Building engineering data information intelligent management platform

Abstract

The invention discloses a constructional engineering data information intelligent management platform, and relates to the technical field of constructional engineering intelligent management, and the platform comprises the steps: collecting construction data in real time through a sensor at a construction site, and carrying out the preprocessing of the construction data; performing feature interaction on the preprocessed construction data, constructing a construction progress prediction model, and predicting a construction progress delay risk index; according to the construction progress delay risk index, evaluating a construction progress state and optimizing a construction plan; the optimized construction plan is verified through virtual simulation, and potential problems causing construction progress delay are identified; and carrying out feasibility analysis on the optimized construction plan according to an identification result, and carrying out further iterative adjustment on the optimized construction plan. Through construction of the construction progress prediction model and feasibility analysis, accurate prediction of the construction progress is realized, feasibility of the construction plan is improved, construction delay and resource waste are effectively reduced finally, and project management efficiency is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management of construction projects, and particularly to an intelligent management platform for construction project data information. Background Art

[0002] With the continuous expansion of the scale and the increasing complexity of construction projects, how to effectively manage the construction progress, resource allocation, and compliance inspection has become an urgent problem in the construction industry. Traditional project management methods rely on manual records, supervision, and analysis. Although they can meet the project management needs to a certain extent, they are inefficient, have large errors, and are difficult to cope with complex construction environments and changing construction conditions. In recent years, with the rapid development of Internet of Things, big data, and artificial intelligence technologies, construction projects have gradually transformed towards intelligent management. Real-time collection of various data on the construction site through sensors, intelligent devices, and data platforms, and analysis and prediction combined with machine learning algorithms have become an important trend in modern construction project management. This intelligent transformation can not only improve construction efficiency but also effectively reduce the risks that may occur during the construction process.

[0003] However, there are still some deficiencies in the existing intelligent management platforms for construction projects that need to be solved urgently. First, although some platforms can predict the construction progress based on historical data, most rely on traditional linear models or simple time series analysis methods and cannot fully capture the non-linear dynamic characteristics in the construction data. As a result, when facing the risk of construction progress delay, the prediction accuracy is low, which in turn affects the overall progress management of the project. Second, in the process of optimizing the construction plan in the existing technology, usually only the balance between progress and cost is concerned, while the comprehensive consideration of multi-dimensional factors such as resource utilization rate, equipment health status, and environmental impact is ignored. As a result, during the implementation of the optimized construction plan, problems such as improper resource allocation or equipment failure may occur, affecting the smooth progress of the construction. Summary of the Invention

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

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

[0006] To solve the above technical problems, the present invention provides the following technical solutions: An embodiment of the present invention provides an intelligent management platform for construction engineering data information, which includes a data acquisition module that collects construction data in real time through sensors at the construction site and preprocesses the construction data; a delay risk prediction module that performs feature interaction on the preprocessed construction data, constructs a construction progress prediction model, and predicts the construction progress delay risk index; a construction plan optimization module that evaluates the construction progress status and optimizes the construction plan according to the construction progress delay risk index; a construction plan verification module that verifies the optimized construction plan through virtual simulation and identifies potential problems that cause construction progress delays; a feasibility analysis module that performs feasibility analysis on the optimized construction plan according to the identification results and further iteratively adjusts the optimized construction plan.

[0007] As a preferred solution of the intelligent management platform for construction engineering data information according to the present invention, wherein: the specific steps of collecting construction data in real time through sensors at the construction site are as follows, Collect the number of workers and working hours through personnel positioning sensors; Collect the usage duration and operating status of equipment through equipment sensors; Collect the transportation and consumption of materials through RFID tags; Collect the environmental parameters at the construction site through environmental sensors.

[0008] As a preferred solution of the intelligent management platform for construction engineering data information according to the present invention, wherein: the specific steps of preprocessing the construction data are as follows, Adopt data cleaning to remove incomplete, duplicate, and incorrect data in the construction data; Adopt data standardization to convert construction data with different dimensions into the same standard; Align and integrate the construction data according to the time dimension through data fusion to form a global construction progress data set.

