Construction engineering safety supervision method based on gradient boosting tree and related equipment

Abstract

The invention discloses a construction engineering safety supervision method based on a gradient boosting tree and related equipment, which can timely discover and deal with potential safety risks and realize real-time supervision of a construction site. The method comprises the following steps: acquiring historical data of a construction site, wherein the historical data comprises historical construction environment parameters, behavior data of historical constructors and physiological index data; preprocessing the historical data to obtain preprocessed data; training a gradient boosting tree model by using the preprocessed data to obtain a target gradient boosting tree model, the target gradient boosting tree model being used for identifying and predicting behaviors and potential dangerous environments of workers on the construction site; behavior data, construction environment parameters and physiological index data of workers on a construction site are collected in real time; and inputting the behavior data of the field staff, the construction environment parameters and the physiological index data of the staff into the target gradient boosting tree model to obtain a risk assessment result.

Description

Technical Field

[0001] The present application relates to the field of building safety technology, and in particular to a construction engineering safety supervision method and related equipment based on a gradient boosting tree. Background Art

[0002] In the field of construction engineering, safety supervision of construction sites is a key link in ensuring the progress of the project and the safety of the lives of construction workers. However, traditional safety supervision methods mainly rely on manual monitoring and experience-based judgment, which have many limitations. Especially in complex and changeable construction environments, high-risk operations such as aerial operations and heavy object handling are frequently carried out, which greatly increases the difficulty of safety supervision.

[0003] Traditional safety supervision methods often rely on the experience and intuition of construction site managers, but this method is difficult to fully and accurately identify and predict potential safety hazards. On the one hand, manual monitoring is difficult to achieve all-weather, no-blind-angle coverage, and it is easy to miss key safety information; on the other hand, even if managers discover certain unsafe behaviors or environmental factors, it is often difficult to quickly make accurate judgments and response measures.

[0004] With the continuous development of information technology, although some construction sites have begun to try to use simple monitoring equipment and data recording methods to assist safety supervision, these methods can usually only provide limited information and lack intelligent analysis and prediction capabilities. For example, the existing monitoring system can record certain behaviors and environmental parameters of the construction site, but it is often unable to automatically identify the relationship between these data and potential safety hazards, nor can it dynamically evaluate safety risks based on real-time data, resulting in some avoidable safety accidents that still occur frequently, posing a huge threat to the safety of workers' lives and project progress. Summary of the invention

[0005] In order to solve the above technical problems, the present application provides a construction project safety supervision method and related equipment based on a gradient boosting tree.

[0006] The technical solution provided in this application is described below:

[0007] The first aspect of the present application provides a construction engineering safety supervision method based on a gradient boosting tree, the method comprising:

[0008] Acquire historical data of the construction site, wherein the historical data includes historical construction environment parameters, historical construction personnel behavior data and physiological index data;

[0009] Preprocessing the historical data to obtain preprocessed data;

[0010] Using the preprocessed data to train a gradient boosting tree model to obtain a target gradient boosting tree model, wherein the target gradient boosting tree model is used to identify and predict the behavior of workers and potential dangerous environments at the construction site;

[0011] Collecting the behavior data, construction environment parameters and physiological index data of the workers at the construction site in real time;

[0012] Inputting the behavior data of the on-site workers, the construction environment parameters and the physiological index data of the workers into the target gradient boosting tree model to obtain risk assessment results;

[0013] Determining a risk level based on the risk assessment results, and determining a target operation based on the risk level;

[0014] The target operation is used to achieve safety supervision of the construction site.

