An engineering construction progress monitoring management system and method based on an internet of things

Abstract

This invention discloses an IoT-based engineering construction progress monitoring and management system and method, belonging to the field of building engineering information management technology. The system includes: acquiring construction site data and transmitting it to a central data processing center via a wireless local area network for preliminary processing; tracking construction resource status data in real time and, combined with a set of construction characteristic information, project plans, and current project progress, calculating the phased predicted resource demand using a resource demand assessment method to generate a construction resource demand report; combining the construction resource demand report with real-time site conditions and resource availability, and automatically adjusting the resource allocation scheme using intelligent algorithms to formulate an engineering construction progress plan. By applying multi-source heterogeneous data fusion algorithms and intelligent assessment and prediction of phased predicted resource demand, the efficiency of engineering construction progress monitoring and management and the project success rate are improved.

Description

Technical Field

[0001] This invention relates to the field of information management technology for construction projects, and in particular to an Internet of Things-based project construction progress monitoring and management system and method. Background Technology

[0002] In recent years, with the rapid development of IoT technology and its widespread application in various industries, the engineering construction industry has gradually introduced intelligent management systems to improve work efficiency and management level. The application of IoT technology provides a new approach to solving these problems. By deploying various sensor devices on-site, such as temperature, humidity, and pressure sensors, information such as various environmental parameters and machinery operating status at the construction site can be collected in real time. This data, after processing, can provide project managers with detailed information on construction progress, greatly improving the accuracy and efficiency of project management.

[0003] Nevertheless, existing engineering construction progress monitoring and management systems still have some shortcomings. Data collected by different types of sensors comes in various formats, and there is a lack of an efficient method to integrate and process this multi-source heterogeneous data, resulting in incomplete and inaccurate data analysis results. Regarding resource scheduling, current systems mainly rely on manual experience to formulate resource allocation plans. This approach struggles to achieve optimal configuration, especially in complex construction scenarios, often failing to respond promptly to changes and adjust plans, thus impacting the overall project schedule. Summary of the Invention

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

[0005] Therefore, this invention provides an IoT-based method for monitoring and managing engineering construction progress, which solves the problems of difficulty in integrating multi-source heterogeneous data and inflexible resource scheduling.

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

[0007] In a first aspect, the present invention provides an Internet of Things-based method for monitoring and managing the progress of engineering construction, which includes acquiring construction site data and transmitting it to a central data processing center via a wireless local area network for preliminary processing.

[0008] By using a multi-source heterogeneous data fusion algorithm, the pre-processed construction site data is integrated, and the integrated construction data is deeply mined to identify construction modes and construction progress trends, and to obtain a set of construction feature information.

[0009] Real-time tracking of construction resource status data, combined with construction characteristic information set, project plan and current project progress, and using resource demand assessment methods to calculate the phased predicted resource demand and generate a construction resource demand report;

[0010] By combining construction resource demand reports with real-time site conditions and resource availability, and using intelligent algorithms to automatically adjust resource allocation plans, a construction schedule can be developed.

[0011] As a preferred embodiment of the IoT-based engineering construction progress monitoring and management method of the present invention, the construction site data includes the construction environment, the status of construction equipment, and the location of construction personnel.

[0012] As a preferred embodiment of the IoT-based engineering construction progress monitoring and management method of the present invention, the construction site data is transmitted to a central data processing center for timestamp standardization, field standardization, missing data processing, and abnormal data detection and filtering to obtain the preliminary processed construction site data.

[0013] As a preferred embodiment of the IoT-based engineering construction progress monitoring and management method of the present invention, the step of integrating the pre-processed construction site data through a multi-source heterogeneous data fusion algorithm includes the following specific steps.

[0014] The format characteristics, field structure, and encoding methods of data sources from different construction sites are parsed and the structure is identified. Field names, data types, and hierarchical relationship information are extracted, and natural language processing methods are used to identify semantic relationships and structural differences between fields.

[0015] Semantic parsing and formatting parsing are performed on unstructured and semi-structured construction site data, which are then transformed into standard fields that can be integrated. A dynamic field transformation relationship mapping table is generated by combining the semantic relationships and structural differences between the fields.

[0016] Based on a dynamic field transformation relationship mapping table, ETL tools are used to extract, transform, and load data into a unified data format.

[0017] Calculate the conditional probability weights between various data sources for construction site data in a unified data format, and use the conditional probability weights to determine the reliability and fusion ratio, perform weighted integration, and generate a construction data set.

[0018] Perform logical checks and cross-data source verifications on the construction data set to obtain integrated construction data.

[0019] As a preferred embodiment of the IoT-based engineering construction progress monitoring and management method of the present invention, the specific steps for obtaining the construction feature information set are as follows:

[0020] Based on integrated construction data, a construction progress time series was constructed and statistical analysis was performed to obtain the construction progress trend.

