Intelligent collaborative optimization system and method for building construction

Abstract

The invention provides an intelligent collaborative optimization system and method for building construction, and is applied to the field of data processing application. The method comprises the following steps: processing BIM model data to generate BIM digital asset information; processing data of each platform to generate real-time carbon emission monitoring and report information, unified data warehouse and interaction information, and field real-time acquisition and synchronization information; processing BIM digital asset information, real-time carbon emission monitoring and report information, unified data warehouse and interaction information, and on-site real-time acquisition and synchronization information to generate central information integrated with multi-source data; processing the central information based on historical data and real-time progress data in the central information to generate resource scheduling, process optimization suggestions, risk early warning and coping strategy information; and on the basis of resource scheduling, process optimization suggestions, risk early warning and coping strategy information, construction management optimization result information is generated in combination with a building engineering construction target.

Description

Technical Field

[0001] The present invention relates to the field of data processing applications, and in particular to an intelligent collaborative optimization system and method for building construction. Background Art

[0002] In the construction sector, traditional models face numerous technical bottlenecks, severely hindering industry development and urgently requiring innovative breakthroughs. Currently, data in construction is siloed. BIM model data, carbon emissions data, and construction progress data are stored in separate systems, lacking a unified management framework. This hinders data flow and makes it difficult for all parties involved to obtain comprehensive and accurate information in real time. For example, when the designer updates the BIM model, the contractor cannot synchronize with it in a timely manner, resulting in a disconnect between construction and design, impacting both efficiency and quality.

[0003] Traditional construction platforms rely on manual data analysis to make decisions. Faced with a complex and ever-changing construction environment, manual data processing is slow and error-prone, making it difficult to respond to dynamic changes in construction in real time. When the construction schedule is suddenly delayed, manual analysis and adjustment of resource allocation takes a lot of time, making it impossible to make effective decisions in a timely manner, thus delaying the construction period. The integration of AI technology into the construction process is insufficient. On the one hand, resource allocation lacks an accurate basis, resulting in serious resource waste, such as excessive material procurement or idle machinery and equipment; on the other hand, construction efficiency improvements are limited, making it difficult to meet the needs of efficient modern building construction. Existing single BIM management tools or independent carbon emission monitoring systems can only achieve partial functions, cannot achieve multi-source data integration and closed-loop optimization, and cannot provide comprehensive and dynamic support for construction management.

[0004] As the construction industry expands in scale and complexity, traditional construction techniques are no longer able to meet market demand. There is an urgent need for innovative technologies that can integrate multi-source data, enable real-time intelligent decision-making, optimize resource allocation, and reduce environmental impact. This will drive the digital and intelligent transformation of construction and enhance the industry's overall competitiveness.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore includes information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0006] The purpose of this application is to provide an intelligent collaborative optimization system and method for building construction that, at least to a certain extent, overcomes the problems of existing technologies. By collecting multi-source construction data, it converts BIM models into lightweight digital assets and associates multiple types of information to achieve full lifecycle traceability. It integrates multi-platform data construction hubs for real-time sharing, uses AI to optimize resource allocation and process decision-making, identifies risks, improves resource allocation efficiency, achieves green and intelligent goals, supports third-party access, and promotes the digital and intelligent development of the construction industry.

[0007] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the invention.

[0008] According to one aspect of the present application, an intelligent collaborative optimization method for construction is provided, including: obtaining BIM model data, construction progress data, cost data, carbon emission data, construction carbon emission platform data, DMP platform data, and smart construction site platform data in the construction of the building project; processing the BIM model data based on the construction progress data, cost data, and carbon emission data, converting it into lightweight digital assets and associating relevant tags to generate BIM digital asset information; based on the construction carbon emission platform, DMP platform, and smart construction site platform, processing the data of each platform respectively to generate real-time carbon emission monitoring and reporting information, a unified data warehouse and interaction information, and on-site real-time collection and synchronization information; processing the BIM digital asset information, real-time carbon emission monitoring and reporting information, a unified data warehouse and interaction information, and on-site real-time collection and synchronization information to generate central information integrating multi-source data; processing the central information based on historical data and real-time progress data in the central information to generate resource scheduling, process optimization suggestions, risk warnings, and response strategy information; based on resource scheduling, process optimization suggestions, risk warnings, and response strategy information, combined with the construction goals of the building project, generating construction management optimization result information.

[0009] Another aspect of the present application is an intelligent collaborative optimization device for building construction, characterized in that it includes: an acquisition module for acquiring BIM model data, construction progress data, cost data, carbon emission data, construction carbon emission platform data, DMP platform data, and smart construction site platform data in construction engineering; a processing module for processing BIM model data based on construction progress data, cost data, and carbon emission data, converting it into lightweight digital assets and associating relevant tags to generate BIM digital asset information; and processing the data of each platform based on the construction carbon emission platform, DMP platform, and smart construction site platform. , generate real-time carbon emission monitoring and reporting information, unified data warehouse and interactive information, on-site real-time collection and synchronization information; process BIM digital asset information, real-time carbon emission monitoring and reporting information, unified data warehouse and interactive information, on-site real-time collection and synchronization information to generate central information that integrates multi-source data; based on the historical data and real-time progress data in the central information, process the central information to generate resource scheduling, process optimization suggestions, risk warning and response strategy information; based on resource scheduling, process optimization suggestions, risk warning and response strategy information, combined with the construction goals of the building project, generate construction management optimization result information.

[0010] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the computer program implements the above-mentioned intelligent collaborative optimization method for construction.

[0011] The present application provides an intelligent collaborative optimization system and method for building construction. The server collects multi-source data during construction, converts the BIM model into a lightweight digital asset, and associates information such as construction progress, cost and carbon emissions to achieve full life cycle traceability. At the same time, it integrates multi-platform data to build a "system with brain center" to achieve real-time data sharing. AI algorithms are used to analyze data to optimize resource allocation and process decisions, such as predicting resource demand to improve the efficiency of machinery and manpower allocation, and recommending low-carbon processes to reduce carbon emissions. In addition, machine learning is used to identify construction risks and respond in advance. With the help of AI to achieve dynamic decision-making, resource allocation efficiency is improved by 25%; green and intelligent goals are achieved, carbon emission intensity is reduced by 15%, and material loss rate is reduced by 10%; it also supports third-party system access and is adaptable to various business scenarios. This technology provides an efficient solution for construction management and promotes the digital and intelligent development of the industry.

[0012] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A flowchart of an intelligent collaborative optimization method for building construction provided by an embodiment of the present application is shown;

[0014] Figure 2 A schematic structural diagram of an intelligent collaborative optimization device for construction provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0015] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0016] The following combination Figure 1 To describe the intelligent collaborative optimization method for construction according to an exemplary embodiment of the present application. In one embodiment, the present application also proposes an intelligent collaborative optimization system and method for construction. Figure 1 As shown, the method is applied to the server and includes:

[0017] S101, obtaining BIM model data, construction progress data, cost data, carbon emission data, construction carbon emission platform data, DMP platform data, and smart construction site platform data in the construction project.

