A construction progress control method in engineering supervision

Abstract

The present invention discloses a construction progress control method for engineering supervision, comprising: calculating the current on-time completion rate and process handover delay time of each subcontractor based on a real-time progress data set and a pre-established engineering project network diagram, identifying progress fluctuation patterns in different engineering stages through a time series analysis method, and establishing a correlation model between subcontractors and engineering stages; dynamically adjusting the construction plans and resource allocation plans of each subcontractor based on priority scores, with minimizing overall construction delays and resource idleness as the objective function, using an optimization algorithm to generate an optimized project schedule, including specific work arrangements and resource allocation suggestions for each subcontractor; and analyzing successful coordination strategies in historical projects, and recommending coordination measures and generating a communication matrix for project managers based on the characteristics and progress status of the current project, wherein the coordination measures include resource allocation suggestions, process optimization plans, and communication strategy templates.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a construction progress control method in engineering supervision. Background Art

[0002] In large, complex engineering projects, the simultaneous construction of multiple subcontractors presents a key technical contradiction: significant variations in on-time completion rates and process handover delays. This variability is not only related to the subcontractor's own factors but also influenced by the overall stage of the project's progress. Specifically, subcontractors in the early stages of the project often face greater uncertainty, resulting in lower on-time completion rates and longer process handover delays. Subcontractors in the later stages, however, have substantially completed their previous work and therefore have relatively higher on-time completion rates and shorter process handover delays. However, this discrepancy can lead to an imbalance in the overall project progress, causing process backlogs or idle resources on certain critical paths, which in turn impacts the construction pace of subsequent subcontractors. Further complicating matters, process connections between different specialized subcontractors are technically dependent, and a delay by one subcontractor can have ripple effects on multiple related subcontractors. This multi-layered and multi-dimensional interaction makes traditional project schedule management methods ineffective. There is an urgent need for an intelligent management system that can dynamically balance the construction progress of each subcontractor, optimize resource allocation, and coordinate process connections. Furthermore, this complex project environment presents significant communication challenges. Information exchange between subcontractors, between subcontractors and the general contractor, and between subcontractors and the client is often delayed, distorted, or incomplete. These communication barriers not only exacerbate schedule discrepancies and resource allocation conflicts, but can also lead to misguided decisions and unnecessary conflicts. Traditional unified communication methods struggle to adapt to the needs and characteristics of different subcontractors at different project stages. Therefore, establishing a customized communication strategy that can dynamically adjust to the characteristics of each party and the project stage is key to addressing this complex issue. Summary of the Invention

[0003] The purpose of the present invention is to solve the problems in the prior art and to propose a construction progress control method in engineering supervision.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] A construction progress control method in engineering supervision comprises the following steps:

[0006] S1, uses a data acquisition system to obtain real-time progress data from each subcontractor's construction site, transmits it to the central data processing platform, cleans, de-duplicates, and formats the collected raw data to obtain a structured real-time progress data set;

[0007] S2, based on the real-time progress data set and the pre-established project network diagram, calculates each subcontractor's current on-time completion rate and process handover delay time. It uses time series analysis to identify progress fluctuation patterns in different project phases and establishes a correlation model between subcontractors and project phases.

[0008] S3, based on project construction information, analyzes the technical dependencies between processes, constructs a process dependency network diagram, identifies bottleneck processes and potential risk points on the critical path, calculates the impact of each process on subsequent construction, generates a process impact factor matrix, and predicts the on-time completion rate and process handover delay of each subcontractor in the future based on current project characteristics and real-time progress data sets, resulting in a multi-dimensional progress forecast.

[0009] S4, based on the correlation model between subcontractor performance and project phases, evaluate the performance expectations of each subcontractor at different stages. Combined with the process impact factor matrix, analyze the impact of each process on the overall progress. Based on the multi-dimensional progress forecast results, identify any progress deviations and risk points, establish a comprehensive scoring model, and derive priority scores for each subcontractor and process.

[0010] S5, based on the priority scores and with minimizing overall construction delays and resource idleness as the objective function, uses an optimization algorithm to dynamically adjust the construction plans and resource allocation plans of each subcontractor, generating an optimized project schedule that includes work arrangements for each subcontractor and resource allocation recommendations;

[0011] S6: Analyze successful coordination strategies from past projects and, based on the characteristics and progress of the current project, recommend coordination measures and generate a communication matrix for project managers. The coordination measures include resource allocation suggestions, process optimization plans, and communication strategy templates.

[0012] S7, based on the optimized schedule plan and coordination strategy, automatically generates task decomposition and progress control indicators for each subcontractor, distributes the task decomposition, progress control indicators and communication matrix in real time through the project management information system, and continuously monitors the execution status. When the execution status exceeds the set deviation threshold, an early warning is issued through the preset reporting mechanism and problem escalation process.

[0013] Compared with the prior art, the present invention has the following advantages:

[0014] This invention discloses a construction progress control method for project supervision. This method addresses issues such as untimely progress data collection, low progress forecast accuracy, irrational resource allocation, and lack of targeted coordination strategies, which are common in traditional project supervision. Through a real-time data acquisition system and a central data processing platform, the method enables efficient collection and standardized processing of real-time progress data from construction sites, providing a reliable data foundation for subsequent analysis. Time series analysis and correlation models are used to accurately identify progress fluctuation patterns and predict future progress, effectively improving the accuracy of progress forecasts. Combining a process dependency network and an influencing factor matrix, the method comprehensively assesses the impact of each process on the overall progress, enabling more accurate risk identification and priority assessment. An optimization algorithm dynamically adjusts construction plans and resource allocation, significantly improving resource utilization efficiency. Furthermore, based on historical project experience and current project characteristics, a customized coordination strategy and communication matrix are generated, significantly enhancing the targetedness and effectiveness of project management. Finally, through automated task decomposition, indicator issuance, and execution monitoring mechanisms, comprehensive and refined progress control is achieved, effectively reducing the risk of construction delays and improving the overall management level of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of a construction progress control method in engineering supervision proposed by the present invention;

