to the structure and responsibilities of the project team, different user roles are defined, such as project manager, data analyst, engineer, auditor, etc. Each role defines a different scope of permissions. Operation permissions cover data access, editing, exporting and deletion. It also supports real-time dynamic adjustment of user permissions based on project progress and changes in team members' responsibilities, ensuring the flexibility and adaptability of permission allocation.

[0032] like Figure 2 As shown, a construction cost data calculation management system is used to implement the above-mentioned construction cost data calculation management method, including the following modules: Data collection module: used to collect multi-dimensional data including project planning, design drawings, bill of quantities and market material prices through various data source interfaces related to engineering projects, and to format, standardize and clean the collected multi-dimensional data; Data modeling module: used to establish a global cost prediction model based on the processed multi-dimensional data. The global cost prediction model includes a construction quantity model, a material cost model, a labor cost model, and a time cost model, and to perform correlation analysis on the data between different models to identify key cost drivers and potential risks, and generate prediction results for the overall cost of the project; Data fusion and optimization module: It is used to comprehensively process data from different sources using data fusion technology based on the global cost prediction model, and train historical data through machine learning algorithms to optimize the global cost prediction model, automatically adjust parameters and weights to meet the needs of different types of projects, and achieve real-time updates; Dynamic analysis and early warning module: It is used to dynamically analyze the real-time data during the project implementation process based on the optimized global cost prediction model, generate real-time cost control reports, predict future cost change trends, set multiple cost early warning thresholds, and automatically trigger early warnings and provide specific adjustment suggestions when the actual cost approaches or exceeds the predetermined threshold; Cost analysis module: used to conduct a comprehensive analysis of all cost data after the project is completed and generate a multi-dimensional cost analysis report, including overall project cost analysis, cost distribution at each stage, and budget deviation analysis; Data storage module: used to store all generated data and reports in the cloud database, and adopts distributed storage technology to ensure data security and scalability.

[0033] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0034] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for calculating and managing engineering cost data, characterized in that: The following steps are involved: S1, data collection and processing: collect multi-dimensional data through various data source interfaces related to the project, including project planning, design drawings, market labor prices, bills of quantities and market material prices. The data sources include BIM models, CAD drawings, project management systems and market databases. Format and standardize the collected multi-dimensional data, and use data cleaning technology to remove redundant data and outliers; S2, data modeling and correlation analysis: Based on the processed multidimensional data, a global cost prediction model is established, which includes a construction quantity model, a material cost model, a labor cost model, and a time cost model. A multidimensional data analysis algorithm is used to perform correlation analysis on the data between different models, identify cost driving factors and potential risks, and thus generate a prediction result for the overall cost of the engineering project; S3, data fusion and optimization calculation: Based on the global cost prediction model constructed in S2, data fusion technology is used to comprehensively process data from different sources. During the data fusion process, machine learning algorithms are used to train historical data to further optimize the global cost prediction model, automatically adjust parameters and weights to meet the needs of different types of projects, and update them in real time; S4, dynamic cost control and early warning: Based on the optimized global cost prediction model, the real-time data during the project implementation is dynamically analyzed to generate real-time cost control reports, predict future cost change trends, and set multiple cost early warning thresholds in combination with cost control goals. When the actual cost approaches or exceeds the preset threshold, the system automatically triggers an early warning and provides specific adjustment suggestions; S5, cost analysis and report generation: After the project is completed, the system conducts a comprehensive analysis of all cost data and generates a multi-dimensional cost analysis report, including overall project cost analysis, cost distribution at each stage, and budget deviation analysis; S6, Data Storage and Management: All generated data and reports are stored in a cloud database, using distributed storage technology to ensure data security and scalability.

2. A method for calculating and managing construction cost data according to claim 1, characterized in that: The S1 specifically includes: S11. Establishment of data source interface: interface connection of various data sources related to the project; S12. Multidimensional data collection: Collect multidimensional data from various data sources through established interfaces; S13. Data formatting: formatting the collected multidimensional data; S14. Data standardization: Standardize the formatted data to facilitate subsequent analysis and calculation.

3. A method for calculating and managing construction cost data according to claim 2, characterized in that: The S2 specifically includes: S21, Engineering quantity model: Based on the processed multidimensional data, a linear regression algorithm is used to establish an engineering quantity model to predict the various engineering quantities required in the project; S22, material cost model: Based on the collected market material price data and the output of the engineering quantity model, a material cost model is established using the weighted average method to estimate the cost of different materials; S23, labor cost model: Based on the collected project planning and market labor price data, a labor cost model is established using a multivariate linear regression algorithm to estimate the labor cost required in the project; S24, time cost model: Based on the project planning data, a time cost model is established using the time series analysis method to evaluate the time cost required for the project; S25, multidimensional data analysis and correlation analysis: using multidimensional data analysis algorithms, correlation analysis is performed on the output data of the engineering quantity model, material cost model, labor cost model and time cost model, and principal component analysis is used to identify the main cost driving factors; S26, Potential Risk Identification: Based on the correlation of multi-dimensional data, use correlation analysis and regression analysis to identify potential cost risks; S27, comprehensive generation of a global cost prediction model: Integrate the output results of the engineering quantity model, material cost model, labor cost model and time cost model to generate a global cost prediction model.

