Engineering amount real-time generation and cost early warning system based on BIM and Ai dynamic pricing

Abstract

The invention relates to the technical field of project management, in particular to an engineering quantity real-time generation and cost early warning system based on BIM and Ai dynamic pricing, which comprises a BIM data acquisition module, an attribute change monitoring module, a market price matching module, a pricing generation module and a cost early warning module. According to the method, the component attribute data in the BIM model are extracted in real time, dynamic matching and fluctuation compensation are carried out in combination with an artificial intelligence algorithm, a bill of quantity and a price checking result are accurately generated, and component attribute changes are dynamically monitored, so that timely response to each detail in the construction process is ensured, the price checking accuracy and the reliability of project quantity calculation are improved, and the construction efficiency is improved. Each stage is dynamically adjusted in combination with the project progress and the risk coefficient model, potential cost deviation is identified in time, risks caused by market fluctuation or project progress delay are reduced, real-time management and control of the whole process of the engineering project are achieved, cost management is finer, and management vulnerabilities caused by data lag or incomplete information are reduced.

Description

Technical Field

[0001] This invention relates to the field of project management technology, and in particular to a real-time quantity generation and cost early warning system for engineering projects based on BIM and AI dynamic pricing. Background Technology

[0002] The field of project management technology encompasses the systematic research and application of planning, resource allocation, schedule control, cost management, and risk monitoring throughout the entire process of engineering construction activities. The core content of this field includes using information technology and data models to break down and quantify engineering tasks, conducting cost accounting by combining quota standards and bills of quantities, and dynamically monitoring project progress and resource utilization through process-based comparison and verification. Overall, this field emphasizes ensuring the standardization and controllability of management through standardized data, real-time information collection, and comprehensive analysis during project implementation, while also covering a full-cycle management approach from project initiation and construction to final settlement.

[0003] The BIM and AI-based dynamic pricing system for real-time quantity generation and cost early warning refers to the system that extracts structured attribute data of design components and construction processes using building information modeling (BIM), and then uses artificial intelligence technology to match and compare the quantity data with quota databases and material market price databases to generate corresponding bills of quantities and pricing results. Simultaneously, the system establishes an early warning rule base for discrepancy comparisons and cost anomaly detection in cost management, and provides cost early warning alerts by comparing historical project data and dynamic price change information. Its functions encompass the analysis of component attribute data used to generate the bill of quantities, the alignment of material prices with quota standards used for pricing, and the comparison and discrepancy identification of historical data used for early warning. This is primarily accomplished through information modeling extraction, data matching calculations, and rule-based comparison.

[0004] Existing technologies rely on static quota standards and manual data input, making timely adjustments difficult in response to market fluctuations or changes in project progress. The lack of dynamic monitoring of component data in the BIM model prevents the rapid identification of attribute changes during construction, impacting the accuracy of pricing and quantity calculations. Cost warning mechanisms depend on historical data and fail to respond promptly to actual project progress, thus failing to effectively prevent cost deviations. Due to the slow response to real-time data, existing technologies cannot handle dynamic changes in complex projects, consequently affecting project execution efficiency and cost control. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing a real-time engineering quantity generation and cost early warning system based on BIM and AI dynamic pricing.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a real-time quantity generation and cost early warning system for engineering projects based on BIM and AI dynamic pricing includes: The BIM data acquisition module obtains component data from the BIM model through the BIM software interface, including component ID parameters and attribute value parameters, and generates BIM component data. The attribute change monitoring module, based on the BIM component data, calls the component ID parameter and attribute value parameter, registers an event listener to monitor attribute modification events in the BIM software, calculates the difference in attribute values ​​before and after the change, and if the difference exceeds the threshold, it triggers an extraction action to generate changed attribute data. The market price matching module calls the attribute value parameters based on the changed attribute data, obtains the release timestamp of the market price and the effective timestamp of the quota standard to calculate the time difference, calls historical price data, applies an interpolation algorithm to adjust the price, and generates matching price data. The pricing generation module calls price parameters based on the matched price data, combines component attribute parameters to calculate the quantity of work, and generates pricing result data. The cost early warning module calls the pricing parameters based on the pricing result data, collects project progress parameters, calls the project stage characteristic parameters to calculate the risk coefficient, generates the risk coefficient, calls the benchmark threshold based on the risk coefficient, adjusts the threshold, and determines whether to trigger an early warning.

[0007] As a further aspect of the present invention, the BIM component data specifically includes component ID, attribute value, and component type; the change attribute data includes attribute value difference, modification type, and change time; the matching price data includes market price, historical price, and price after fluctuation compensation; the pricing result data includes project quantity, component size, and price adjustment value; and the cost early warning result includes risk coefficient, adjustment threshold, pricing difference, and schedule deviation.