[0016] Figure 2 This is a schematic diagram of a construction progress control method in engineering supervision proposed by the present invention;

[0017] Figure 3 This is another schematic diagram of the construction progress control method in engineering supervision proposed by the present invention. Implementation Method

[0018] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] In the description of the present invention, it should be understood that the terms "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside", "outside", etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0020] like Figure 1-3 The present embodiment provides a construction progress control method in engineering supervision, which may specifically include:

[0021] In step S1, a data acquisition system is used to obtain real-time progress data from each subcontractor's construction site, including process completion status, resource usage status, and personnel distribution information, and transmit it to the central data processing platform. The collected raw data is cleaned, deduplicated, and formatted to obtain a structured real-time progress data set.

[0022] Real-time progress data with the subcontractor's unique identification number is obtained, including process completion status, resource utilization, and personnel distribution information. The real-time progress data is uploaded by the subcontractor's construction site through mobile applications and spreadsheets. The raw data is sent to the central data processing platform using an encrypted transmission protocol based on the real-time progress data. After receiving the raw data, the central data processing platform performs preliminary screening and classification. The data after preliminary sorting is subjected to a data cleaning process, including: using regular expressions to verify the data format, eliminating outliers and invalid data, and using hash tables to detect duplicate data and eliminate duplicate records. The cleaned data is standardized and formatted according to a preset data format template to obtain a structured real-time progress data set.

[0023] Specifically, when collecting real-time progress data from construction sites, subcontractors use a dedicated mobile application to report daily workloads, such as 10 cubic meters of concrete poured or 500 kilograms of rebar tied. Furthermore, a spreadsheet upload function supports batch import of resource usage data, such as equipment usage hours and material consumption. Personnel distribution information is automatically collected using tracking devices worn by workers, with accuracy within a 5-meter range. The collected data is encrypted using the AES-256 encryption algorithm and transmitted to the central data processing platform via HTTPS. During data cleansing, the regular expression ^[0-9]+(.[0-9]{1,2})?$ is used to validate numeric formats and remove illegal characters and data outside the acceptable range. Duplicate data detection uses the MD5 hash algorithm, concatenating the key fields of each record to generate a hash value. Duplicate records can be quickly identified by comparing the hash values. Standardization processing converts data in different units to a uniform format, such as converting hours to minutes.

[0024] In step S2, based on the real-time progress data set and the pre-established project network diagram, the current on-time completion rate and process handover delay time of each subcontractor are calculated. The progress fluctuation pattern of different project stages is identified through time series analysis method, and a correlation model between subcontractors and project stages is established.

[0025] The process completion time of each subcontractor was obtained from the real-time progress dataset. Each subcontractor's current on-time completion rate was calculated based on the process completion time and the planned completion time specified in the pre-established project network diagram. If the process completion time was later than the planned completion time, the process handover delay was recorded. A moving average method was used to conduct time series analysis on the on-time completion rate and process handover delay, with a seven-day time window. Based on the time series analysis results, the progress fluctuation patterns of different project phases were classified, including trends in on-time completion rate as increasing, decreasing, and stable. Based on the subcontractor's on-time completion rate, process handover delay, and project phase progress fluctuation pattern classification, a decision tree algorithm was used to construct an association model between subcontractors and project phases. The decision tree algorithm includes feature selection, tree building, and pruning. Information gain was used as the feature selection criterion, the ID3 algorithm was used for tree building, and the pessimistic pruning method was used for pruning. The accuracy of the association model was evaluated using cross-validation, selecting a portion of the total data set as the training set and the remaining data set as the test set. Calculate the prediction accuracy of the association model on the test set to facilitate the adjustment of the association model.

[0026] Specifically, if the actual completion time is later than the planned completion time, the process handover delay time is recorded. The specific calculation method is the difference between the actual completion time of the current process and the planned start time of the next process. For the calculated on-time completion rate and process handover delay time data, the moving average method is used to perform time series analysis. The time window is set to 7 days, and the average on-time completion rate and average process handover delay time of each subcontractor in different time periods are calculated. The decision tree construction process includes feature selection, tree generation and pruning. Information gain is selected as the feature selection criterion. The ID3 algorithm is used to generate the decision tree, and the pessimistic pruning method is used to optimize the tree. The accuracy of the association model is evaluated by cross-validation. 80% of the data is selected as the training set and 20% as the test set. The prediction accuracy of the model on the test set is calculated.

[0027] Furthermore, in actual application, the real-time progress dataset extracted the completion date of Subcontractor A's concrete pouring process as March 15, 2024, while the planned completion date specified in the project network diagram was March 10, 2024. The calculated on-time completion rate was 83.33%. Calculation of process handover delays showed that the actual completion time of the current process was five days later than the scheduled start time of the next rebar tying process. Applying a moving average to the data over the past seven days yielded an average on-time completion rate of 85.71% for Subcontractor A, with an average process handover delay of 3.5 days. Analysis of progress fluctuation patterns showed that Subcontractor A's on-time completion rate was on an upward trend, gradually increasing from 80% to 90%.

[0028] In step S3, based on the engineering construction information, the technical dependency relationship between processes is analyzed, a process dependency network diagram is constructed, bottleneck processes and potential risk points on the critical path are identified, the impact of each process on subsequent construction is calculated, and a process impact factor matrix is ​​generated. Based on the current project characteristics and real-time progress data set, the on-time completion rate and process handover delay time of each subcontractor in the future are predicted to obtain multi-dimensional progress prediction results.

