An intelligent management platform for construction engineering data information

Abstract

This invention discloses an intelligent management platform for construction engineering data, belonging to the field of intelligent management technology for construction engineering. The platform includes: real-time collection of construction data through sensors at the construction site; preprocessing of the construction data; feature interaction of the preprocessed construction data to construct a construction progress prediction model and predict a construction progress delay risk index; assessment of the construction progress status and optimization of the construction plan based on the construction progress delay risk index; verification of the optimized construction plan through virtual simulation to identify potential problems leading to construction progress delays; and feasibility analysis of the optimized construction plan based on the identification results, followed by further iterative adjustments. This invention, through the construction of a construction progress prediction model and feasibility analysis, achieves accurate prediction of construction progress, improves the feasibility of construction plans, effectively reduces construction delays and resource waste, and significantly improves project management efficiency.

Description

Technical Field

[0001] This invention relates to the field of intelligent management technology for building engineering, and in particular to an intelligent management platform for building engineering data and information. Background Technology

[0002] With the continuous expansion and increasing complexity of construction projects, effectively managing construction progress, resource allocation, and compliance checks has become a pressing issue in the construction industry. Traditional project management methods rely on manual recording, supervision, and analysis. While these methods can meet project management needs to some extent, they are inefficient, prone to errors, and struggle to cope with complex construction environments and changing conditions. In recent years, with the rapid development of the Internet of Things (IoT), big data, and artificial intelligence (AI) technologies, construction projects are gradually transforming towards intelligent management. Real-time collection of various data from the construction site through sensors, smart devices, and data platforms, combined with machine learning algorithms for analysis and prediction, has become a significant trend in modern construction project management. This intelligent transformation not only improves construction efficiency but also effectively reduces potential risks during construction.

[0003] However, existing intelligent management platforms for construction projects still have some shortcomings in practical applications that urgently need to be addressed. First, although some platforms can predict construction progress based on historical data, most rely on traditional linear models or simple time series analysis methods, failing to fully capture the nonlinear dynamic characteristics of construction data. This results in low prediction accuracy when facing the risk of construction delays, thus affecting the overall project schedule management. Second, existing technologies, in the process of optimizing construction plans, typically only focus on balancing schedule and cost, neglecting the comprehensive consideration of multi-dimensional factors such as resource utilization, equipment health status, and environmental impact. This can lead to problems such as improper resource allocation or equipment failure during the execution of the optimized construction plan, affecting the smooth progress of construction. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides an intelligent management platform for construction engineering data information to solve the problems of inaccurate prediction of construction progress delay risks and insufficient consideration of multi-dimensional factors in the process of construction plan optimization.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] This invention provides an intelligent management platform for construction engineering data, comprising: a data acquisition module, which collects construction data in real time through sensors at the construction site and preprocesses the data; a delay risk prediction module, which performs feature interaction on the preprocessed construction data, constructs a construction progress prediction model, and predicts a construction progress delay risk index; a construction plan optimization module, which evaluates the construction progress status and optimizes the construction plan based on the construction progress delay risk index; a construction plan verification module, which verifies the optimized construction plan through virtual simulation and identifies potential problems that may cause construction progress delays; and a feasibility analysis module, which performs a feasibility analysis on the optimized construction plan based on the identification results and further iteratively adjusts the optimized construction plan.

[0008] As a preferred embodiment of the intelligent management platform for construction engineering data information described in this invention, the specific steps for collecting construction data in real time through sensors at the construction site are as follows:

[0009] The number of workers and their working hours are collected using personnel positioning sensors.

[0010] The device's usage time and operating status are collected through its sensors.

[0011] The transportation and consumption of materials are collected through RFID tags;

[0012] Environmental parameters at the construction site are collected using environmental sensors.

[0013] As a preferred embodiment of the intelligent management platform for construction engineering data information described in this invention, the preprocessing of construction data includes the following specific steps.

[0014] Data cleaning is used to remove incomplete, duplicate, and erroneous data from the construction data;

[0015] Data standardization is used to convert construction data of different dimensions into the same standard;

[0016] By fusion, construction data is aligned and integrated according to the time dimension to form a global construction progress dataset.

[0017] As a preferred embodiment of the intelligent management platform for construction engineering data information described in this invention, the specific steps for performing feature interaction on the preprocessed construction data are as follows:

[0018] Statistical analysis was used to extract feature vectors for the number of workers, equipment usage time, and material consumption.

