Constructional engineering information management system

Abstract

The invention relates to the field of information management, and discloses a constructional engineering information management system, which comprises a data acquisition module, an intelligent analysis module, a risk prediction module, a resource optimization module and a feedback learning module, the data acquisition module is used for acquiring multi-source data related to constructional engineering; the intelligent analysis module carries out fusion, preprocessing and feature extraction on the collected data; the risk prediction module predicts possible risks in the future by using a statistical analysis model; the resource optimization module dynamically adjusts and optimizes manpower, equipment, materials and process arrangement of the construction site according to the risk prediction result; and the feedback learning module is used for collecting a system execution result, risk prediction accuracy and user feedback, and recording an optimized execution result. The method has the advantage of realizing efficient engineering management and decision support.

Description

Technical Field

[0001] The invention relates to the field of information management, and in particular to a construction engineering information management system. Background Art

[0002] The current construction engineering information management system has achieved certain application results in project management, progress tracking, cost control, etc., but there are still problems such as information islands, poor data sharing, and insufficient dynamic monitoring. These problems lead to a lack of efficient coordination between various links of engineering management, untimely information flow, and affect the scientific nature of construction decisions and the overall efficiency of engineering implementation. Especially in terms of multi-project parallel management, real-time monitoring of the construction process, and resource scheduling optimization, the existing system often relies on manual statistics and manual updates, and the data acquisition and entry methods are relatively traditional, resulting in information lags, making it difficult to meet the needs of modern engineering construction for efficient data integration and real-time response.

[0003] As the complexity of construction projects continues to increase, the data sources of construction sites are becoming increasingly diverse. Traditional systems find it difficult to effectively integrate heterogeneous data sources, such as building information models, IoT sensor data, video surveillance information, drone image acquisition, geographic information systems, etc. This data isolation phenomenon not only hinders the intelligent management of engineering information, but also leads to the inability to timely discover abnormal situations during the construction process, affecting safety control, quality supervision and project progress assessment. At the same time, the lack of advanced data analysis and automatic early warning capabilities makes it difficult for managers to make accurate and fast decisions when faced with emergencies, which may cause construction delays, waste of resources, and even safety accidents. Therefore, it is necessary to design a construction engineering information management system that can intelligently predict potential risks. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a construction project information management system, which has the advantages of achieving efficient project management and decision support, and solves the problems in the above-mentioned background technology.

[0006] (II) Technical solution

[0007] In order to achieve the above-mentioned purpose of realizing efficient engineering management and decision support, the present invention provides the following technical solutions: a construction engineering information management system, including a data acquisition module, an intelligent analysis module, a risk prediction module, a resource optimization module and a feedback learning module;

[0008] The data acquisition module is responsible for acquiring multi-source data related to the construction project.

[0009] Preferably, the data acquisition module further includes real-time monitoring of the construction site environment and equipment status through a variety of sensors, and uses LoRa, NB-IoT, 5G, combined with edge computing for data cleaning and compression. It uses high-definition cameras, thermal imagers, drones and computer vision algorithms to achieve construction safety monitoring, integrates building structure and construction information using BIM technology, supports the IFC standard, combines lidar with three-dimensional point cloud scanning for construction progress comparative analysis, integrates historical data and external environment data for intelligent analysis, and uses cloud storage, big data platforms and blockchain technology to ensure data security, optimizing data indexing and distributed computing.

[0010] The intelligent analysis module fuses, preprocesses and extracts features from the collected data.

[0011] Preferably, the intelligent analysis module further includes using a unified format and through interpolation, time series alignment, normalization, combined with statistical and machine learning techniques, removing outliers and using dimensionality reduction methods to optimize calculation efficiency, using time series analysis and deep learning to predict construction progress and equipment status changes, using CNN to analyze safety hazards in video data, combining BIM + point cloud to detect construction errors, and extracting key factors affecting construction from environmental data. It uses Apache Kafka, Flink, and combines Hadoop, HBase to optimize large-scale data storage.

[0012] The risk prediction module uses statistical analysis models to predict possible future risks.

[0013] Preferably, the risk prediction module further includes using Bayesian Network, ARIMA, GARCH to construct risk prediction models for construction safety, equipment failure, project duration delay, and cost overrun, and combines SVM, random forest, XGBoost and deep neural networks. It constructs the relationships between construction technology, personnel, equipment, and environmental factors through an engineering management knowledge graph, uses LSTM, Transformer for real-time prediction, and at the same time analyzes long-term construction trends based on grey prediction and Markov chain. It uses object detection technology to identify safe behaviors at the construction site, combines edge computing, monitors the structural health status through a variety of sensors, combines weather API, historical meteorological data with the LSTM model to predict the impact of bad weather, optimizes the prediction of resource requirements based on time series analysis and game theory, dynamically adjusts the weights of the prediction model through reinforcement learning, and combines engineering expert knowledge and rule engines to correct AI prediction results.