[0029] Based on engineering construction information, the technical dependencies between processes are obtained. A graph theory algorithm is used to construct a process dependency network diagram, resulting in an adjacency matrix for the process dependency network diagram. The connection relationships between processes are represented by the adjacency matrix. The critical path method is used to identify the critical path, calculate the earliest and latest start times for each process, and determine that processes with zero time margin are bottleneck processes. A comprehensive assessment of the time margin and resource requirements of the processes is conducted to identify potential risk points and set risk thresholds. If the assessment result of a process exceeds the preset risk threshold, the process is marked as a high-risk process. The process dependency network diagram is topologically sorted to determine the execution order of the processes. The degree of impact of each process on subsequent construction is calculated. A direct scoring method is used to construct an impact factor matrix, which is scored based on the process duration, resource consumption, and technical complexity. The final impact factor is obtained through normalization. The on-time completion rate and process handover delays of each subcontractor were obtained from the real-time progress dataset. Combined with the current project characteristics, exponential smoothing was used to predict the on-time completion rate and process handover delays for the future. A smoothing coefficient of α was selected as 0.3, and the prediction formula Ft+1=αXt+(1-α)Ft was used to calculate future values. The process influencing factor matrix was combined with the predicted on-time completion rate and process handover delays to construct a multidimensional progress prediction model. Monte Carlo simulation was used to generate multiple possible progress scenarios. Duration and resource consumption were selected as random variables, and their probability distributions were determined. The number of simulations was set to 1000. The total project duration and critical path changes under each scenario were calculated, resulting in a multidimensional progress prediction. The statistical output included the average duration, the shortest duration, the longest duration, and the duration distribution probability.

[0030] Specifically, in practical application, 20 key processes were extracted from construction data, and a 20x20 adjacency matrix was constructed to represent the dependencies between these processes. Using the critical path method, the critical path was calculated to consist of eight processes with a total construction duration of 120 days. Three bottleneck processes with zero time margin were identified: concrete pouring, steel structure installation, and exterior wall decoration. By evaluating process time margins and resource requirements, a risk threshold of 0.8 was set, and two high-risk processes were identified: scaffolding erection and curtain wall installation. A direct scoring method was used to construct an impact factor matrix, scoring the 20 processes on a scale of 1 to 10. After normalization, the concrete pouring process had the highest impact factor, at 0.15. Data from the last 30 days was extracted from the real-time progress dataset, and forecasting was performed using the exponential smoothing method, with a smoothing coefficient α set to 0.3. The forecast results indicate that the on-time completion rate for main subcontractor A is expected to be 92%, and the process handover delay is expected to be 1.5 days. In the multi-dimensional schedule forecasting model, the project duration was set to a triangular distribution, with a maximum value of 120 days, a minimum of 110 days, and a maximum of 135 days. Resource consumption was set to a normal distribution, with a mean of the planned value and a standard deviation of 10% of the planned value. 1,000 Monte Carlo simulations revealed an average duration of 122 days, a minimum of 113 days, and a maximum of 133 days. Probabilistic analysis of the duration distribution indicated an 80% probability that the project would be completed within 118-126 days.

[0031] In step S4, based on the correlation model between subcontractor performance and project stages, the performance expectations of each subcontractor at different stages are evaluated. Combined with the process impact factor matrix, the impact of each process on the overall progress is analyzed. Based on the multi-dimensional progress prediction results, the progress deviations and risk points are identified, and a comprehensive scoring model is established to derive the priority scores of each subcontractor and process.

[0032] Based on the correlation model between subcontractor performance and project phases, we extracted historical performance data for each subcontractor across different project phases. We then used a weighted average method to calculate each subcontractor's expected performance score for future project phases, with weights set at 0.5 for the most recent month's data, 0.3 for the previous two months, and 0.2 for earlier data. This resulted in a subcontractor performance expectation matrix. Using the process impact factor matrix, we normalized the impact factor for each process and mapped it to a score range of 0-100 using a logarithmic function. This resulted in a score for the degree of impact of the process on the overall schedule. We then extracted the difference between the predicted and planned durations from the multi-dimensional schedule forecast results, setting a schedule deviation threshold of 5% of the planned duration. If the difference exceeded the preset schedule deviation threshold, it would be marked as a schedule deviation point. Furthermore, we used a risk matrix method to identify risk points, combining the importance of the process and the probability of delay, to generate a list of schedule deviations and risk points. A comprehensive scoring model was constructed, with the expected subcontractor performance score, process impact score, schedule deviation and risk point assessment results as input variables. The model was trained using a multi-layer perceptron neural network algorithm. The input layer had 10 nodes, the hidden layer had 20 nodes, and the output layer had 1 node. The ReLU function was used as the activation function, the mean square error was used as the loss function, and the Adam optimizer was used as the optimization algorithm. The priority scores of each subcontractor and process were output on a 0-100 scale, with higher scores indicating higher priorities.