[0008] As a further aspect of the present invention, the BIM data acquisition module includes: The component data extraction submodule obtains component data from the BIM model through the BIM software interface, calls the component ID parameter and attribute value parameter in the BIM model to extract and deconstruct the data, identifies and stores each component and its attributes based on the component ID, further analyzes and classifies the attribute values, and uses data structures to process and store the obtained component data to generate BIM component data. The component attribute acquisition submodule, based on the BIM component data, calls the component ID parameter and attribute value parameter to extract the structured attributes of each component in the BIM model, analyzes the changing trends of each attribute value, performs correlation analysis to provide a basis for subsequent calculations, effectively classifies and stores the data according to the component attributes in the model, and generates BIM component attribute data.

[0009] As a further aspect of the present invention, the attribute change monitoring module includes: The attribute change detection submodule, based on the BIM component data, calls the component ID parameter and attribute value parameter, registers an event listener to monitor attribute modification events in the BIM software, tracks attribute changes in real time, captures the time of change and the content of the change, records the change information of attribute values, and generates monitoring record data. The difference comparison calculation submodule compares the attribute values ​​before and after the change based on the monitoring record data, calculates the absolute difference between the two, filters the difference using a preset threshold, determines whether the attribute value change exceeds the threshold range, filters the data based on the threshold result, and generates difference values. The change data generation submodule calls the difference value. If the difference exceeds the threshold, it triggers a data extraction action to extract the attribute change-related data and generate change attribute data.

[0010] As a further aspect of the present invention, the market price matching module includes: The price-time matching submodule calls the attribute value parameters based on the changed attribute data, obtains the market price release timestamp parameter and the quota standard effective timestamp parameter, performs time difference calculation, calculates the difference between the release time and the effective time, determines the time deviation value, adjusts and synchronizes the price data based on the time difference, and generates the time deviation value. The fluctuation compensation submodule calls historical price data based on the time deviation value, applies an interpolation algorithm to compensate for market price fluctuations, adjusts the current price in combination with the fluctuation trend of historical data, and generates an adjusted price value by calculating the fluctuation amplitude of historical data. The price matching generation submodule compares the adjusted price value with the quota standard parameters, performs price matching, determines whether the adjusted price value meets the quota requirements, and generates matching price data.

[0011] As a further aspect of the present invention, the price generation module includes: The price calculation submodule calls the price parameters based on the matched price data, and performs quantity calculations by combining the component attribute data in the bill of quantities, including size values ​​and weight. Based on the size and related parameters of the component, it calculates the quantity of each component and applies a preset quota coefficient to generate the quantity calculation results. The component attribute calculation submodule adjusts the price of each component based on the project quantity calculation results, combined with other attributes such as component size, material type, and construction process. It then calculates the final price of the component using the corresponding quota standard and market price, generating the price calculation result data.

[0012] As a further aspect of the present invention, the step of combining the component attribute data in the bill of quantities, including dimension values ​​and weight calculation formulas, specifically includes: , in, The value represents the overall attribute trade-off of the component. This represents the length dimension of component numbered 2 or category 2 in the bill of quantities. This represents the width dimension of component number 2 or category 2 in the bill of quantities. This represents the height dimension of component category 2 or number 2 in the bill of quantities. This represents the weight data of component number 2 or category 2 in the bill of quantities. Represents the first to the second in category 2 or component number 2. Summation is performed after deducting the volume items. The first item representing the second category or number 2 of the component in the bill of quantities. The volume value after deducting volume items. This represents the number of deducted volume items associated with the component of category 2 or number 2. The representative volume reference constant is used for volume dimensionless processing. Represents the square root operator. The representative weight reference constant is used for dimensionless weight processing. This represents the first to the second items recorded in the bill of quantities for components of category 2 or number 2. The equivalent diameter data are averaged and summed. The first part represents the second category or number 2 of the component in the bill of quantities. Equivalent diameter data, The arithmetic mean of the equivalent diameter data and , This represents the total number of equivalent diameter data related to components of category 2 or number 2. The symbol represents the absolute value operator, and the letter subscript c2 indicates that the variable belongs to the second category or the component dataset numbered 2.