[0021] Deep analysis of construction integration data is performed. The K-means algorithm is used to group construction integration data with similar behavioral patterns, identify different types of construction activities, and summarize them into different construction modes.

[0022] The Granger causality test method was used to analyze the causal relationship between construction mode and construction progress trend.

[0023] The construction mode, construction progress trend and causal relationship are organized into a visual format through three-dimensional visualization rendering to form a set of construction feature information.

[0024] As a preferred embodiment of the IoT-based engineering construction progress monitoring and management method of the present invention, the specific steps for real-time tracking of construction resource status data are as follows:

[0025] The identification information and location of construction resources are recorded by RFID tags, the precise coordinates of construction resources are provided by GPS sensors, and the usage status of construction resources is monitored by sensor networks.

[0026] The identity information and location of construction resources, their precise coordinates, and their usage status are transmitted to the central data processing center to generate construction resource status data.

[0027] As a preferred embodiment of the IoT-based engineering construction progress monitoring and management method of the present invention, the step of calculating the phased predicted resource demand by combining the set of construction characteristic information, project plan, and current project progress using a resource demand assessment method is as follows:

[0028] Based on the project contract, technical design documents, and construction organization design, a Gantt chart and network diagram are created in Microsoft Project using the task breakdown structure to obtain the project plan;

[0029] The construction mode and construction progress trend are extracted from the construction feature information set, and statistical analysis is performed on the completed tasks and resource consumption in conjunction with the project plan to obtain the current project progress status.

[0030] Compare the data on tasks and resource inputs at each stage of the construction mode and construction progress trend, and statistically analyze the frequency and intensity of resource use at different construction stages to obtain resource use characteristics.

[0031] By inputting resource usage characteristics, construction resource status data, and current project progress status into a time series forecasting model, the consumption rate of various construction resources within future time windows is calculated to obtain the phased predicted resource demand.

[0032] As a preferred embodiment of the IoT-based engineering construction progress monitoring and management method of the present invention, the specific steps for generating the construction resource demand report are as follows:

[0033] Based on the phased forecast of resource demand, a resource demand urgency index is obtained by calculating the ratio. The resource demand urgency index is then sorted using the bubble sort algorithm, and the resource names are listed in order according to the sorting results to form a resource allocation priority list.

[0034] Analyze historical periodic resource demand forecasts and set demand thresholds. Compare the phased resource forecast demand;

[0035] The phased resource forecast demand, resource allocation priority list, and demand comparison results are integrated using Pandas, and a construction resource demand report is generated using the Python programming language.

[0036] As a preferred embodiment of the IoT-based engineering construction progress monitoring and management method of the present invention, the specific steps for formulating the engineering construction progress plan are as follows:

[0037] Real-time monitoring of the construction site is achieved through IoT sensors and drones, providing real-time information on site conditions and resource availability.

[0038] Based on the construction resource demand report, set construction resource constraints;

[0039] Based on real-time site conditions and resource availability, and in conjunction with construction resource constraints, the resource allocation scheme in the project plan is dynamically adjusted using the particle swarm optimization algorithm.

[0040] By using Microsoft Project in conjunction with custom algorithm scripts, dynamically adjusted resource allocation schemes can be transformed into specific engineering construction schedules.

[0041] Secondly, the present invention provides an Internet of Things-based engineering construction progress monitoring and management system, including a data acquisition module for acquiring construction site data and transmitting it to a central data processing center via a wireless local area network for preliminary processing.

[0042] The data fusion and analysis module is used to integrate the pre-processed construction site data through multi-source heterogeneous data fusion algorithms, perform in-depth mining of the integrated construction data, identify construction modes and construction progress trends, and obtain a set of construction feature information.

[0043] The resource tracking and assessment module is used to track construction resource status data in real time, and combine it with the set of construction characteristic information, project plan and current project progress to calculate the phased predicted resource demand using resource demand assessment methods, and generate a construction resource demand report.

[0044] The schedule planning module is used to combine construction resource demand reports with real-time site conditions and resource availability, and to automatically adjust resource allocation schemes using intelligent algorithms to formulate a construction schedule plan.

[0045] The beneficial effects of this invention are as follows: By applying a multi-source heterogeneous data fusion algorithm and intelligent assessment and prediction of phased resource demand, efficient integration of construction site data and accurate prediction of future resource needs are achieved. The former ensures the accuracy and reliability of data processing, providing a solid foundation for identifying construction patterns and progress trends; the latter optimizes resource allocation through modern information technology and mathematical models, avoiding resource waste or shortages, thus jointly improving the efficiency of engineering construction progress monitoring and management and the success rate of projects. Attached Figure Description

[0046] 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.

[0047] Figure 1 This is a flowchart of an IoT-based engineering construction progress monitoring and management method.

[0048] Figure 2 This is a schematic diagram of an IoT-based engineering construction progress monitoring and management system.

