Engineering project dynamic cost management and control system

Abstract

The invention discloses an engineering project dynamic cost management and control system, which relates to the technical field of engineering project management, and comprises the following steps of: in a data acquisition layer, acquiring multi-dimensional data such as energy consumption of construction equipment, water and electricity consumption, design budget, purchase contract, construction progress and the like in real time by virtue of butt joint between Internet of Things equipment and a multi-service system AP I; the collected data is cleaned and standardized, real-time cost data is dynamically compared with budget and historical data, an analysis report is generated by calculating a cost deviation coefficient (CDC), abnormal early warning is triggered according to a multi-level threshold value, a cost prediction model is trained based on a machine learning algorithm, and the real-time cost prediction is realized. The cost fluctuation trend and risk level evaluation of each link are output, prospective anticipation of risks is achieved, data barriers of departments such as design, purchase, construction and finance are broken through, multi-terminal real-time access and sharing are supported, all departments can collaboratively formulate and execute processing schemes online, whole-process closed-loop management is achieved, and economic benefits are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering project management, and in particular to a dynamic cost control system for engineering projects. Background Art

[0002] In the field of engineering project management, the importance of cost control is self-evident.

[0003] In the prior art, for example, patent publication number CN113780991B discloses a cost management system for an engineering project, which implements control by formulating a project budget table and regularly checking cost data.

[0004] This patent relies on structured data in business systems (such as contract lists and change orders), but lacks the ability to directly collect real-time data from the construction site. Dynamic data such as fluctuations in fuel consumption and material loss of construction equipment cannot be fed back into the cost model in real time, resulting in delayed detection of cost deviations.

[0005] Data from design, procurement, and construction processes still relies on manual entry or static integration between systems. Design changes must be manually synchronized to the cost system, without automatically linking to procurement contracts and construction schedule adjustments, resulting in inefficient cross-departmental collaboration.

[0006] This patent does not involve machine learning or historical data mining. The cost deviation analysis is based only on the comparison of current data with target costs, and lacks the prediction of future cost trends. For example, it is impossible to predict the impact of material price fluctuations on subsequent costs based on historical project data, making it difficult to identify potential risks in advance.

[0007] The "2024 China Construction Industry Development Report" reports that over 60% of construction projects experience varying degrees of cost overruns. Traditional methods, lacking in real-time data, multi-dimensional collaborative analysis, and intelligent forecasting, make it difficult to meet the demands of modern, refined project management. To address this, we propose a project cost management system. Summary of the Invention

[0008] The purpose of the present invention is to provide a dynamic cost control system for engineering projects to solve the problem of difficulty in timely cost prediction raised in the above background technology.

[0009] In order to achieve the above-mentioned object of the invention, the present invention adopts the following technical solutions:

[0010] The present invention provides a dynamic cost control system for engineering projects, comprising:

[0011] S101, a data collection module, for collecting cost data of each link of the engineering project in real time through IoT devices and business system API interfaces. The cost data includes budget data of the design phase, contract data of the procurement phase, and progress and expense data of the construction phase;

[0012] S102, a data processing module, which is in communication with the data acquisition module and is used to clean and standardize the collected cost data and build a multi-dimensional cost database based on a preset data model;

[0013] S103, a dynamic monitoring module, which is in communication with the data processing module, is used to dynamically compare the real-time cost data with the project budget and historical data to establish a cost deviation coefficient formula:

[0014]

[0015] Among them C r C is the actual cost data collected in real time at a certain stage. b is the budget cost data for this stage, C h-b Generate a cost deviation analysis report based on the average value of historical cost data for that period and trigger an abnormal cost warning;

[0016] S104, an intelligent prediction module, which is in communication with the dynamic monitoring module, trains historical data in the cost database based on a machine learning algorithm to build a cost prediction model:

[0017]

[0018] Where Y is the predicted cost, X i is the factor affecting the cost, β i is the corresponding coefficient, ∈ is the error term; coefficient β i Determined by the least squares method;

[0019] S105, collaborative management module, is used to break down data barriers between design, procurement, construction, finance and other departments, and supports real-time sharing of cost data and deviation handling solutions among multiple participants.