[0009] As a preferred solution of the intelligent management platform for construction engineering data information according to the present invention, wherein: the specific steps of performing feature interaction on the preprocessed construction data are as follows, Extract the feature vectors of the number of workers, equipment usage duration, and material consumption through statistical analysis methods; Extract the frequency features and trend information of environmental parameters from time series data through Fourier transform; Adopt frequency analysis methods to extract the failure frequency and working efficiency of equipment; Perform feature interaction according to the feature vectors of different data in the construction progress data set to generate interaction features that can reflect the linkage effect between different data; The feature interaction includes the following steps, Using the method of exponential weighting, perform feature interaction on the construction data in the construction progress dataset to generate a first-order exponential weighted interaction feature vector, and the expression is: ; Among them, represents the j-th first-order exponential weighted interaction feature vector, is the i-th feature vector, represents the weight coefficient of the i-th feature vector during exponential weighted interaction, n is the number of samples, and i represents the feature vector index of the construction data; Through the method of logarithmic transformation, perform feature interaction on the construction data in the construction progress dataset to generate a first-order logarithmic transformation interaction feature vector, and the expression is: ; Among them, represents the j-th first-order logarithmic transformation interaction feature vector, represents the (i + 1)-th sample feature vector, is the weight coefficient of the i-th feature vector during logarithmic transformation interaction; Through the method of nested non-linear combination, further interact the first-order exponential weighted interaction feature and the first-order logarithmic transformation interaction feature to generate a second-order non-linear interaction feature, and the expression is: ; Among them, is the j-th second-order non-linear interaction feature vector.

[0010] As a preferred solution of the intelligent management platform for building engineering data information described in the present invention, wherein: constructing the construction progress prediction model to predict the construction progress delay risk index, the specific steps are as follows, By combining three feature interaction methods of exponential weighting interaction, logarithmic transformation, and nested non-linear combination, construct a construction progress prediction model to predict the construction progress risk index, and the expression is: ; Among them, is the construction progress delay risk index at time point t.

[0011] As a preferred solution of the intelligent management platform for building engineering data information described in the present invention, wherein: evaluating the construction progress status and optimizing the construction plan according to the construction progress delay risk index, the specific steps are as follows, Based on historical data and project nature, define a low delay risk threshold and a high delay risk threshold ; When When it is determined that there is no risk of delay in the current construction progress, the current construction plan is maintained; When it is determined that there is a mild risk of delay in the current construction progress, more workers are allocated in the construction plan, the usage time of equipment is extended, and the transportation of construction materials is accelerated; When it is determined that there is a severe risk of delay in the current construction progress, workers are urgently increased and their working hours are extended, standby equipment and construction materials are urgently allocated, and alternative materials are used for construction at the same time.

[0012] As a preferred solution of the intelligent management platform for construction project data information of the present invention, wherein: the optimized construction plan is tested through virtual simulation to identify potential problems causing construction progress delay, and the specific steps are as follows. According to the optimized construction plan and construction data, a simulation model of the construction process and resource allocation is constructed on the virtual simulation platform to simulate the progress, processes, and resource consumption links of different construction stages; Through the virtual simulation platform, a simulation test is carried out to simulate the implementation of the construction plan at different time points and under different environmental conditions; During the process of simulating the construction plan, key indicators in the construction plan are monitored in real time to identify potential problems causing construction progress delay; The construction data in the simulated construction plan is monitored in real time, and potential problems causing construction progress delay are identified by analyzing the abnormal fluctuations of the historical trend and current change rate of the construction data; The potential problems causing construction progress delay include improper resource allocation, equipment failure, material supply delay, insufficient workers, and the influence of environmental factors.

