Digital monitoring system and method for intelligent construction

Abstract

The present invention relates to the field of intelligent construction, and in particular to a digital monitoring system and method for intelligent construction. The system comprises: a data acquisition module which acquires environmental data, an equipment state and a personnel state during a construction process, and generates a current dataset and a historical dataset; a data analysis module which reads the current dataset and the historical dataset generated by the data acquisition module for analysis processing, identifies trends and abnormalities in the current dataset and the historical dataset, and generates a real-time monitoring report; a prediction and evaluation module which analyzes the real-time monitoring report generated by the data analysis module to obtain a project progress prediction result, a project cost prediction result and a safety risk evaluation result; and a response strategy generation module which correspondingly generating a response strategy on the basis of the project progress prediction result, the project cost prediction result and the personnel safety risk evaluation result obtained by the prediction and evaluation module. The present invention involves collecting data, analyzing data, predicting results, and formulating targeted response strategies, to provide decision support for managers and assist managers in making decisions more quickly and accurately, thereby improving management efficiency.

Description

A system and method for digital monitoring of intelligent construction Technical Field

[0001] This invention relates to the field of intelligent construction, and in particular to a system and method for digital monitoring of intelligent construction. Background Technology

[0002] Traditional engineering construction has a series of problems. Construction monitoring and management often rely on manual monitoring, paper records and regular progress reports. In the process of monitoring and managing building construction, the planning of project progress and construction strategies is usually done manually, which is labor-intensive and inefficient.

[0003] With the rapid development of information technology, especially the continuous maturation of technologies such as the Internet of Things, big data, artificial intelligence, and machine learning, the construction management of nuclear power plants is evolving towards intelligent construction. Intelligent construction refers to improving the efficiency, quality, and safety of the construction industry by utilizing advanced information technology, automation technology, and artificial intelligence. It involves multiple fields, including architectural design, construction management, operation, and maintenance. The core concept of intelligent construction is to optimize the entire lifecycle of a building through digitalization and intelligentization. Currently, for the construction process of nuclear power plants, there is a lack of systems capable of comprehensively monitoring and managing construction, predicting project progress, and proposing corresponding strategies. Summary of the Invention

[0004] This invention provides a system and method for intelligent construction digital monitoring, which addresses the lack of existing systems capable of comprehensive monitoring and management of construction, predicting project progress, and proposing corresponding strategies.

[0005] The technical solution of the present invention is as follows:

[0006] This invention proposes an intelligent construction digital monitoring system, which includes a data acquisition module, a data analysis module, a prediction and evaluation module, and a response strategy generation module. The data acquisition module acquires environmental data, equipment status, and personnel status during the construction process, generating current and historical datasets. The data analysis module reads and analyzes the current and historical datasets generated by the data acquisition module, identifies trends and anomalies in the current and historical datasets, and generates real-time monitoring reports. The prediction and evaluation module analyzes the real-time monitoring reports generated by the data analysis module to obtain project progress prediction results, project cost prediction results, and safety risk assessment results. The response strategy generation module generates corresponding response strategies based on the project progress prediction results, project cost prediction results, and personnel safety risk assessment results obtained by the prediction and evaluation module.

[0007] In some embodiments, the environmental data, equipment status, and personnel status acquired by the data acquisition module specifically include: environmental data specifically includes at least one of temperature, humidity, air quality, noise level, and light intensity; equipment status includes at least one of equipment ID, equipment type, operating status, energy consumption data, and maintenance status; personnel status includes at least one of personnel ID, personnel name, location information, and timestamp; the data acquisition module includes sensors and edge computing devices, the sensors are used to detect environmental data, equipment status, and personnel status during the construction process, and the edge computing devices are used to filter and compress sensor data using an edge computing framework.