[0033] Specifically, in practical application, the correlation model extracts performance data from five major subcontractors across four project phases over the past three months. For example, Subcontractor A's performance score for the foundation construction phase in the most recent month was 85. A weighted average method was used to calculate future performance expectations, resulting in an expected score of 88 for Subcontractor A in the next main structure phase. The influencing factors of 20 key processes were processed. For example, the original impact factor of the concrete pouring process was 0.85, but after logarithmic mapping to a 0-100 scale, it scored 92. The schedule forecast indicated that the project's estimated completion time was eight days behind schedule, exceeding the 5% deviation threshold and thus marked as a schedule deviation point. A 5x5 risk matrix was used to assess process risk, with importance (1-5) on the horizontal axis and delay probability (1-5) on the vertical axis. Processes with scores greater than 20 were marked as high-risk points, and three high-risk processes were identified. The comprehensive scoring model's input layer includes 29 input nodes, including five subcontractor performance expectation scores, 20 process impact scores, one schedule deviation marker, and three risk point markers. After processing by 20 hidden nodes, the final output layer produces 29 priority scores. The model was trained using historical project data, totaling 500 samples, with 80% used as the training set and 20% as the validation set. After 1,000 rounds of iterative training, the model's mean squared error on the validation set dropped below 0.05. The trained model was applied to the current project, resulting in a priority score of 92 for Subcontractor A and 88 for the concrete pouring process. This provides the project management team with a precise basis for resource allocation and risk management.

[0034] In step S5, based on the priority scores and with minimizing overall construction delays and resource idleness as the objective function, an optimization algorithm is used to dynamically adjust the construction plans and resource allocation plans of each subcontractor, and generate an optimized project schedule, including the specific work arrangements and resource allocation suggestions for each subcontractor.

[0035] Based on the priority scores of each subcontractor and process, a multi-objective optimization model was constructed. Minimizing construction delays and resource idleness was set as the objective function, with each subcontractor's construction plan and resource allocation as the decision variable. Priority scores were incorporated into the objective function by assigning weight coefficients, with higher-priority processes being given greater weight. Construction sequence constraints were expressed as the forward-backward dependencies between processes, while resource constraints included daily available manpower, equipment, and material supply. A genetic algorithm was used to solve the multi-objective optimization problem, using real-number encoding. Each chromosome represented a complete construction plan and resource allocation solution. The population size was set to 100, the crossover probability to 0.8, the mutation probability to 0.1, and the number of iterations to 1000. The fitness function was defined as the inverse of the weighted objective function value, with weights determined based on the importance of construction delays and resource idleness. The population was evolved using roulette wheel selection, two-point crossover, and uniform mutation. The optimal solution obtained by the optimization algorithm was decoded, and the real values ​​in the chromosomes were mapped to specific time points and resource quantities, resulting in the construction plan and resource allocation solution for each subcontractor. Generate a project schedule in the form of a Gantt chart, including the start time, end time, required resource type and quantity for each process. Set up a regular weekly re-optimization mechanism and define trigger conditions, such as initiating dynamic adjustments when the actual progress deviation exceeds 5%. Based on the optimized schedule, calculate the workload and resource utilization of each subcontractor, and generate a specific work schedule and resource allocation recommendations. Establish an evaluation and feedback mechanism to collect actual execution data daily, calculate the deviation between the plan and the actual, and trigger a fine-tuning process if the deviation exceeds the preset threshold. The fine-tuning process includes re-executing the optimization process of the multi-objective optimization model to obtain an updated construction plan and resource allocation plan. Set buffer time and backup resources to address uncertain factors such as weather impacts and material supply delays, monitor changes in external factors in real time, and adjust optimization parameters in a timely manner.

[0036] Specifically, in practical application, the optimization model was constructed based on 20 key processes from five major subcontractors. The concrete pouring process, with the highest priority score, was assigned a weight of 0.2, with weights assigned to the remaining processes proportionally based on their priorities. Construction sequence constraints required that foundation construction be completed before the main structure. Resource constraints were set at 200 workers, 10 pieces of large equipment, and 500 cubic meters of concrete available daily. The genetic algorithm's chromosome length was 100, with the first 80 bits representing the start and end times of the 20 processes, and the last 20 bits representing the resource allocation ratio. In the fitness function, delays were weighted 0.6, and idle resources were weighted 0.4. After 1,000 iterations, the optimal solution revealed a total project duration of 180 days, five days shorter than originally planned. Decoding revealed that the concrete pouring process was scheduled to begin on the 30th day and last for seven days, requiring 50 workers and three pump trucks per day. The resulting Gantt chart clearly displays the timeline and resource requirements for each process. A re-optimization was automatically triggered at 2:00 AM every Monday. Simultaneously, the monitoring system detected that the actual progress of foundation construction was 8% slower than planned, immediately initiating a dynamic adjustment process. The optimized work schedule indicated that Subcontractor A's workload for the first week was 1,000 square meters of wall construction, requiring 30 workers and two concrete mixers. The evaluation and feedback mechanism revealed that 920 square meters of wall construction was actually completed in the first week, a deviation of 8%. This triggered a fine-tuning process, adjusting the workload for the following week to 1,050 square meters. Based on the weather forecast, a half-day rain buffer was reserved on the 45th day, and 20% more spare transport vehicles were added on the 60th day, during the peak material supply period, to ensure the robustness of the optimization plan.

[0037] Step S6: Analyze successful coordination strategies in historical projects, and based on the characteristics and progress of the current project, recommend coordination measures to project managers and generate a communication matrix. The coordination measures include resource allocation suggestions, process optimization plans, and communication strategy templates.