4. A method for calculating and managing construction cost data according to claim 3, characterized in that: The S3 specifically includes: S31, multi-source data fusion: the multi-dimensional data in S1 that has been cleaned, formatted and standardized is fused using the weighted average method; S32, training of machine learning algorithms: using the random forest algorithm to train and optimize historical data, and enhancing the accuracy of the global cost prediction model through cross-validation and hyperparameter adjustment; S33, real-time update and optimization: using incremental learning and real-time feedback mechanisms, dynamically adjust model parameters and weights to ensure the continuous adaptability and accuracy of the global cost prediction model in different projects.

5. A method for calculating and managing construction cost data according to claim 4, characterized in that: The S4 specifically includes: S41, real-time data monitoring and collection: collect real-time data during project implementation, including material usage, labor input, equipment usage and progress; S42, Dynamic Analysis and Cost Control Report Generation: Based on the optimized global cost prediction model, dynamic analysis is performed on real-time data to generate a cost control report containing current costs and future cost trends; S43, cost warning threshold setting: according to the cost control target of the project, set and adjust the cost warning threshold in real time to ensure the flexibility of the warning mechanism; S44, early warning triggering and adjustment suggestion generation: When the actual cost reaches or exceeds the early warning threshold, the system automatically triggers an early warning and generates adjustment suggestions.

6. A method for calculating and managing construction cost data according to claim 5, characterized in that: The S5 specifically includes: S51, Cost Data Arrangement: Summarize and organize all cost data after the project is completed to provide a basis for subsequent analysis; S52, Multi-dimensional Cost Analysis: Multi-dimensional analysis of the aggregated cost data, including overall project cost analysis, cost distribution analysis at each stage, and budget deviation analysis; S53, cost analysis report generation: Generate a comprehensive cost analysis report, use visualization technology to display the analysis results, and support output and archiving in multiple formats.

7. A method for calculating and managing construction cost data according to claim 6, characterized in that: The S6 includes: S61, Data storage: Design and configure a cloud database to categorize and store the generated cost data and reports; S62, Storage Structure: Apply distributed storage technology to ensure data security, high availability and scalability through data redundancy, encryption and automatic expansion.

8. A method for calculating and managing construction cost data according to claim 1, characterized in that: The S6 includes data backup and recovery functions. The cloud database is configured with a regular automatic backup strategy. The backup data is stored in an independent disaster recovery center. A disaster recovery plan is formulated and implemented, including data recovery priorities and recovery time objectives, to ensure that data and services can be restored in the event of data loss or system failure.

9. A method for calculating and managing construction cost data according to claim 1, characterized in that: The S6 includes a multi-user authority management function. Different user roles are defined according to the structure and responsibilities of the project team. Each role defines a different scope of authority. The operation authority covers data access, editing, exporting and deletion. It also supports real-time dynamic adjustment of user authority according to the progress of the project and changes in the responsibilities of team members.

10. A construction cost data calculation management system, used to implement a construction cost data calculation management method as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Data collection module: used to collect multi-dimensional data including project planning, design drawings, bill of quantities and market material prices through various data source interfaces related to engineering projects, and to format, standardize and clean the collected multi-dimensional data; Data modeling module: used to establish a global cost prediction model based on the processed multi-dimensional data. The global cost prediction model includes a construction quantity model, a material cost model, a labor cost model, and a time cost model, and to perform correlation analysis on the data between different models to identify key cost drivers and potential risks, and generate prediction results for the overall cost of the project; Data fusion and optimization module: It is used to comprehensively process data from different sources using data fusion technology based on the global cost prediction model, and train historical data through machine learning algorithms to optimize the global cost prediction model, automatically adjust parameters and weights to meet the needs of different types of projects, and achieve real-time updates; Dynamic analysis and early warning module: It is used to dynamically analyze the real-time data during the project implementation process based on the optimized global cost prediction model, generate real-time cost control reports, predict future cost change trends, set multiple cost early warning thresholds, and automatically trigger early warnings and provide specific adjustment suggestions when the actual cost approaches or exceeds the predetermined threshold; Cost analysis module: used to conduct a comprehensive analysis of all cost data after the project is completed and generate a multi-dimensional cost analysis report, including overall project cost analysis, cost distribution at each stage, and budget deviation analysis; Data storage module: used to store all generated data and reports in the cloud database, and adopts distributed storage technology to ensure data security and scalability.

Images