[0013] As a further aspect of the present invention, the cost early warning module includes: The progress parameter acquisition submodule calls the pricing parameters based on the pricing result data, collects the project progress parameters in the progress plan, including the percentage of completed work, collects progress data of each stage of the project, integrates the progress information, and generates progress data. The risk coefficient calculation submodule, based on the progress data, calls the project stage characteristic parameters and inputs them into the risk coefficient model to calculate the stage weight coefficient. According to the different stage characteristics of the project, the risk value of each stage is calculated using a weighted algorithm and stage adjustment coefficient to generate the risk coefficient. The cost threshold adjustment submodule calls the baseline threshold parameter in the cost plan according to the risk coefficient, adjusts the cost threshold, calculates the adjusted threshold based on the relationship between the risk coefficient and the cost baseline, compares the pricing parameter with the adjusted threshold, and generates cost early warning data.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In this invention, by extracting component attribute data from the BIM model in real time and combining it with artificial intelligence algorithms for dynamic matching and fluctuation compensation, the bill of quantities and pricing results are accurately generated. Dynamic monitoring of component attribute changes ensures timely response to every detail during construction, improving pricing accuracy and the reliability of quantity calculation. Combined with project schedule and risk coefficient models, dynamic adjustments are made to each stage to promptly identify potential cost deviations, reduce risks caused by market fluctuations or project delays, and achieve real-time control of the entire project process. This makes cost management more refined and reduces management loopholes caused by data lag or incomplete information. Attached Figure Description