[0019] By using Fourier transform, frequency characteristics and trend information of environmental parameters are extracted from time series data;

[0020] Frequency analysis was used to extract the equipment's failure frequency and operating efficiency.

[0021] Based on the feature vectors of different data in the construction progress dataset, feature interaction is performed to generate interactive features that can reflect the linkage effect between different data.

[0022] The feature interaction includes the following steps.

[0023] An exponentially weighted approach is used to perform feature interaction on the construction data in the construction progress dataset, generating a first-order exponentially weighted interactive feature vector, expressed as:

[0024] ;

[0025] in, Let j represent the j-th first-order exponentially weighted interactive feature vector. It is the i-th eigenvector. represents the weight coefficient of the i-th feature vector in the exponentially weighted interaction, n is the number of samples, and i represents the feature vector index of the construction data;

[0026] By performing logarithmic transformation on the construction data in the construction progress dataset, a first-order logarithmic transformation interactive feature vector is generated, expressed as:

[0027] ;

[0028] in, Let j represent the interactive eigenvector of the first-order logarithmic transformation. This represents the feature vector of the (i+1)th sample. It is the weight coefficient of the i-th eigenvector when the logarithmic change occurs;

[0029] By nesting nonlinear combinations, the first-order exponentially weighted interaction feature and the first-order logarithmic transformation interaction feature are further interacted to generate a second-order nonlinear interaction feature, expressed as:

[0030] ;

[0031] in, It is the j-th second-order nonlinear interactive eigenvector.

[0032] As a preferred embodiment of the intelligent management platform for construction engineering data information described in this invention, the specific steps for constructing a construction progress prediction model and predicting the construction progress delay risk index are as follows:

[0033] By combining three feature interaction methods—exponential weighted interaction, logarithmic variation, and nested nonlinear combination—a construction progress prediction model is constructed to predict the construction progress risk index, expressed as:

[0034] ;

[0035] in, It is the construction progress delay risk index at time point t.

[0036] As a preferred embodiment of the intelligent management platform for construction engineering data information described in this invention, the specific steps for assessing the construction progress status and optimizing the construction plan based on the construction progress delay risk index are as follows:

[0037] Based on historical data and the nature of the project, a low-latency risk threshold is defined. and high latency risk threshold ;

[0038] when At that time, it was determined that there was no risk of delay in the current construction progress, and the current construction plan was maintained;

[0039] when At that time, it was believed that there was a slight risk of delay in the current construction progress, so more workers were deployed to carry out construction, the service life of equipment was extended, and the transportation of construction materials was accelerated.

[0040] when At that time, it was believed that there was a serious risk of delay in the current construction progress, so an emergency increase in the number of workers was made and their working hours were increased. Emergency allocation of spare equipment and construction materials was also made, and alternative materials were used for construction.

[0041] As a preferred embodiment of the intelligent management platform for construction engineering data information described in this invention, the step of testing the optimized construction plan through virtual simulation to identify potential problems leading to construction delays includes the following specific steps.

[0042] Based on the optimized construction plan and construction data, a simulation model of the construction process and resource allocation is built on the virtual simulation platform to simulate the progress, procedures and resource consumption of different construction stages.

[0043] Simulation tests are conducted using a virtual simulation platform to simulate the execution of the construction plan at different times and under different environmental conditions.

[0044] During the simulation of the construction plan, key indicators in the construction plan are monitored in real time to identify potential problems that may cause delays in the construction schedule.

[0045] Real-time monitoring of construction data in the simulated construction plan; by analyzing the historical trends and abnormal fluctuations in the current rate of change of the construction data, potential problems that may cause delays in construction progress can be identified.

[0046] Potential problems that could lead to construction delays include improper resource allocation, equipment failure, material supply delays, labor shortages, and the impact of environmental factors.