[0014] The resource optimization module dynamically adjusts and optimizes the arrangement of manpower, equipment, materials and processes at the construction site according to the risk prediction results.

[0015] Preferably, the resource optimization module further includes adopting a multi-objective optimization algorithm, intelligently adjusting rotation in combination with fatigue monitoring, optimizing equipment utilization based on discrete event simulation and Markov decision process, arranging maintenance in advance through predictive maintenance, combining GIS+A* pathfinding algorithm, adopting time series prediction and inventory optimization algorithm, dynamically adjusting material inventory according to the construction progress, enhancing the transparency of the supply chain by combining blockchain and smart contract technologies, real-time monitoring the material transportation status through IoT+5G, using the critical path method and BIM 5D modeling, and dynamically adjusting the construction process in combination with reinforcement learning, automatically adjusting the construction plan with the help of weather prediction and construction simulation.

[0016] The feedback learning module is used to collect the system execution results, risk prediction accuracy, and user feedback, and record the results of optimization execution.

[0017] Preferably, the feedback learning module further includes using BIM 5D modeling, Internet of Things sensors, and construction logs to record construction data in real time, evaluating the risk prediction accuracy rate using MSE, F1-score, and ROC curve, combining manual feedback, expert systems, and NLP parsing to manage opinions, forming structured improvement suggestions, using DQN and PPO reinforcement learning to optimize resource scheduling and risk prediction strategies, dynamically adjusting model parameters by combining Bayesian optimization and adaptive gradient algorithm, using robust statistics and self-supervised learning to detect and correct abnormal data, dynamically adjusting the construction plan and resource allocation based on the construction period deviation, resource utilization rate, and construction safety index, combining deep learning and expert knowledge rules, sharing optimization experience among different projects through federated learning, presenting the optimization execution results using BIM+GIS+AR / VR technology, and combining knowledge graph and causal reasoning.

[0018] (III) Beneficial effects

[0019] Compared with the prior art, the present invention provides a building engineering information management system, which has the following beneficial effects:

[0020] The present invention efficiently obtains multi-source data through a data acquisition module to achieve comprehensive perception of the construction site. The intelligent analysis module fuses, preprocesses, and extracts features from the data to improve data quality and consistency, providing efficient support for subsequent analysis. The risk prediction module accurately predicts potential risks such as construction safety, schedule delays, and equipment failures based on statistical analysis and machine learning models to achieve early warning. The resource optimization module dynamically adjusts the arrangements of manpower, equipment, materials, and processes according to the prediction results, improves resource utilization rate, reduces construction waste, and ensures the project schedule. The feedback learning module combines historical data, manual feedback, and reinforcement learning techniques to continuously optimize system parameters and prediction models, enabling the system to have self-learning and adaptation capabilities. The system can enhance the intelligent level of construction project management, improve construction efficiency, reduce risk costs, and ensure project quality and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic structural diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0023] The present invention provides a technical solution: a construction project information management system, including a data acquisition module, an intelligent analysis module, a risk prediction module, a resource optimization module, and a feedback learning module;

[0024] The data acquisition module is responsible for obtaining multi-source data related to construction projects.

[0025] Deploy sensors for temperature and humidity, vibration, noise, air quality, dust concentration, stress and strain, light, wind speed, equipment status, etc., to achieve real-time monitoring of the construction site environment and equipment status. Adopt wireless communication technologies such as LoRa, NB-IoT, 5G, Zigbee, Wi-Fi, etc., to ensure low latency, high reliability, and wide coverage of transmission. Combine edge computing to perform data cleaning, compression, and denoising at the on-site terminal, reduce the cloud computing burden, and improve data transmission efficiency. Combine devices such as high-definition cameras, thermal imagers, and drones to monitor the construction site all-weather. Adopt computer vision algorithms to identify information such as construction worker behavior, illegal operations, safety helmet wearing, and equipment operation status. Combine deep learning and object detection technologies to improve the accuracy of safety hazard identification and support automatic alarm for abnormal events. Adopt BIM technology to integrate information such as building structure, construction progress, material list, and equipment layout. Support IFC standard data format to ensure the interoperability of BIM data and be compatible with different design software (such as Revit, ArchiCAD). Combine lidar and 3D point cloud scanning to update construction progress data in real time and detect the deviation between the actual construction and the BIM model. Integrate historical construction data (such as progress, cost, safety accident records) for intelligent analysis to improve prediction ability. Combine weather API, traffic data, and supply chain management system to obtain construction environment and external influencing factors in real time. Adopt web crawler technology and API interfaces to automatically update external data and improve the accuracy and applicability of prediction. Adopt cloud storage, big data platform, and distributed database to support large-scale data management. Combine blockchain technology to ensure the immutability and high security of data, improve data credibility. Adopt data index optimization and distributed computing to improve data query efficiency and support multi-terminal remote access.