[0013] As a preferred solution of the intelligent management platform for construction project data information of the present invention, wherein: the feasibility analysis of the optimized construction plan is carried out according to the identification results, and the specific steps are as follows. According to the potential problems causing construction progress delay identified by the virtual simulation platform, considering the construction period, cost, and resource utilization rate comprehensively and introducing a risk feedback function, the feasibility score of the optimized construction plan is predicted, and the expression is: ;

[0014] Among them, S is the feasibility score of the current construction plan, is the actual construction period, is the target construction period, α is the adjustment coefficient of the construction period influence, represents the non-linear degree of the construction period influence, is the time cost during the process of implementing the simulated construction plan, For the budget cost in the process of implementing the simulated construction plan, is the adjustment coefficient of cost impact, indicating the non - linear degree of cost impact, is the actual resource utilization rate, is the maximum resource utilization rate, indicating the adjustment factor of resource utilization rate impact, is the risk feedback function, is the risk change rate; Based on historical project data, define a feasibility standard threshold ; When then the current construction plan is considered to have a high feasibility and execute the current construction plan; When then the current construction plan is considered to have a low feasibility and needs to be further optimized.

[0015] As a preferred solution of the intelligent management platform for building engineering data information described in the present invention, wherein: the risk feedback function is specifically as follows, According to the construction progress delay risk index at time point t and the risk change rate , dynamically predict the influence degree of resource utilization rate on the feasibility score, and the expression is: ;

[0016] Wherein, is the influence degree of resource utilization rate on the feasibility score.

[0017] As a preferred solution of the intelligent management platform for building engineering data information described in the present invention, wherein: further iteratively adjust the optimized construction plan, and the specific steps are as follows, When the feasibility of the optimized construction plan is low, return to the construction plan optimization module, adjust the construction plan again, and conduct a feasibility analysis again until the feasibility score S of the current construction plan ≥ the feasibility standard threshold At this time, stop the iterative adjustment and execute the current construction plan.

[0018] The beneficial effects of the present invention are as follows: By feature interaction, capturing complex non - linear relationships significantly speeds up the accuracy and reliability of construction progress prediction. The construction progress prediction model combines risk assessment to dynamically adjust the construction plan to prevent progress 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. Finally, through the 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. Brief Description of the Drawings

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0020] Figure 1 It is the flowchart of the intelligent management platform for construction project data information in Embodiment 1.

[0021] Figure 2 It is the flowchart of evaluating the construction progress status according to the construction progress delay risk index in Embodiment 1. Specific Embodiments

[0022] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification.

[0023] Many specific details are set forth in the following description to facilitate a thorough understanding of the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0024] Secondly, the so-called "one embodiment" or "embodiment" herein refers to specific features, structures, or characteristics that can be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that mutually excludes other embodiments.

[0025] Embodiment 1, referring to Figure 1 and Figure 2 , is the first embodiment of the present invention. This embodiment provides an intelligent management platform for construction project data information, including the following steps: S1: Real-time collect construction data through sensors at the construction site and preprocess the construction data.

[0026] S1.1: Collect the number of workers and working hours through personnel positioning sensors; It should be noted that a personnel locator is a device used to track and record the location and activity status of workers in real time, usually relying on technologies such as GPS, Bluetooth, or ultra-wideband (UWB).

[0027] S1.2: Collect the usage duration and operating status of equipment through equipment sensors; It should be noted that the equipment sensor is a sensor device installed on construction equipment, used to monitor the operating status, usage duration, working load, and health status of the equipment in real time.

[0028] S1.3: Collect the transportation and consumption of materials through an RFID reader. It should be noted that an RFID reader is a device that uses radio frequency identification technology (RFID) to read and process the information of objects with RFID chips.

[0029] S1.4: Collect the environmental parameters at the construction site through environmental sensors.

[0030] It should be noted that environmental sensors include temperature sensors and humidity sensors.

[0031] S1.5: Use data cleaning to remove incomplete, duplicate, and incorrect data in the construction data. It should be noted that the specific process of data cleaning includes: First, identify incomplete entries in the construction data through preset rules or missing value detection algorithms, and then fill or delete them according to the context or historical data; Next, use a deduplication algorithm to detect and delete duplicate data records to avoid biases in statistics or analysis; Finally, identify abnormal or incorrect values in the data through verification rules or machine learning models and correct or eliminate them, so as to ensure that the final dataset is complete, accurate, and consistent, providing reliable basic data for subsequent analysis and processing.