[0047] As a preferred embodiment of the intelligent management platform for construction engineering data information described in this invention, the specific steps for performing a feasibility analysis on the optimized construction plan based on the identification results are as follows:

[0048] Based on the potential problems identified by the virtual simulation platform that could lead to construction delays, and taking into account factors such as schedule, cost, and resource utilization, a risk feedback function is introduced to predict the feasibility score of the optimized construction plan. The expression is as follows:

[0049] ;

[0050] Where S is the feasibility score of the current construction plan. This refers to the actual construction period. For the target project duration, α is the adjustment coefficient for the impact on project duration. This indicates the degree of nonlinearity in the impact on the project duration. To account for the time cost during the execution of the simulated construction plan, To calculate the budgeted costs during the simulated construction process, It is an adjustment factor for the cost impact. This indicates the degree of non-linearity in the cost impact. For actual resource utilization rate, To maximize resource utilization, The moderating factor representing the impact of resource utilization rate It is a risk feedback function. It is the rate of change of risk;

[0051] Based on historical project data, a feasibility standard threshold is defined. ;

[0052] when If the current construction plan is deemed highly feasible, then the current construction plan will be implemented.

[0053] when If the current construction plan is deemed to have low feasibility and requires further optimization, then it is considered to be feasible.

[0054] As a preferred embodiment of the intelligent management platform for building engineering data information described in this invention, the risk feedback function is as follows:

[0055] Based on the construction progress delay risk index at time point t and risk change rate The dynamic prediction of the impact of resource utilization rate on feasibility score is expressed as follows:

[0056] ;

[0057] in, This refers to the degree to which resource utilization rate affects the feasibility score.

[0058] As a preferred embodiment of the intelligent management platform for construction engineering data information described in this invention, the optimized construction plan is further iteratively adjusted, and the specific steps are as follows.

[0059] If the optimized construction plan has low feasibility, return to the construction plan optimization module to adjust the plan again and perform another feasibility analysis until the feasibility score S of the current construction plan is greater than or equal to the feasibility standard threshold. When that happens, stop iterative adjustments and execute the current construction plan.

[0060] The beneficial effects of this invention are as follows: By capturing complex nonlinear relationships through feature interaction, the accuracy and reliability of construction progress prediction are significantly improved. The construction progress prediction model, combined with risk assessment, dynamically adjusts the construction plan to prevent delays. The virtual simulation module verifies the feasibility of the plan in advance, identifies potential problems, and ensures that the construction plan is optimized multiple times before execution. Ultimately, through an iterative optimization mechanism, the platform can continuously improve the feasibility of the construction plan, reduce the risk of delays and resource waste, and enhance construction management efficiency and project success rate. Attached Figure Description

[0061] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is a flowchart of the intelligent management platform for building engineering data information in Example 1.

[0063] Figure 2 This is a flowchart of assessing the construction progress status based on the construction progress delay risk index in Example 1. Detailed Implementation

[0064] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0065] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0066] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0067] Example 1, referring to Figure 1 and Figure 2 This is the first embodiment of the present invention, which provides an intelligent management platform for construction engineering data information, including the following steps:

[0068] S1: Real-time collection of construction data through sensors at the construction site, followed by preprocessing of the construction data.

[0069] S1.1: Collect data on the number of workers and working hours using personnel positioning sensors;

[0070] It should be noted that a personnel locator is a device used to track and record the location and activity of workers in real time, and typically relies on technologies such as GPS, Bluetooth, or ultra-wideband (UWB).

[0071] S1.2: Collect data on the usage time and operating status of the equipment through its sensors;

[0072] It should be noted that the equipment sensor is a sensor device installed on the construction equipment to monitor the equipment's operating status, usage time, workload, and health status in real time.

[0073] S1.3: Collect data on material transportation and consumption using RFID readers;

[0074] It should be noted that an RFID reader is a device that uses radio frequency identification (RFID) technology to read and process information about objects with RFID chips.

[0075] S1.4: Collect environmental parameters at the construction site using environmental sensors.

[0076] It should be noted that environmental sensors include temperature sensors and humidity sensors.

[0077] S1.5: Use data cleaning to remove incomplete, duplicate, and erroneous data from the construction data;

[0078] It should be noted that the specific process of data cleaning includes: First, identifying incomplete entries in the construction data through preset rules or missing value detection algorithms, and then filling or deleting them based on context or historical data; next, using deduplication algorithms to detect and delete duplicate data records to avoid bias during statistics or analysis; finally, identifying and correcting or removing abnormal or erroneous values ​​in the data through validation rules or machine learning models, thereby ensuring that the final dataset is complete, accurate, and consistent, providing reliable basic data for subsequent analysis and processing.