[0018] In one implementation, for a large commercial complex construction project, the design team used professional BIM modeling software, such as Revit, to construct a BIM model based on the architectural design drawings, including detailed information about the building structure, building services, electrical systems, and plumbing systems. This model was accurate down to the specifications, location, and interconnections of every beam, slab, and pipe. The construction company accessed this BIM model data through a cloud platform shared with the design team, or directly from files exported from the design software, providing a foundation for subsequent construction management and digital collaboration.

[0019] During the construction process, construction personnel use project management software, such as Primavera P6, to develop a detailed construction schedule, including the start and end times and logical relationships of each phase, including foundation construction, main structure construction, and interior decoration. During construction, on-site managers use the project management software on their mobile phones or computers to update the actual construction progress in real time. Foundation construction was completed on X / X, X days ahead of schedule; the main structure is currently pouring the Xth floor, with completion expected on X / X. This data is aggregated into the project management system and becomes the source of construction progress data. Cost data primarily comes from the finance and materials procurement departments. The finance department is responsible for recording various expenses, such as labor costs, equipment rental costs, and utility bills. For example, this month's construction personnel salary expenditures are X million yuan, and the construction equipment rental costs are X million yuan. The materials procurement department records the procurement costs of construction materials, such as purchasing X tons of steel at X yuan per ton, for a total cost of X million yuan; purchasing X tons of cement, for a total cost of X million yuan, and so on. This cost data is categorized and compiled by different cost categories to form a comprehensive cost data set for analyzing the composition and changing trends of construction costs.

[0020] Carbon emissions data is collected using various monitoring devices installed at construction sites. At concrete mixing plants, carbon emission monitors are installed to monitor in real time the carbon emissions generated by energy consumption during concrete production. For example, the carbon emissions for each cubic meter of concrete produced are X kilograms. Construction vehicles are equipped with GPS positioning and carbon emission monitoring devices to record mileage, fuel consumption, and the corresponding carbon emissions. For example, if a concrete transport vehicle traveled X kilometers and consumed X liters of diesel this month, the carbon emissions would be calculated as X kilograms based on the carbon emission coefficient of diesel. Furthermore, electricity and gas consumption in temporary office and living areas at the construction site are also included in carbon emission monitoring. Data collected through smart electricity and gas meters is converted into carbon emissions, providing a comprehensive understanding of carbon emissions during the construction process.

[0021] Take the Fourth Bureau's carbon emissions platform as an example. It integrates data from various carbon emissions monitoring points on the construction site. During concrete production, the platform collects real-time carbon emissions data from monitoring equipment at the mixing plant, including information on carbon emissions during raw material transportation and mixing. During transportation, monitoring devices on vehicles capture carbon emissions data during transportation. Combined with information such as transportation routes and distances, the platform calculates the carbon emissions for each transportation task. The platform also analyzes and processes this data to generate a dynamic carbon footprint report, showcasing carbon emission trends and key emission nodes throughout the construction process. Construction parties can access this detailed carbon emissions data and analysis reports from the platform to monitor and manage carbon emissions during construction. The DMP (Data Management Platform) integrates data from multiple phases, including design, construction, and operations and maintenance. During the design phase, the platform stores building design drawings and design specifications, such as structural and electrical design drawings. This data contains various technical parameters and design requirements. During the construction phase, the platform collects various data from the construction process, including progress data, quality inspection data, and change records. For example, design change records during construction detail the reasons, content, and impact of the changes. During the operations and maintenance phase, the platform stores equipment maintenance records and energy consumption data. Through the DMP platform's interfaces or data query functions, construction parties can access design data related to the current construction phase, construction process data, and reference data for the operations and maintenance phase. This enables cross-system data query and interaction, providing comprehensive data support for construction management.

[0022] The smart construction site platform uses IoT sensors to collect on-site data. Various sensors installed at the construction site, such as cameras, temperature and humidity sensors, noise sensors, and displacement sensors, collect real-time data on the site's progress, environment, and equipment status. Cameras monitor construction progress and, using image recognition technology, analyze the work of construction personnel and the operating status of construction equipment. For example, cameras can detect abnormal oscillations in a tower crane during operation. Temperature and humidity sensors monitor the temperature and humidity of the construction site in real time, issuing warnings when they exceed suitable working ranges. Noise sensors monitor noise levels at the construction site to ensure compliance with environmental standards. Displacement sensors, installed on building structures, monitor changes in their movement and are used to assess their safety during construction. Data collected by these sensors is transmitted to the smart construction site platform in real time via wireless networks. Construction teams can view and manage this data on the platform in real time, enabling them to identify and resolve any construction site issues promptly.

[0023] S102, based on construction progress data, cost data, and carbon emission data, the BIM model data is processed, converted into lightweight digital assets and associated with relevant tags to generate BIM digital asset information.

[0024] In one implementation, in the early stages of the project, the design team used Autodesk Revit software to build a detailed BIM model covering all disciplines including architecture, structure, water supply and drainage, and electrical. However, the original model data volume is huge, which is not conducive to smooth calling and collaborative work on multiple platforms. At this time, a special BIM lightweight conversion tool, such as the lightweight plug-in of Glodon BIM5D, is used to convert the original BIM model into a lightweight BIM model in IFC format. During the conversion process, the plug-in will optimize and compress the geometric information and attribute information of the model, remove some unnecessary details, and retain key building component information and relationships. For example, the originally complex architectural decoration details are presented in simplified geometric shapes in the lightweight model, but the key information such as the size, position, and material of the main structural components such as walls, beams, and plates are fully retained, and finally a lightweight BIM model is generated that can be easily loaded and viewed on a variety of mobile devices and web pages.

[0025] The construction team uses Project project management software to develop a construction schedule. Taking one of the houses as an example, the key nodes of the foundation project include the start time of earth excavation (March 1), the pouring time of the foundation cushion layer (March 15), and the completion time of the foundation steel bar binding (March 25), etc.; the key nodes of the main structure construction include the pouring time of the first-floor column concrete (April 10), the construction period of each standard floor (7 days per floor), etc. During the construction process, the on-site management personnel record the actual progress data on the project management APP on their mobile phones every day, and the system automatically analyzes this data. For example, after analysis, it was found that due to underground obstacles encountered during the foundation construction phase, the completion time of the foundation steel bar binding was postponed to March 30. By comparing with the planned progress, a progress deviation feature with time as the sequence was generated, such as the overall delay of the foundation construction phase by 5 days, which provided a basis for subsequent resource allocation and progress adjustment.

[0026] The project's finance and materials procurement departments collaborated to record cost data. Regarding material costs, the procurement department found that during the main structure construction phase, steel procurement costs amounted to 5 million yuan, representing 40% of the total material cost; cement procurement costs amounted to 2 million yuan, representing 20%. Regarding labor costs, labor costs were 1.5 million yuan during the foundation construction phase, rising to 3 million yuan during the main structure construction phase as the number of construction workers increased. The finance department categorized this data by construction phase and plotted cost percentage charts and trend curves. These charts and curves show that the proportion of steel and cement in the material cost remained relatively stable as the project progressed, but the proportion of labor costs in the total cost increased from 30% during the foundation construction phase to 35% during the main structure construction phase, showing an upward trend and clearly reflecting the changing cost structure.