[0038] Successful project coordination strategy data is obtained from a historical project database. This coordination strategy data includes resource allocation plans, process optimization records, and communication strategy implementation status. The TF-IDF algorithm is used to extract textual features from the coordination strategy data to obtain a coordination strategy feature vector. Based on this feature vector, a coordination strategy knowledge base is constructed. Based on the current project's characteristics and progress, a feature vector is designed for the current project. This feature vector includes indicators such as project size, complexity, schedule deviation rate, and resource utilization. A comprehensive similarity metric is constructed using cosine similarity and Euclidean distance. The similarity between the current project's feature vector and the feature vectors of historical projects is calculated, and the historical projects with the highest similarity are selected as reference samples. For example, the top 10 projects with the highest similarity are selected as reference samples. A coordination strategy cluster analysis is performed on the reference samples. A hierarchical clustering algorithm is used to categorize coordination strategies into three categories: resource allocation, process optimization, and communication strategies. The frequency of use and success rate of each strategy category are calculated to generate a list of recommended coordination measures. Based on this list of recommended coordination measures, a decision tree algorithm is used to generate a process optimization plan. Decision rules are constructed using process characteristics as input variables and optimization strategies as output variables. These decision rules are used to guide process optimization in the current project. Based on the recommended coordination measures, a project communication matrix was constructed. The rows and columns of the communication matrix represent the project stakeholders, and the cell contents include communication frequency, method, and key information. The analytic hierarchy process was used to determine the communication importance weights for each stakeholder. A judgment matrix was established and the weight vectors were calculated. The weight vectors were then checked for consistency to generate a communication strategy template. The accuracy of the recommended results was verified using cross-validation, with the historical dataset divided into training and test sets to evaluate the effectiveness of the recommended coordination measures.

[0039] Specifically, in practical application, coordination strategy data from 500 successful projects was extracted from a historical database. The text was processed using the TF-IDF algorithm to obtain 10,000 feature words. These strategies were then grouped into 20 themes using a topic model. The current project feature vector contained 10 indicators, such as a project size of 100,000 square meters, a complexity score of 8.5 out of 10, a schedule deviation rate of -5%, and a resource utilization rate of 85%. In the comprehensive similarity calculation, a cosine similarity weight of 0.6 and a Euclidean distance weight of 0.4 were used to select the 10 reference projects with the highest similarity. A hierarchical clustering algorithm was used with a clustering threshold of 0.7, resulting in three strategy categories: resource allocation (40%), process optimization (35%), and communication strategy (25%). A decision tree algorithm using the CART method was used with a tree depth of 4 and a minimum leaf node sample size of 5, generating 15 process optimization rules. The communication matrix involved eight stakeholders. The weight vectors derived from the AHP were [0.25, 0.20, 0.15, 0.12, 0.10, 0.08, 0.06, 0.04], with a consistency ratio (CR) of 0.03 < 0.1, passing the consistency test. Cross-validation, using a 5-fold method, achieved an average accuracy of 85%. Ultimately, three resource allocation recommendations, five process optimization rules, and two communication strategy templates were recommended.

[0040] Step S6 also includes generating a customized communication strategy template for each subcontractor based on the analysis of historical projects and the characteristics of the current project, including recommendations on communication frequency, methods, and content, as well as specific reporting mechanisms and problem escalation processes.

[0041] Subcontractor communication records were extracted from a historical project database and classified using the Naive Bayesian algorithm. Frequency statistics were generated for categories such as progress reports, quality issues, and resource requirements. Based on these frequency statistics and evaluations of communication effectiveness using metrics such as resolution time and satisfaction ratings, a basic communication strategy model was constructed. A content-based recommendation algorithm was used to calculate the similarity between the current project and previous projects, taking into account project size, complexity, and deadline requirements. The historical projects with the highest similarity were selected as reference samples. Based on each subcontractor's characteristics, such as expertise and historical performance, and taking into account project phase and work content, a random forest algorithm was used to generate a customized communication strategy. This strategy included recommended communication frequency, preferred communication methods, and key communication content. The optimal strategy was determined through voting results from multiple decision trees. Based on the generated communication strategy, a reporting mechanism and escalation process were established. Key indicator thresholds were set, and escalation processes were triggered when these thresholds were exceeded. A rules engine, which includes rule definitions, priority settings, and triggering mechanisms, was used to automatically generate corresponding report templates and escalation paths. Integrate the generated communication strategy with project management software to achieve automated reminders and execution, regularly collect feedback data on the effectiveness of strategy execution, and continuously optimize the communication strategy template through machine learning algorithms to improve the applicability and effectiveness of the strategy.

[0042] Specifically, in a practical application, 50,000 subcontractor communication records from 1,000 projects were extracted from a historical database. Using the Naive Bayesian algorithm, these records were categorized into five categories: progress reports (40%), quality issues (25%), resource requirements (20%), safety issues (10%), and other (5%). Communication effectiveness was evaluated based on issue resolution time (weighted 0.6) and satisfaction rating (weighted 0.4), resulting in a comprehensive score. The current project's feature vector contained eight indicators, such as project size of 100,000 square meters, complexity of 8.5 out of 10, and construction duration of 360 days. A content-based recommendation algorithm calculated similarity with historical projects and selected the 10 most similar projects as references. A random forest algorithm used 100 decision trees, each with a maximum depth of 5 and a minimum leaf node sample size of 10, to generate customized communication strategies. For example, for earthwork subcontractors in the foundation construction phase, daily progress reports were recommended, with mobile apps as the preferred communication method. Key communication content included the daily volume completed and the next day's plan. The rules engine has 20 basic rules, such as triggering an escalation process when the daily progress deviation exceeds 10%. After integration with project management software, communication reminders are automatically sent to subcontractors at 8:00 AM each day. Feedback data shows that after one month of implementation, the average problem resolution time has been reduced from 2 days to 1.5 days, and satisfaction scores have increased from 7.5 to 8.2 out of 10. Based on this feedback, a machine learning algorithm automatically fine-tunes the communication strategy every weekend, slightly increasing the frequency of communication for high-frequency issues.

[0043] Step S6 also includes extracting the complexity and risk assessment results of the project based on the characteristics and progress of the current project, and generating a dynamically adjusted communication matrix, including stakeholder analysis, communication responsibilities, and communication methods.