[0079] S1.6: Use data standardization to convert construction data of different dimensions into the same standard;

[0080] It should be noted that the focus of data standardization is to convert construction data with different dimensions into the same scale. This is typically achieved through methods such as min-max normalization or Z-score standardization, which scales the values ​​of each variable to a uniform range or a standard normal distribution. This eliminates differences between different dimensions, allowing data such as the number of workers, equipment usage time, and material consumption to be comprehensively analyzed and processed on the same scale, improving data comparability and the accuracy of subsequent models.

[0081] S1.7: By fusion, construction data is aligned and integrated according to the time dimension to form a global construction progress dataset.

[0082] It should be noted that the core steps of data fusion include: collecting construction data from different sensors (such as the number of workers, equipment usage time, etc.), aligning them by time dimension to ensure synchronization, and avoiding misalignment caused by differences in collection frequency. Subsequently, the multi-dimensional data is merged into a unified global construction progress dataset through data integration algorithms, providing complete and continuous information for subsequent progress assessment, risk prediction, and plan optimization.

[0083] S2: Perform feature interaction on the preprocessed construction data to build a construction progress prediction model and predict the construction progress delay risk index.

[0084] S2.1: Extract feature vectors of worker number, equipment usage time, and material consumption through statistical analysis;

[0085] For example, the number of workers can be used to extract feature vectors by calculating the daily average and variance; equipment usage time can be used to generate features by statistically analyzing the total daily usage time and utilization rate; and material consumption can be used to extract feature vectors by calculating the total daily consumption and its rate of change.

[0086] S2.2: Extract frequency characteristics and trend information of environmental parameters from time series data through Fourier transform;

[0087] For example, by using Fourier transform, time-series data of environmental parameters such as temperature and humidity at the construction site can be converted into the frequency domain, from which the main frequency components, such as the main frequency of the daytime temperature cycle and the amplitude of the change, can be extracted, thereby identifying the periodic fluctuations and long-term trend information of environmental parameters.

[0088] S2.3: Use frequency analysis to extract the equipment's failure frequency and operating efficiency;

[0089] For example, by analyzing the data on the operating status of equipment through frequency analysis, abnormal vibration or noise patterns at specific frequencies can be identified, and the fault frequencies of the equipment can be extracted. At the same time, by analyzing the frequency distribution of equipment operating time and downtime, the working efficiency characteristics of the equipment can be extracted, and the periodic patterns of efficient or inefficient operation can be identified.

[0090] S2.4: Based on the feature vectors of different data in the construction progress dataset, perform feature interaction to generate interactive features that can reflect the linkage effect between different data.

[0091] It should be noted that by performing feature interaction on different feature vectors in the construction progress dataset, interactive features reflecting the linkage effect between data can be generated. This can capture the complex relationships between multi-dimensional data such as the number of workers, equipment usage, and material consumption, thereby improving the model's accuracy in identifying and predicting construction progress delay risks and enhancing the decision support capability of construction management.

[0092] S2.4: The feature interaction includes the following steps,

[0093] S2.4.1: Using an exponentially weighted approach, feature interactions are performed on the construction data in the construction progress dataset to generate a first-order exponentially weighted interactive feature vector, expressed as:

[0094] ;

[0095] in, Let j represent the j-th first-order exponentially weighted interactive feature vector. It is the i-th eigenvector. represents the weight coefficient of the i-th feature vector in the exponentially weighted interaction, n is the number of samples, and i represents the feature vector index of the construction data;

[0096] It should be noted that by using an exponential weighting method to perform feature interaction on construction data, and combining different feature vectors according to their weights to generate a first-order exponentially weighted interactive feature vector, the ability to capture nonlinear trends and long-term dependencies in construction data can be effectively enhanced. This improves the model's prediction accuracy for schedule delays and risks in complex construction environments, and provides more accurate construction management decision support.

[0097] S2.4.2: Through logarithmic transformation, feature interaction is performed on the construction data in the construction progress dataset to generate a first-order logarithmic transformation interaction feature vector, the expression of which is:

[0098] ;

[0099] in, Let j represent the interactive eigenvector of the first-order logarithmic transformation. This represents the feature vector of the (i+1)th sample. It is the weight coefficient of the i-th eigenvector when the logarithmic change occurs;

[0100] It should be noted that by using logarithmic transformation for feature interaction, the feature vectors of adjacent samples are weighted and combined and then logarithmically transformed to generate a first-order logarithmic transformation interaction feature vector. This can effectively compress the range of feature values, reduce the impact of outliers on the model, and capture the nonlinear relationship between data, thereby further improving the stability and robustness of construction progress delay risk prediction.