[0015] Optionally, historical data of the construction site is obtained, wherein the historical data includes historical construction environment parameters, historical construction personnel behavior data and physiological index data, including:

[0016] Determine the history start time and data type;

[0017] Retrieving various types of construction site data from a database according to the historical start time;

[0018] Retrieving the historical data from multiple types of data at the construction site according to the data type, the historical data including historical construction environment parameters, historical construction personnel behavior data and physiological index data;

[0019] The historical construction environment parameters include average temperature and average humidity;

[0020] The average temperature is:

[0021] Among them, Ti is the temperature value of the i-th record, N is the total number of records, and S is the average temperature;

[0022] The average humidity is:

[0023] Among them, Ti is the humidity value of the i-th record, N is the total number of records, and R is the average humidity;

[0024] The historical physiological index data of the construction workers include average heart rate and average body temperature;

[0025] The average heart rate is:

[0026] Among them, HRi is the heart rate value of the i-th record, K is the total number of records, and P is the average heart rate;

[0027] The average body temperature is:

[0028] Among them, BTi is the heart rate value of the i-th record, K is the total number of records, and M is the average heart rate.

[0029] Optionally, preprocessing the historical data to obtain preprocessed data includes:

[0030] Determine whether the historical data contains non-construction environment parameters, non-historical construction personnel behavior data, and non-physiological index data;

[0031] If yes, data cleaning is performed on the historical data to obtain target historical data, wherein the data cleaning is used to process non-construction environment parameters, non-historical construction personnel behavior data, and non-physiological indicator data;

[0032] The target historical data is standardized to obtain the preprocessed data.

[0033] Optionally, the behavior data of the on-site workers, the construction environment parameters and the physiological index data of the workers are input into the target gradient boosting tree model to obtain risk assessment results, including:

[0034] Preprocessing the behavior data of the on-site staff, the construction environment parameters and the physiological index data of the staff to obtain target preprocessed data;

[0035] Inputting the target preprocessed data into the target gradient boosting tree model to obtain a first risk assessment result;

[0036] Determining a risk level based on the risk assessment results, and determining a target operation based on the risk level, including:

[0037] A low risk level is determined according to the first risk assessment result, and an operation of issuing an alarm is determined according to the low risk level.

[0038] Optionally, the behavior data of the on-site workers, the construction environment parameters and the physiological index data of the workers are input into the target gradient boosting tree model to obtain risk assessment results, including:

[0039] Preprocessing the behavior data of the on-site staff, the construction environment parameters and the physiological index data of the staff to obtain target preprocessed data;

[0040] Inputting the target preprocessed data into the target gradient boosting tree model to obtain a second risk assessment result;

[0041] Determining a risk level based on the risk assessment results, and determining a target operation based on the risk level, including:

[0042] The medium risk level is determined according to the second risk assessment result, and the risk information is sent to the management terminal according to the medium risk level, so that the management terminal sends the risk information to the management personnel.

[0043] Optionally, the behavior data of the on-site workers, the construction environment parameters and the physiological index data of the workers are input into the target gradient boosting tree model to obtain risk assessment results, including:

[0044] Preprocessing the behavior data of the on-site staff, the construction environment parameters and the physiological index data of the staff to obtain target preprocessed data;

[0045] Inputting the target preprocessed data into the target gradient boosting tree model to obtain a third risk assessment result;

[0046] Determining a risk level based on the risk assessment results, and determining a target operation based on the risk level, including:

[0047] A high risk level is determined according to the third risk assessment result, and information is sent to an alarm center and a medical care center according to the high risk level.

[0048] Optionally, after determining a high risk level according to the third risk assessment result and sending information to an alarm center and a medical care center according to the high risk level, the method further includes:

[0049] Obtaining the positioning position of the construction site and the positioning position of a target medical care center, wherein the target medical care center is a medical care center within a preset range that is closest to the construction site;

[0050] Planning an optimal rescue route according to the location of the construction site and the location of the target medical center;

[0051] When the ambulance vehicle terminal is identified, the optimal rescue route is sent to the ambulance vehicle terminal.