[0027] Carbon emission data is quantified and analyzed to generate carbon emission intensity and total volume characteristics for each construction phase and link. Various carbon emission monitoring devices were installed on the construction site. At the concrete mixing plant, sensors monitor the electricity, cement, and other resources consumed per cubic meter of concrete produced, converting these into carbon emissions. For example, the carbon emission intensity per cubic meter of concrete produced is 150 kilograms. During the construction and transportation phase, each transport vehicle is equipped with a carbon emission monitoring device to record mileage and fuel consumption and calculate carbon emissions. For example, a concrete transport vehicle travels 5,000 kilometers in a month and consumes 1,000 liters of diesel. Based on the carbon emission coefficient of diesel, the vehicle's total carbon emissions for that month are calculated to be 2,700 kilograms. Carbon emission data for each link is aggregated and analyzed by construction phase, revealing a total carbon emission of 50 tons during the foundation construction phase. Due to the high amount of concrete used during the main structure construction phase, carbon emissions rise to 100 tons. This clearly demonstrates the carbon emission intensity and total volume characteristics of each construction phase and link.

[0028] Based on these characteristics, they are associated with components in the lightweight BIM model to generate BIM digital asset information with associated construction progress, cost, and carbon emission labels. Leveraging the BIM model's open interface, key construction progress nodes and time series characteristics, cost proportions and changing trends, and carbon emission intensity and total volume characteristics for each construction phase and stage are associated with components in the lightweight BIM model. For example, by selecting a beam component in the lightweight BIM model, the database linked to the interface can display the beam's planned pouring date (e.g., May 10th), the actual completion date (May 15th, indicating a delay), the contribution of its material costs (such as steel and concrete) to the overall cost, and the carbon emissions generated throughout the entire construction process, from raw material transportation and processing to on-site pouring. In this way, each component is assigned labels related to construction progress, cost, and carbon emissions, forming comprehensive and traceable BIM digital asset information, providing intuitive and accurate data support for project management.

[0029] S103, based on the construction carbon emission platform, DMP platform, and smart construction site platform, processes the data of each platform respectively to generate real-time carbon emission monitoring and reporting information, unified data warehouse and interactive information, and real-time on-site collection and synchronization information.

[0030] In one implementation, during large-scale bridge construction, concrete production and transportation are key nodes for carbon emissions. A carbon emissions platform is built by installing high-precision carbon emissions monitoring equipment at concrete mixing plants to monitor in real time the carbon emissions generated by the consumption of energy and raw materials, such as electricity and cement, during each batch of concrete production. For example, if the production of 50 cubic meters of concrete consumes 500 kWh of electricity and 20 tons of cement, the carbon emissions for this batch of concrete can be calculated to be 30 tons based on the corresponding carbon emission coefficient. This represents the carbon emissions monitoring data for this key node. Long-term monitoring can analyze the differences in carbon emissions from concrete with different mix ratios and production equipment, creating a key node carbon emissions monitoring signature. The platform continuously tracks carbon emissions data at each stage of the construction process. During the bridge foundation construction phase, carbon emissions are high due to the high amount of concrete used and the frequent operation of construction equipment. As construction of the main structure progresses, the use of some construction equipment is reduced, concrete consumption decreases, and carbon emissions decrease accordingly. By plotting a graph of carbon emissions over time, the platform clearly displays the dynamic trends of carbon emissions, providing a basis for construction parties to promptly adjust construction plans and implement energy conservation and emission reduction measures.

[0031] Combining carbon emission data from various stages of concrete production, transportation, and construction, the construction carbon emissions platform generates detailed carbon footprint reports. The report not only includes carbon emissions at each stage but also analyzes the contribution of carbon emissions by source, such as concrete production accounting for 60% of total carbon emissions and transportation accounting for 20%. The report also compares carbon emissions across different construction areas and time periods, providing comprehensive carbon footprint information to construction parties to accurately formulate carbon reduction strategies. Based on the aforementioned key node carbon emission monitoring features, dynamic carbon emission trend characteristics, and carbon footprint report generation features, the platform generates real-time carbon emission monitoring and reporting information. Construction managers can use the platform interface to view real-time carbon emissions for the current construction phase, a comparison with planned emissions, and a detailed carbon footprint report at any time, keeping abreast of project carbon emission trends and providing early warnings of over-emission risks.

[0032] During the bridge project design phase, the DMP platform integrates various design data, including structural design drawings, geological survey reports, and seismic design parameters. For example, structural data such as bridge span, beam height, and pier dimensions are combined with geological data to form a complete design data set. This integration of data allows construction parties to clearly understand the design intent, providing a foundation for technical decisions during construction. During construction, the DMP platform collects construction data such as construction progress, quality inspection results, and equipment operating data, as well as post-construction operation and maintenance data, such as regular inspection reports and equipment maintenance records. For example, during the construction of a particular bridge pier, the platform integrates construction progress data (start time, completion time, and duration of each process), quality inspection data (concrete strength test results, rebar spacing test data), and settlement monitoring data from subsequent operation and maintenance, creating a complete construction and operation data chain for the pier, enabling construction parties and operation and maintenance personnel to fully understand the pier's status. The DMP platform supports cross-system queries, allowing construction parties to query data from different systems related to bridge construction. For example, through the platform interface, construction personnel can obtain cost data for a specific construction phase from the cost management system and current construction progress deviation data from the progress management system. The platform also provides APIs to allow other systems to access and share data. For example, the construction progress management system can transmit the latest progress data to the DMP platform through the API, ensuring real-time and consistent data.

[0033] Based on features such as design data integration, construction and operation and maintenance data fusion, cross-system query, and API interaction, the DMP platform builds a unified data warehouse to store and manage various types of data. Construction personnel, designers, and operation and maintenance personnel can easily query and obtain required data through the platform's interactive interface, interact with data, and improve project collaboration efficiency. At bridge construction sites, the smart construction site platform collects construction progress data in real time through cameras, sensors, and other equipment installed in key construction areas. For example, using cameras on tower cranes and image recognition technology, the frequency of crane lifting of construction materials and the operating conditions in the construction area can be identified to determine the construction progress of the bridge's main structure. Furthermore, electronic fences and personnel positioning equipment are installed at the construction site to provide real-time information on the distribution and work status of construction personnel, thereby accurately obtaining on-site progress information.