[0026] Through Internet of Things sensors and video monitoring, the construction environment is monitored in real time, and safety hazards such as illegal operations and high-altitude operation risks are automatically detected. Combined with intelligent analysis, potential accidents are automatically warned, the safety management pressure is reduced, and the safety level of the construction site is improved. Combine BIM and sensor data to monitor the construction progress in real time, automatically compare the planned progress with the actual progress, and promptly discover deviations. Optimize the construction plan through external environment data to reduce the risk of construction period delay. Monitor the equipment status in real time through IoT data, predict equipment failures, arrange maintenance in advance, and reduce sudden shutdown events. Combine intelligent prediction models to extend the service life of equipment and optimize equipment utilization rate. Combine supply chain data, inventory information, and historical material consumption records to intelligently adjust material procurement and storage plans and reduce waste. Through the docking of BIM and construction data, precise scheduling of manpower, machinery, and materials is achieved, and resource utilization rate is improved. Ensure data security through blockchain technology, prevent tampering, ensure the traceability of data, and improve the credibility of building engineering data. Combine cloud storage and distributed computing to achieve remote collaboration and data sharing, and improve the flexibility of project management.

[0027] The intelligent analysis module performs data fusion, preprocessing, and feature extraction on the collected data.

[0028] Integrate IoT sensor data, video surveillance data, BIM data, historical engineering data, environmental data, etc. to form a unified data format. For data at different spatio-temporal scales, methods such as interpolation, time series alignment, and data synchronization are used to improve data consistency. Normalize and regularize data with different units and formats to ensure data analysis on the same numerical scale. Use methods such as mean filling, interpolation, KNN filling, and autoencoder completion to correct missing data and improve data integrity. Combine statistical methods and machine learning algorithms to eliminate outliers and ensure data quality. Use methods such as principal component analysis and linear discriminant analysis to reduce data dimensions and improve calculation efficiency. Adopt methods such as sliding window, Fourier transform, and wavelet transform to extract periodic and trend features of sensor data. Use long short-term memory networks and autoregressive integrated moving average models to analyze the construction progress and the changing trend of equipment status. Use convolutional neural networks to extract information such as personnel behavior, mechanical operation status, and safety hazards in the construction site video. Combine BIM + point cloud data to analyze the integrity of the building structure and detect construction errors. Combine weather data, geological data, and traffic data to extract key factors that may affect construction progress and safety, and improve the adaptability of the prediction model. Use Apache Kafka, Flink, and Spark Streaming to perform real-time analysis on high-frequency data and improve the response speed. Adopt Hadoop, HBase, and Elasticsearch for large-scale data storage to improve query efficiency and ensure system scalability. For engineering data, use blockchain technology to ensure the immutability of data and improve data security and credibility.

[0029] By filling in missing values, detecting anomalies, and reducing data dimensions, the integrity and accuracy of data are effectively improved, providing high-quality data support for subsequent analysis. False judgments caused by data noise are avoided, and the accuracy of risk prediction and resource scheduling is improved. Through time series alignment and feature extraction, the deep integration of IoT data, video surveillance, BIM models, and environmental data is achieved, improving the completeness of construction site information. Connections are established between different data sources to achieve intelligent monitoring and optimization of the construction process. Combining machine learning anomaly detection algorithms can detect potential risks in advance, such as equipment failures, structural deformations, and personnel's irregular operations, improving construction safety. By using CNN + computer vision to analyze video data, problems such as helmet wearing, mechanical overload, and non-standard high-altitude operations can be automatically detected and alarms can be given in a timely manner. Combining time series feature extraction, the deviation of the construction progress is predicted, the construction plan is adjusted in a timely manner, and the project duration delay is reduced. By analyzing BIM + point cloud data, building structure errors are detected, construction techniques are optimized, and the project quality is improved. The real-time streaming processing technology is adopted to ensure that high-frequency data (such as sensor data, video streams) can respond in milliseconds, improving the real-time performance of the management system. Combining distributed computing, the large-scale data processing capacity is enhanced, supporting parallel management of multiple projects.