[0052] The second aspect of the present application provides a construction engineering safety supervision system based on a gradient boosting tree, the system comprising:

[0053] A first acquisition unit is used to acquire historical data of the construction site, wherein the historical data includes historical construction environment parameters, historical construction personnel behavior data and physiological index data;

[0054] A preprocessing unit, used for preprocessing the historical data to obtain preprocessed data;

[0055] A second acquisition unit uses the preprocessed data to train a gradient boosting tree model to obtain a target gradient boosting tree model, wherein the target gradient boosting tree model is used to identify and predict the behavior of workers at the construction site and a potential dangerous environment;

[0056] A collection unit, used to collect the behavior data, construction environment parameters and physiological index data of the workers on the construction site in real time;

[0057] An input unit, used to input the behavior data of the on-site workers, the construction environment parameters and the physiological index data of the workers into the target gradient boosting tree model to obtain a risk assessment result;

[0058] a determination unit, configured to determine a risk level according to the risk assessment result, and determine a target operation according to the risk level;

[0059] An execution unit is used to implement safety supervision of the construction site through the target operation.

[0060] The third aspect of the present application provides a construction engineering safety supervision device based on a gradient boosting tree, the device comprising:

[0061] Processor, memory, input-output unit, and bus;

[0062] The processor is connected to the memory, the input and output unit, and the bus;

[0063] The memory stores a program, and the processor calls the program to execute the method as described in the first aspect and any one of the first aspects.

[0064] A fourth aspect of the present application provides a computer-readable storage medium, on which a program is stored. When the program is executed on a computer, the method described in the first aspect and any one of the first aspects is performed.

[0065] It can be seen from the above technical solutions that this application has the following advantages:

[0066] 1. The use of the gradient boosting tree model can effectively handle complex data relationships and nonlinear problems. By training a large amount of historical data, the model can accurately identify the behavior patterns of construction site workers and potential dangerous environments, thereby improving the accuracy of risk assessment.

[0067] 2. This method can collect data from the construction site in real time and immediately process it through the target gradient boosting tree model to obtain risk assessment results, which enables safety supervisors to promptly discover and respond to potential safety risks and achieve real-time supervision of the construction site.

[0068] 3. Through automated data collection and analysis, work efficiency can be significantly improved and the workload of safety supervisors can be reduced.

[0069] 4. The risk assessment results and risk level classification provided by this method provide a scientific basis for decision-making for safety supervisors, so that they can formulate targeted safety measures and emergency plans based on these results, thereby more effectively ensuring the safety of the construction site.

[0070] 5. Real-time collection and analysis of staff behavior data can promptly identify and correct unsafe behaviors. At the same time, the feedback mechanism can enhance staff safety awareness, form a virtuous circle, and further improve the overall safety level of the construction site. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solution in the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0072] Figure 1 A schematic diagram of an embodiment of a construction engineering safety supervision method based on a gradient boosting tree of the present application;

[0073] Figure 2 This is a schematic diagram of another embodiment of the construction project safety supervision method based on the gradient boosting tree of the present application;

[0074] Figure 3 This is a schematic diagram of another embodiment of the construction project safety supervision method based on the gradient boosting tree of the present application;

[0075] Figure 4 This is a schematic diagram of another embodiment of the construction project safety supervision method based on the gradient boosting tree of the present application;

[0076] Figure 5 This is a schematic diagram of an embodiment of a construction engineering safety supervision method system based on a gradient boosting tree of the present application;

[0077] Figure 6 This is a schematic diagram of an embodiment of a construction project safety supervision method device based on a gradient boosting tree in the present application. DETAILED DESCRIPTION

[0078] It should be noted that the construction engineering safety supervision method based on the gradient boosting tree provided in this application can be applied to a terminal, a system, or a server. For example, the terminal can be a smart phone or a computer, a tablet computer, a smart TV, a portable computer terminal, or a fixed terminal such as a desktop computer. For the convenience of explanation, this application uses the terminal as an example for the execution subject.