[0101] S2.4.3: By nesting nonlinear combinations, the first-order exponentially weighted interaction feature and the first-order logarithmic transformation interaction feature are further interacted to generate a second-order nonlinear interaction feature, the expression of which is:

[0102] ;

[0103] in, It is the j-th second-order nonlinear interactive eigenvector.

[0104] It should be noted that by nesting nonlinear combinations, the first-order exponentially weighted interaction features and the first-order logarithmic transformation interaction features are further combined to generate second-order nonlinear interaction features. This can capture more complex nonlinear relationships and interaction effects between features, thereby improving the model's expressive power and prediction accuracy when processing multi-dimensional construction data, and helping to more accurately identify potential risks of construction progress delays.

[0105] S2.5: By combining three feature interaction methods—exponential weighted interaction, logarithmic variation, and nested nonlinear combination—a construction progress prediction model is constructed to predict the construction progress risk index. The expression is as follows:

[0106] ;

[0107] in, It is the construction progress delay risk index at time point t.

[0108] It should be noted that a complex construction schedule prediction model is constructed by integrating three feature interaction methods: exponential weighting, logarithmic transformation, and nested nonlinear combination. Exponential weighting captures the long-term dependencies of data, logarithmic transformation compresses the range of feature values ​​and reduces the impact of outliers, and nested nonlinear combination further explores the deep relationships between features. Finally, a construction schedule delay risk index is calculated using various nonlinear functions (such as sine, logarithmic, and hyperbolic tangent). This model effectively improves the prediction accuracy of schedule delay risks in complex construction environments, enhances the ability to capture complex linkage effects between multi-dimensional features, and has strong robustness and stability.

[0109] S3: Assess the construction progress status and optimize the construction plan based on the construction progress delay risk index.

[0110] S3.1: Define a low-latency risk threshold based on historical data and project characteristics. and high latency risk threshold ;

[0111] It should be noted that historical data refers to time-series data related to schedule collected from past construction projects, such as the number of workers, equipment usage time, material consumption, and environmental conditions. Analyzing this data can identify patterns and trends in delay risks. Project characteristics include factors such as project scale, complexity, schedule requirements, resource allocation, and environmental conditions. These characteristics determine the project's risk tolerance and reasonable schedule standards for different milestones. Combining historical data and project characteristics allows for the reasonable definition of a low-delay risk threshold. and high latency risk threshold This allows for a more accurate assessment of the risk level of project progress.

[0112] S3.1.1: When At that time, it was determined that there was no risk of delay in the current construction progress, and the current construction plan was maintained;

[0113] S3.1.2: When At that time, it was believed that there was a slight risk of delay in the current construction progress, so more workers were deployed to carry out construction, the service life of equipment was extended, and the transportation of construction materials was accelerated.

[0114] For example, when the construction progress delay risk index Between and In the meantime, the system will identify minor delay risks and recommend increasing the number of workers by 10% and extending equipment usage time by 2 hours to ensure that critical tasks are completed on time. In addition, the frequency of construction material transportation will be increased to ensure materials arrive in time before construction milestones, thus mitigating the impact of delays on the overall schedule.

[0115] S3.1.3: When At that time, it was believed that there was a serious risk of delay in the current construction progress, so an emergency increase in the number of workers was made and their working hours were increased. Emergency allocation of spare equipment and construction materials was also made, and alternative materials were used for construction.

[0116] For example, when the construction progress delay risk index Exceed Upon identifying a severe delay risk, the system immediately deployed an additional 20% of workers and extended daily working hours to 10 hours. Simultaneously, backup equipment was urgently called in to replace faulty equipment, and more construction materials were quickly deployed to the site. If raw material supplies were insufficient, the system recommended the use of feasible alternatives to ensure construction could continue and minimize the impact of delays on the overall project schedule.

[0117] S4: Verify the optimized construction plan through virtual simulation and identify potential problems that may cause delays in construction progress.

[0118] S4.1: Based on the optimized construction plan and construction data, construct a simulation model of the construction process and resource allocation on the virtual simulation platform to simulate the progress, procedures and resource consumption of different construction stages.