[0030] The risk prediction module uses statistical analysis models to predict possible future risks.

[0031] Adopt methods such as Bayesian Network, ARIMA, and GARCH to construct risk prediction models for construction safety, equipment failures, project delays, cost overruns, etc. Combine support vector machines, random forests, XGBoost, and deep neural networks to classify and regression predict various construction risks and improve prediction accuracy. Construct an engineering management knowledge graph to establish the relationships among construction processes, personnel, equipment, and environmental factors, and improve the interpretability of risk analysis. Use deep learning models such as LSTM and Transformer to make real-time predictions on construction data, equipment operation parameters, and personnel operation behaviors, and timely discover short-term safety hazards. Based on methods such as grey prediction, Markov chain, and dynamic time warping, analyze the long-term change trends of construction progress, resource consumption, and project quality, and provide strategic decision-making support. Use object detection to identify risk behaviors such as safety helmet wearing, personnel gathering, and high-altitude operations at the construction site, and give real-time warnings through edge computing devices. Combine the data of vibration sensors, pressure sensors, and temperature and humidity sensors to detect the structural health status in real time, such as the stability of bridges, tunnels, and foundation pits, and prevent accidents such as collapses. Combine weather APIs, historical meteorological data, and geological data, and use the random forest + LSTM model to predict the impact of severe weather on construction progress and safety, and optimize the construction plan. Based on time series analysis and game theory optimization, predict the changes in the demand for building materials, mechanical equipment, and labor, and reduce the risks brought by resource shortages or surpluses. Combine reinforcement learning to dynamically adjust the weights of the risk prediction model according to newly input data to adapt to different construction environments and project requirements. Introduce engineering expert knowledge to correct the prediction results of the AI model through a rule engine and enhance the credibility of decision-making.

[0032] Real-time monitoring of on-site operations through computer vision + IoT sensors, automatically warning of high-risk behaviors such as not wearing safety helmets and entering dangerous areas illegally, reducing the risk of safety accidents. Combining BIM + structural health monitoring to detect minor deformations of building structures, discovering potential structural safety hazards in advance, and reducing accidents such as collapses. Combining time series analysis + external environmental factor prediction to accurately evaluate construction progress deviations, adjusting the construction plan in a timely manner, and improving the on-time delivery rate of projects. Through multi-source data fusion + trend prediction, identifying key factors that may affect the project duration in advance, reducing unplanned shutdowns. Using deep learning + time series analysis to predict the failure trend of mechanical equipment, arranging maintenance in advance, and avoiding construction interruptions caused by sudden failures. Through intelligent maintenance optimization, reducing unnecessary maintenance costs, extending the service life of equipment, and improving construction efficiency. Combining supply chain analysis + dynamic game model to predict the demand for building materials and labor, avoiding material shortages or over-purchasing, and reducing construction costs. Through intelligent resource allocation, improving the utilization rate of mechanical equipment and labor, reducing resource waste, and enhancing construction benefits. Combining reinforcement learning + expert system to continuously optimize the risk prediction model, enabling the system to adapt to different engineering scenarios and improving the prediction accuracy. Through an adaptive weight adjustment mechanism, optimizing model parameters to make risk prediction more in line with the actual construction situation and improving the intelligent management level.

[0033] Based on the risk prediction results, the resource optimization module dynamically adjusts and optimizes the arrangements of manpower, equipment, materials, and processes at the construction site.