[0079] See also Figure 1 The present application first provides an embodiment of a construction engineering safety supervision method based on a gradient boosting tree, the embodiment comprising:

[0080] 101. Acquire historical data of the construction site, wherein the historical data includes historical construction environment parameters, historical construction personnel behavior data, and physiological index data;

[0081] 102. Preprocess the historical data to obtain preprocessed data;

[0082] 103. Using the preprocessed data to train a gradient boosting tree model to obtain a target gradient boosting tree model, wherein the target gradient boosting tree model is used to identify and predict the behavior of workers at the construction site and a potential dangerous environment;

[0083] 104. Collecting the behavior data, construction environment parameters and physiological index data of the workers at the construction site in real time;

[0084] 105. Inputting the behavior data of the on-site staff, the construction environment parameters and the physiological index data of the staff into the target gradient boosting tree model to obtain a risk assessment result;

[0085] 106. Determine a risk level according to the risk assessment result, and determine a target operation according to the risk level;

[0086] 107. Achieve safety supervision of the construction site through the target operation.

[0087] In an embodiment of the present application, historical data of the construction site are first obtained, including historical construction environment parameters, historical construction personnel behavior data and physiological indicator data; the historical data are then preprocessed to obtain preprocessed data, and the obtained preprocessed data is used to train a gradient boosting tree model. The purpose of training the gradient boosting tree model is to obtain a target gradient boosting tree model. The target gradient boosting tree model generated by training can be used to identify and predict the behavior of construction site workers and potential dangerous environments; after the target gradient boosting tree model is obtained through training, the behavior data, construction environment parameters and physiological indicator data of the construction site workers are collected in real time; and the behavior data, construction environment parameters and physiological indicator data of the site workers are input into the target gradient boosting tree model to obtain a risk assessment result, and finally the risk level is determined according to the risk assessment result, and the target operation is determined according to the risk level, and the safety supervision of the construction site is achieved through the target operation.

[0088] In step 101, before acquiring historical data, the specific type and scope of the required data are first clarified. For a construction site, historical data mainly includes three categories: historical construction environment parameters, historical construction personnel behavior data, and physiological indicator data.

[0089] Historical construction environmental parameters: reflect the environmental conditions of the construction site, such as temperature, humidity, noise level, air quality, including dust concentration, harmful gas concentration, etc.

[0090] Historical construction worker behavior data: This type of data records the specific operations and behavioral habits of workers at the construction site, such as compliance with work procedures, use of safety equipment, records of illegal operations, etc. By analyzing this data, potential dangerous behavior patterns can be identified.

[0091] Physiological indicator data: This type of data is usually obtained through wearable devices or regular physical examinations, including physiological indicators such as heart rate, blood pressure, and fatigue index. This data helps to assess the physiological state of workers during the construction process, thereby determining whether there are safety risks caused by factors such as fatigue and stress.

[0092] Historical data collection methods for construction sites:

[0093] Sensors and monitoring equipment: Various sensors and monitoring equipment are installed at the construction site, such as temperature and humidity sensors, noise monitors, air quality monitors, etc., to collect environmental parameter data in real time or regularly, and wearable devices are provided to workers to monitor their physiological indicator data.

[0094] Video surveillance and image recognition: By installing surveillance cameras, the construction site can be monitored around the clock. Using image recognition technology, the behavior data of workers can be extracted from the video, such as operating movements, wearing of safety equipment, etc.

[0095] In step 102, the main purpose of preprocessing the historical data is to solve various problems that may exist in the historical data, such as missing values, outliers, noise, inconsistency, etc., so as to improve the integrity, accuracy and availability of the data. Through preprocessing, the data can better meet the requirements of the gradient boosting tree model training and improve the prediction accuracy and generalization ability of the gradient boosting tree model.