[0008] In some embodiments, the data analysis module reads and analyzes the current dataset and historical dataset generated by the data acquisition module to identify trends and anomalies in the current and historical datasets and generate a real-time monitoring report. Specifically, the data analysis module uses linear interpolation to fill in missing data in the current and historical datasets and uses the Z-Score method to detect and remove outliers, thereby obtaining cleaned data; the data analysis module aggregates the cleaned data of monitoring points in different spatial areas by minute, hour, or day, and calculates the average, maximum, and minimum values ​​of the aggregated dataset to obtain aggregated data; the data analysis module uses a linear regression model to identify the long-term trend of the aggregated data and uses the Z-score method to detect outliers in the aggregated data; the data analysis module generates a visualized real-time monitoring report from the aggregated data, long-term trends, and outliers.

[0009] In some embodiments, linear interpolation is used to estimate the linear relationship between data points to calculate the reasonable value of missing data points; the Z-Score method calculates the ratio of the standard deviation of each data point to the mean of the dataset, and outliers are identified by comparing the standard deviation ratios; the linear regression model fits the long-term trend of the aggregated data using a formula, specifically as shown in formula (1): y=β0+β1x (1)

[0010] Where y is the dependent variable, i.e. the predicted value, x is the independent variable, i.e. time, β0 is the intercept, and β1 is the slope.

[0011] In some embodiments, the Z-score method uses formula (2) to detect outliers in aggregated data. Specifically, formula (2) is:

[0012] Where X represents the data points, σ ​​represents the mean of the aggregated data, and μ represents the standard deviation of the aggregated data;

[0013] In some embodiments, real-time monitoring reports are sent to users in a visual format, including at least one of charts, graphs, heatmaps, line graphs, bar charts, and scatter plots.

[0014] In some embodiments, a digital monitoring system for intelligent construction is characterized in that the prediction and evaluation module uses an ARIMA model to obtain the project progress prediction result, specifically as shown in formula (3):

[0015] Where y t is the predicted value for time t, representing the progress of the project or the degree of completion of the task; c is a constant term, which is a bias term in the ARIMA model; θ is the autoregressive coefficient, which is autocorrelated with historical progress data; p is the order of the autoregressive term, representing the model's memory; θ is the moving average coefficient, representing the impact of historical errors on current predictions; q is the order of the moving average term, representing the model's memory of past errors; ∈ t This is the error term, representing the difference between the actual value and the predicted value;

[0016] The prediction and evaluation module uses the COCOMO II model to obtain the project cost prediction results, as shown in formula (4):

[0017] Where E represents workload; A is a constant, a constant in the COCOMO II model; KLOC is project size, representing the number of tasks; B is the size index, representing the project's complexity, size, and experience level; EM i These are cost drivers, representing the impact of different aspects of a project on costs.

[0018] The prediction and assessment module uses the FAIR model to obtain the safety risk assessment results, as shown in formula (5): RisK=Loss Event Frequency×Probable Loss Magnitude (5)

[0019] Where Loss Event Frequency is the probability of a loss event, representing the probability of a loss event occurring, and Probable Loss Magnitude is the possible magnitude of the loss, representing the maximum possible loss when the event occurs.

[0020] In some embodiments, the response strategies generated by the response strategy generation module include responses to environmental anomalies, responses to equipment failures, and responses to personnel safety issues. Responses to environmental anomalies use response measures from historical datasets as a reference, and combine this with data from real-time monitoring reports to generate response strategies using a decision function. Responses to equipment failures use equipment maintenance records from historical data as a reference, and combine this with data from real-time monitoring reports to generate response strategies using a decision function. Responses to personnel safety issues use safety event records from historical data as a reference, and combine this with data from real-time monitoring reports to generate response strategies using a decision function. The decision function used by the strategy generation module is as follows: (6)

[0021] Strategy=f(Environment,Equipment,Personnel,Historical Data) (6)

[0022] Where Strategy is the generated response strategy, f is the decision function, Environment, Equipment, and Personnel are data from the real-time monitoring report, and Historical Data is data from the historical dataset.

[0023] This invention proposes a digital monitoring method for intelligent construction, the method comprising:

[0024] Step 1: The data acquisition module acquires environmental data, equipment status, and personnel status during the construction process, and generates the current dataset and historical dataset;

[0025] Step 2: The data analysis module analyzes and processes the current dataset and historical datasets, identifies trends and anomalies in the current dataset and historical datasets, and generates a real-time monitoring report;

[0026] Step 3: The prediction and assessment module analyzes the real-time monitoring report to obtain project schedule prediction results, project cost prediction results, and safety risk assessment results;

[0027] Step 4: The response strategy generation module generates response strategies based on the project schedule forecast, project cost forecast, and personnel safety risk assessment results.