[0034] Temperature and humidity sensors, noise sensors, and dust sensors are deployed at construction sites to collect environmental parameters in real time. For example, a temperature and humidity sensor may detect a temperature of 30°C and a humidity of 60%, a noise sensor may detect construction noise levels of 80 decibels, and a dust sensor may detect an airborne dust concentration of 50 mg / m³. This data can help construction teams determine whether the construction environment is suitable and whether measures such as dust reduction and cooling are necessary. Sensors are installed on various mechanical equipment at the construction site, such as concrete pumps, cranes, and mixers, to monitor their status. These sensors collect real-time operating parameters, such as pump pressure on pump trucks, lifting weight on cranes, and mixing speed on mixers. If any equipment parameters exceed normal ranges, the platform will issue a prompt warning, alerting operators to perform maintenance and preventing equipment failures from impacting construction progress.

[0035] The smart construction site platform synchronizes data collected through real-time on-site progress, environmental parameters, and equipment status data to the central layer via a wireless network. The central layer receives the latest construction site data, supporting subsequent data analysis and decision-making. Based on these features, the smart construction site platform generates real-time on-site collection and synchronization information. Construction managers can view real-time progress, environmental conditions, and equipment status information from their office or on mobile devices, identifying and addressing issues promptly and improving construction site management efficiency.

[0036] S104, processing BIM digital asset information, real-time carbon emission monitoring and reporting information, unified data warehouse and interactive information, on-site real-time collection and synchronization information to generate central information integrating multi-source data.

[0037] In one implementation, in a bridge project, BIM digital assets detailed the construction schedule for each component. Analysis revealed that the foundation pile construction for a pier on the main bridge, originally scheduled for completion on the 20th day, was not completed until the 25th, a five-day delay. Further analysis revealed that the delayed foundation pile construction also delayed the construction of the pier's cap. The cap reinforcement binding work, originally scheduled to begin on the 22nd day, was postponed to the 27th day. This information, which correlates abnormal progress between components, helps the project team identify progress risks promptly and adjust subsequent construction arrangements in advance.

[0038] BIM digital assets are linked to cost information for each bridge component. Analysis revealed that the actual material cost of a box girder section on the approach bridge exceeded the budget by 15%. Investigation revealed that due to design changes, the concrete grade of the box girder was increased, resulting in higher costs for materials such as cement and admixtures. Furthermore, labor costs also rose by 10% due to increased construction difficulty. This cost-related deviation information provides key evidence for cost control, enabling the project team to take targeted measures to control costs. BIM digital assets are linked to carbon emission data during component construction. Analysis revealed that during the prefabrication of a certain T-beam during the construction phase of the bridge superstructure, the carbon emission intensity exceeded the expected standard by 8%. Further investigation revealed that this was due to the high energy consumption of the maintenance equipment at the prefabrication site, as well as the aging of some equipment, which led to increased energy consumption. This carbon emission-related warning information prompted the project team to promptly inspect and replace equipment to reduce carbon emissions.

[0039] Concrete pouring is a critical construction node in bridge construction. Real-time carbon emission monitoring revealed that carbon emissions reached 80 tons during the large-volume concrete pouring of the main bridge, exceeding the planned emissions by 25%. Analysis revealed that the excessive carbon emissions were caused by increased fuel consumption during the concrete mixing plant's production process due to the increased distances required to transport raw materials. This information was promptly fed back to the project team, enabling them to optimize transportation routes or adjust production methods. An analysis of carbon emission data over a period of time revealed that, as bridge construction progressed, carbon emissions did not decrease as expected with the optimization of construction processes, but instead fluctuated and increased. Further research revealed that recent delays in replacing construction equipment led to increased energy consumption for some older equipment, as well as inappropriate construction of temporary facilities at the construction site, resulting in energy waste and causing the abnormal increase in carbon emissions. This unusual trend prompted the project team to accelerate equipment upgrades and optimize the layout of temporary facilities. The carbon footprint report documents the sources and flows of carbon emissions during construction. The analysis found that carbon emissions from transportation accounted for 45% of total carbon emissions, far exceeding the expected 35%. In-depth investigation revealed that due to poor transport route planning, frequent empty-load round trips, and low fuel efficiency of some transport vehicles, carbon emissions from the transport process increased significantly. This abnormal carbon footprint report information provided guidance for optimizing transportation plans.

[0040] A unified data warehouse integrates design data for the bridge project. During the extraction and screening process, a conflict was discovered between the reinforcement information for a particular pier in the bridge structure design drawings and the embedded parts layout at that pier location in the anti-collision facility design drawings. The structural design required a 20cm spacing between the main reinforcement bars in the piers, but the installation space for the embedded parts of the anti-collision facility did not meet this reinforcement requirement. This design conflict was identified, avoiding errors and rework during construction. Construction and operation and maintenance data is stored in the unified data warehouse. Screening revealed a five-day discrepancy between the installation time of a bridge monitoring device recorded during the construction phase and the commissioning time recorded during the operation and maintenance phase. Verification revealed that the construction record-keeper had mistakenly entered the installation time. This data discrepancy was discovered and promptly corrected, ensuring data accuracy and providing a reliable basis for subsequent operation and maintenance management. The project utilizes multiple systems for collaborative work, and the unified data warehouse supports cross-system queries. During a cross-system interaction, a failure was discovered when retrieving construction progress data from the progress management system, preventing data from being transmitted properly. After investigation, it was found that the data format was incompatible due to incorrect interface settings. This cross-system interaction failure information was extracted so that technicians could fix the problem in time and ensure smooth data interaction between systems.

[0041] The smart construction site platform collects on-site construction progress information in real time. Through comparison, it was found that the construction progress of the bridge approach was 12% behind the planned progress. After analysis, it was found that due to the recent large turnover of construction personnel and insufficient personnel in some key positions, some processes could not be carried out as planned. This progress deviation information was promptly fed back to the project management team to adjust personnel arrangements and speed up the construction progress. The environmental sensors installed on site collect parameters such as temperature, humidity, and noise in real time. One day, the noise sensor showed that the noise at the construction site reached 95 decibels, exceeding the national construction noise emission standards (70 decibels during the day and 55 decibels at night). This may not only affect the physical health of the construction workers, but may also cause complaints from surrounding residents. This abnormal environmental parameter information was extracted and the relevant personnel were notified to take noise reduction measures.

[0042] During real-time data collection and comparison of construction equipment status, an abnormal oil temperature sensor in a key component of a bridge-building machine was discovered, with the oil temperature outside the normal range. Inspection revealed a sensor malfunction. If not promptly repaired, this could damage the bridge-building machine components, impacting construction safety and progress. This equipment status failure information promptly notified maintenance personnel for repair. During data synchronization on the smart construction site platform, it was discovered that some data collected on-site had not been synchronized to the central system in a timely manner. Inspection revealed that the data transmission was interrupted due to an unstable wireless network signal. This data synchronization anomaly was recorded, and technicians promptly adjusted the network equipment to ensure normal data synchronization.

[0043] The DS evidence theory was chosen as a data fusion algorithm, expressing the degree of confidence in different propositions through the basic probability distribution function (BPA). In the data fusion scenario of bridge projects, various types of abnormal information are considered different sources of evidence, each with its own assigned "confidence" for abnormalities in different aspects of the project (such as progress, cost, and carbon emissions). For example, for schedule anomalies, component schedule-related anomaly information and on-site schedule deviation information can be considered two pieces of evidence, each with different "confidence" in the judgment of schedule anomalies. Through the synthesis rules of DS evidence theory, the "confidence" of these different pieces of evidence can be fused to obtain a more accurate judgment of schedule anomalies.