[0096] In step 103, the preprocessed data is used to train the gradient boosting tree model to obtain the target gradient boosting tree model, wherein the gradient boosting tree model (GBT) builds a strong learning model by combining multiple decision trees. In each iteration, GBT will try to reduce the gradient of the loss function to make the model's prediction closer to the actual value. This step-by-step iterative method enables GBT to gradually improve the performance of the model and achieve a higher accuracy. The preprocessed data is divided into a training set and a test set. The training set is used to train the model, and the test set is used to evaluate the performance of the model. Then the gradient boosting tree model uses the training set to start the iterative training process, and after generating the target gradient boosting tree model, the test set is used for training. When the generated results meet the requirements, the target gradient is used to identify and predict the behavior of the workers at the construction site and the potential dangerous environment.

[0097] In step 104, environmental parameter data can be collected in real time through various sensors and monitoring equipment at the construction site, such as temperature and humidity sensors, noise monitors, air quality monitors, etc. At the same time, since the workers are equipped with wearable devices, the physiological index data of the workers can be monitored through the wearable devices. Then, by installing surveillance cameras, the construction site is monitored around the clock, and the behavior data of the workers can be extracted from the video using image recognition technology. After that, in order to ensure the real-time nature of the data, wireless communication technologies such as Wi-Fi, Bluetooth, Zigbee, etc. are used to transmit the collected data in real time to the data center or cloud for processing and analysis.

[0098] In step 105, before the collected behavior data of the on-site staff, construction environment parameters and physiological index data of the staff are input into the target gradient boosting tree model, a series of data preprocessing is required to ensure that the format, quality and consistency of the data meet the requirements of the model. The preprocessing process includes steps such as data cleaning, normalization, and feature selection. Cleaning the data is to remove noise and outliers, normalization is to scale the data to a uniform range, and feature selection is to extract the features that have the greatest impact on model prediction.

[0099] After preprocessing, the behavioral data of on-site staff, construction environment parameters and physiological indicator data of staff are used as input and sent to the trained target gradient boosting tree model. The model will perform calculations and inferences based on the input data and use the learned patterns and relationships to obtain risk assessment results.

[0100] In step 106, after obtaining the risk assessment results according to the target gradient boosting tree model, the risk assessment results are further interpreted, and then different risk thresholds are set according to actual needs and management standards. These thresholds are used to divide the risk assessment results into different risk levels. The risk level can be divided into three levels: "low", "medium" and "high".

[0101] After determining the risk level, further determine the corresponding target operations according to the risk level. The target operations include reminding workers to pay attention to safety, adjusting the construction environment, providing necessary training, adding safety equipment, and formulating emergency plans. If there are multiple target operations to be performed, they should be prioritized according to the risk level and urgency to ensure that the most important operations are performed first.

[0102] In step 107, safety supervision of the construction site is implemented through target operations. By executing target operations, it can be ensured that the safety conditions of the construction site are effectively controlled and improved, thereby more effectively ensuring the safety of the construction site.

[0103] Reference Figure 2 According to some embodiments of the present invention, historical data of the construction site is obtained in step 101. The historical data includes historical construction environment parameters, historical construction personnel behavior data and physiological index data, and specifically may include, but are not limited to, the following:

[0104] 201. Determine the historical start time and data type;

[0105] 202. Retrieving various types of data of the construction site from a database according to the historical start time;

[0106] 203. Retrieve the historical data from multiple types of data at the construction site according to the data type, wherein the historical data includes historical construction environment parameters, historical construction personnel behavior data, and physiological index data.

[0107] In the embodiment of the present application, to determine the historical start time and data type, it is first necessary to select a suitable historical start time point, based on which sufficient data can be obtained for analysis, and then it is necessary to clarify what types of data are needed. For example, construction environment parameters such as temperature and humidity, construction personnel behavior data such as operation records and violations, and physiological index data such as heart rate and blood pressure.

[0108] After determining the data type and historical start time, retrieve various types of construction site data from the database according to the historical start time. Specifically, use appropriate database management tools or programming languages ​​(such as SQL, Python, etc.) to access the database storing construction site data, and then set time filtering conditions in the database query to select only data after the historical start time. Execute database queries to extract various types of construction site data, including but not limited to construction environment parameters, construction personnel behavior data, and physiological indicator data.