[0044] The project management database extracts current project characteristics and progress data, including project size, duration, and completion percentage. Principal component analysis is used to calculate the project complexity score. Project risk is quantitatively assessed using the Project Review and Evaluation Technique (PERT) to calculate a risk value. Using the complexity score and risk value as input, the Analytical Hierarchy Process (AHP) is used to construct a stakeholder influence matrix and calculate the weight coefficients for each stakeholder. Stakeholders are categorized into high, medium, and low groups based on their weight coefficients. Communication priorities and frequencies are determined for each group. If the weight coefficient exceeds a preset threshold, the stakeholder is assigned to the high priority group; otherwise, it is assigned to the medium or low priority group. Based on the project organizational structure and personnel responsibilities, a responsibility allocation matrix is ​​constructed. An adjacency matrix is ​​used to represent the responsibility network. Node degrees are calculated to identify key communication stakeholders and assign corresponding communication stakeholders to each stakeholder group. Based on the project phase and communication content, a decision tree algorithm is used to generate communication method decision rules. The most appropriate communication method is automatically selected based on the real-time project status, creating a dynamically adjusted communication matrix that maps stakeholders, communication responsibilities, and communication methods. A weekly update trigger is set to trigger matrix adjustments upon key project milestones. Establish a feedback mechanism, collect communication effectiveness data through questionnaires, and use regression analysis to continuously optimize the weight coefficients and decision rules in the communication matrix.

[0045] Specifically, in practical application, 10 key characteristics of the current project were extracted from the project management database, including project size of 100,000 square meters, duration of 360 days, and completion percentage of 35%. Principal component analysis calculated a project complexity score of 8.5 (out of 10). The PERT technique assessed 50 potential risk points and calculated a project risk value of 0.65. Based on these two parameters, the analytic hierarchy process constructed a 10x10 stakeholder influence matrix, identifying five high-priority stakeholders (weights > 0.15), three medium-priority stakeholders (weights 0.05 < ≤ 0.15), and two low-priority stakeholders (weights ≤ 0.05). A responsibility assignment matrix comprised 30 roles, and a 20x20 adjacency matrix was used to represent the responsibility network. Node degrees were calculated to identify three key communication responsibilities. A decision tree algorithm generated 15 communication method decision rules, such as "If the risk value is > 0.6 and the stakeholder priority is high, then use daily video conferencing." The dynamic communication matrix initially contained 50 communication items and was automatically updated every Monday at 2:00 AM. Additional adjustments were triggered at 30%, 60%, and 90% project completion. A feedback mechanism included a monthly online questionnaire to collect communication satisfaction scores (on a scale of 1-10). Regression analysis showed that increasing the frequency of communication with high-priority stakeholders from twice to three times per week resulted in an average increase in satisfaction of 1.2 points. Based on this information, the four weighting coefficients and two decision rules in the communication matrix were automatically adjusted.

[0046] In step S7, based on the optimized schedule plan and coordination strategy, task decomposition and progress control indicators are automatically generated for each subcontractor. The task decomposition, progress control indicators and communication matrix are distributed in real time through the project management information system, and the execution status is continuously monitored. When the execution status exceeds the set deviation threshold, an early warning is issued through the preset reporting mechanism and problem escalation process.

[0047] Based on the optimized schedule and coordination strategy, the work breakdown structure method was used to decompose the subcontractor's work content. Task time parameters, including the earliest start time, latest finish time, and total time difference for each task, were calculated using the critical path method combined with resource balancing and risk assessment. This resulted in a task breakdown tree and progress control indicators. The task breakdown tree, progress control indicators, and communication matrix were integrated into the project management information system database and pushed to the subcontractor's mobile devices via a data interface. RabbitMQ message queue technology was used to ensure reliable and real-time data transmission. IoT sensors and mobile applications were used to capture real-time progress data from subcontractors' construction sites, including process completion status, resource utilization, and personnel distribution. This progress data was cleaned and standardized before being stored in the project management information system. The data cleaning process included outlier detection, missing value handling, and format standardization. Z-score analysis was used for standardization. Multi-level deviation thresholds were set, and a real-time comparison algorithm was used to monitor execution against plan. The algorithm calculated deviation values ​​through data matching and time series analysis. If the deviation exceeded the preset threshold, a report generation process and issue escalation procedures were triggered, and alerts were issued to the relevant responsible personnel through pre-defined notification channels. Receive reports and problem escalation information, intelligently classify and prioritize warning information, use the naive Bayes algorithm to classify warning content, and determine priority based on urgency and impact scope.

[0048] Specifically, in a practical application, a task breakdown was performed on a large construction project, generating a work breakdown tree with 500 task nodes. The critical path method calculated that the project's critical path consisted of 35 tasks, with a total construction duration of 360 days. After resource balancing, 20% of non-critical tasks were adjusted in time, and a risk assessment identified 10 high-risk task nodes. The task breakdown tree and progress indicators were pushed to the mobile devices of 50 subcontractors via a RabbitMQ message queue at a rate of 100 messages per second. 200 IoT sensors were deployed on-site, collecting data every 5 minutes, while a mobile application collected 300 progress reports daily. During data cleaning, 5% of outliers and 3% of missing values ​​were detected. After data normalization, 95% of the data fell within ±3 standard deviations. A real-time comparison algorithm performed a full comparison every hour, with an average processing time of 30 seconds. Three deviation thresholds were set: 5%, 10%, and 20%. A total of 200 alerts were triggered that month, of which 80% were level 1 alerts, 15% were level 2 alerts, and 5% were level 3 alerts. The Naive Bayes algorithm categorizes warnings into three categories: schedule delays, quality issues, and safety hazards, with an accuracy rate of 85%. Prioritization marks 30% of warnings as high priority, requiring immediate attention.