[0032] S1.6: Use data standardization to convert construction data with different dimensions into the same standard. It should be noted that the key point of data standardization is to convert construction data with different dimensions into the same scale, usually through methods such as min-max normalization or Z-score normalization, to scale the values of each variable into a unified range or standard normal distribution. This can eliminate the differences between different dimensions, enabling comprehensive analysis and processing of data such as the number of workers, equipment usage duration, and material consumption on the same scale, improving the comparability of data and the accuracy of subsequent models.

[0033] S1.7: Align and integrate the construction data in the time dimension through data fusion to form a global construction progress dataset.

[0034] It should be noted that the core steps of data fusion include: Collect construction data from different sensors (such as the number of workers, equipment usage duration, etc.), align them in the time dimension to ensure synchronization, and avoid misalignment caused by differences in acquisition frequencies. Subsequently, use a data integration algorithm to merge multi-dimensional data into a unified global construction progress dataset, providing complete and continuous information for subsequent progress evaluation, risk prediction, and plan optimization.

[0035] S2: Perform feature interaction on the preprocessed construction data to construct a construction progress prediction model and predict the construction progress delay risk index.

[0036] S2.1: Extract the feature vectors of the number of workers, equipment usage duration, and material consumption through statistical analysis methods; For example, for the number of workers, its feature vector can be extracted by calculating the daily average value and variance. The equipment usage duration can generate features by statistically analyzing the total daily usage duration and utilization rate, while the material consumption can extract the feature vector through the total daily consumption and its change rate.

[0037] S2.2: Extract the frequency features and trend information of environmental parameters from time series data through Fourier transform; For example, through Fourier transform, the time series data of environmental parameters such as temperature and humidity at the construction site can be transformed into the frequency domain, and the main frequency components can be extracted from it, such as the main frequency of the daily temperature cycle and the amplitude of the change, so as to identify the periodic fluctuations and long-term trend information of environmental parameters.

[0038] S2.3: Adopt frequency analysis methods to extract the failure frequency and working efficiency of equipment; For example, through frequency analysis methods, analyzing the data of the equipment operation status can identify abnormal vibration or noise patterns at specific frequencies and extract the failure frequency of the equipment. At the same time, by analyzing the frequency distribution of the equipment operation time and downtime, the working efficiency characteristics of the equipment can be extracted to identify the periodic laws of efficient or inefficient operation.

[0039] S2.4: Perform feature interaction based on the feature vectors of different data in the construction progress dataset to generate interaction features that can reflect the linkage effect between different data; It should be noted that by performing feature interaction on different feature vectors in the construction progress dataset to generate interaction features that reflect the linkage effect between data, the complex relationships among multi-dimensional data such as the number of workers, equipment usage, and material consumption can be captured, thereby improving the recognition and prediction accuracy of the model for construction progress delay risks and enhancing the decision-making support ability of construction management.

[0040] S2.4: The feature interaction includes the following steps S2.4.1: Adopt an exponentially weighted method to perform feature interaction on the construction data in the construction progress dataset to generate a first-order exponentially weighted interaction feature vector, and the expression is: ;

[0041] Where represents the j-th first-order exponentially weighted interaction feature vector, is the i-th eigenvector, represents the weight coefficient of the i-th eigenvector during exponentially weighted interaction. n is the number of samples, and i represents the index of the eigenvector of the construction data; It should be noted that by performing feature interaction on the construction data through the exponentially weighted method, different eigenvectors are combined according to weights to generate the first-order exponentially weighted interaction eigenvector, which can effectively enhance the ability to capture the non-linear trends and long-term dependencies in the construction data, thereby improving the prediction accuracy of the model for schedule delays and risks in complex construction environments and providing more accurate decision support for construction management.