[0044] Component progress anomaly information indicates a five-day delay in the construction of foundation piles for a pier on the main bridge. This information has a "confidence level" of 0.7 for an overall progress anomaly, indicating a 70% probability of impacting the overall progress. On-site progress deviation information indicates that the approach bridge construction is 12% behind schedule, with a "confidence level" of 0.8 for an overall progress anomaly. Using DS evidence theory for fusion and calculation based on the synthesis rule, the combined "confidence level" is likely to increase to 0.9. This means the project team can be more certain of an anomaly in the overall project progress. By integrating these two pieces of information, they can clearly determine that not only the approach bridge is behind schedule, but also the delayed construction of the main bridge piers has impacted the overall progress, providing a more comprehensive understanding of the overall project progress.

[0045] Cost-related deviation information indicated that the actual material cost of a box girder section on the approach bridge exceeded the budget by 15%. The confidence level that the cost deviation stemmed from design changes was assumed to be 0.6. Regarding missing or conflicting design data, regarding the increased construction difficulty caused by the box girder design changes, the confidence level that the cost deviation stemmed from design issues was assumed to be 0.7. Using DS evidence theory, the combined confidence level associated with the cost deviation and design issues was 0.85. This gave the project team greater confidence that the root cause of the cost deviation was closely related to the design changes, facilitating in-depth analysis of the causes and enabling targeted measures, such as reassessing the necessity of design changes and optimizing construction plans to control costs.

[0046] Carbon emission-related warning information indicates that the carbon emission intensity during the prefabrication of a T-beam in the bridge superstructure exceeded expectations by 8%, leading to a confidence level of 0.7 for the carbon emission anomaly in this area. Information on excessive carbon emissions at key nodes indicates that carbon emissions during the pouring of large-volume concrete on the main bridge exceeded plans by 25%, leading to a confidence level of 0.8 for the carbon emission anomaly during the overall construction phase. Information on abnormal carbon emission trends indicates that carbon emissions fluctuate and increase as construction progresses, leading to a confidence level of 0.75 for problems with carbon emission management. Information on abnormal carbon footprint reports indicates that carbon emissions from the transportation sector account for 45%, far exceeding expectations, leading to a confidence level of 0.8 for the transportation sector being the primary carbon emission issue. Using DS evidence theory to integrate this information, the overall confidence level of 0.9 is obtained, indicating that serious problems exist in the project's carbon emission management and that transportation is a key factor. This provides comprehensive data support for the project's carbon emission management, allowing the project team to identify the need for focused attention on the transportation sector and implement measures such as optimizing transportation routes and replacing energy-efficient vehicles to reduce carbon emissions.

[0047] After fusing various types of abnormal information through DS evidence theory, a central information structure integrating multi-source data is formed. This central information includes comprehensive abnormalities in various aspects such as progress, cost, and carbon emissions, as well as the corresponding "trust level." Based on this information, the project team can quickly determine which links in the project are most likely to have problems and the severity of the problems. For example, based on the integrated progress information, the team can promptly allocate resources to prioritize solving progress problems on the critical path; based on cost information, adjust procurement plans or optimize construction processes to control costs; and based on carbon emission information, formulate targeted energy-saving and emission reduction measures. This helps the project team promptly identify and resolve various problems during the construction process, ensuring the smooth progress of the bridge project.

[0048] S105, based on the historical data and real-time progress data in the central information, the central information is processed to generate resource scheduling, process optimization suggestions, risk warning and response strategy information.

[0049] In one implementation, in a bridge project, analysis of component progress anomaly information within the central information revealed that the construction progress of a pier foundation on the main bridge was five days behind schedule. This would prevent the timely arrival of machinery, equipment, and personnel required for subsequent construction phases. Consequently, a resource demand anomaly message was generated, alerting the project team that additional resources might be needed to ensure progress. Cost deviation information revealed that the actual material cost of a box girder section on the approach bridge exceeded the budget by 15%. Analysis revealed that this was due to a design change that resulted in an increase in the concrete grade, which in turn increased the costs of materials such as cement and admixtures. This situation generated a cost control anomaly message, indicating a cost control issue and requiring the project team to take measures, such as reassessing the need for design changes or optimizing procurement channels to control costs. Regarding carbon emission warning information, during the bridge superstructure construction phase, the carbon emission intensity of a T-beam prefabrication process exceeded the expected standard by 8%. This was likely due to high energy consumption and aging of some of the maintenance equipment at the prefabrication site. This carbon emission anomaly message alerted the project team to address equipment energy consumption issues and promptly replace or upgrade equipment to reduce carbon emissions.

[0050] Exceeded carbon emissions at key nodes indicate that carbon emissions during the main bridge's massive concrete pouring exceeded planned emissions by 25%. This data indicates a risk of exceeding carbon emissions standards at this critical construction node, potentially causing the project's overall carbon emissions to fall below standards. This generates a carbon emissions excess risk information, prompting the project team to take measures to reduce carbon emissions, such as optimizing the concrete mixing plant's production process and adjusting transportation routes. Analysis of carbon emissions data over a period of time revealed an unusually high carbon emissions trend. Further investigation revealed that this was due to untimely equipment upgrades and inappropriate temporary facility construction, resulting in energy waste. This situation generated a carbon emissions excess risk information, prompting the project team to accelerate equipment upgrades and optimize the layout of temporary facilities to avoid the risk of continued carbon emissions increases. Abnormal carbon footprint reports indicate that transportation accounts for 45% of carbon emissions, far exceeding the expected 35%. This indicates a significant carbon emissions issue in the transportation sector, prompting the project team to optimize transportation plans, such as optimizing routes and replacing energy-efficient vehicles, to reduce carbon emissions in the transportation sector.

[0051] While extracting and filtering design data from the unified data warehouse, a conflict was discovered between the reinforcement information for a particular pier in the bridge structure design drawings and the embedded component layout for the same pier in the anti-collision facility design drawings. This inconsistency in design data could lead to construction errors and rework, resulting in a data integrity exception message, alerting the project team to promptly resolve the design conflict and ensure smooth construction. Regarding inconsistencies in construction and operation data, a five-day discrepancy was discovered between the installation time of a bridge monitoring device recorded during the construction phase and the commissioning time recorded during the operation and maintenance phase. This discrepancy could impact the accuracy of equipment maintenance plans and data analysis, generating a data consistency exception message. The project team needed to verify and correct the data to ensure accuracy and consistency. During cross-system interaction, an error occurred while retrieving construction progress data from the progress management system, preventing data transmission. This indicated a problem with system interaction, generating a system interaction exception message. Technical personnel were required to promptly troubleshoot any issues with interface settings to ensure smooth data exchange between systems.