[0049] Figure 3 The flowchart for obtaining the set of construction feature information.

[0050] Figure 4 A flowchart for calculating the phased forecast of resource demand. Detailed Implementation

[0051] 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.

[0052] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used 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 different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0054] Reference Figures 1-4 This is one embodiment of the present invention, which provides an Internet of Things-based method for monitoring and managing the progress of engineering construction, including the following steps:

[0055] S1. Acquire construction site data and transmit it to the central data processing center via wireless local area network for preliminary processing.

[0056] S1.1 Construction site data includes the construction environment, the status of construction equipment, and the location of construction personnel.

[0057] S1.2 Transmit the construction site data to the central data processing center for timestamp standardization, field standardization, missing data processing, and abnormal data detection and filtering to obtain the preliminary processed construction site data.

[0058] It should be noted that the construction site data is transmitted to the central data processing center, where the time fields of the data from each construction site are uniformly parsed and calibrated. Time information from different formats and time zones is converted into standardized UTC time and time series alignment is completed. Subsequently, the field names, types, and units are standardized according to the preset data standard template to ensure consistency in data structure and meaning. On this basis, missing data is filled in using methods such as linear interpolation, moving average, or previous value imputation according to type. Finally, abnormal data is identified and processed using a combination of statistical tests and business rules. Minor anomalies are smoothed and corrected, while severe anomalies are removed, resulting in the preliminary processed construction site data.

[0059] S2. The preliminary processed construction site data is integrated using a multi-source heterogeneous data fusion algorithm.

[0060] S2.1 Perform format parsing and structure recognition on the format characteristics, field structure and encoding methods of data sources from different construction sites, extract field names, data types and hierarchical relationship information, and combine natural language processing methods to identify semantic associations and structural differences between fields.

[0061] It should be noted that the central data processing center reads different types of construction site data from sensor logs, equipment messages, manually entered forms, and monitoring system outputs. It identifies the file format, data encapsulation method, and encoding type of each type of construction site data, including CSV, JSON, XML, TXT formats, and database table structures. Through structural analysis algorithms, it extracts field names, field data types (numerical, text, Boolean, time, etc.), and field hierarchy information from each type of construction site data, constructing a structural mapping relationship for the construction site data. Based on this, it uses natural language processing methods to perform word segmentation, part-of-speech tagging, and semantic matching on field names and field descriptions, analyzing the semantic information contained in the field names. Through semantic similarity calculation, it identifies semantically identical or similar field names and meanings from different construction site data sources, obtaining semantic associations and structural differences between fields.

[0062] S2.2. Perform semantic parsing and formatting parsing on unstructured and semi-structured construction site data, and transform them into standard fields that can participate in fusion. Combine the semantic relationships and structural differences between fields to generate a dynamic field transformation relationship mapping table.

[0063] It should be noted that, firstly, natural language processing methods are applied to preprocess the construction site data, such as word segmentation and annotation, to extract construction elements (such as construction methods, process flow, material usage, equipment status, personnel configuration, and environmental conditions), and semantic roles are identified; then, based on the correspondence between the extracted construction elements and existing standard fields, and combined with the semantic associations and structural differences of the construction site data, conversion rules are designed; then, based on these rules, the construction site data is mapped to unified standard fields, generating a dynamic field conversion relationship mapping table;

[0064] It should also be noted that the transformation rules include specifying how to extract key information from the text (such as matching specific patterns through regular expressions and locating important entities using named entity recognition technology), how to process and format the extracted construction site data to meet predetermined standard field requirements (such as unified date format and unit conversion), and how to map the logical relationships between fields based on the semantic associations between construction site data.

[0065] S2.3 Based on the dynamic field transformation relationship mapping table, data extraction, data transformation and data loading are performed through ETL tools to convert the data into a unified data format.

[0066] It should be noted that ETL tools are used to extract construction site data from different sources, identify and collect construction elements, and perform transformation operations on these construction elements according to predefined transformation rules, including format adjustment, value mapping and anomaly handling, to ensure that all construction site data conforms to a unified standard.

[0067] S2.4 Calculate the conditional probability weights between each data source for construction site data in a unified data format, and determine the reliability and fusion ratio based on the conditional probability weights. Perform weighted integration to generate a construction data set.

[0068] It should be noted that a Bayesian probabilistic inference mechanism is introduced into the construction site data based on a unified data format. The performance of historical data sources and expert experience are used as prior evidence. The conditional probability weights of each data source are derived through the relationship between the prior and the characteristics of the on-site data to reflect the credibility of the data source. Then, the fusion ratio is allocated according to the conditional probability weights, and the same fields from different data sources are fused according to the weight ratio. This makes the fused data more reflective of the actual construction status as a whole, and finally forms a set of construction data obtained by weighted fusion.

[0069] S2.5 Perform logical checks and cross-data source verification on the construction data set to obtain integrated construction data.