[0119] S4.2: Conduct simulation tests through a virtual simulation platform to simulate the execution of the construction plan at different times and under different environmental conditions;

[0120] S4.3: During the simulation of the construction plan, monitor the key indicators in the construction plan in real time and identify potential problems that may cause delays in the construction schedule;

[0121] S4.4: Monitor construction data in the simulated construction plan in real time, and identify potential problems that may cause delays in construction progress by analyzing the historical trends and abnormal fluctuations in the current rate of change of the construction data.

[0122] S4.5: The potential problems that could lead to delays in construction schedule include improper resource allocation, equipment failure, material supply delays, labor shortages, and the impact of environmental factors.

[0123] S5: Based on the identification results, conduct a feasibility analysis on the optimized construction plan and further iterate and adjust the optimized construction plan.

[0124] S5.1: Based on the potential problems identified by the virtual simulation platform that could lead to construction delays, and taking into account factors such as schedule, cost, and resource utilization, a risk feedback function is introduced to predict the feasibility score of the optimized construction plan. The expression is as follows:

[0125] ;

[0126] Where S is the feasibility score of the current construction plan. This refers to the actual construction period. For the target project duration, α is the adjustment coefficient for the impact on project duration. This indicates the degree of nonlinearity in the impact on the project duration. To account for the time cost during the execution of the simulated construction plan, To calculate the budgeted costs during the simulated construction process, It is an adjustment factor for the cost impact. This indicates the degree of non-linearity in the cost impact. For actual resource utilization rate, To maximize resource utilization, The moderating factor representing the impact of resource utilization rate It is a risk feedback function. It is the rate of change of risk;

[0127] It should be noted that by introducing three key factors—construction period, cost, and resource utilization—and combining them with a risk feedback function, this approach can achieve the desired results. The feasibility score S of the construction plan is predicted. Each part of the expression measures the difference between the actual and target construction periods, the deviation between actual and budgeted costs, and the ratio of actual resource utilization to maximum resource utilization. The effects of construction period and cost are refined through nonlinear adjustment coefficients k and m. The risk feedback function incorporates the current risk index. and risk change rate Further assessment of potential risk impacts is needed.

[0128] It should also be noted that, Part of it incorporates a dynamic risk adjustment mechanism, which not only considers the ratio of actual resource utilization to maximum resource utilization, but also uses a risk feedback function. This system reflects the changing trends and impacts of risks during construction in real time. This design overcomes the limitations of traditional construction plan evaluations that rely solely on resources or schedule. It allows for flexible responses to dynamically changing risk factors during construction while managing resources, thereby enabling more accurate feasibility prediction and optimization of the construction plan, improving risk resistance, and ensuring the robustness and flexibility of the construction plan.

[0129] S5.2: Define a feasibility standard threshold based on historical project data. ;

[0130] It should be noted that "historical project data" refers to various types of data accumulated from previously completed or ongoing construction projects. This data typically covers key factors such as project duration, cost, resource utilization, risk events, and schedule delays. Analyzing this historical data allows us to summarize performance patterns, common problems, and the reasons for success or failure in different projects. This data forms the basis for defining standard thresholds for construction feasibility. It provides a basis for predicting the feasibility of current projects and optimizing future construction decisions and plans.

[0131] S5.2.1: When If the current construction plan is deemed highly feasible, then the current construction plan will be implemented.

[0132] S5.2.2: When If the current construction plan is deemed to have low feasibility and requires further optimization, then it is considered to be feasible.

[0133] S5.3: The risk feedback function is as follows:

[0134] S5.3.1: Construction progress delay risk index based on time point t and risk change rate The dynamic prediction of the impact of resource utilization rate on feasibility score is expressed as follows:

[0135] ;

[0136] in, This refers to the degree to which resource utilization rate affects the feasibility score.

[0137] It should be noted that the risk feedback function design considered two key factors: First, This ensures that the impact of the risk index on the score is non-linear, as... As it increases, the degree of impact increases rapidly; secondly, The absolute value of the risk change rate is introduced to capture the fluctuation range of risk, thereby reflecting the impact of dynamic risk changes on feasibility. The overall function adopts a reciprocal form to ensure that when the risk index and change rate are high, the positive contribution of resource utilization rate to the feasibility score will be significantly weakened, reflecting that the efficiency of resource utilization under high risk is more sensitive to the impact on project success. This design can dynamically adjust the model's trade-off between risk and resources, improving the flexibility and accuracy of construction planning.