[0015] Figure 1 This is a system flowchart of the present invention; Figure 2 This is a flowchart of the sub-modules of the present invention; Figure 3 This is the overall system flowchart of the present invention; Figure 4 This is a flowchart of the BIM data acquisition module of the present invention; Figure 5 This is a flowchart of the attribute change monitoring module of the present invention; Figure 6 This is a flowchart of the market price matching module of the present invention; Figure 7 This is a flowchart of the pricing generation module of the present invention; Figure 8 This is a flowchart of the cost early warning module of the present invention. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0017] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0018] Please see Figures 1-3 The real-time quantity generation and cost early warning system for engineering projects based on BIM and AI dynamic pricing includes: The BIM data acquisition module obtains component data from the BIM model through the BIM software interface, including component ID parameters and attribute value parameters, to generate BIM component data. The attribute change monitoring module is based on BIM component data. It calls the component ID parameter and attribute value parameter, registers an event listener to monitor attribute modification events in the BIM software, performs parameter difference comparison calculation, calculates the absolute value difference of attribute values ​​before and after the change, and if the difference exceeds the preset threshold, it triggers the extraction action to generate changed attribute data. The market price matching module calls attribute value parameters based on the changed attribute data, obtains the release timestamp parameter of the market price and the effective timestamp parameter of the quota standard, performs time difference calculation, determines the deviation value, calls historical price data parameters, applies interpolation algorithm to perform fluctuation compensation calculation, adjusts the current price value, and matches and compares it with the quota parameter to generate matching price data; The pricing generation module calls price parameters based on matching price data, and combines them with component attribute parameters such as size values ​​in the bill of quantities to perform quantity calculations and generate pricing result data. The cost early warning module calls the pricing parameters based on the pricing result data, collects the project progress parameters in the schedule plan, including the percentage of completed work, calls the project stage characteristic parameters, inputs the risk coefficient model to calculate the stage weight coefficient, generates the risk coefficient, calls the benchmark threshold parameter in the cost plan based on the risk coefficient, performs threshold adjustment calculation, and then compares the pricing parameters with the adjusted threshold to determine whether an early warning is triggered. BIM component data specifically includes component ID, attribute value, and component type; change attribute data includes attribute value differences, modification type, and change time; matching price data includes market price, historical price, and price after fluctuation compensation; pricing result data includes quantity, component size, and price adjustment value; cost warning results include risk coefficient, adjustment threshold, pricing difference, and schedule deviation. Please see Figure 4 The BIM data acquisition module includes: The component data extraction submodule obtains component data from the BIM model through the BIM software interface, calls the component ID parameter and attribute value parameter in the BIM model to extract and deconstruct the data, identifies and stores each component and its attributes based on the component ID, further analyzes and classifies the attribute values, and uses data structures to process and store the obtained component data to generate BIM component data. First, the component data extraction submodule obtains component data from the BIM model through the BIM software interface. This process is based on component IDs and attribute value parameters for data extraction and deconstruction. Each component in the BIM model has a unique component ID, which serves as an identifier to distinguish each component during the extraction process. Component attributes refer to various characteristic values ​​of a specific component in the BIM model, such as dimensions, materials, and location information. During data extraction, it is essential to ensure compatibility between the BIM software interface and the target BIM model by extracting component IDs and their attribute values ​​through a programming interface. After extraction, the system will identify and store each component and its attributes according to the component ID. For example, a single component might have the ID "C1001" and attributes including "Dimensions: 2.5m x 2.5m" and "Material: Steel." This information will be automatically obtained and stored in the database through the software interface. Next, the extracted component data is further analyzed and classified. The goal of this process is to ensure that all component data is systematically categorized and stored according to its attribute characteristics. The specific execution process includes: first, cleaning and deduplicating the attribute values ​​of all components, including filtering out invalid or duplicate attribute data; then, classifying the attribute data according to type, such as "size," "material," and "location"; next, performing statistical analysis on the values ​​of each attribute category to extract common value ranges and outliers to assist in subsequent functional optimization or data-driven decision-making; assuming that "size" attribute data for 10 components is extracted, 7 of which have a size of "2.5m x 2.5m," which can be considered a common value, while outlier sizes such as "5m x 5m" need to be marked as outliers for further processing; finally, this component data will be stored in a database, effectively organized using data structures such as tree structures or relational database tables for subsequent analysis and retrieval; the result of this process is the successful generation of BIM component data through accurate component IDs and attribute identifiers. The component attribute acquisition submodule, based on BIM component data, calls the component ID parameter and attribute value parameter to extract the structured attributes of each component in the BIM model, analyzes the changing trends of each attribute value, performs correlation analysis to provide a basis for subsequent calculations, effectively classifies and stores the data according to the component attributes in the model, and generates BIM component attribute data. First, based on the previously extracted component data, the component ID parameter and attribute value parameter are called to further extract the structured attributes of each component in the BIM model. The specific steps are: first, extract all attribute values ​​of the components to ensure the data is complete and without omissions; for example, the "Dimensions" attribute of a single component C1001 is "2.5m x 2.5m", and the "Material" attribute is "Steel". These two pieces of information will form structured data after extraction, facilitating further analysis. Next, the system needs to analyze the attribute values ​​of each component to identify the trend of attribute value changes; for example, for the component's "Dimensions" attribute, its changes over time or construction stages can be analyzed to identify the reasons for the size changes, such as construction errors or design changes. In the trend analysis, the change range of each component attribute is first calculated. For example, if the size of a single component is "2.5m x 2.5m" at the beginning of construction, and changes to "2.6m x 2.6m" during construction. The variation range is 0.1m. Next, statistical analysis is performed on the variation ranges of all components to identify the component with the largest variation and further investigate its cause. For data correlation analysis, statistical methods, such as the Pearson correlation coefficient, are needed to determine whether there is a significant correlation between different attribute values. This includes analyzing the correlation between the "material" and "size" attributes. Assuming that steel components are generally larger in size, while wood components are relatively smaller, correlation analysis can derive the correlation rules between material and size. Finally, based on this structured attribute data, the system will effectively classify and store the data, ensuring that each component and its attribute information are accurately recorded for subsequent querying, analysis, and decision-making. This includes storing all "steel" components and "size greater than 2.5m" as a single category for future searching and comparison of similar components. Ultimately, through this process, the system successfully generates BIM component attribute data. Please see Figure 5 The attribute change monitoring module includes: The attribute change detection submodule is based on BIM component data. It calls the component ID parameter and attribute value parameter, registers an event listener to monitor attribute modification events in the BIM software, tracks attribute changes in real time, captures the time of change and the content of the change, records the change information of attribute values, and generates monitoring record data. First, based on the BIM component data, the component ID and attribute value parameters are extracted to obtain the unique identifier of the target component and its associated attribute data, such as dimensions, material, and location. Next, the system registers an event listener to monitor attribute