[0028] This invention proposes a digital monitoring method for intelligent construction, wherein step two specifically includes:

[0029] Step 2.1: The data analysis module uses linear interpolation to fill in missing data in the dataset and uses the Z-Score method to detect and remove outliers, thus obtaining cleaned data;

[0030] Step 2.2: The data analysis module aggregates the cleaning data of monitoring points in different spatial areas by minute, hour or day, and calculates the average, maximum and minimum values ​​of the aggregated dataset to obtain the aggregated data;

[0031] Step 2.3: The data analysis module uses a linear regression model to identify the long-term trend of the aggregated data;

[0032] Step 2.4: The data analysis module uses the Z-score method to detect outliers in the aggregated data;

[0033] Step 2.5: The data analysis module will aggregate data, long-term trends, and outliers to generate a visualized real-time monitoring report.

[0034] The implementation of this invention has the following beneficial effects:

[0035] 1. This invention proposes a system and method for intelligent construction digital monitoring. The invention acquires current and historical datasets through a data acquisition module, providing a basis for subsequent prediction and evaluation of the system. The invention employs a data analysis module to analyze the dataset, determine the long-term direction of data change, help predict future trends, and support long-term planning and decision-making for projects. At the same time, the data analysis module detects outliers in the data, helping to discover potential problems or abnormal events.

[0036] 2. This invention uses a prediction and evaluation module to forecast the future completion status of projects, combined with predicted project costs, to provide a basis for budget control and assess safety risks at construction sites to provide a reference for developing safety measures. Based on the analysis and forecast results, this invention uses a response strategy generation module to develop targeted response strategies, providing decision support for managers and assisting them in making decisions more quickly and accurately, thereby improving management efficiency. Attached Figure Description

[0037] Figure 1 is a flowchart of a digital monitoring method for intelligent construction proposed in an embodiment of the present invention;

[0038] Figure 2 is a schematic diagram of a digital monitoring system for intelligent construction proposed in an embodiment of the present invention. Detailed Implementation

[0039] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] As shown in Figures 1 and 2, this invention proposes an intelligent construction digital monitoring system. The system includes a data acquisition module, a data analysis module, a prediction and evaluation module, and a response strategy generation module. The data acquisition module acquires environmental data, equipment status, and personnel status during the construction process, generating a current dataset and a historical dataset. The data analysis module reads and analyzes the current and historical datasets generated by the data acquisition module, identifies trends and anomalies in the current and historical datasets, and generates a real-time monitoring report. The prediction and evaluation module analyzes the real-time monitoring report generated by the data analysis module to obtain project progress prediction results, project cost prediction results, and safety risk assessment results. The response strategy generation module generates corresponding response strategies based on the project progress prediction results, project cost prediction results, and personnel safety risk assessment results obtained by the prediction and evaluation module.

[0041] The data acquisition module includes sensors and edge computing devices. Sensors are used to detect environmental data, equipment status, and personnel status during construction. Edge computing devices are used to filter and compress sensor data using an edge computing framework. The environmental data, equipment status, and personnel status acquired by the data acquisition module specifically include: environmental data includes at least one of temperature, humidity, air quality, noise level, and light intensity. Air quality includes PM2.5, PM10, and CO2 concentrations.

[0042] Equipment status includes at least one of the following: equipment ID, equipment type, operating status, energy consumption data, and maintenance status. Operating status includes normal, fault, and standby; maintenance status includes no maintenance required, under maintenance, and pending maintenance.

[0043] Personnel status includes at least one of the following: personnel ID, personnel name, location information, and timestamp. Location information includes longitude, latitude, and elevation.