[0138] S5.4: When the optimized construction plan has low feasibility, return to the construction plan optimization module to readjust the construction plan and perform feasibility analysis again until the feasibility score S of the current construction plan is greater than or equal to the feasibility standard threshold. When that happens, stop iterative adjustments and execute the current construction plan.

[0139] It should be noted that when the feasibility score S of the optimized construction plan is lower than the feasibility standard threshold... If the feasibility score is too low, the system will automatically return to the construction plan optimization module and readjust parameters such as schedule, cost, and resource allocation. If the original schedule was too short, resulting in a low feasibility score, the system may adjust by extending the schedule or increasing the number of workers or equipment. Subsequently, the system performs another feasibility analysis. If the score still does not meet the standard, it continues iterative optimization until the feasibility score S ≥ 1. Ensure that the current construction plan is reasonable and feasible before implementing it.

[0140] In summary, this invention significantly improves the accuracy and reliability of construction schedule prediction by: capturing complex nonlinear relationships through feature interaction; dynamically adjusting the construction plan in conjunction with risk assessment to prevent delays; and using a virtual simulation module to verify the feasibility of the plan in advance, identify potential problems, and ensure that the construction plan is optimized multiple times before execution. Finally, through an iterative optimization mechanism, the platform can continuously improve the feasibility of construction plans, reduce delay risks and resource waste, and enhance construction management efficiency and project success rate.

[0141] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An intelligent management platform for construction engineering data information, characterized in that: include, The data acquisition module collects construction data in real time through sensors at the construction site and preprocesses the construction data. The delay risk prediction module performs feature interaction on the preprocessed construction data, builds a construction progress prediction model, and predicts the construction progress delay risk index. The construction plan optimization module assesses the construction progress status and optimizes the construction plan based on the construction progress delay risk index. The construction plan verification module uses virtual simulation to verify the optimized construction plan and identify potential problems that may cause construction delays. The specific steps are as follows. Based on the optimized construction plan and construction data, a simulation model of the construction process and resource allocation is built on the virtual simulation platform to simulate the progress, procedures and resource consumption of different construction stages. Simulation tests are conducted using a virtual simulation platform to simulate the execution of the construction plan at different times and under different environmental conditions. During the simulation of the construction plan, key indicators in the construction plan are monitored in real time to identify potential problems that may cause delays in the construction schedule. Real-time monitoring of construction data in the simulated construction plan; by analyzing the historical trends and abnormal fluctuations in the current rate of change of the construction data, potential problems that may cause delays in construction progress can be identified. The potential problems that could lead to delays in construction include improper resource allocation, equipment failure, material supply delays, labor shortages, and the impact of environmental factors. The feasibility analysis module performs a feasibility analysis on the optimized construction plan based on the identification results, and further iterates and adjusts the optimized construction plan. The feature interaction includes the following steps. An exponentially weighted approach is used to perform feature interaction on the construction data in the construction progress dataset, generating a first-order exponentially weighted interactive feature vector. By performing logarithmic transformation on the construction data in the construction progress dataset, a first-order logarithmic transformation interactive feature vector is generated. By using a nested nonlinear combination approach, the first-order exponential weighted interaction feature and the first-order logarithmic transformation interaction feature are further interacted to generate a second-order nonlinear interaction feature. By combining three feature interaction methods—exponential weighted interaction, logarithmic variation, and nested nonlinear combination—a construction progress prediction model is constructed to predict the construction progress risk index.

2. The intelligent management platform for construction engineering data information as described in claim 1, characterized in that: The construction data is collected in real time using sensors at the construction site. The specific steps are as follows: The number of workers and their working hours are collected using personnel positioning sensors. The device's usage time and operating status are collected through its sensors. The transportation and consumption of materials are collected through RFID tags; Environmental parameters at the construction site are collected using environmental sensors.

3. The intelligent management platform for construction engineering data information as described in claim 2, characterized in that: The specific steps for preprocessing the construction data are as follows. Data cleaning is used to remove incomplete, duplicate, and erroneous data from the construction data; Data standardization is used to convert construction data of different dimensions into the same standard; By fusion, construction data is aligned and integrated according to the time dimension to form a global construction progress dataset.