[0052] The smart construction site platform collects real-time on-site construction progress information. Comparison revealed that the approach bridge construction progress was 12% behind schedule. This deviation could cause delays to the entire project, generating a site progress risk warning. The project team needed to promptly adjust personnel arrangements, add construction equipment, or optimize construction processes to accelerate progress. Noise sensors installed on-site indicated that the construction site noise level reached 95 decibels, exceeding the national construction noise emission standard (70 decibels during the day and 55 decibels at night). This not only impacts the health of construction workers but also may trigger complaints from surrounding residents, generating environmental risk warnings. The project team needs to implement noise reduction measures, such as using soundproofing equipment and arranging construction schedules. Real-time collection and comparison of construction equipment status revealed an abnormal oil temperature sensor on a key component of a bridge erection machine, indicating that the oil temperature was outside the normal range. This could lead to damage to the machine components, affecting construction safety and progress. This generated an equipment failure risk warning, urging maintenance personnel to promptly inspect and repair the equipment. During data synchronization, the smart construction site platform discovered that some data collected on-site had not been synchronized to the central system in a timely manner. This data synchronization anomaly may affect the real-time nature of data and the accuracy of decision-making, and generate data synchronization risk information. Technical personnel need to check network equipment in a timely manner to ensure normal data synchronization.

[0053] When using decision tree algorithms to process bridge project data, information gain and the Gini coefficient are important metrics. They play a key role in feature selection and determine the direction of decision tree construction. The following details the calculation process for these two metrics, using actual data from bridge projects.

[0054] Information entropy is used to measure the uncertainty of data, and the formula is: Where D is the dataset, n is the number of categories in the dataset, and p iis the proportion of samples of type i in the data set. In the bridge project cost control analysis, there are 100 cost data samples, 30 of which are due to cost increases due to design changes, 50 due to cost increases due to rising material prices, and 20 due to cost increases due to construction process problems. Calculate the information entropy of this data set:

[0055] Ratio of each category: (Design Change), (Rising material prices), (Construction technology issues).

[0056] Information entropy calculation: H(D)=-0.3×log20.3-0.5×log20.5-0.2×log20.2≈1.485.

[0057] Conditional entropy is the uncertainty of a data set under certain characteristic conditions, and the formula is Where A is the feature, V is the number of values ​​of feature A, and D v This is the dataset when feature A takes the value v. For example, consider the feature "Is the cost increase related to design changes?", which has two possible values: "yes" and "no." Assume that there are 40 samples in the "yes" subset, 30 of which are due to cost increases caused by design changes, and 10 are due to other reasons. In the "no" subset, there are 60 samples, 50 of which are due to cost increases caused by rising material prices, and 10 are due to construction process issues. Calculate the conditional entropy of this feature:

[0058] Calculate the information entropy of the "yes" subset:

[0059] H(D 是 )=-0.75×log20.75-0.25×

[0060] log20.25≈0.811.

[0061] Calculate the information entropy of the "No" subset: H(D 否 )=-0.833×log20.833-0.167×log20.167≈0.602.

[0062] Conditional entropy calculation:

[0063] Information gain is the difference between information entropy and conditional entropy, using the formula Gain(D, A) = H(D) - H(D|A). Based on the above calculations, the information gain for this feature is: Gain(D, A) = 1.485 - 0.686 = 0.799. A greater information gain indicates a greater contribution to classification, and a greater tendency to select this feature for node partitioning when building a decision tree.

[0064] The Gini coefficient is used to measure the impurity of the data set, and the formula is Still taking the bridge project cost control dataset as an example, calculate the Gini coefficient: Gini coefficient calculation: Gain(D)=1-0.3 2 -0.5 2 -0.2 2 =0.62.

[0065] Similar to conditional entropy, the conditional Gini coefficient is the impurity of the data set under a certain characteristic condition, and the formula is Continuing with the feature “whether the cost increase is related to the design change” as an example, calculate the conditional Gini coefficient: Calculate the Gini coefficient of the “yes” subset: Gini(D 是 )=1-0.75 2 -0.25 2 = 0.375. Calculate the Gini coefficient for the “No” subset: Conditional Gini coefficient calculation: The smaller the Gini coefficient, the lower the impurity of the dataset, and the more suitable it is for use as a partitioning feature when building a decision tree. By comparing the conditional Gini coefficients of different features and selecting the feature with the smallest conditional Gini coefficient for node partitioning, we can build a decision tree and provide a basis for resource scheduling, process optimization, and risk management in projects.

[0066] S106, based on resource scheduling, process optimization suggestions, risk warning and response strategy information, combined with the construction project construction goals, generate construction management optimization result information.

[0067] In one implementation, during bridge construction, resource scheduling information revealed that five concrete pump trucks and 20 construction workers were deployed from other construction areas to address the delayed progress of the main bridge's pier foundations. The resource allocation adjustment was significant, reflecting the scale of this resource allocation. Simultaneously, by calculating the standard deviation of resource allocation across construction areas, and measuring resource allocation balance, it was found that resource allocation across areas was relatively uneven after the adjustment, with some areas experiencing resource constraints and others experiencing relatively loose resources. Based on this information, a resource allocation amplitude feature and a resource allocation balance feature were generated. For example, if the resource allocation amplitude was "large-scale allocation," the resource allocation balance feature would indicate "unbalanced, with resource constraints in some areas." These two features intuitively demonstrate the resource scheduling situation, helping the project team understand the impact of resource allocation intensity and balance on construction.

[0068] The process optimization proposals include two low-carbon processes: nighttime low-energy construction and replacing traditional materials with new environmentally friendly materials. Evaluation shows that nighttime low-energy construction is relatively easy to implement under current construction conditions and has a high likelihood of adoption, estimated at 80%. However, while new environmentally friendly materials can significantly reduce carbon emissions, their adoption is only 50% due to supply and cost issues. Regarding the efficiency gains from process improvements, nighttime low-energy construction is expected to increase construction efficiency by 15%, while the replacement with new environmentally friendly materials is expected to increase efficiency by 10%. This generates a low-carbon process feasibility profile (nighttime low-energy construction: high feasibility; replacement with new environmentally friendly materials: moderate feasibility) and a process efficiency improvement profile (nighttime low-energy construction: 15% efficiency improvement; replacement with new environmentally friendly materials: 10% efficiency improvement), providing a quantitative basis for the project team to select appropriate low-carbon processes.

[0069] Risk warning and response strategy information indicates that the current project faces three types of risks: schedule deviation, quality defects, and safety accidents. The probability of schedule deviation risk is 60%, primarily due to construction personnel turnover and equipment failure; the probability of quality defect risk is 30%, related to lax raw material quality control and non-standard construction techniques; and the probability of safety accidents is 10%, mostly caused by poor construction site management. Based on this, a quantitative characteristic of three risk types and a probability characteristic of risk occurrence are generated (schedule deviation risk: 60%; quality defect risk: 30%; safety accident risk: 10%). This allows the project team to clearly understand the types of risks facing the project and the likelihood of each risk occurring, facilitating the development of targeted measures in advance.