[0070] It should be noted that, firstly, a set of logical rules and cross-data source verification standards are defined. Based on these logical rules and verification standards, the logical consistency and data accuracy within the construction dataset and between different construction site data sources are checked. Next, logical checks are performed to identify construction site data items that violate the predefined logical rules. At the same time, cross-construction site data source comparison verification is performed to discover and resolve data conflicts or mismatches. Then, the detected inconsistent data is corrected or deleted, and the adjustment process is recorded for auditing purposes. Finally, after confirming that the data in all construction datasets meet the consistency requirements, the data in the integrated construction datasets are combined to form the final integrated construction data.

[0071] It should also be noted that logical rules refer to a series of predefined conditions or standards based on business needs and actual conditions, used to ensure that data items within a construction dataset conform to the expected logical relationships. For example, in construction site data, logical rules may include checking whether timestamps are reasonable (e.g., no future dates), whether equipment status values ​​are within their possible range, and the matching of construction activities with resource usage, to ensure that the data items in the construction dataset support each other and do not have logical contradictions.

[0072] Cross-data source validation criteria refer to specific guidelines used to compare and verify the consistency and accuracy of data items from different data sources in a construction dataset. These criteria aim to identify and resolve conflicts or discrepancies between different data sources in a construction dataset, such as comparing the consistency of location information from sensors and manually recorded data, or verifying whether the time and resource usage of the same construction activity in different reports are consistent.

[0073] S3. Conduct in-depth mining of construction integration data to identify construction modes and construction progress trends, and obtain a set of construction characteristic information.

[0074] S3.1 Based on the integrated construction data, construct a construction progress time series and perform statistical analysis to obtain the construction progress trend.

[0075] It should be noted that key indicators reflecting construction progress are extracted from the integrated construction data, including the percentage of task completion, the amount of work completed, the resource consumption rate, and the planned deviation. These key indicators are then arranged in chronological order to form a continuous construction progress time series. Subsequently, the construction progress time series is smoothed and trend identified. The triple exponential smoothing method is used to smooth short-term fluctuations in the series to highlight long-term change characteristics. Based on the smoothing results, the upward, downward, or stable trends of construction progress are identified through time series statistical analysis, and the trend change rate, fluctuation amplitude, and periodic characteristic parameters are extracted to finally obtain a construction progress trend that reflects the dynamic changes in construction progress.

[0076] S3.2. Perform in-depth analysis of the construction integration data, use the K-means algorithm to group the construction integration data with similar behavioral patterns, identify different types of construction activities, and summarize them into different construction modes.

[0077] It should be noted that the following steps are taken: A feature set for behavioral characterization is extracted from the integrated construction data. The integrated construction data is then aligned by recording time and combined into a feature vector. The feature vectors of the integrated construction data are standardized to convert feature values ​​of different dimensions into comparable scales, and similarity between samples is established based on Euclidean distance. Next, in the K-means algorithm, multiple initial centroids are randomly generated for the integrated construction data. Each piece of integrated construction data is assigned to a corresponding centroid according to the minimum distance principle, completing one clustering assignment operation. After the clustering assignment operation is completed, the centroid position is updated with the clustering assignment result. The clustering assignment operation and centroid update operation are then repeated until two consecutive clustering assignment results remain unchanged or the change in centroid position is below a threshold, at which point the iteration stops. After the clustering iteration is completed, the clustering results are labeled with meaning based on the mean, variance, and frequently occurring construction elements of each cluster's feature vector. Through field meaning comparison, keyword matching, and consistency checks with project plan task names, each cluster is mapped to a construction activity type. Based on the common characteristics of construction activity types in terms of time distribution, resource usage, and schedule impact, multiple construction activity types are summarized into different construction modes.

[0078] S3.3. The Granger causality test method is used to analyze the causal relationship between the construction mode and the construction progress trend.

[0079] It should be noted that time series samples are constructed based on the set of construction modes and construction progress trend data. The stationarity of the two time series is tested, and non-stationary characteristics are eliminated through differencing or smoothing. Then, after determining the number of lag periods, a Granger causality test equation is established, with the construction mode time series as the independent variable and the construction progress trend time series as the dependent variable for prediction testing. Next, the difference in explanatory accuracy between the prediction equations that include construction mode variables and those that do not is compared, and a significance test is used to determine whether changes in construction modes have a predictive effect on construction progress trends. Finally, based on the test results, the pairing relationships between construction modes and construction progress trends with significant causal relationships are determined, forming a set of causal relationships between construction modes and construction progress trends.

[0080] S3.4. The construction mode, construction progress trend and causal relationship are organized into a visualization format through three-dimensional visualization rendering to form a set of construction feature information.