[0049] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solutions and inventive concepts of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A construction progress control method in engineering supervision, characterized in that: The following steps are involved: S1, uses a data acquisition system to obtain real-time progress data from each subcontractor's construction site, transmits it to the central data processing platform, cleans, de-duplicates, and formats the collected raw data to obtain a structured real-time progress data set; S2, based on the real-time progress data set and the pre-established project network diagram, calculates each subcontractor's current on-time completion rate and process handover delay time. It uses time series analysis to identify progress fluctuation patterns in different project phases and establishes a correlation model between subcontractors and project phases. S3, based on construction information, analyzes the technical dependencies between processes, constructs a process dependency network diagram, identifies bottleneck processes and potential risk points on the critical path, calculates the impact of each process on subsequent construction, generates a process impact factor matrix, and combines current project characteristics with real-time progress data sets to predict the on-time completion rate and process handover delay time of each subcontractor in the future, resulting in a multi-dimensional progress forecast. S4: Based on the subcontractor-project phase correlation model, evaluate the performance expectations of each subcontractor at different stages. Combined with the process impact factor matrix, analyze the impact of each process on the overall progress. Combined with multi-dimensional progress forecast results, identify progress deviations and risk points, establish a comprehensive scoring model, and derive priority scores for each subcontractor and process. S5, based on the priority scores, with minimizing overall construction delays and resource idleness as the objective function, uses an optimization algorithm to dynamically adjust the construction plans and resource allocation plans of each subcontractor to generate an optimized project schedule; S6: Analyze successful coordination strategies in historical projects and, based on the characteristics and progress of the current project, recommend coordination measures and generate a communication matrix for project managers. S7, based on the optimized schedule and coordination strategy, automatically generates task decomposition and progress control indicators for each subcontractor. These are then distributed in real time through the project management information system, along with the communication matrix. Execution is continuously monitored, and when the execution exceeds the set deviation threshold, an alert is issued through the pre-set reporting mechanism and escalation process. The S2 includes: Obtain each subcontractor's process completion time from the real-time progress data set, and calculate each subcontractor's current on-time completion rate based on the process completion time and the planned completion time specified in the pre-established project network diagram; If the process completion time is later than the planned completion time, the process handover delay time is recorded; For on-time completion rate and process handover delay time, the moving average method is used to conduct time series analysis, and the time window of the moving average method is 7 days; Based on the results of time series analysis, the progress fluctuation patterns of different project stages are classified, including the change trend of on-time completion rate into three types: increasing, decreasing and stable; Based on the subcontractor's on-time completion rate and process handover delay time, as well as the classification of progress fluctuation patterns in the project phase, a decision tree algorithm is used to build a correlation model between subcontractors and project phases. The S3 includes: The technical dependency relationship between processes is obtained based on engineering construction information, and a process dependency network diagram is constructed using graph theory algorithms to obtain the adjacency matrix of the process dependency network diagram. The connection relationship between processes is represented by the adjacency matrix, the critical path method is used to identify the critical path, and the earliest and latest start times of each process are calculated; Comprehensively evaluate the time margin and resource requirements of a process. If the evaluation result of a process exceeds the preset risk threshold, the process will be marked as a high-risk process. Perform topological sorting on the process dependency network diagram to determine the process execution order, calculate the impact of each process on subsequent construction, and use the direct scoring method to construct an impact factor matrix. Scores are given based on the process duration, resource consumption, and technical complexity, and the final impact factor is obtained through normalization. The on-time completion rate and process handover delay time of each subcontractor are obtained from the real-time progress data set. Combined with the current project characteristics, the exponential smoothing method is used to predict the on-time completion rate and process handover delay time in the future. The process influencing factor matrix is ​​combined with the predicted on-time completion rate and process handover delay time to construct a multi-dimensional progress prediction model. The Monte Carlo simulation method is used to generate multiple possible progress scenarios. The total project duration and critical path changes under each scenario are calculated to obtain multi-dimensional progress prediction results.

2. The construction progress control method in engineering supervision according to claim 1, characterized in that: Said S1 comprises: Obtain real-time progress data with subcontractor unique identification numbers, including process completion status, resource usage, and personnel distribution information, which is uploaded by subcontractor construction sites through mobile applications and electronic forms; According to the real-time progress data, the original data is sent to the central data processing platform using an encrypted transmission protocol. After receiving the original data, the central data processing platform will conduct preliminary screening and classification. Perform data cleaning on the initially collated data, including: using regular expressions to verify the data format and remove outliers and invalid data; Afterwards, a hash table is used to detect duplicate data and eliminate duplicate records; The cleaned data is standardized and formatted according to the preset data format template to obtain a structured real-time progress data set.

3. The construction progress control method in engineering supervision according to claim 1, characterized in that: The S4 includes: Obtain the historical performance data of subcontractors at different project stages, and calculate the expected performance score of each subcontractor in the future project stage using the weighted average method based on the historical performance data to obtain the subcontractor performance expectation matrix; Normalize the influencing factors of each process in the process influencing factor matrix, map the influencing factors to the score range using a logarithmic function, and calculate the degree of influence of the process on the overall progress; The difference between the predicted duration and the planned duration is extracted from the multi-dimensional progress forecast results. If the difference exceeds the preset progress deviation threshold, it is marked as a progress deviation point. At the same time, the risk matrix method is used to identify risk points based on the importance of the process and the probability of delay, and a list of progress deviations and risk points is obtained. Construct a comprehensive scoring model, taking subcontractor performance expectation scores, process impact scores, schedule deviations, and risk point assessment results as input variables; The multilayer perceptron neural network algorithm is used to train the comprehensive scoring model. The multilayer perceptron neural network includes an input layer, a hidden layer and an output layer. The input layer receives input variables, and the output layer outputs the priority scores of each subcontractor and process.