[0070] The characteristics of resource allocation amplitude, resource allocation balance, low-carbon process feasibility, process efficiency improvement, risk type quantity, and risk occurrence probability are integrated. For example, resource allocation is large-scale and unbalanced. Among low-carbon processes, nighttime low-energy construction is highly feasible and has significantly improved efficiency. However, it faces multiple risks and has a high probability of schedule deviation. Combining this information, the generated comprehensive construction management characteristics are "large but unbalanced resource allocation, great application potential of low-carbon processes (nighttime low-energy construction), diverse risk types, and prominent schedule deviation risks." This characteristic comprehensively reflects the current comprehensive status of the project in terms of resources, processes, risks, etc., providing a key basis for subsequent decision-making.

[0071] Based on the characteristics of comprehensive construction management and considering the uneven allocation of resources and high risk of schedule deviation, the direction of resource allocation optimization is to prioritize resource supply in key construction areas (such as the main bridge pier foundation construction area), while balancing resources in other areas to avoid idleness or excessive concentration of resources. For example, a detailed resource allocation plan is developed to allocate appropriate resources from relatively resource-scarce areas to key areas to ensure coordinated construction progress across all areas. Given the high feasibility and significant efficiency gains of nighttime, low-energy construction among low-carbon processes, a process improvement implementation plan has been developed. Nighttime equipment commissioning and personnel training are scheduled to be completed within a week. Nighttime low-energy construction will officially begin next week and is expected to continue until the completion of the main bridge structure. During implementation, changes in construction efficiency and quality will be closely monitored, and the construction plan will be adjusted promptly. Based on the risk type and probability of occurrence, the priority risk prevention and control focus is schedule deviation risk. Prevention and control measures are being developed, such as strengthening construction personnel management and establishing a stable construction team; increasing the frequency of equipment inspections; and pre-stocking vulnerable parts to ensure normal equipment operation. At the same time, the risks of quality defects and safety accidents cannot be ignored. We must strengthen the quality inspection of raw materials and construction site safety management, formulate emergency plans, and reduce losses when risks occur.

[0072] The integration of resource allocation optimization directions, process improvement implementation plans, and risk prevention and control priorities generates information on construction project management optimization results. For example, "In the upcoming construction, prioritize resource allocation to the main bridge pier foundation construction area, balancing resources in other areas; implement low-energy nighttime construction starting next week until the main bridge structure is completed, closely monitoring construction progress during this period; focus on preventing and controlling schedule deviation risks, strengthen personnel and equipment management, and simultaneously consider quality and safety risk prevention and control." This provides the project team with clear construction management guidance, helping to optimize construction management and ensure the smooth progress of the bridge project.

[0073] In the field of construction, traditional models have problems such as data silos, delayed decision-making, and insufficient intelligence, which seriously restrict construction efficiency and quality. The "Smart Hub Digital Twin Modeling and Collaborative Optimization Method and System" of the present invention is committed to solving these problems and realizing digital collaborative management of the entire construction process of construction projects. The present invention first obtains multi-source data such as BIM models, progress, costs, carbon emissions, etc. during construction. The BIM model is then converted into a lightweight digital asset and associated with various data tags to achieve full life cycle traceability; multi-platform data is integrated to build a "system with brain center" to share information in real time. AI algorithms are used to deeply analyze data, optimize resource allocation and process decisions, and improve construction efficiency and quality. For example, by predicting resource needs through historical data and real-time progress, optimizing machinery and manpower allocation, efficiency can be increased by 20%; carbon emissions and work efficiency data are analyzed to recommend low-carbon processes and reduce carbon emission intensity.

[0074] Machine learning technology is used to identify construction risks and generate response strategies in advance. It achieves full data integration, reduces information silos by 90%, and breaks down data barriers. It leverages AI algorithms to achieve dynamic decision-making, improves resource allocation efficiency by 25%, and rapidly responds to construction changes. It achieves green and intelligent goals, reduces carbon emission intensity by 15%, and reduces material loss by 10%. It has good scalability, supports third-party system access, and is adaptable to a variety of business scenarios. Through data integration, central coordination, and intelligent deepening, this technology provides comprehensive and efficient solutions for construction management, driving the construction industry toward digitalization and intelligence. It has important application value in improving construction management, reducing costs, and minimizing environmental impact.

[0075] In one embodiment, Figure 2 As shown, the present application also provides an intelligent collaborative optimization device for building construction, comprising:

[0076] Acquisition module 201, for acquiring BIM model data, construction progress data, cost data, carbon emission data, construction carbon emission platform data, DMP platform data, and smart construction site platform data in construction projects;

[0077] Processing module 202 is used to process BIM model data based on construction progress data, cost data, and carbon emission data, convert it into lightweight digital assets and associate relevant tags to generate BIM digital asset information; based on the construction carbon emission platform, DMP platform, and smart construction site platform, process the data of each platform respectively to generate real-time carbon emission monitoring and reporting information, unified data warehouse and interactive information, on-site real-time collection and synchronization information; process BIM digital asset information, real-time carbon emission monitoring and reporting information, unified data warehouse and interactive information, on-site real-time collection and synchronization information to generate central information integrating multi-source data; based on the historical data and real-time progress data in the central information, process the central information to generate resource scheduling, process optimization suggestions, risk warning and response strategy information; based on resource scheduling, process optimization suggestions, risk warning and response strategy information, combined with the construction goals of the construction project, generate construction management optimization result information.

[0078] Each embodiment in this application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the intelligent collaborative optimization method, electronic device, electronic device, and readable storage medium for evaluating construction, since they are basically similar to the embodiments of the intelligent collaborative optimization method for construction described above, the description is relatively simple, and the relevant parts can be referred to the partial description of the embodiments of the intelligent collaborative optimization method for construction described above.

Claims

1. An intelligent collaborative optimization method for building construction, characterized in that: include: Obtain BIM model data, construction progress data, cost data, carbon emission data, construction carbon emission platform data, DMP platform data, and smart construction site platform data during construction projects; Based on construction progress data, cost data, and carbon emission data, BIM model data is processed, converted into lightweight digital assets, and associated with relevant tags to generate BIM digital asset information; Based on the construction carbon emission platform, DMP platform, and smart construction site platform, the data of each platform is processed separately to generate real-time carbon emission monitoring and reporting information, unified data warehouse and interactive information, and real-time on-site collection and synchronization information; Process BIM digital asset information, real-time carbon emission monitoring and reporting information, unified data warehouse and interactive information, and on-site real-time collection and synchronization information to generate central information that integrates multi-source data; Based on the historical data and real-time progress data in the central information, the central information is processed to generate resource scheduling, process optimization suggestions, risk warnings and response strategy information; Based on resource scheduling, process optimization suggestions, risk warning and response strategy information, combined with the construction project construction goals, construction management optimization result information is generated.