[0020] Preferably, the Internet of Things devices include but are not limited to sensors, smart electricity meters, and smart water meters installed on the construction equipment, which are used to collect energy consumption cost data and water consumption cost data of the construction equipment in real time.

[0021] Preferably, the business system API interface includes a design software system API interface, a procurement management system API interface, and a construction management system API interface, which are respectively used to obtain detailed budget data in the design stage, contract details data in the procurement stage, and specific progress and cost details data in the construction stage.

[0022] Preferably, the data cleaning process includes removing duplicate data, erroneous data and missing data in the collected cost data, and processing the missing data by using mean filling, median filling or a prediction filling method based on machine learning.

[0023] Preferably, the standardization process is to convert the collected cost data in different formats and units into a standard format and unit.

[0024] Preferably, the cost deviation analysis report includes the specific value of the cost deviation, analysis of the main causes of the deviation, and an assessment of the impact on the subsequent costs of the project. The report is presented in the form of visual charts and detailed text descriptions.

[0025] Preferably, the abnormal cost warning sets multiple warning thresholds, and when the cost deviation coefficient CDC exceeds different thresholds, different levels of warnings are triggered respectively.

[0026] Preferably, the influencing factor X in the cost prediction model is i It also includes macroeconomic factors such as market raw material price index and labor market price fluctuation index.

[0027] Preferably, in the dynamic monitoring module, a quantitative assessment of cost risk is achieved by constructing a comprehensive cost fluctuation factor, and the comprehensive cost fluctuation factor is calculated by taking a weighted average of the fluctuation amplitudes of multiple cost influencing factors.

[0028] Preferably, the collaborative management module supports multiple participants to access and share cost data and deviation processing solutions in real time through mobile clients and web pages. The system has data access permission management function, and different participants access different levels of data according to their roles and permissions.

[0029] Compared with the existing technology, one or more of the above technical solutions have the following beneficial effects:

[0030] This system builds an integrated dynamic management system focused on the full lifecycle cost control needs of engineering projects. At the data collection level, IoT devices connect to multiple business system APIs to collect real-time, multi-dimensional data on construction equipment energy consumption, water and electricity usage, design budgets, procurement contracts, and construction progress, ensuring timeliness and comprehensiveness. This collected data is cleaned, standardized, and stored in a multi-dimensional cost database, laying a solid foundation for subsequent analysis.

[0031] In the cost monitoring and forecasting phase, the system dynamically compares real-time cost data with budget and historical data, generates analysis reports by calculating the cost deviation coefficient (CDC), and triggers abnormality warnings based on multi-level thresholds. Simultaneously, a cost forecasting model trained using machine learning algorithms outputs cost fluctuation trends and risk level assessments for each link, enabling forward-looking risk prediction.

[0032] In terms of collaborative management, the system breaks down data barriers between departments such as design, procurement, construction, and finance, supports real-time multi-device access and sharing, and assigns permissions based on roles to ensure data security and control. When cost deviations occur, departments can collaborate online to develop and implement solutions, achieving closed-loop management of the entire process. These features effectively address the shortcomings of traditional cost control models in terms of real-time data, collaborative analysis, and intelligent forecasting, helping projects improve economic efficiency and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0034] Figure 1 This is a schematic diagram of the overall structure proposed according to one embodiment of the present invention;

[0035] Figure 2 This is a schematic diagram of the overall system architecture proposed according to one embodiment of the present invention;

[0036] Figure 3 2. It is a detailed structural diagram of a data acquisition module proposed according to one embodiment of the present invention;

[0037] Figure 4 This is a schematic diagram of a data processing module flow according to an embodiment of the present invention;

[0038] Figure 5 Schematic diagram of a monitoring and prediction interaction architecture proposed according to one embodiment of the present invention;