modification events in the BIM software. This way, once a component's attribute changes, the system will capture the moment of the change in real time. For example, in a building project, if a component's material attribute changes from "steel" to "aluminum," the listener will capture this change and record its details. Through event listening, the system can accurately track attribute changes and capture the timing of the changes, including, for example, if the change occurs on September 1, 2025, at 13:30:00, the system will record the timestamp and the change in attribute value. Based on this, the system will generate monitoring record data. The difference comparison calculation submodule compares attribute values ​​before and after changes based on monitoring record data, calculates the absolute difference between the two, filters the differences using a preset threshold, determines whether the attribute value changes exceed the threshold range, filters the data based on the threshold results, and generates difference values. First, after acquiring the monitoring data, the system compares the differences in attribute values ​​before and after the change. Assuming the attribute value before the change is "steel" with a standard value of 8.0, and the attribute value after the change is "aluminum" with a standard value of 5.0, the system calculates the difference based on the absolute difference between the two. In this case, the difference is calculated as |8.0 - 5.0| = 3.0. Next, the system filters based on preset thresholds. For example, if the threshold is set to 2.0, a difference of 3.0 exceeds the threshold, indicating that the attribute change is significant and requires further processing. At this point, the system determines whether the change meets the predetermined standards. If it exceeds the set threshold range, the changed data will be filtered out and recorded. In this way, the system can effectively filter critical attribute changes that exceed the normal range, preventing minor changes from being processed, thus focusing on changes that have a significant impact on the project and generating difference values. The change data generation submodule calls the difference value. If the difference exceeds the threshold, it triggers the data extraction action to extract the data related to the attribute change and generate the change attribute data. First, when the difference value exceeds the threshold, the system will trigger a data extraction action to extract data related to the change of that attribute. For example, if the difference value after the change is 3.0 and exceeds the set threshold of 2.0, the system will extract detailed information about the attribute, including the original attribute value, the changed attribute value, timestamp, component ID, etc., to form the changed attribute data. Please see Figure 6 The market price matching module includes: The price-time matching submodule calls the attribute value parameters based on the changed attribute data, obtains the market price publication timestamp parameter and the quota standard effective timestamp parameter, performs time difference calculation, calculates the difference between the publication time and the effective time, determines the time deviation value, adjusts and synchronizes the price data based on the time difference, and generates the time deviation value. First, attribute value parameters are extracted from the changed attribute data to obtain the market price publication timestamp parameter and the quota standard effective timestamp parameter. Next, the time difference is calculated, which is the difference between the publication timestamp and the effective timestamp. For example, if the publication time of a single price data point is 12:00:00 on September 1, 2025, and the effective time is 09:00:00 on September 1, 2025, then the time difference is 3 hours. The system adjusts and synchronizes the price data, mainly by comparing the difference between the two timestamps. The calculated time difference is used to adjust the price data. If the time difference is large, it may mean that the price was published too early or too late, requiring corresponding price adjustments to ensure that the market price reflects a more accurate effective time. This process involves comparing and adjusting historical price data to ensure price synchronization, and finally, a time deviation value is generated. The volatility compensation submodule calls historical price data based on the time deviation value, applies an interpolation algorithm to compensate for market price fluctuations, adjusts the current price based on the volatility trend of historical data, and generates an adjusted price value by calculating the volatility amplitude of historical data. First, based on the time deviation value, the system further calls upon historical price data and uses an interpolation algorithm to compensate for market price fluctuations. The purpose of the interpolation algorithm is to fill in any missing parts in the price data based on time differences, compensating for potential fluctuations. If historical data shows that the market price fluctuated significantly during a certain period, the interpolation algorithm will adjust the current price according to these historical fluctuation trends, adjusting the price to a level consistent with the historical price fluctuation range. This makes the current price closer to the actual market fluctuation state. Specifically, historical price data includes price records for different time periods such as daily and hourly. The system will identify the patterns of historical price fluctuations through data analysis, and use linear or polynomial interpolation methods to fine-tune the price based on the time difference, finally generating the adjusted price value. The price matching generation submodule compares the adjusted price value with the quota standard parameters to perform price matching, determines whether the adjusted price value meets the quota requirements, and generates matching price data. First, the adjusted price value is compared with the quota standard parameters. The system will determine whether the adjusted price meets the quota requirements. Specifically, the adjusted price is compared item by item with each price condition in the quota standard. If the price range set by the quota standard is 105 yuan to 110 yuan, and the adjusted price is 108 yuan, then the adjusted price meets the quota requirements. If the price exceeds this range, further adjustments are needed to ensure that the market price ultimately meets the requirements of the quota standard. The price matching process is to compare the adjusted price with the maximum and minimum values ​​in the quota standard to determine whether it falls within the range. If it exceeds the specified range, a price adjustment will be triggered, and the price data will be resynchronized until it meets the quota standard requirements, and finally, matched price data will be generated. Please see Figure 7 The pricing generation module includes: The price calculation submodule calls price parameters based on matching price data, combines component attribute data in the bill of quantities, including size values, weight, etc., to perform quantity calculation. Based on the component's size and related parameters, it calculates the quantity of each component and applies preset quota coefficients to generate the quantity calculation results. Based on the component attribute data in the bill of quantities, including dimensional values ​​and weight calculation formulas, the specific details are as follows: , in, The value represents the overall attribute trade-off of the component. This represents the length dimension of component numbered 2 or category 2 in the bill of quantities. This represents the width dimension of component number 2 or category 2 in the bill of quantities. This represents the height dimension of component category 2 or number 2 in the bill of quantities. This represents the weight data of component number 2 or category 2 in the bill of quantities. Represents the first to the second in category 2 or component number 2. Summation is performed after deducting the volume items. The first part represents the second category or number 2 of the component in the bill of quantities. The volume value after deducting volume items. This represents the number of deducted volume items associated with the component of category 2 or number 2. The representative volume reference constant is used for volume dimensionless processing. Represents the square root operator. The representative weight reference constant is used for dimensionless weight processing. This represents the first to the second items recorded in the bill of quantities for components of category 2 or number 2. The equivalent diameter data are averaged and summed. The first part represents the second category or number 2 of the component in the bill of quantities. Equivalent diameter data, The arithmetic mean of the equivalent diameter data and , This represents the total number of equivalent diameter data related to components of category 2 or number 2. The symbol represents the absolute value operator, and the letter subscript c2 indicates that the variable belongs to the second category or the component dataset numbered 2. Assumption: Size data acquisition: Dimensions of components were measured on-site. m, m, m; Deduct volume item: Two holes were detected through 3D scanning, with volumes of [missing information]. m 3 , m 3 , ; Reference volume: Reference industry standard component design m 3 ; Weight calculation: The material density is 2400 kg / m³ 3 Original volume m 3 ,weight kg; Reference weight: Typical weight of similar components is set as kg; Equivalent diameter data: The diameters of three measuring points were collected respectively. mm, mm, mm, average mm, ; Table 1 Component Parameters and Data Details