[0081] It should be noted that, firstly, the analyzed and verified data on construction modes, construction progress trends, and their causal relationships are integrated; then, a suitable 3D visualization tool or platform is selected, and a visualization scheme is designed to intuitively display these complex relationships, such as using a time axis as the third dimension to dynamically present the changes of different construction modes over time and their impact on construction progress; then, 3D graphs are drawn according to the set parameters and indicators, allowing users to interactively explore the correlations and trends between various variables; finally, the final 3D visualization report is generated and optimized to form an easily understandable set of construction feature information.

[0082] S4. Track construction resource status data in real time, and combine it with construction characteristic information set, project plan and current project progress to calculate the phased predicted resource demand using resource demand assessment methods.

[0083] S4.1 Record the identity information and location of construction resources through RFID tags, provide accurate coordinates of construction resources using GPS sensors, and monitor the usage status of construction resources through a sensor network.

[0084] It should be noted that, firstly, each construction resource is equipped with an RFID tag to store its unique identification information; then, RFID readers installed at the construction site automatically capture the information from the RFID tags to achieve real-time tracking of the resource's identity and approximate location; simultaneously, GPS sensors are used to provide precise geographic coordinates for mobile construction resources to ensure their positioning accuracy; and an integrated sensor network continuously monitors the usage status of construction resources (such as operating temperature, running time, etc.), and the collected data is transmitted to the central management system via wireless communication technology for processing and analysis, ultimately achieving real-time monitoring of the status, location, and usage of construction resources.

[0085] S4.2 Transmit the identity information and location of the construction resources, the precise coordinates of the construction resources, and the usage status of the construction resources to the central data processing center to generate construction resource status data.

[0086] It should be noted that, firstly, it is necessary to ensure that all information collected from RFID tags, GPS sensors and other monitoring devices can be effectively integrated and transmitted encrypted to the central data processing center via wireless networks (such as Wi-Fi, 4G / 5G or dedicated wireless LAN). After arriving at the center, this raw data will be decoded and preliminarily processed, including format conversion, timestamp synchronization and missing value filling, to generate standardized construction resource status data.

[0087] S4.3. Based on the project contract, technical design documents, and construction organization design, use the task breakdown structure to create Gantt charts and network diagrams in Microsoft Project to obtain the project plan.

[0088] It should be noted that the project contract, technical design documents, and construction organization design should be analyzed against clauses and drawing entries. Task names, milestone names, schedule requirements, mandatory constraints, and key deliverables should be extracted by comparing each clause with chapter titles, drawing numbers, and work order lists. A hierarchical numbering system and parent-child relationships from phases to sub-tasks should be established using a task breakdown structure. Subsequently, in Microsoft... In the Project window, set the project start time and work calendar. Enter task names, hierarchical relationships, planned durations, and earliest start times according to the task breakdown structure. Based on the dependencies in the project contract, technical design documents, and construction organization design, define Finish-to-Start, Start-to-Start, or Finish-to-Finish relationships in the "Predecessor Tasks" field, and enter positive or negative floats as needed. Next, based on the resource allocation requirements in the technical design documents and the work group arrangements in the construction organization design, assign resource names and availability to tasks to form basic resource load data. When resource overload occurs, load balancing is achieved through task splitting or relationship adjustment. Then, in the Gantt chart view, verify that the critical path, float, and milestone due dates are consistent with the project contract, and perform timing consistency checks by comparing bar chart positions and milestone markers. Finally, switch to the network diagram view to review whether logical links are closed and free of circular dependencies. Correct any broken links or multiple dependencies found in the "Predecessor Tasks" and "Subsequent Tasks" fields, generating a project plan containing critical path, milestone, and resource allocation information.

[0089] S4.4 Extract construction mode and construction progress trend from the construction feature information set, and combine with the project plan to conduct statistical analysis on the amount of completed tasks and resource consumption to obtain the current project progress status.

[0090] It should be noted that the process involves extracting construction mode data reflecting the construction execution status and construction progress trend data reflecting the changing patterns of construction time from the construction feature information set, and matching them with the task decomposition structure in the project plan to determine the task stage corresponding to each construction mode. Then, based on the planned duration, task start time, and end time recorded in the project plan, the actual task completion time recorded in the construction feature information set is compared to calculate the completion ratio of each task. Next, the actual completion duration, cumulative completed work volume, and resource consumption data of all completed tasks are summarized, and the planned duration and planned resource usage of the corresponding tasks in the project plan are compared to calculate the task completion deviation and resource consumption deviation. Finally, the results of the task completion ratio, progress deviation, and resource usage deviation are combined to determine the current project progress status and output the project progress status information.

[0091] S4.5. Compare the data on tasks and resource inputs at each stage of the construction mode and construction progress trend, and statistically analyze the frequency and intensity of resource use at different construction stages to obtain resource use characteristics.