[0039] Figure 6 It is a schematic diagram of a collaborative management module proposed according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0041] See also Figures 1-6 The present invention provides a dynamic cost control system for engineering projects, including installing various types of Internet of Things devices at the engineering project site for real-time collection of cost-related data, and installing sensors on construction equipment, such as fuel consumption sensors and power sensors, to monitor the energy consumption of the construction equipment in real time. These sensors transmit the collected energy consumption data to a data acquisition gateway via wireless communication technology, and the gateway then uploads the data to the system server. Smart electricity meters and smart water meters are installed to record the electricity and water consumption at the construction site, respectively. The smart electricity meters and smart water meters have the function of remote data transmission, and can regularly send energy consumption data to the system for calculating the water and electricity costs during the construction phase.

[0042] By connecting to API interfaces of business systems such as design software systems, procurement management systems, and construction management systems, cost data for each stage of the project can be obtained: By connecting to the design software system, detailed budget data for the design phase can be obtained, including the list of materials required for the design plan, labor cost estimates, and equipment rental costs. By connecting to the procurement management system, contract data for the procurement phase can be obtained in real time, such as the contract amount, purchase quantity, and supplier information. By connecting to the construction management system, progress and cost data for the construction phase can be collected, including actual work completed, construction personnel attendance records, and the length of time construction equipment is in use.

[0043] Clean the collected cost data to remove duplicate data, erroneous data, and missing data: For duplicate data, identify it by comparing the key information of the data (such as contract number, construction date, etc.), and delete the duplicate records. For erroneous data, judge and correct it according to the logical relationship and business rules of the data. If the amount in a certain procurement contract data is found to be negative, it will be marked as erroneous data and corrected after verification with the procurement management system. For missing data, choose the appropriate filling method based on the characteristics of the data and business needs. For numerical data, you can use mean filling, median filling, or machine learning-based predictive filling methods; for text data, you can infer based on the context or supplement it through manual intervention.

[0044] Standardize the cleaned data to unify the data format and units. Date data in different formats will be converted to a standard date format. Procurement contract data in different currencies will be converted based on the project base currency. If the project base currency is RMB and some procurement contract data is denominated in USD, USD will be converted to RMB based on the real-time exchange rate.

[0045] Based on a pre-set data model, the standardized data is stored in a multi-dimensional cost database. This database uses either a relational or non-relational database, categorizing and storing data based on type and purpose to facilitate subsequent query and analysis.

[0046] Dynamically compare the real-time collected cost data with the project budget data and historical data to calculate the cost deviation coefficient CDC:

[0047]

[0048] Among them C r C is the actual cost data collected in real time at a certain stage. b is the budget cost data for this stage, C h-b Generate a cost deviation analysis report based on the average value of historical cost data for that period and trigger an abnormal cost warning;

[0049] Generate a cost deviation analysis report based on the calculation results of the cost deviation coefficient.

[0050] The report includes: the specific values ​​and trends of cost deviations, visualized through charts (e.g., line graphs, bar charts, etc.). An analysis of the primary causes of the deviations, analyzing whether they are due to design changes, purchase price fluctuations, or construction delays, based on the actual project situation. An assessment of the impact on subsequent project costs, predicting future cost trends based on current cost deviations, and providing corresponding recommendations and measures.

[0051] Set multiple levels of warning thresholds. When the cost deviation coefficient (CDC) exceeds different thresholds, different levels of warnings are triggered. When the CDC exceeds the first warning threshold, the system sends an alert message to project managers via SMS or email, reminding them to pay attention to cost changes. When the CDC exceeds the second warning threshold, in addition to sending SMS and email alerts, the system also pops up an alert window on the system interface, prompting project managers to take urgent measures.

[0052] Based on machine learning algorithms, historical data in the cost database is trained to build a cost prediction model:

[0053]

[0054] Where Y is the predicted cost, X i is the factor affecting the cost, β i is the corresponding coefficient, ∈ is the error term; coefficient β iDetermined through the least squares method; based on the cost forecast model and the calculation results of the comprehensive cost fluctuation factor, the cost fluctuation trend and risk level assessment for each link are output. Cost fluctuation trends are displayed through charts (such as trend line charts), and risk level assessments are presented in the form of text descriptions and risk level labels (such as low risk, medium risk, and high risk).