[0019] Table 1 lists all the parameters involved in the calculation. Substitute the values ​​into the formula to perform the calculation. Original volume of the component: m 3 2; Subtract volume and sum: m3 3; Net volume: m 3 4; Absolute value of volume ratio: 5; The square root of the weight ratio: 6; Results in Part 1: 7; Diameter deviation: , , ; Average value calculation: 8; Final result: ; Assuming the design specifies an excellent range of [0.8, 1.2], the calculation results are as follows: It falls within the range.

[0020] This result indicates that: The ratio of net volume to reference volume is close to 1, indicating that the component volume is reasonable; the ratio of weight to reference value is high but reasonable; the dimensional deviation is small, indicating that the component has high processing precision. Therefore, the component is judged to have excellent comprehensive properties in the current calculation step and can be used as an input parameter for subsequent engineering quantity calculation results. The component attribute calculation submodule adjusts the price of each component based on the project quantity calculation results, combined with other attributes such as component size, material type, and construction process. It then calculates the final price of the component using the corresponding quota standard and market price, generating the price calculation result data. First, the system receives the generated quantity calculation results. It then adjusts the price based on other attributes of each component, such as size, material type, and construction process. For example, assuming a single component's size is calculated to be 15 cubic meters, the system adjusts the price based on the component's material type (e.g., steel, concrete) and construction process (e.g., complexity, construction method). For instance, if the steel price is 5000 yuan per ton, but the construction process is complex, a construction adjustment coefficient of 1.3 is set. The system uses this coefficient to weight and adjust the component's price, multiplying its base price by 1.3 to arrive at the adjusted price. Furthermore, the system references current market prices to correct the pricing results, ensuring the price better reflects actual market conditions. If the market price of steel increases by 10%, the system multiplies the adjusted price by 1.1 to obtain the final pricing result. Through the integration and calculation of this data, the system can generate the final pricing data for each component based on the quantity calculation results, component attributes, and market prices. Please see Figure 8 The cost early warning module includes: The progress parameter acquisition submodule calls the pricing parameters based on the pricing result data, collects the project progress parameters in the progress plan, including the percentage of completed work, collects progress data of each stage of the project, integrates the progress information, and generates progress data. First, pricing parameters are extracted from the pricing results data. These parameters include the project budget and the cost calculation standards for each engineering unit. These parameters play a fundamental role in subsequent progress monitoring and cost early warning. By calling data from the schedule plan, the system collects the percentage of completed work at each stage of the project and gradually integrates the progress information of each stage. For example, if the completed work at a certain stage is 30%, this data will be captured and recorded in the progress dataset. After the progress dataset is integrated, the system further standardizes it according to the characteristic data of the progress. For example, it may involve adjusting parameters such as project duration, resource consumption, and equipment input, and finally generates a complete progress dataset. The risk coefficient calculation submodule uses progress data to call project stage characteristic parameters and input them into the risk coefficient model to calculate stage weight coefficients. Based on the different stage characteristics of the project, it uses a weighted algorithm and stage adjustment coefficients to calculate the risk value of each stage and generate the risk coefficient. First, based on the collected progress data and the project's phase characteristic parameters, these parameters are input into the risk coefficient model to calculate phase weight coefficients. The characteristics of each phase, such as its complexity, resource investment, and changes in the external environment, all affect the risk weight of that phase. The calculation process of the weight coefficients involves gradually adjusting the parameters in the model to ensure it reflects the actual progress of the project. For example, if a project phase has high complexity and many uncertainties in the external environment, then the weight coefficient for that phase will be larger. The system calculates the risk value for each phase through a weighted algorithm and the application of phase adjustment coefficients. The risk value reflects the degree of risk of project deviation or cost overruns that may occur due to various factors at that phase. For example, if the calculated risk value for a phase is 0.7, it indicates a high risk level for that phase, which may have a significant impact on the overall project. To ensure the accuracy of the calculations, the model periodically corrects the risk values ​​to ensure they match the actual project progress, generating a risk coefficient based on the risk value of each phase. The cost threshold adjustment submodule calls the baseline threshold parameter in the cost plan based on the risk coefficient, adjusts the cost threshold, calculates the adjusted threshold based on the relationship between the risk coefficient and the cost baseline, compares the pricing parameter with the adjusted threshold, and generates cost early warning data. First, based on the risk coefficient, the system adjusts the cost threshold by calling the baseline threshold parameter in the cost plan. During this process, the system first analyzes the relationship between the risk coefficient and the baseline threshold set in the cost plan, then applies an adjustment algorithm to calculate the adjusted threshold, which represents the reasonable cost warning line for the project after considering risk factors. Assuming the original threshold in the cost plan is 1 million and the risk coefficient is 0.7, the adjusted threshold is calculated as 1 million × (1 + 0.7) = 1.7 million, indicating that the project's budget cost ceiling has been adjusted to 1.7 million. In this calculation process, the system also considers budget changes at different project stages. For example, if the budget for some stages is more strained than others, the adjusted threshold may need to be adjusted individually for the risks at different stages. Through this process, the system can dynamically adjust the cost threshold based on real-time risks, thereby generating more accurate cost warning data.