2. The method according to claim 1, wherein Based on construction progress data, cost data, and carbon emission data, BIM model data is processed, converted into lightweight digital assets, and associated with relevant tags to generate BIM digital asset information, including: Convert BIM model data into a new format to generate a lightweight BIM model; Analyze and process construction progress data to generate key nodes and time series characteristics of construction progress; Perform classified statistical processing on cost data to generate various cost proportions and change trend characteristics used to characterize material costs and labor costs; Quantitatively analyze and process carbon emission data to generate carbon emission intensity and total amount characteristics for each construction stage and each link; Based on the key nodes and time series characteristics of the construction progress, the proportion and changing trend characteristics of various costs, and the carbon emission intensity and total amount characteristics of each construction stage and link, they are associated with the components in the lightweight BIM model to generate BIM digital asset information associated with the construction progress, cost, and carbon emission labels.

3. The method according to claim 1, wherein Based on the construction carbon emission platform, DMP platform, and smart construction site platform, data from each platform is processed to generate real-time carbon emission monitoring and reporting information, a unified data warehouse and interactive information, and real-time on-site collection and synchronization information, including: Monitor and analyze the data of the construction carbon emission platform to generate key node carbon emission monitoring characteristics, carbon emission dynamic change trend characteristics, and carbon footprint report generation characteristics; Integrate and mine DMP platform data to generate design data integration features, construction and operation data fusion features, cross-system query and API interaction features; Collect and transmit data from the smart construction site platform to generate real-time collection features for on-site progress, environmental parameters, equipment status, and data synchronization to the central layer; Generate real-time carbon emission monitoring and reporting information based on key node carbon emission monitoring characteristics, carbon emission dynamic change trend characteristics, and carbon footprint report generation characteristics; Generate a unified data warehouse and interactive information based on design data integration features, construction and operation and maintenance data fusion features, cross-system query and API interaction features; Based on the real-time collection features of on-site progress, real-time collection features of environmental parameters, real-time collection features of equipment status, and real-time synchronization of data to the central layer, real-time on-site collection and synchronization information is generated.

4. The method according to claim 1, wherein Process BIM digital asset information, real-time carbon emission monitoring and reporting information, unified data warehouse and interactive information, and on-site real-time collection and synchronization information to generate central information that integrates multi-source data, including: Extract and analyze BIM digital asset information to generate component progress-related abnormality information, cost-related deviation information, and carbon emission-related warning information; Extract, analyze and process real-time carbon emission monitoring and reporting information to generate information on carbon emission exceeding standards at key nodes, abnormal carbon emission trends, and abnormal carbon footprint reports; Extract and filter the unified data warehouse and interactive information to generate information on missing or conflicting design data, inconsistent construction and operation data, and cross-system interactive faults; Extract and compare the real-time on-site collection and synchronization information to generate on-site progress deviation information, environmental parameter abnormality information, equipment status failure information, and data synchronization abnormality information; Based on the data fusion algorithm, component progress-related abnormal information, cost-related deviation information, carbon emission-related warning information, key node carbon emission exceeding standard information, carbon emission trend abnormal information, carbon footprint report abnormal information, design data missing or conflicting information, construction and operation and maintenance data inconsistency information, cross-system interaction failure information, on-site progress deviation information, environmental parameter abnormal information, equipment status failure information, and data synchronization abnormal information are processed to generate central information that integrates multi-source data.

5. The method according to claim 1, wherein Based on the historical data and real-time progress data in the central information, the central information is processed to generate resource scheduling, process optimization suggestions, risk warnings and response strategy information, including: Extract and classify component progress-related abnormal information, cost-related deviation information, and carbon emission-related warning information in the central information to generate resource demand abnormal information, cost control abnormal information, and carbon emission abnormal information; Extract and classify information on excessive carbon emissions at key nodes, abnormal carbon emission trends, and abnormal carbon footprint reports to generate risk information on excessive carbon emissions, abnormal carbon emission trends, and abnormal carbon footprint reports; Extract and classify missing or conflicting design data, inconsistent construction and operation data, and cross-system interaction failure information to generate data integrity anomaly information, data consistency anomaly information, and system interaction anomaly information; Extract and classify on-site progress deviation information, environmental parameter anomaly information, equipment status failure information, and data synchronization anomaly information to generate on-site progress risk information, environmental risk information, equipment failure risk information, and data synchronization risk information; Based on machine learning algorithms, abnormal information on resource demand, abnormal cost control, abnormal carbon emissions, risk information on exceeding carbon emission standards, abnormal carbon emission trends, abnormal carbon footprint risk information, abnormal data integrity, abnormal data consistency, abnormal system interaction, on-site progress risk information, environmental risk information, equipment failure risk information, and data synchronization risk information are processed to generate resource scheduling information, process optimization suggestions, risk warnings, and response strategy information.

6. The method according to claim 5, wherein Based on resource scheduling, process optimization suggestions, risk warnings and response strategy information, combined with construction project construction goals, construction management optimization results information is generated, including: Perform feature extraction processing on the resource allocation adjustment range and resource allocation balance information in the resource scheduling information to generate resource allocation range features and resource allocation balance features; Perform feature extraction on the possibility of adopting low-carbon processes and the degree of efficiency improvement of process improvements in process optimization suggestions to generate low-carbon process feasibility features and process efficiency improvement features; Perform feature extraction on the number of risk types and the probability of occurrence of various risks in the risk warning and response strategy information to generate risk type quantity features and risk occurrence probability features; Integrate the resource allocation range characteristics, resource allocation balance characteristics, low-carbon process feasibility characteristics, process efficiency improvement characteristics, risk type quantity characteristics, and risk occurrence probability characteristics to generate comprehensive construction management characteristics; Analyze comprehensive construction management characteristics and generate resource allocation optimization directions, process improvement implementation plans, and risk prevention and control priorities based on different characteristic combinations; Integrate resource allocation optimization direction, process improvement implementation plan, and risk prevention and control priorities to generate construction project construction management optimization result information.

7. An intelligent collaborative optimization device for construction, characterized in that: The device comprises: The acquisition module is used to obtain BIM model data, construction progress data, cost data, carbon emission data, construction carbon emission platform data, DMP platform data, and smart construction site platform data in construction projects; The processing module is used to process BIM model data based on construction progress data, cost data, and carbon emission data, convert it into lightweight digital assets and associate relevant tags to generate BIM digital asset information; based on the construction carbon emission platform, DMP platform, and smart construction site platform, the data of each platform is processed respectively to generate real-time carbon emission monitoring and reporting information, a unified data warehouse and interactive information, and on-site real-time collection and synchronization information; BIM digital asset information, real-time carbon emission monitoring and reporting information, a unified data warehouse and interactive information, and on-site real-time collection and synchronization information are processed to generate central information that integrates multi-source data; based on the historical data and real-time progress data in the central information, the central information is processed to generate resource scheduling, process optimization suggestions, risk warnings, and response strategy information; based on resource scheduling, process optimization suggestions, risk warnings, and response strategy information, combined with the construction goals of the construction project, construction management optimization result information is generated.

8. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; The first processor is configured to execute the intelligent collaborative optimization method for building construction according to any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the intelligent collaborative optimization method for building construction described in any one of claims 1 to 6 is implemented.

Images