[0044] The data analysis module uses linear interpolation to fill in missing data in the current and historical datasets, and uses the Z-Score method to detect and remove outliers, thus obtaining cleaned data. The linear interpolation method estimates the linear relationship between data points to calculate the reasonable value of missing data points. The Z-Score method calculates the ratio of the standard deviation of each data point to the average of the dataset, and identifies outliers by comparing the standard deviation ratios. Then, the data analysis module aggregates the cleaned data of monitoring points in different spatial regions by minute, hour, or day, and calculates the average, maximum, and minimum values ​​of the aggregated dataset to obtain aggregated data. Then, the data analysis module uses a linear regression model to identify the long-term trend of the aggregated data and uses the Z-score method to detect outliers in the aggregated data. The linear regression model identifies the long-term trend of the aggregated data, and the specific fitting formula is as shown in formula (1): y=β0+β1x (1)

[0045] Where y is the dependent variable, i.e. the predicted value, x is the independent variable, i.e. time, β0 is the intercept, and β1 is the slope;

[0046] The Z-score method uses formula (2) to detect outliers in aggregated data. The specific formula (2) is as follows:

[0047] Where X represents the data point, σ represents the mean of the aggregated data, and μ represents the standard deviation of the aggregated data.

[0048] Finally, the data analysis module aggregates data, long-term trends, and outliers to generate a visualized real-time monitoring report. This report is sent to the user in a visual format, including at least one of the following: charts, line graphs, heatmaps, line charts, bar charts, and scatter plots.

[0049] The prediction and evaluation module analyzes the real-time monitoring report generated by the data analysis module to obtain project schedule prediction results, project cost prediction results, and safety risk assessment results. The prediction and evaluation module uses the ARIMA model to obtain the project schedule prediction result, as shown in formula (3):

[0050] Where y t is the predicted value for time t, representing the progress of the project or the degree of completion of the task; c is a constant term, which is a bias term in the ARIMA model; θ is the autoregressive coefficient, which is autocorrelated with historical progress data; p is the order of the autoregressive term, representing the model's memory; θ is the moving average coefficient, representing the impact of historical errors on current predictions; q is the order of the moving average term, representing the model's memory of past errors; 0 tThis is the error term, representing the difference between the actual and predicted values. All the above parameters were set manually based on actual conditions and obtained from real-time monitoring reports.

[0051] The prediction and evaluation module uses the COCOMO II model to obtain the project cost prediction results, as shown in formula (4):

[0052] Where E represents workload; A is a constant, a constant in the COCOMO II model; KLOC is project size, representing the number of tasks; B is the size index, representing the project's complexity, size, and experience level; EM i These are cost drivers, representing the impact of different aspects of the project on costs. All parameters were manually set based on actual conditions and obtained from real-time monitoring reports.

[0053] The prediction and assessment module uses the FAIR model to obtain the safety risk assessment results, as shown in formula (5): RisK=Loss Event Frequency×Probable Loss Magnitude (5)

[0054] Where Loss Event Frequency is the probability of a loss event, representing the likelihood of the event occurring, and Probable Loss Magnitude is the maximum potential loss when the event occurs. All these parameters are set manually based on actual conditions and obtained from real-time monitoring reports.

[0055] The response strategies generated by the response strategy generation module include responses to environmental anomalies, equipment failures, and personnel safety. For environmental anomalies, response measures from historical datasets are used as a reference, and a decision function is used to generate the response strategy in conjunction with data from real-time monitoring reports. For equipment failures, equipment maintenance records from historical data are used as a reference, and a decision function is used to generate the response strategy in conjunction with data from real-time monitoring reports. For personnel safety, safety incident records from historical data are used as a reference, and a decision function is used to generate the response strategy in conjunction with data from real-time monitoring reports. The decision function used by the response strategy generation module is as follows (6): Strategy=f(Environment,Equipment,Personnel,Historical Data) (6)

[0056] Where Strategy is the generated response strategy, f is the decision function, Environment, Equipment, and Personnel are data from the real-time monitoring report, and Historical Data is data from the historical dataset.