[0092] It should be noted that, based on the construction phases defined in the construction mode, task execution records for the corresponding time periods are extracted from the construction progress trend, and resource input information for the same time period, including the usage and duration of labor, machinery, equipment, and materials, is extracted from the construction resource status data. Then, a correspondence between tasks and resource input data is established according to the construction phases, and the task list within each construction phase is matched with the resource usage records to form a task-resource correspondence table. Next, the frequency of each type of resource appearing in each construction phase is counted in the task-resource correspondence table as the resource usage frequency, and the ratio of the total resource input to the duration of the construction phase is calculated as the resource consumption intensity. Finally, the resource usage frequency and resource consumption intensity results of all construction phases are summarized to form a resource usage characteristic data set.

[0093] S4.6 Input the resource usage characteristics, construction resource status data and current project progress status into the time series prediction model, calculate the consumption rate of various construction resources in the future time window, and obtain the staged resource forecast demand.

[0094] It should be noted that the specific expression for calculating the phased forecast of resource demand is as follows:

[0095] ;

[0096] in, It is the first Forecasted resource demand at each stage It is the first The weighting coefficient of each construction mode. It is the first The activity level of each construction mode It is a construction resource state function. It is the first The remaining amount of construction resources. It is the first The usage status of construction resources It is a function that affects the construction progress. This is the current task completion rate. It is the first Construction progress trend It is a causal relationship correction function. It is the first The construction mode and the first The strength of the causal relationship between the trends in construction progress It is an index variable for the construction mode. This represents the total number of construction modes. It is an index of construction tasks. This represents the total number of construction tasks. It is an index variable for construction resources. It is an index variable for the construction progress trend. It is the first Baseline demand for construction resources (unit: resource quantity). It is the first in the project plan The construction task is for the first The dimensionless ratio obtained after standardizing the demand for construction resources of this type. It is a stable term, with an example value of 0.05.

[0097] It should also be noted that, It is the construction resource state function, defined as:

[0098] ;

[0099] in, It is an adjustment coefficient that balances the impact of resource surplus and usage status on the resource state function;

[0100] It is the construction progress influence function, defined as:

[0101] ;

[0102] in, It is the sensitivity coefficient of the function that controls the deviation between the construction progress trend and the current task completion rate on the progress.

[0103] It is a causal relationship correction function, defined as:

[0104] ;

[0105] in, It is the critical value for filtering out weak causal relationships between construction modes and construction progress trends.

[0106] It should be noted that, This refers to the critical value used to judge the strength of the causal relationship between the construction mode and the construction progress trend. When the strength of the causal relationship is lower than this critical value, the causal relationship is considered weak and is filtered out.

[0107] S5. Generate a construction resource demand report.

[0108] S5.1 Based on the phased forecast of resource demand, the resource demand urgency index is obtained by calculating the ratio.

[0109] It should be noted that the proportional calculation method is used to compare the actual demand for each resource with the projected maximum demand or historical average demand in the project plan to obtain the proportional coefficient of resource demand; then, the urgency of demand for each resource is assessed based on these proportional coefficients, where resources with higher proportions are considered to have a higher demand urgency index.

[0110] S5.2. Sort the resource demand urgency index using the bubble sort algorithm, and list the resource names in order according to the sorting results to form a resource allocation priority list.

[0111] It should be noted that, firstly, a list is compiled of all resources and their corresponding urgency indicators; then, the bubble sort algorithm is applied to compare and swap resources in this list pairwise according to their urgency indicators from high to low, and this process is repeated until the entire list is sorted by urgency; finally, the resource names are listed in order based on the sorted results to form a resource allocation priority list.

[0112] S5.3 Analyze historical periodic resource demand forecasts and set demand thresholds. Phased resource forecast demand Compare;

[0113] when This indicates a shortage of construction resources, which is affecting the progress of the project.

[0114] when When the time is right, it means that there are sufficient construction resources and the progress of the project will not be affected.

[0115] It should be noted that, firstly, the demand data for various resources in past projects should be collected and organized; then, statistical techniques (such as mean, standard deviation calculation or time series analysis) should be used to identify the patterns and fluctuations in resource demand, and to determine the demand level and its changing patterns within the normal range; then, based on these analysis results, reasonable demand thresholds should be set. The demand threshold can be the average demand plus a certain number of standard deviations, or it can be defined according to a specific percentile of a particular project.

[0116] S5.4 Integrate the phased resource forecast demand, resource allocation priority list, and demand comparison results using Pandas, and generate a construction resource demand report using the Python programming language.

[0117] It should be noted that, firstly, the Pandas library is used to import the phased resource forecast demand, resource allocation priority list, and demand comparison results into a data frame for data cleaning and integration, ensuring that all data is organized in a uniform format. Next, Python scripts are used to perform necessary calculations and analyses on this data, such as summary statistics and trend analysis, and charts or visualizations are generated based on the analysis results. Then, based on the integrated data and generated charts, a detailed construction resource demand report is created using templated or automated report generation functions.