[0055] Machine learning algorithms can process vast amounts of historical data, uncovering complex relationships and hidden patterns that are difficult to detect using traditional analytical methods. They comprehensively consider various cost-influencing factors and their interactions. Compared to forecasting methods based on experience or simple statistical models, they can more accurately predict costs, reduce the subjectivity and errors of human judgment, and ensure that forecasts are closer to reality. Through continuous training and learning from historical data, the model can predict future cost fluctuations. By combining comprehensive cost volatility factors, it can proactively identify potential cost risks and present them intuitively in the form of risk level assessments. This foresight allows project managers to take pre-emptive measures to avoid cost overruns and mitigate project risks. Engineering projects are subject to a variety of factors, including market price fluctuations, design changes, and changes in construction schedules, resulting in complex and dynamic cost structures. Machine learning models can dynamically adjust parameters based on real-time data, adapting to changes in the project environment and promptly reflecting the impact of new circumstances on costs. Compared to traditional models based on fixed rules, they can better cope with uncertainty and ensure predictive effectiveness.

[0056] By establishing data interfaces and data sharing platforms, the data barriers between departments such as design, procurement, construction, and finance are broken down. The business systems of various departments are connected to the collaborative management module to achieve real-time synchronization and sharing of data, and support multiple participants to access and share cost data and deviation processing solutions in real time through mobile clients and web pages. The system has data access permission management functions, and different access levels are assigned according to the roles and permissions of different participants. Project managers can view the overall cost data of the project, cost deviation analysis reports, and risk level assessment results, and make decisions and management. Designers can view cost data and deviations in the design phase to optimize and adjust the design plan. Procurement personnel can grasp the cost data and contract execution status of the procurement phase in real time and adjust procurement strategies in a timely manner. Construction personnel can view the progress and cost data of the construction phase to ensure cost control during the construction process. Financial personnel can review and calculate the cost data of the project and provide financial support and decision-making recommendations.

[0057] When cost deviations occur, the collaborative management module supports collaboration across departments to jointly develop and implement deviation resolution plans. Departments can communicate and exchange information in real time within the system, providing feedback on resolution progress and results to ensure effective implementation of the resolution plan.

[0058] This system can realize the real-time collection, processing, monitoring, prediction and collaborative management of cost data of each link of the engineering project, helping project managers to timely discover cost deviations and risks, take effective measures for cost control and risk management, and improve the economic benefits and management level of the engineering project.

[0059] Working principle:

[0060] Data collection: IoT devices are installed on project sites, such as fuel consumption and power consumption sensors on construction equipment, as well as smart electricity and water meters. These collect real-time data on equipment energy consumption, water, and electricity usage, and upload it to a server via wireless communication. Furthermore, APIs are used to connect with business systems such as design, procurement, and construction to obtain cost data for each process.

[0061] Data processing involves cleaning collected data to remove duplicate, erroneous, and missing data. Duplicate data is identified and deleted by comparing key information. Erroneous data is corrected based on logical relationships and business rules. Missing data is filled in using appropriate methods based on data characteristics and requirements. Standardization is then performed to unify data formats and units, such as date format and currency, before storage in a multi-dimensional cost database.

[0062] Cost monitoring dynamically compares real-time cost data with budget data and historical data to calculate the cost deviation coefficient (CDC). Based on the CDC, a cost deviation analysis report is generated, including the deviation value, trend, cause, and impact assessment on subsequent costs. Multiple warning thresholds can be set to trigger different levels of warnings.

[0063] Cost forecasting: Using machine learning algorithms to train historical data from the cost database, we build a cost forecasting model. This model, combined with the calculation of comprehensive cost fluctuation factors, outputs cost fluctuation trends and risk level assessments for each link, presenting them in charts and text.