[0057] This invention proposes a digital monitoring method for intelligent construction, the method comprising:

[0058] Step 1: The data acquisition module acquires environmental data, equipment status, and personnel status during the construction process, generating a current dataset and a historical dataset. Environmental data includes at least one of temperature, humidity, air quality, noise level, and light intensity; air quality includes PM2.5, PM10, and CO2 concentrations. Equipment status includes at least one of equipment ID, equipment type, operating status, energy consumption data, and maintenance status; operating status includes normal, fault, and standby; maintenance status includes no maintenance required, under maintenance, and pending maintenance. Personnel status includes at least one of personnel ID, personnel name, location information, and timestamp; location information includes longitude, latitude, and elevation.

[0059] Step 2: The data analysis module analyzes and processes the current dataset and historical datasets, identifies trends and anomalies in the current dataset and historical datasets, and generates real-time monitoring reports.

[0060] Step 2.1: The data analysis module uses linear interpolation to fill in missing data in the dataset and uses the Z-Score method to detect and remove outliers, resulting in cleaned data. Linear interpolation estimates the reasonable value of missing data points based on the linear relationship between data points. The Z-Score method calculates the ratio of the standard deviation of each data point to the dataset mean, and identifies and removes outliers by comparing these ratios, ensuring the accuracy and reliability of the dataset.

[0061] Step 2.2: The data analysis module aggregates the cleaning data from monitoring points in different spatial areas by minute, hour, or day, and calculates the average, maximum, and minimum values ​​of the aggregated dataset to obtain aggregated data. By calculating the average, maximum, and minimum values ​​of the dataset within each time unit, the data analysis module reflects the trend and fluctuation range of the data over time. By aggregating the cleaning data and calculating the average value for each area, the module can assess the overall level of the environment, equipment, or personnel status in different areas, thereby helping managers make more informed decisions and improve construction efficiency and safety.

[0062] Step 2.3: The data analysis module uses a linear regression model to identify the long-term trend of the aggregated data. The linear regression model fits the long-term trend of the aggregated data using the formula shown in formula (1): y=β0+β1x (1)

[0063] Where y is the dependent variable, i.e. the predicted value, x is the independent variable, i.e. time, β0 is the intercept, and β1 is the slope;

[0064] Step 2.4: The data analysis module uses the Z-score method to detect outliers in the aggregated data. Specifically, the Z-score method is shown in formula (2):

[0065] Where X represents the data point, σ represents the mean of the aggregated data, and μ represents the standard deviation of the aggregated data.

[0066] Step 2.5: The data analysis module generates a visualized real-time monitoring report from aggregated data, long-term trends, and outliers. The real-time monitoring report is sent to the user's terminal in a visualized format, including at least one of the following: charts, line graphs, heatmaps, line charts, bar charts, and scatter plots.

[0067] Step 3: The prediction and evaluation module analyzes the real-time monitoring report to obtain the project schedule prediction results, project cost prediction results, and safety risk assessment results. The prediction and evaluation module uses the ARIMA model to obtain the project schedule prediction results, as shown in formula (3):

[0068] Where y t is the predicted value for time t, representing the progress of the project or the degree of completion of the task; c is a constant term, which is a bias term in the ARIMA model; θ is the autoregressive coefficient, which is autocorrelated with historical progress data; p is the order of the autoregressive term, representing the model's memory; θ is the moving average coefficient, representing the impact of historical errors on current predictions; q is the order of the moving average term, representing the model's memory of past errors; ∈ t This is the error term, representing the difference between the actual value and the predicted value.

[0069] The prediction and evaluation module uses the COCOMO II model to obtain the project cost prediction results, as shown in formula (4):

[0070] Where E represents workload; A is a constant, a constant in the COCOMO II model; KLOC is project size, representing the number of tasks; B is the size index, representing the project's complexity, size, and experience level; EM i These are cost drivers, representing the impact of different aspects of a project on costs.

[0071] The prediction and assessment module uses the FAIR model to obtain the safety risk assessment results, as shown in formula (5): RisK=Loss Event Frequency×Probable Loss Magnitude (5)

[0072] Where Loss Event Frequency is the probability of a loss event, representing the probability of a loss event occurring, and Probable Loss Magnitude is the possible magnitude of the loss, representing the maximum possible loss when the event occurs.