[0118] S6. Combine the construction resource demand report with real-time site conditions and resource availability, and use intelligent algorithms to automatically adjust the resource allocation plan and formulate a construction schedule.

[0119] S6.1. Real-time monitoring of the construction site is achieved through IoT sensors and drones to obtain real-time site conditions and resource availability.

[0120] It should be noted that, firstly, various types of IoT sensors are installed at key locations on the construction site to monitor information such as environmental parameters, equipment status, material locations, and worker activities; simultaneously, drones are used to conduct aerial photography of the construction site regularly or as needed to acquire high-definition images and video data to assess project progress and site layout; then, the data is transmitted in real time to the central monitoring system via wireless communication technology for data integration and processing, generating real-time reports and visualizations on the site status and resource availability.

[0121] S6.2 Based on the construction resource demand report, set construction resource constraints.

[0122] It should be noted that the constraints on construction resources include total resource limits, fulfillment of task requirements, and non-negativity constraints.

[0123] S6.3. Based on real-time site conditions and resource availability, and in conjunction with construction resource constraints, the resource allocation scheme in the project plan is dynamically adjusted using the particle swarm optimization algorithm.

[0124] It should be noted that, firstly, the latest construction site data is collected and monitored through IoT sensors and drones to assess the actual availability and demand of current resources. Next, this real-time information, along with preset resource limits, task requirement fulfillment, and non-negativity constraints, is input into the particle swarm optimization algorithm. Then, the particle swarm optimization algorithm is used to simulate and explore different resource allocation schemes to find the optimal solution that maximizes project progress or resource utilization efficiency while satisfying all constraints. During this process, the resource allocation strategy in the original project plan is dynamically adjusted based on the output of the particle swarm optimization algorithm.

[0125] S6.4. Using Microsoft Project in conjunction with custom algorithm scripts, the dynamically adjusted resource allocation scheme is transformed into a specific engineering construction schedule.

[0126] It should be noted that, firstly, the key parameters (such as task start time, duration, and required resources) in the dynamically adjusted resource allocation scheme are extracted; next, a project plan is created or updated in Microsoft Project, these optimized resource allocation data are entered, and the dependencies and scheduling logic between tasks are set using Project's built-in functions; then, a custom algorithm script is written to automate the handling of complex resource balancing and scheduling problems, ensuring that all adjustments meet the actual needs and constraints of the project; finally, the script is run to synchronously update the plan view in Microsoft Project, generating a detailed project construction schedule.

[0127] This embodiment also provides an Internet of Things-based engineering construction progress monitoring and management system, including: a data acquisition module, used to acquire construction site data and transmit it to the central data processing center via a wireless local area network for preliminary processing;

[0128] The data fusion and analysis module is used to integrate the pre-processed construction site data through multi-source heterogeneous data fusion algorithms, perform in-depth mining of the integrated construction data, identify construction modes and construction progress trends, and obtain a set of construction feature information.

[0129] The resource tracking and assessment module is used to track construction resource status data in real time, and combine it with the set of construction characteristic information, project plan and current project progress to calculate the phased predicted resource demand using resource demand assessment methods, and generate a construction resource demand report.

[0130] The schedule planning module is used to combine construction resource demand reports with real-time site conditions and resource availability, and to automatically adjust resource allocation schemes using intelligent algorithms to formulate a construction schedule plan.

[0131] In summary, this invention achieves efficient integration of construction site data and accurate prediction of future resource needs by applying multi-source heterogeneous data fusion algorithms and intelligent assessment and prediction of phased resource forecasting requirements. The former ensures the accuracy and reliability of data processing, providing a solid foundation for identifying construction patterns and progress trends; the latter optimizes resource allocation through modern information technology and mathematical models, avoiding resource waste or shortages, thus jointly improving the efficiency of engineering construction progress monitoring and management and the success rate of projects.