[0042] S2.4.2: Through logarithmic transformation, perform feature interaction on the construction data in the construction progress dataset to generate the first-order logarithmic transformation interaction eigenvector. The expression is: ;

[0043] where, represents the j-th first-order logarithmic transformation interaction eigenvector, represents the (i + 1)-th sample eigenvector, is the weight coefficient of the i-th eigenvector during logarithmic transformation interaction; It should be noted that by performing feature interaction through logarithmic transformation, the adjacent sample eigenvectors are weighted and combined and then the logarithm is taken to generate the first-order logarithmic transformation interaction eigenvector, which can effectively compress the eigenvalue range, reduce the influence of outliers on the model, and at the same time capture the non-linear relationships between data, further improving the stability and robustness of the construction schedule delay risk prediction.

[0044] S2.4.3: Through the method of nested non-linear combination, further interact the first-order exponentially weighted interaction feature and the first-order logarithmic transformation interaction feature to generate the second-order non-linear interaction feature. The expression is: ;

[0045] where, is the j-th second-order non-linear interaction eigenvector.

[0046] It should be noted that by the method of nested non-linear combination, further combine the first-order exponentially weighted interaction feature and the first-order logarithmic transformation interaction feature to generate the second-order non-linear interaction feature, which can capture more complex non-linear relationships and interaction effects between features, thereby enhancing the expression ability and prediction accuracy of the model when dealing with multi-dimensional construction data, and helping to more accurately identify the potential risks of construction schedule delays.

[0047] S2.5: By combining three feature interaction methods of exponentially weighted interaction, logarithmic transformation, and nested non-linear combination, a construction progress prediction model is constructed to predict the construction progress risk index, and the expression is: ;

[0048] where is the construction progress delay risk index at time point t.

[0049] It should be noted that by integrating three feature interaction methods of exponentially weighted interaction, logarithmic transformation interaction, and nested non-linear combination, a complex construction progress prediction model is constructed. The long-term dependence of data is captured by exponential weighting, the eigenvalue range is compressed by logarithmic transformation and the influence of outliers is reduced, and the deep relationship between features is further explored by nested non-linear combination. Finally, the construction progress delay risk index is calculated through various non-linear functions (such as sine, logarithm, hyperbolic tangent, etc.) This model effectively improves the prediction accuracy of the progress delay risk in complex construction environments, enhances the ability to capture the complex coupling effects between multi-dimensional features, and has strong robustness and stability.

[0050] S3: According to the construction progress delay risk index, evaluate the construction progress status and optimize the construction plan.

[0051] S3.1: Based on historical data and project nature, define a low delay risk threshold and a high delay risk threshold ; It should be noted that historical data refers to time series data related to progress such as the number of workers, equipment usage duration, material consumption, and environmental conditions collected in past construction projects. By analyzing these data, the laws and trends of delay risks can be identified; project nature includes factors such as project scale, complexity, construction period requirements, resource allocation, and environmental conditions. These characteristics determine the project's risk tolerance and reasonable progress standards for different nodes. Combining historical data and project nature, the low delay risk threshold and the high delay risk threshold can be reasonably defined to more accurately evaluate the risk level of the project progress.

[0052] S3.1.1: When , it is considered that there is no delay risk in the current construction progress, and the current construction plan is maintained; S3.1.2: When , it is considered that there is a mild delay risk in the current construction progress, and more workers are allocated in the construction plan for construction, the equipment usage time is extended, and the transportation of construction materials is accelerated; For example, when the construction progress delay risk index is between and When it is between, the system will identify a mild delay risk, recommend increasing the number of workers by 10%, and extending the equipment usage time by 2 hours to ensure that key tasks are completed on time. In addition, accelerate the transportation frequency of construction materials to ensure that the materials are in place in time before the construction nodes to mitigate the impact of delays on the overall progress.

[0053] S3.1.3: When it is considered that there is a severe delay risk in the current construction progress, urgently increase the number of workers for construction and increase the working hours of workers, urgently allocate spare equipment and construction materials, and at the same time use alternative materials for construction.

[0054] For example, when the construction progress delay risk index exceeds the system identifies a severe delay risk, immediately allocates an additional 20% of workers, and extends the daily working hours to 10 hours. At the same time, urgently call for spare equipment to replace the faulty equipment, and quickly allocate more construction materials to the site. If the supply of raw materials is insufficient, the system recommends using feasible alternative materials to ensure that the construction can continue and minimize the impact of delays on the overall project duration.