4. The intelligent management platform for construction engineering data information as described in claim 3, characterized in that: The specific steps for performing feature interaction on the preprocessed construction data are as follows: Statistical analysis was used to extract feature vectors for the number of workers, equipment usage time, and material consumption. By using Fourier transform, frequency characteristics and trend information of environmental parameters are extracted from time series data; Frequency analysis was used to extract the equipment's failure frequency and operating efficiency. Based on the feature vectors of different data in the construction progress dataset, feature interaction is performed to generate interactive features that can reflect the linkage effect between different data. The first-order exponentially weighted interactive feature vector is generated as follows: ； in, Let j represent the j-th first-order exponentially weighted interactive feature vector. It is the i-th eigenvector. represents the weight coefficient of the i-th feature vector in the exponentially weighted interaction, n is the number of samples, and i represents the feature vector index of the construction data; The expression for generating the first-order logarithmic transform interactive eigenvector is: ； in, Let j represent the interactive eigenvector of the first-order logarithmic transformation. This represents the feature vector of the (i+1)th sample. It is the weight coefficient of the i-th eigenvector when the logarithmic change occurs; The second-order nonlinear interaction feature is generated as follows: ； in, It is the j-th second-order nonlinear interactive eigenvector.

5. The intelligent management platform for construction engineering data information as described in claim 4, characterized in that: The specific steps for constructing a construction progress prediction model and predicting the construction progress delay risk index are as follows. The expression for the predicted construction progress risk index is: ； in, It is the construction progress delay risk index at time point t.

6. The intelligent management platform for construction engineering data information as described in claim 5, characterized in that: The specific steps for assessing the construction progress status and optimizing the construction plan based on the construction progress delay risk index are as follows. Based on historical data and the nature of the project, a low-latency risk threshold is defined. and high latency risk threshold ; when At that time, it was determined that there was no risk of delay in the current construction progress, and the current construction plan was maintained; when At that time, it was believed that there was a slight risk of delay in the current construction progress, so more workers were deployed to carry out construction, the service life of equipment was extended, and the transportation of construction materials was accelerated. when At that time, it was believed that there was a serious risk of delay in the current construction progress, so an emergency increase in the number of workers was made and their working hours were increased. Emergency allocation of spare equipment and construction materials was also made, and alternative materials were used for construction.

7. The intelligent management platform for construction engineering data information as described in claim 6, characterized in that: The feasibility analysis of the optimized construction plan based on the identification results is performed in the following steps. Based on the potential problems identified by the virtual simulation platform that could lead to construction delays, and taking into account factors such as schedule, cost, and resource utilization, a risk feedback function is introduced to predict the feasibility score of the optimized construction plan. The expression is as follows: ； Where S is the feasibility score of the current construction plan. This refers to the actual construction period. For the target project duration, α is the adjustment coefficient for the impact on project duration. This indicates the degree of nonlinearity in the impact on the project duration. To account for the time cost during the execution of the simulated construction plan, To calculate the budgeted costs during the simulated construction process, It is an adjustment factor for the cost impact. This indicates the degree of non-linearity in the cost impact. For actual resource utilization rate, To maximize resource utilization, The moderating factor representing the impact of resource utilization rate It is a risk feedback function. It is the rate of change of risk; Based on historical project data, a feasibility standard threshold is defined. ; when If the current construction plan is deemed highly feasible, then the current construction plan will be implemented. when If the current construction plan is deemed to have low feasibility and requires further optimization, then it is considered to be feasible.

8. The intelligent management platform for construction engineering data information as described in claim 7, characterized in that: The risk feedback function is as follows: Based on the construction progress delay risk index at time point t and risk change rate The dynamic prediction of the impact of resource utilization rate on feasibility score is expressed as follows: ； in, It is a risk feedback function that reflects the degree of influence of resource utilization on feasibility score.

9. The intelligent management platform for construction engineering data information as described in claim 8, characterized in that: The optimized construction plan will be further iterated and adjusted, with the following specific steps: If the optimized construction plan has low feasibility, return to the construction plan optimization module to adjust the plan again and perform another feasibility analysis until the feasibility score S of the current construction plan is greater than or equal to the feasibility standard threshold. When that happens, stop iterative adjustments and execute the current construction plan.

Images