[0034] Based on mixed-integer linear programming, genetic algorithms, and reinforcement learning, optimize the work schedule according to the construction progress, worker skill matching, and task urgency to reduce human resource waste. Use multi-objective optimization algorithms to optimize the work efficiency of workers while ensuring the construction progress, reducing waiting time and cross-operation conflicts. Combine personnel fatigue monitoring and health status assessment to intelligently adjust personnel rotation and reduce safety accidents caused by fatigue operations. Based on discrete event simulation and Markov decision processes, analyze equipment utilization rate, reduce equipment idle rate, and improve construction efficiency. Adopt predictive maintenance algorithms to predict equipment failures, arrange maintenance in advance, and reduce the impact of sudden failures on the construction progress. Combine GIS+A* pathfinding algorithms to optimize the movement paths of construction machinery, reduce fuel consumption, and improve operation efficiency. Use time series forecasting and inventory optimization algorithms to dynamically adjust material inventory based on construction progress and risk prediction, reducing overstocking and out-of-stock situations. Combine blockchain+smart contract technology to improve the transparency of material supply, prevent fake and inferior materials from entering the construction site, and ensure construction quality. Connect with suppliers based on IoT+5G to monitor the material transportation status in real time and improve the response speed of the supply chain. Use the critical path method and BIM 5D modeling to dynamically adjust the construction sequence, reduce conflicts and waiting time between processes, and improve construction efficiency. Combine reinforcement learning to dynamically adjust the construction process and speed up the project progress on the premise of ensuring safety and quality. Utilize weather forecasting+construction progress simulation to automatically adjust the construction plan under bad weather or special environmental conditions to avoid project delays.

[0035] Through dynamic manpower allocation and equipment utilization optimization, ensure that the construction progress is not affected by resource waste or improper scheduling, and improve the on-time delivery rate of the project. Combine process optimization to reduce delays caused by task conflicts and improve the overall construction efficiency. Through intelligent inventory management, reduce the overstocking of materials and lower the capital occupation cost. Combine intelligent equipment scheduling to improve equipment utilization rate, reduce leasing and maintenance costs, and improve the economic benefits of construction. Combine IoT+blockchain technology to improve the transparency and reliability of the supply chain and reduce the impact of material shortages or quality problems on the construction progress. Through real-time supply chain collaboration, ensure the timely supply of construction materials and reduce construction stagnation caused by material shortages. Through intelligent personnel scheduling+fatigue monitoring, optimize the working hours of construction personnel and reduce safety accidents caused by fatigue operations. Combine automatic path optimization+equipment failure prediction to reduce equipment accidents and improve the safety management level of the construction site.

[0036] The feedback learning module is used to collect the system execution results, risk prediction accuracy, and user feedback, and record the results of optimization execution.

[0037] By means of BIM 5D modeling, Internet of Things sensors, construction logs, etc., record the construction progress, resource usage, safety incidents, and engineering quality assessment data in real time. By comparing historical prediction data with actual events, calculate the accuracy rate of risk prediction (such as mean squared error MSE, F1-score, ROC curve) for optimizing the prediction model. Combine manual feedback + expert system + natural language processing to analyze the subjective opinions of project management personnel and form structured improvement suggestions. Adopt methods such as Deep Q-Learning (DQN) and Proximal Policy Optimization (PPO) to enable the system to continuously adjust resource scheduling and risk prediction strategies according to historical feedback, improving decision-making quality. Combine Bayesian optimization + adaptive gradient algorithm to automatically adjust the weights of various model parameters (such as risk prediction, resource scheduling) in different construction environments, improving adaptability. Adopt robust statistical methods + self-supervised learning to detect and correct abnormal data, preventing incorrect feedback from affecting system optimization. Based on system performance evaluation indicators (such as project duration deviation, resource utilization rate, construction safety index), dynamically adjust the construction plan, risk warning, and resource allocation. Combine deep learning with expert knowledge rules to enable the system to take historical experience into account during model optimization, improving the credibility of optimization. Combine federated learning to share optimization experiences in different construction projects, forming an evolving intelligent building engineering management system. Utilize BIM + GIS + AR / VR technologies to visually present the optimized implementation results of the construction site, enabling managers to grasp the construction status in real time. Combine knowledge graph + causal reasoning to provide construction strategy suggestions to help project management personnel make more scientific decisions. Based on automatic report generation (NLP + data analysis), the system automatically outputs an evaluation report on the construction execution effect for management review and optimization of subsequent project planning.

[0038] Through reinforcement learning and adaptive weight adjustment, the system can continuously optimize construction resource scheduling according to real-time feedback, improving the intelligence level of the system. Combine the abnormal data self-correction mechanism to reduce prediction deviation and improve the accuracy of risk assessment and optimization strategies. Through closed-loop feedback control, adjust the construction strategy in real time, reduce resource waste, and improve the accuracy of project progress management. Combine data-driven decision support to reduce manual intervention and improve management efficiency. Combine historical data + dynamic adjustment model to improve the accuracy rate of risk prediction and reduce false alarms and missed reports. Through the integration and optimization of expert system + AI, enhance the stability of the prediction model and improve the construction safety management ability. Combine visual analysis to help project management personnel intuitively understand the implementation effect of construction optimization and improve decision-making transparency. Through automatic report generation, reduce the workload of manual data processing and improve management efficiency.