[0055] S4: Verify the optimized construction plan through virtual simulation and identify potential problems causing construction progress delays.

[0056] S4.1: According to the optimized construction plan and construction data, build a simulation model of the construction process and resource allocation on the virtual simulation platform to simulate the progress, processes, and resource consumption links of different construction stages; S4.2: Conduct simulation tests through the virtual simulation platform to simulate the implementation of the construction plan at different time points and under different environmental conditions; S4.3: During the process of simulating the construction plan, real-time monitor key indicators in the construction plan to identify potential problems causing construction progress delays; S4.4: Real-time monitor the construction data in the simulated construction plan, and identify potential problems causing construction progress delays by analyzing abnormal fluctuations in the historical trends and current change rates of the construction data; The potential problems causing construction progress delays include improper resource allocation, equipment failures, material supply delays, insufficient workers, and the impact of environmental factors.

[0057] S5: Conduct a feasibility analysis of the optimized construction plan based on the identification results and further iteratively adjust the optimized construction plan.

[0058] S5.1: Based on the potential problems identified by the virtual simulation platform that cause construction schedule delays, comprehensively consider the construction period, cost, and resource utilization rate, and introduce a risk feedback function to predict the feasibility score of the optimized construction plan. The expression is as follows: ;

[0059] where S is the feasibility score of the current construction plan, is the actual construction period, is the target construction period, α is the adjustment coefficient for the impact of the construction period, represents the non - linear degree of the impact of the construction period, is the time cost during the execution of the simulated construction plan, is the budget cost during the execution of the simulated construction plan, is the adjustment coefficient for the impact of cost, represents the non - linear degree of the impact of cost, is the actual resource utilization rate, is the maximum resource utilization rate, represents the adjustment factor for the impact of resource utilization rate, is the risk feedback function, is the risk change rate; It should be noted that by introducing the three key factors of the construction period, cost, and resource utilization rate, and combining the risk feedback function , the feasibility score S of the construction plan is predicted. Each part of the expression measures the difference between the actual construction period and the target construction period, the deviation between the actual cost and the budget cost, and the ratio of the actual resource utilization rate to the maximum resource utilization rate, and the impacts of the construction period and cost are refined through the non - linear adjustment coefficients k and m. The risk feedback function combines the current risk index and the risk change rate to further evaluate the potential risk impacts.

[0060] It should also be noted that part, by introducing a dynamic risk adjustment mechanism, not only considers the ratio of the actual resource utilization rate to the maximum resource utilization rate, but also through the risk feedback function , reflects the changing trend and its impact of risks during the construction process in real - time. This design breaks through the limitations of simply relying on resources or the construction period in traditional construction plan evaluation, can flexibly respond to the dynamically changing risk factors during the construction process while managing resources, thereby achieving more accurate feasibility prediction and optimization of the construction plan, improving the risk - resistance ability, and ensuring the robustness and flexibility of the construction plan.

[0061] S5.2: Based on historical project data, define a feasibility standard threshold ; It should be noted that "historical project data" refers to various data accumulated in previous completed or ongoing construction projects. These data typically cover key factors such as project duration, cost, resource utilization rate, risk events, and schedule delays. By analyzing these historical data, performance patterns, common problems, and reasons for success or failure of different projects can be summarized. These data provide a basis for defining the threshold of construction feasibility criteria to help predict the feasibility of the current project and optimize future construction decisions and plans.

[0062] S5.2.1: When holds, the current construction plan is considered to have a relatively high feasibility, and the current construction plan is executed; S5.2.2: When holds, the current construction plan is considered to have a relatively low feasibility, and further optimization is required.

[0063] S5.3: The risk feedback function is specifically as follows. S5.3.1: Based on the construction schedule delay risk index at time point t and the risk change rate , the impact degree of resource utilization rate on the feasibility score is dynamically predicted, and the expression is: ;

[0064] where is the impact degree of resource utilization rate on the feasibility score.