[0073] Step Four: The response strategy generation module generates response strategies based on the project schedule forecast, project cost forecast, and personnel safety risk assessment results. Environmental anomaly response includes generating response strategies based on anomaly patterns in environmental data. The module uses historical data as a reference and combines it with data from real-time monitoring reports to employ decision functions. For example, if the temperature is too high or too low, strategies to increase or decrease the operating time of ventilation equipment are generated, referencing historical response measures such as adding air purification equipment.

[0074] Equipment failure response involves using historical equipment maintenance records as a reference, and combining data from real-time monitoring reports with decision functions to generate equipment repair or replacement strategies based on abnormal equipment status patterns.

[0075] Personnel safety response involves using historical safety incident records as a reference, combined with data from real-time monitoring reports, to generate response strategies using decision functions based on abnormal patterns in personnel status. For example, if personnel are in a high-risk area, strategies for personnel evacuation or safety alerts may be generated.

[0076] The decision function used by the strategy generation module is as follows (6): Strategy=f(Environment,Equipment,Personnel,Historical Data) (6)

[0077] Where Strategy is the generated response strategy, f is the decision function, Environment, Equipment, and Personnel are data from the real-time monitoring report, and Historical Data is data from the historical dataset.

[0078] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A digital monitoring system for intelligent construction, characterized in that, The system includes a data acquisition module, a data analysis module, a prediction and evaluation module, and a response strategy generation module. The data acquisition module acquires environmental data, equipment status, and personnel status during the construction process, generating a current dataset and a historical dataset. The data analysis module reads and analyzes the current and historical datasets generated by the data acquisition module, identifies trends and anomalies in the current and historical datasets, and generates a real-time monitoring report. The prediction and evaluation module analyzes the real-time monitoring report generated by the data analysis module to obtain project progress prediction results, project cost prediction results, and safety risk assessment results. The response strategy generation module generates corresponding response strategies based on the project progress prediction results, project cost prediction results, and personnel safety risk assessment results obtained by the prediction and evaluation module.

2. The intelligent construction digital monitoring system according to claim 1, characterized in that, The environmental data, equipment status, and personnel status acquired by the data acquisition module specifically include: environmental data including at least one of temperature, humidity, air quality, noise level, and light intensity; equipment status including at least one of equipment ID, equipment type, operating status, energy consumption data, and maintenance status; and personnel status including at least one of personnel ID, personnel name, location information, and timestamp. The data acquisition module includes sensors and edge computing devices. The sensors are used to detect environmental data, equipment status, and personnel status during the construction process, and the edge computing devices are used to filter and compress the sensor data using an edge computing framework.

3. The intelligent construction digital monitoring system according to claim 1, characterized in that, The data analysis module reads and analyzes the current and historical datasets generated by the data acquisition module, identifies trends and anomalies in the current and historical datasets, and generates a real-time monitoring report. Specifically, the data analysis module uses linear interpolation to fill in missing data in the current and historical datasets, and uses the Z-Score method to detect and remove outliers, thus obtaining cleaned data. The data analysis module aggregates the cleaned data from monitoring points in different spatial regions by minute, hour, or day, and calculates the average, maximum, and minimum values ​​of the aggregated dataset to obtain aggregated data. The data analysis module uses a linear regression model to identify the long-term trend of the aggregated data and uses the Z-score method to detect outliers in the aggregated data. The data analysis module then uses the aggregated data, long-term trends, and outliers to generate a visualized real-time monitoring report.

4. The intelligent construction digital monitoring system according to claim 3, characterized in that, The linear interpolation method estimates the linear relationship between data points, thereby calculating the reasonable value of missing data points; the Z-Score method calculates the ratio of the standard deviation of each data point to the mean of the dataset, and identifies outliers by comparing the standard deviation ratios. The linear regression model fits the long-term trend of the aggregated data using the formula shown in formula (1): y=β0+β1x (1) Where y is the dependent variable, i.e. the predicted value, x is the independent variable, i.e. time, β0 is the intercept, and β1 is the slope.