[0064] Collaborative management, data interfaces, and sharing platforms break down data barriers between departments. Each department's business system connects to the collaborative management module, enabling real-time data synchronization and sharing. The system assigns access levels based on roles and permissions. When cost deviations occur, departments can collaborate on developing and executing solutions, providing real-time feedback on progress and results.

[0065] Through the coordinated operation of the above links, comprehensive and dynamic management of engineering project costs can be achieved, and cost control and risk management capabilities can be improved.

[0066] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A dynamic cost control system for engineering projects, characterized by: include: S101, a data collection module, for collecting cost data of each link of the engineering project in real time through IoT devices and business system API interfaces. The cost data includes budget data of the design phase, contract data of the procurement phase, and progress and expense data of the construction phase; S102, a data processing module, which is in communication with the data acquisition module and is used to clean and standardize the collected cost data and build a multi-dimensional cost database based on a preset data model; S103, a dynamic monitoring module, which is in communication with the data processing module, is used to dynamically compare the real-time cost data with the project budget and historical data to establish a cost deviation coefficient formula: Among them C r C is the actual cost data collected in real time at a certain stage. b is the budget cost data for this stage, C h-b Generate a cost deviation analysis report based on the average value of historical cost data for that period and trigger an abnormal cost warning; S104, an intelligent prediction module, which is in communication with the dynamic monitoring module, trains historical data in the cost database based on a machine learning algorithm to build a cost prediction model: Where Y is the predicted cost, X i is the factor affecting the cost, β i is the corresponding coefficient, ∈ is the error term; coefficient β i Determined by the least squares method; S105, collaborative management module, is used to break down data barriers between design, procurement, construction, finance and other departments, and supports real-time sharing of cost data and deviation handling solutions among multiple participants.

2. The dynamic cost control system for engineering projects according to claim 1 is characterized in that: The IoT devices include but are not limited to sensors, smart electricity meters, and smart water meters installed on construction equipment, which are used to collect energy consumption cost data and water consumption cost data of construction equipment in real time.

3. The dynamic cost control system for engineering projects according to claim 1 is characterized in that: The business system API interface includes the design software system API interface, the procurement management system API interface, and the construction management system API interface, which are respectively used to obtain detailed budget data in the design stage, contract details data in the procurement stage, and specific progress and cost details data in the construction stage.

4. The dynamic cost control system for engineering projects according to claim 1, characterized in that: The data cleaning process includes removing duplicate data, erroneous data and missing data in the collected cost data, and processing the missing data using mean filling, median filling or prediction filling methods based on machine learning.

5. The dynamic cost control system for engineering projects according to claim 1 is characterized in that: The standardization process is to convert the collected cost data in different formats and units into a standard format and unit.

6. The dynamic cost control system for engineering projects according to claim 1, characterized in that: The cost deviation analysis report includes the specific values ​​of the cost deviation, analysis of the main causes of the deviation, and an assessment of the impact on the subsequent costs of the project. The report is presented in the form of visual charts and detailed text descriptions.

7. The dynamic cost control system for engineering projects according to claim 1, characterized in that: The abnormal cost warning sets multiple levels of warning thresholds. When the cost deviation coefficient CDC exceeds different thresholds, different levels of warnings are triggered respectively.

8. The engineering project dynamic cost control system according to claim 1, characterized in that: The influencing factor X in the cost prediction model i It also includes macroeconomic factors such as market raw material price index and labor market price fluctuation index.

9. The dynamic cost control system for engineering projects according to claim 1, characterized in that: In the dynamic monitoring module, a quantitative assessment of cost risk is achieved by constructing a comprehensive cost fluctuation factor, which is obtained by calculating the weighted average of the fluctuation ranges of multiple cost influencing factors.

10. The engineering project dynamic cost control system according to claim 1, characterized in that: The collaborative management module supports multiple participants to access and share cost data and deviation processing solutions in real time through mobile clients and web pages. The system has data access permission management function, and different participants can access different levels of data according to their roles and permissions.

Images