[0065] It should be noted that the design of the risk feedback function takes into account two key factors: First, ensures that the impact of the risk index on the score is non - linear. As increases, the impact degree increases rapidly. Second, introduces the absolute value of the risk change rate to capture the fluctuation range of the risk, thereby reflecting the impact of the dynamic change of the risk on the feasibility. The overall function adopts a reciprocal form to ensure that when the risk index and the change rate are high, the positive contribution of the resource utilization rate to the feasibility score will be significantly weakened, reflecting that the utilization efficiency of resources under high risks has a more sensitive impact on project success. This design can dynamically adjust the model's trade - off between risk and resources, improving the flexibility and accuracy of the construction plan.

[0066] S5.4: When the feasibility of the optimized construction plan is relatively low, return to the construction plan optimization module, readjust the construction plan again, and conduct a feasibility analysis again until the feasibility score S of the current construction plan ≥ the feasibility standard threshold at which point, stop the iterative adjustment and execute the current construction plan.

[0067] It should be noted that when the feasibility score S of the optimized construction plan is lower than the feasibility standard threshold , the system will automatically return to the construction plan optimization module to readjust parameters such as the construction period, cost, and resource allocation. Suppose the construction period in the original plan is too short, resulting in a low feasibility score. The system may make adjustments by extending the construction period, increasing the number of workers or equipment, etc. Subsequently, the system conducts a feasibility analysis again. If the score still does not meet the standard, it continues to iterate and optimize until the feasibility score S≥ , ensuring the rationality and executability of the current construction plan before implementation.

[0068] In summary, the present invention, through feature interaction to capture complex non-linear relationships, significantly improves the accuracy and reliability of construction progress prediction. The construction progress prediction model combines risk assessment to dynamically adjust the construction plan and prevent schedule delays. The virtual simulation module verifies the feasibility of the plan in advance, identifies potential problems, and ensures that the construction plan undergoes multiple optimizations before execution. Finally, through the 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.

[0069] 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 them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. An intelligent management platform for construction engineering data information, characterized by: include, The data acquisition module collects construction data in real time through sensors at the construction site and pre-processes the construction data; The delay risk prediction module performs feature interaction on the pre-processed construction data, builds a construction progress prediction model, and predicts the construction progress delay risk index; The construction plan optimization module evaluates the construction progress status and optimizes the construction plan according to the construction progress delay risk index; The construction plan verification module verifies the optimized construction plan through virtual simulation and identifies potential problems that may cause delays in the construction schedule; The feasibility analysis module conducts feasibility analysis on the optimized construction plan based on the identification results, and further iterates and adjusts the optimized construction plan.

2. The intelligent management platform for construction engineering data information according to claim 1, characterized in that: The specific steps of collecting construction data in real time through sensors at the construction site are as follows: Through personnel positioning sensors, the number of workers and working hours are collected; Collect the usage time and operating status of the equipment through equipment sensors; Collect material transportation and consumption through RFID tags; Environmental parameters of the construction site are collected through environmental sensors.

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

4. The intelligent management platform for construction engineering data information according to claim 3, characterized in that: The specific steps of performing feature interaction on the preprocessed construction data are as follows: Through statistical analysis, the characteristic vectors of the number of workers, equipment usage time and material consumption are extracted; Through Fourier transform, the frequency characteristics and trend information of environmental parameters are extracted from time series data; Use frequency analysis method to extract equipment failure frequency and work efficiency; Perform feature interaction based on the feature vectors of different data in the construction progress dataset to generate interactive features that can reflect the linkage effect between different data; The feature interaction includes the following steps: The construction data in the construction progress dataset are interactively analyzed using an exponential weighting method to generate a first-order exponentially weighted interactive feature vector, which is expressed as follows: ； in, represents the jth first-order exponentially weighted interaction eigenvector, is the i-th eigenvector, represents the weight coefficient of the i-th eigenvector in the exponentially weighted interaction, n is the number of samples, and i represents the eigenvector index of the construction data; By means of logarithmic transformation, the construction data in the construction progress dataset are interactively characterized to generate a first-order logarithmic transformation interactive feature vector, which is expressed as follows: ； in, represents the jth first-order logarithmic transformation interaction eigenvector, represents the i+1th sample feature vector, is the weight coefficient of the i-th eigenvector when interacting with logarithmic changes; By nesting nonlinear combinations, the first-order exponentially weighted interaction features and the first-order logarithmic transformation interaction features are further interacted to generate second-order nonlinear interaction features, which are expressed as follows: ； in, is the jth second-order nonlinear interaction eigenvector.