[0132] 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 Internet of Things-based engineering construction progress monitoring management method, characterized in that: include, Data from the construction site is acquired and transmitted to the central data processing center via a wireless local area network for preliminary processing. The preliminary processed construction site data is integrated using a multi-source heterogeneous data fusion algorithm. The specific steps are as follows: The format characteristics, field structure and encoding method of data sources from different construction sites are parsed and the structure is identified. Field names, data types and hierarchical relationship information are extracted, and natural language processing methods are combined to identify the semantic associations and structural differences between fields. Semantic parsing and formatting parsing are performed on unstructured and semi-structured construction site data, which are then transformed into standard fields that can be integrated. A dynamic field transformation relationship mapping table is generated by combining the semantic relationships and structural differences between the fields. Based on a dynamic field transformation relationship mapping table, ETL tools are used to extract, transform, and load data into a unified data format. Calculate the conditional probability weights between various data sources for construction site data in a unified data format, and use the conditional probability weights to determine the reliability and fusion ratio, perform weighted integration, and generate a construction data set. Perform logical checks and cross-data source verifications on the construction dataset to obtain integrated construction data; The following steps involve in-depth analysis of integrated construction data to identify construction patterns and progress trends, and to obtain a set of construction characteristic information. Based on integrated construction data, a construction progress time series was constructed and statistical analysis was performed to obtain the construction progress trend. Deep analysis of construction integration data is performed. The K-means algorithm is used to group construction integration data with similar behavioral patterns, identify different types of construction activities, and summarize them into different construction modes. The Granger causality test method was used to analyze the causal relationship between construction mode and construction progress trend. The construction mode, construction progress trend and causal relationship are organized into a visual format through three-dimensional visualization rendering to form a set of construction feature information; Real-time tracking of construction resource status data, combined with construction characteristic information set, project plan and current project progress, and using resource demand assessment methods to calculate the phased predicted resource demand and generate a construction resource demand report; The project involves combining construction resource demand reports with real-time site conditions and resource availability, and using intelligent algorithms to automatically adjust resource allocation plans and develop a construction schedule. The specific steps are as follows. Real-time monitoring of the construction site is achieved through IoT sensors and drones, providing real-time information on site conditions and resource availability. Based on the construction resource demand report, set construction resource constraints; Based on real-time site conditions and resource availability, and in conjunction with construction resource constraints, the resource allocation scheme in the project plan is dynamically adjusted using the particle swarm optimization algorithm. By using Microsoft Project in conjunction with custom algorithm scripts, dynamically adjusted resource allocation schemes can be transformed into specific engineering construction schedules. 2.The Internet of Things based engineering construction progress monitoring management method according to claim 1, characterized in that: The construction site data includes the construction environment, the status of construction equipment, and the location of construction personnel. 3.The Internet of Things based engineering construction progress monitoring management method according to claim 1, characterized in that: The construction site data is transmitted to the central data processing center for timestamp standardization, field standardization, missing data processing, and abnormal data detection and filtering to obtain the preliminary processed construction site data. 4.The Internet of Things based engineering construction progress monitoring management method according to claim 1, characterized in that: The specific steps for real-time tracking of construction resource status data are as follows: The identification information and location of construction resources are recorded by RFID tags, the precise coordinates of construction resources are provided by GPS sensors, and the usage status of construction resources is monitored by sensor networks. The identity information and location of construction resources, their precise coordinates, and their usage status are transmitted to the central data processing center to generate construction resource status data. 5.The Internet of Things based engineering construction progress monitoring management method according to claim 1, characterized in that: The method of combining construction characteristic information, project plan, and current project progress to calculate the phased predicted resource demand is as follows: Based on the project contract, technical design documents, and construction organization design, a Gantt chart and network diagram are created in Microsoft Project using the task breakdown structure to obtain the project plan; The construction mode and construction progress trend are extracted from the set of construction feature information, and statistical analysis of the completed tasks and resource consumption is carried out in conjunction with the project plan to obtain the current project progress status. By comparing the data on tasks and resource inputs at each stage of the construction mode and construction progress trend, the frequency and intensity of resource use at different construction stages are statistically analyzed to obtain resource use characteristics. By inputting resource usage characteristics, construction resource status data, and current project progress status into a time series forecasting model, the consumption rate of various construction resources within future time windows is calculated to obtain the phased predicted resource demand.

6. The method for monitoring and managing construction progress based on the Internet of Things as described in claim 1, characterized in that: The specific steps for generating the construction resource demand report are as follows: Based on the phased forecast of resource demand, a resource demand urgency index is obtained by calculating the ratio. The resource demand urgency index is then sorted using the bubble sort algorithm, and the resource names are listed in order according to the sorting results to form a resource allocation priority list. Analyze the historical periodic resource demand forecasts and compare the set demand thresholds with the periodic resource demand forecasts. The phased resource forecast demand, resource allocation priority list, and demand comparison results are integrated using Pandas, and a construction resource demand report is generated using the Python programming language.

7. An Internet of Things (IoT)-based engineering construction progress monitoring and management system, based on the IoT-based engineering construction progress monitoring and management method according to any one of claims 1 to 6, characterized in that: include, The data acquisition module is used to acquire construction site data and transmit it to the central data processing center via a wireless local area network for preliminary processing. The data fusion and analysis module is used to integrate the pre-processed construction site data through multi-source heterogeneous data fusion algorithms, perform in-depth mining of the integrated construction data, identify construction modes and construction progress trends, and obtain a set of construction feature information. The resource tracking and assessment module is used to track construction resource status data in real time, and combine it with the set of construction characteristic information, project plan and current project progress to calculate the phased predicted resource demand using resource demand assessment methods, and generate a construction resource demand report. The schedule planning module is used to combine construction resource demand reports with real-time site conditions and resource availability, and to automatically adjust resource allocation schemes using intelligent algorithms to formulate a construction schedule plan.

Images