5. The intelligent construction digital monitoring system according to claim 4, characterized in that, The Z-score method uses formula (2) to detect outliers in the aggregated data. Specifically, formula (2) is: Where X represents the data point, σ represents the mean of the aggregated data, and μ represents the standard deviation of the aggregated data.

6. The intelligent construction digital monitoring system according to claim 5, characterized in that, The real-time monitoring report is sent to the user in a visual format, which includes at least one of the following: charts, graphs, heatmaps, line graphs, bar charts, and scatter plots.

7. The intelligent construction digital monitoring system according to claim 6, characterized in that, The intelligent construction digital monitoring system is characterized in that the prediction and evaluation module uses the ARIMA model to obtain the project progress prediction result, as shown in formula (3): Where y t is the predicted value for time t, representing the progress of the project or the degree of completion of the task; c is a constant term, which is a bias term in the ARIMA model; ε is the autoregressive coefficient, which is autocorrelated with historical progress data; p is the order of the autoregressive term, representing the model's memory; θ is the moving average coefficient, representing the impact of historical errors on current predictions; q is the order of the moving average term, representing the model's memory of past errors; ε t This is the error term, representing the difference between the actual value and the predicted value; The prediction and evaluation module uses the COCOMO II model to obtain the project cost prediction results, as shown in formula (4): Where E represents workload; A is a constant, a constant in the COCOMO II model; KLOC is project size, representing the number of tasks; B is the size index, representing the project's complexity, size, and experience level; EM i These are cost drivers, representing the impact of different aspects of a project on costs. The prediction and assessment module uses the FAIR model to obtain the safety risk assessment results, as shown in formula (5): RisK=Loss Event Frequency×Probable Loss Magnitude (5) Where Loss Event Frequency is the probability of a loss event, representing the probability of a loss event occurring, and Probable Loss Magnitude is the possible magnitude of the loss, representing the maximum possible loss when the event occurs.

8. The intelligent construction digital monitoring system according to claim 1, characterized in that, The response strategy generation module generates response strategies including environmental anomaly response, equipment failure response, and personnel safety response. The environmental anomaly response takes response measures from historical datasets as a reference and combines them with data from real-time monitoring reports to generate response strategies using decision functions. The equipment failure response uses historical equipment maintenance records as a reference and combines them with data from real-time monitoring reports to generate response strategies using decision functions. The personnel safety response uses historical safety incident records as a reference and combines them with data from real-time monitoring reports to generate response strategies using a decision function. The decision function used by the response strategy generation module is as follows: Strategy=f(Environment,Equipment,Personnel,Historical Data) (6) Where Strategy is the generated response strategy, f is the decision function, Environment, Equipment, and Personnel are data from the real-time monitoring report, and Historical Data is data from the historical dataset.

9. A digital monitoring method for intelligent construction according to any one of claims 1-8, characterized in that, The method includes: Step 1: The data acquisition module acquires environmental data, equipment status, and personnel status during the construction process, and generates the current dataset and historical dataset; Step 2: The data analysis module analyzes and processes the current dataset and historical datasets, identifies trends and anomalies in the current dataset and historical datasets, and generates a real-time monitoring report; Step 3: The prediction and assessment module analyzes the real-time monitoring report to obtain project schedule prediction results, project cost prediction results, and safety risk assessment results; Step 4: The response strategy generation module generates response strategies based on the project schedule forecast, project cost forecast, and personnel safety risk assessment results.

10. The intelligent construction digital monitoring method according to claim 9, characterized in that, Step two specifically includes: Step 2.1: The data analysis module uses linear interpolation to fill in the missing data in the dataset and uses the Z-Score method to detect and remove outliers to obtain cleaned data; Step 2.2: The data analysis module aggregates the cleaning data of monitoring points in different spatial areas by minute, hour or day, and calculates the average, maximum and minimum values ​​of the aggregated dataset to obtain aggregated data; Step 2.3: The data analysis module uses a linear regression model to identify the long-term trend of the aggregated data; Step 2.4: The data analysis module uses the Z-score method to detect outliers in the aggregated data; Step 2.5: The data analysis module generates a visualized real-time monitoring report from the aggregated data, long-term trends, and outliers.

Images