5. The intelligent management platform for construction engineering data information according to claim 4, characterized in that: The construction progress prediction model is constructed to predict the construction progress delay risk index. The specific steps are as follows: By combining the three feature interaction modes of exponential weighted interaction, logarithmic change and nested nonlinear combination, a construction progress prediction model is constructed to predict the construction progress risk index. The expression is: ； in, is the construction schedule delay risk index at time point t.

6. The intelligent management platform for construction engineering data information according to claim 5, characterized in that: According to the construction progress delay risk index, the construction progress status is evaluated and the construction plan is optimized. The specific steps are as follows: Define a low latency risk threshold based on historical data and the nature of the project and high latency risk threshold ; when When the construction progress is considered to be free of delay risk, the current construction plan is maintained; when When the construction progress is considered to be at risk of slight delay, more workers will be deployed to carry out the construction, the use time of equipment will be extended, and the transportation of construction materials will be accelerated; when When the construction progress is considered to be at risk of severe delay, additional workers are urgently added to carry out construction and their working hours are increased, spare equipment and construction materials are urgently deployed, and alternative materials are used for construction.

7. The intelligent management platform for construction engineering data information according to claim 6, characterized in that: The optimized construction plan is tested through virtual simulation to identify potential problems that may cause delays in the construction progress. 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, process and resource consumption links of different construction stages; Conduct simulation tests through a virtual simulation platform to simulate the execution of the construction plan at different time points and under different environmental conditions; During the construction plan simulation, key indicators in the construction plan are monitored in real time to identify potential problems that may delay the construction schedule; Real-time monitoring of construction data in simulated construction plans, identifying potential problems that may delay construction progress by analyzing historical trends in construction data and abnormal fluctuations in current rates of change; The potential problems that caused construction schedule delays included improper resource allocation, equipment failure, delayed material supply, insufficient workers and the impact of environmental factors.

8. The intelligent management platform for construction engineering data information according to claim 7, characterized in that: The feasibility analysis of the optimized construction plan is carried out according to the identification results. The specific steps are as follows: According to the potential problems that lead to construction delays identified by the virtual simulation platform, the feasibility score of the optimized construction plan is predicted by comprehensively considering the construction period, cost and resource utilization and introducing the risk feedback function. The expression is: ； Where S is the feasibility score of the current construction plan, is the actual construction period, is the target duration, α is the adjustment coefficient of the duration, Indicates the nonlinear degree of the construction period impact, To simulate the time cost of construction planning, To implement the budget cost during the simulation construction planning process, is the adjustment coefficient for cost impact, Indicates the nonlinear degree of cost impact, is the actual resource utilization rate, For maximum resource utilization, represents the adjustment factor affecting resource utilization, is the risk feedback function, is the risk change rate; Define a feasibility criteria threshold based on historical project data ; when When , the feasibility of the current construction plan is considered to be high, and the current construction plan is executed; when , it is considered that the current construction plan is less feasible and needs further optimization.

9. The intelligent management platform for construction engineering data information according to claim 8, characterized in that: The risk feedback function is as follows: According to the construction progress delay risk index at time point t and the risk change rate , dynamically predict the impact of resource utilization on feasibility score, the expression is: ； in, is the degree of influence of resource utilization on the feasibility score.

10. The intelligent management platform for construction engineering data information according to claim 9, characterized in that: The optimized construction plan is further iterated and adjusted. The specific steps are as follows: When the feasibility of the optimized construction plan is low, return to the construction plan optimization module, adjust the construction plan again, and perform feasibility analysis again until the feasibility score S of the current construction plan ≥ the feasibility standard threshold , stop iterative adjustments and execute the current construction plan.

Images