[0021] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A real-time quantity generation and cost early warning system for engineering projects based on BIM and AI dynamic pricing, characterized in that: The system includes: The BIM data acquisition module obtains component data from the BIM model through the BIM software interface, including component ID parameters and attribute value parameters, and generates BIM component data. The attribute change monitoring module, based on the BIM component data, calls the component ID parameter and attribute value parameter, registers an event listener to monitor attribute modification events in the BIM software, calculates the difference in attribute values ​​before and after the change, and if the difference exceeds the threshold, it triggers an extraction action to generate changed attribute data. The market price matching module calls the attribute value parameters based on the changed attribute data, obtains the release timestamp of the market price and the effective timestamp of the quota standard to calculate the time difference, calls historical price data, applies an interpolation algorithm to adjust the price, and generates matching price data. The pricing generation module calls price parameters based on the matched price data, combines component attribute parameters to calculate the quantity of work, and generates pricing result data. The cost early warning module calls the pricing parameters based on the pricing result data, collects project progress parameters, calls the project stage characteristic parameters to calculate the risk coefficient, generates the risk coefficient, calls the benchmark threshold based on the risk coefficient, adjusts the threshold, and determines whether to trigger an early warning.

2. The real-time quantity generation and cost early warning system for engineering projects based on BIM and AI dynamic pricing as described in claim 1, characterized in that, The BIM component data specifically includes component ID, attribute value, and component type; the change attribute data includes attribute value difference, modification type, and change time; the matching price data includes market price, historical price, and price after fluctuation compensation; the pricing result data includes project quantity, component size, and price adjustment value; and the cost early warning result includes risk coefficient, adjustment threshold, pricing difference, and schedule deviation.

3. The real-time quantity generation and cost early warning system for engineering projects based on BIM and AI dynamic pricing as described in claim 1, characterized in that, The BIM data acquisition module includes: The component data extraction submodule obtains component data from the BIM model through the BIM software interface, calls the component ID parameter and attribute value parameter in the BIM model to extract and deconstruct the data, identifies and stores each component and its attributes based on the component ID, further analyzes and classifies the attribute values, and uses data structures to process and store the obtained component data to generate BIM component data. The component attribute acquisition submodule, based on the BIM component data, calls the component ID parameter and attribute value parameter to extract the structured attributes of each component in the BIM model, analyzes the changing trends of each attribute value, performs correlation analysis to provide a basis for subsequent calculations, effectively classifies and stores the data according to the component attributes in the model, and generates BIM component attribute data.