4. A construction progress control method in engineering supervision according to claim 3, characterized in that: The S5 includes: A multi-objective optimization model is constructed based on the priority scores of each subcontractor and process. The multi-objective optimization model sets minimizing construction delays and resource idleness as the objective function; Genetic algorithm is used to solve multi-objective optimization problems. The encoding method of genetic algorithm adopts real number encoding. Each chromosome represents a complete construction plan and resource allocation scheme. Decode the optimal solution obtained by the genetic algorithm, map the real values ​​in the chromosome to the time points and resource quantities, and obtain the construction plan and resource allocation plan for each subcontractor; Generate a project schedule in the form of a Gantt chart based on the construction plan and resource allocation plan. The project schedule includes the start time, end time, required resource type and quantity of each process.

5. The construction progress control method in engineering supervision according to claim 1, characterized in that: The S6 includes: Obtain successful project coordination strategy data from historical project databases, including resource allocation plans, process optimization records, and communication strategy implementation; The TF-IDF algorithm is used to extract text features from the coordination strategy data to obtain the coordination strategy feature vector; According to the coordination strategy feature vector, a coordination strategy knowledge base is constructed; Design the current project feature vector, which includes project size, complexity, schedule deviation rate, and resource utilization indicators; The cosine similarity and Euclidean distance are used to construct a comprehensive similarity index to calculate the similarity between the current project feature vector and the historical project feature vector; Select the historical project with the highest similarity as the reference sample; Conduct coordination strategy cluster analysis on the reference sample; A hierarchical clustering algorithm is used to classify coordination strategies into three categories: resource allocation, process optimization, and communication strategies. Calculate the frequency and success rate of each type of strategy and generate a recommended list of coordination measures; Based on the recommended list of coordination measures, a decision tree algorithm is used to generate a process optimization plan; Taking process characteristics as input variables and optimization strategies as output variables, we construct decision rules; Decision rules are used to guide the process optimization of the current project; Build a project communication matrix. The rows and columns of the communication matrix represent the project stakeholders, and the cell contents include communication frequency, methods, and key information. Use the analytic hierarchy process to determine the communication importance weight of each stakeholder; Establish a judgment matrix and calculate the weight vector; Perform consistency check on the weight vector and generate a communication strategy template; It also includes: generating customized communication strategy templates for each subcontractor based on analysis of historical projects and characteristics of the current project, including recommendations on communication frequency, methods, and content, as well as specific reporting mechanisms and escalation processes; Based on the characteristics and progress of the current project, the complexity and risk assessment results of the project are extracted to generate a dynamically adjusted communication matrix, including stakeholder analysis, communication responsibilities and communication methods.

6. A construction progress control method in engineering supervision according to claim 5, characterized in that: Based on the analysis of historical projects and the characteristics of the current project, a customized communication strategy template is generated for each subcontractor, including recommendations on communication frequency, methods, and content, as well as specific reporting mechanisms and escalation processes, including: Obtain subcontractor communication records and classify them using the Naive Bayes algorithm to obtain communication frequency statistics for progress reports, quality issues, and resource requirements. Based on the communication frequency statistics, combined with the project size, complexity, and duration requirements, a content-based recommendation algorithm is used to calculate the similarity between the current project and historical projects, and the historical project with the highest similarity is selected as a reference sample; For the reference sample, a random forest algorithm is used to generate customized subcontractor communication strategies, including recommended communication frequency, preferred communication methods, and key communication content; Based on the communication strategy, build a reporting mechanism and problem escalation process, set key indicator thresholds, and trigger the escalation process if the key indicators exceed the preset thresholds.

7. A construction progress control method in engineering supervision according to claim 6, characterized in that: Based on the characteristics and progress of the current project, the complexity and risk assessment results of the project are extracted to generate a dynamically adjusted communication matrix, including stakeholder analysis, communication responsibilities, and communication methods, including: The project complexity score is calculated using principal component analysis, and the project risk is quantitatively assessed using PERT to obtain the risk value; Based on the project complexity score and risk value, the hierarchical analysis method is used to construct a stakeholder influence matrix and determine the weight coefficient of each stakeholder; If the weight coefficient is greater than the preset threshold, the relevant parties are divided into a high priority group, otherwise they are divided into a medium or low priority group; According to the project organizational structure and personnel responsibilities, a responsibility allocation matrix is ​​established. The adjacency matrix is ​​used to represent the responsibility relationship network. The node degree is calculated to determine the key communication responsible persons. Use decision tree algorithms to generate communication method decision rules, automatically select communication methods based on real-time project status, and build a dynamically adjusted communication matrix; Obtain the correspondence between stakeholders, communication responsibilities, and communication methods from the communication matrix, and trigger matrix adjustments when key milestone events occur in the project.

8. A construction progress control method in engineering supervision according to claim 7, characterized in that: The S7 includes: Use the work breakdown structure method to decompose the subcontractor's work content, calculate the task time parameters based on the critical path method combined with resource balancing and risk assessment, and obtain the task decomposition tree and progress control indicators; Integrate the task decomposition tree, progress control indicators and communication matrix into the project management information system database and push them to the subcontractor's mobile terminal through the data interface; Use IoT sensors and mobile applications to obtain real-time progress data from subcontractors' construction sites, cleanse and standardize the progress data, and then store it in the project management information system; Set multi-level deviation thresholds and use real-time comparison algorithms to monitor execution and plan differences. If the deviation exceeds the preset threshold, the report generation process and problem escalation process will be triggered; Receive reports and problem escalation information, intelligently classify and prioritize warning information, use the naive Bayes algorithm to classify warning content, and determine priority based on urgency and impact scope.

Images