[0039] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variation thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0040] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A construction project information management system, characterized in that: It includes data collection module, intelligent analysis module, risk prediction module, resource optimization module and feedback learning module; The data acquisition module is responsible for acquiring multi-source data related to the construction project; The intelligent analysis module performs fusion, preprocessing and feature extraction on the collected data; The risk prediction module uses a statistical analysis model to predict possible future risks; The resource optimization module dynamically adjusts and optimizes the manpower, equipment, materials and process arrangements at the construction site based on the risk prediction results; The feedback learning module is used to collect system execution results, risk prediction accuracy and user feedback, and record the results of optimization execution.

2. A construction engineering information management system according to claim 1, characterized in that: The data acquisition module further includes real-time monitoring of the construction site environment and equipment status through a variety of sensors, and uses LoRa, NB-IoT, 5G, combined with edge computing for data cleaning and compression, using high-definition cameras, thermal imagers, drones and computer vision algorithms to achieve construction safety monitoring, using BIM technology to integrate building structure and construction information, supporting IFC standards, combining lidar and three-dimensional point cloud scanning for construction progress comparison and analysis, integrating historical data and external environment data for intelligent analysis, using cloud storage, big data platform and blockchain technology to ensure data security, and optimizing data indexing and distributed computing.

3. A construction project information management system according to claim 1, characterized in that: The intelligent analysis module further includes adopting a unified format and through interpolation, time series alignment, normalization, combining statistics and machine learning techniques, eliminating outliers and using dimensionality reduction methods to optimize computing efficiency, using time series analysis and deep learning to predict construction progress and equipment status changes, and using CNN to analyze safety hazards in video data, combining BIM+point cloud to detect construction errors, and extracting key factors affecting construction through environmental data, using Apache Kafka, Flink, and combining Hadoop and HBase to optimize large-scale data storage.

4. A construction engineering information management system according to claim 1, characterized in that: The risk prediction module further includes using Bayesian Network, ARIMA, and GARCH to build construction safety, equipment failure, construction delay, and cost overrun risk prediction models, and combining SVM, random forest, XGBoost, and deep neural networks to build the relationship between construction technology, personnel, equipment, and environmental factors through the engineering management knowledge graph, and using LSTM and Transformer for real-time prediction. At the same time, based on gray prediction and Markov chain analysis of long-term construction trends, target detection technology is used to identify safety behaviors on the construction site, and edge computing is combined to monitor the health of the structure through a variety of sensors. The weather API, historical meteorological data, and LSTM model are combined to predict the impact of severe weather, and resource demand is optimized based on time series analysis and game theory. The prediction model weight is dynamically adjusted through reinforcement learning, and the AI ​​prediction results are corrected in combination with engineering expert knowledge and rule engines.

5. A construction engineering information management system according to claim 1, characterized in that: The resource optimization module further includes the use of a multi-objective optimization algorithm, combined with fatigue monitoring to intelligently adjust rotation, optimize equipment utilization based on discrete event simulation and Markov decision process, and arrange maintenance in advance through predictive maintenance, combined with GIS+A* pathfinding algorithm, using time series prediction and inventory optimization algorithm, dynamically adjusting material inventory according to construction progress, combining blockchain and smart contract technology to improve supply chain transparency, real-time monitoring of material transportation status through IoT+5G, using critical path method and BIM 5D modeling, and combining reinforcement learning to dynamically adjust the construction process, with the help of meteorological forecasting and construction simulation, automatically adjusting the construction plan.

6. A construction engineering information management system according to claim 1, characterized in that: The feedback learning module further includes using BIM 5D modeling, IoT sensors and construction logs to record construction data in real time, and using MSE, F1-score, and ROC curves to evaluate the accuracy of risk prediction, combining manual feedback, expert systems and NLP to analyze management opinions to form structured improvement suggestions, using DQN and PPO reinforcement learning to optimize resource scheduling and risk prediction strategies, and combining Bayesian optimization and adaptive gradient algorithms to dynamically adjust model parameters, using robust statistics and self-supervised learning to detect and correct abnormal data, dynamically adjusting construction plans and resource allocation based on construction period deviations, resource utilization, and construction safety index, combining deep learning with expert knowledge rules, and sharing optimization experience among different projects through federated learning, using BIM+GIS+AR / VR technology to present optimization execution results, and combining knowledge graphs with causal reasoning.

Images