4. The real-time quantity generation and cost early warning system for engineering projects based on BIM and AI dynamic pricing as described in claim 1, characterized in that, The attribute change monitoring module includes: The attribute change detection submodule, based on the BIM component data, calls the component ID parameter and attribute value parameter, registers an event listener to monitor attribute modification events in the BIM software, tracks attribute changes in real time, captures the time of change and the content of the change, records the change information of attribute values, and generates monitoring record data. The difference comparison calculation submodule compares the attribute values ​​before and after the change based on the monitoring record data, calculates the absolute difference between the two, filters the difference using a preset threshold, determines whether the attribute value change exceeds the threshold range, filters the data based on the threshold result, and generates difference values. The change data generation submodule calls the difference value. If the difference exceeds the threshold, it triggers a data extraction action to extract the attribute change-related data and generate change attribute data.

5. The real-time quantity generation and cost early warning system for engineering projects based on BIM and AI dynamic pricing as described in claim 1, characterized in that, The market price matching module includes: The price-time matching submodule calls the attribute value parameters based on the changed attribute data, obtains the market price release timestamp parameter and the quota standard effective timestamp parameter, performs time difference calculation, calculates the difference between the release time and the effective time, determines the time deviation value, adjusts and synchronizes the price data based on the time difference, and generates the time deviation value. The fluctuation compensation submodule calls historical price data based on the time deviation value, applies an interpolation algorithm to compensate for market price fluctuations, adjusts the current price in combination with the fluctuation trend of historical data, and generates an adjusted price value by calculating the fluctuation amplitude of historical data. The price matching generation submodule compares the adjusted price value with the quota standard parameters, performs price matching, determines whether the adjusted price value meets the quota requirements, and generates matching price data.

6. The real-time quantity generation and cost early warning system for engineering projects based on BIM and AI dynamic pricing as described in claim 1, characterized in that, The price generation module includes: The price calculation submodule calls the price parameters based on the matched price data, and performs quantity calculations by combining the component attribute data in the bill of quantities, including size values ​​and weight. Based on the size and related parameters of the component, it calculates the quantity of each component and applies a preset quota coefficient to generate the quantity calculation results. The component attribute calculation submodule adjusts the price of each component based on the project quantity calculation results, combined with other attributes such as component size, material type, and construction process. It then calculates the final price of the component using the corresponding quota standard and market price, generating the price calculation result data.

7. The real-time quantity generation and cost early warning system for engineering projects based on BIM and AI dynamic pricing as described in claim 6, characterized in that, The component attribute data combined with the bill of quantities, including dimension values ​​and weight calculation formulas, are as follows: ， in, The value represents the overall attribute trade-off of the component. This represents the length dimension of component numbered 2 or category 2 in the bill of quantities. This represents the width dimension of component number 2 or category 2 in the bill of quantities. This represents the height dimension of component category 2 or number 2 in the bill of quantities. This represents the weight data of component number 2 or category 2 in the bill of quantities. Represents the first to the second in category 2 or component number 2. Summation is performed after deducting the volume items. The first part represents the second category or number 2 of the component in the bill of quantities. The volume value after deducting volume items. This represents the number of deducted volume items associated with the component of category 2 or number 2. The representative volume reference constant is used for volume dimensionless processing. Represents the square root operator. The representative weight reference constant is used for dimensionless weight processing. This represents the first to the second items recorded in the bill of quantities for components of category 2 or number 2. The equivalent diameter data are averaged and summed. The first part represents the second category or number 2 of the component in the bill of quantities. Equivalent diameter data, The arithmetic mean of the equivalent diameter data and , This represents the total number of equivalent diameter data related to components of category 2 or number 2. The symbol represents the absolute value operator, and the letter subscript c2 indicates that the variable belongs to the second category or the component dataset numbered 2.

8. The real-time quantity generation and cost early warning system for engineering projects based on BIM and AI dynamic pricing as described in claim 1, characterized in that, The cost early warning module includes: The progress parameter acquisition submodule calls the pricing parameters based on the pricing result data, collects the project progress parameters in the progress plan, including the percentage of completed work, collects progress data of each stage of the project, integrates the progress information, and generates progress data. The risk coefficient calculation submodule, based on the progress data, calls the project stage characteristic parameters and inputs them into the risk coefficient model to calculate the stage weight coefficient. According to the different stage characteristics of the project, the risk value of each stage is calculated using a weighted algorithm and stage adjustment coefficient to generate the risk coefficient. The cost threshold adjustment submodule calls the baseline threshold parameter in the cost plan according to the risk coefficient, adjusts the cost threshold, calculates the adjusted threshold based on the relationship between the risk coefficient and the cost baseline, compares the pricing parameter with the adjusted threshold, and generates cost early warning data.

Images