[0109] The data extracted from the database are then classified and stored according to data types, for example, construction environment parameters, construction personnel behavior data and physiological index data are stored in different data structures, so as to facilitate subsequent corresponding processing.

[0110] Specifically, the historical construction environment parameters include average temperature and average humidity;

[0111] The average temperature is:

[0112] Among them, Ti is the temperature value of the i-th record, N is the total number of records, and S is the average temperature;

[0113] The average humidity is:

[0114] Among them, Ti is the humidity value of the i-th record, N is the total number of records, and R is the average humidity;

[0115] The historical physiological index data of the construction workers include average heart rate and average body temperature;

[0116] The average heart rate is:

[0117] Among them, HRi is the heart rate value of the i-th record, K is the total number of records, and P is the average heart rate;

[0118] The average body temperature is:

[0119] Among them, BTi is the heart rate value of the i-th record, K is the total number of records, and M is the average heart rate.

[0120] Reference Figure 3 According to some embodiments of the present invention, preprocessing the historical data in step 102 to obtain preprocessed data may specifically include, but is not limited to, the following:

[0121] 301. Determine whether the historical data includes non-construction environment parameters, non-historical construction personnel behavior data, and non-physiological index data;

[0122] 302. If yes, clean the historical data to obtain target historical data, wherein the data cleaning is used to process non-construction environment parameters, non-historical construction personnel behavior data, and non-physiological indicator data;

[0123] 303. Standardize the target historical data to obtain the preprocessed data.

[0124] In an embodiment of the present application, whether the identification data contains non-construction environment parameters, such as weather data unrelated to construction, non-historical construction worker behavior data, such as activity records of non-construction workers, and non-physiological indicator data, such as health data unrelated to construction workers, etc., the identified non-target data types are marked, and then all data marked as non-construction environment parameters, non-historical construction worker behavior data, and non-physiological indicator data are deleted, and then the target historical data is processed such as normalization and standardization (Z-score) to obtain preprocessed data, and the obtained preprocessed data is organized into a format suitable for subsequent analysis or model training.

[0125] Through the above steps, it can be ensured that the non-target data types contained in the historical data are effectively processed and the data quality of the target data types is improved, providing a reliable data foundation for subsequent risk assessment, model training or data analysis.

[0126] Reference Figure 4 According to some embodiments of the present invention, in step 105, the behavior data of the on-site staff, the construction environment parameters and the physiological index data of the staff are input into the target gradient boosting tree model to obtain the risk assessment results, which may specifically include, but are not limited to, the following:

[0127] 401. Preprocessing the behavior data of the on-site staff, the construction environment parameters, and the physiological index data of the staff to obtain target preprocessed data;

[0128] 402. Input the target preprocessed data into the target gradient boosting tree model to obtain a risk assessment result;

[0129] In the embodiment of the present application, there are three types of risk assessment results, and corresponding target operations are performed according to different types of risk assessment results, specifically:

[0130] 1. Input the target preprocessing data into the target gradient boosting tree model to obtain a first risk assessment result; determine a low risk level according to the first risk assessment result, and determine an operation of issuing an alarm prompt according to the low risk level to remind the staff to pay attention to safety.

[0131] 2. Input the target preprocessed data into the target gradient boosting tree model to obtain a second risk assessment result; determine the medium risk level according to the second risk assessment result, and send the risk information to the management terminal according to the medium risk level, so that the management terminal sends the risk information to the management personnel, so that the management personnel can make corresponding operations according to the risk information. Of course, when a medium risk level prompt appears, a corresponding low risk level operation will also be executed, that is, a corresponding alarm prompt operation will also be issued.

[0132] 3. Input the target preprocessed data into the target gradient boosting tree model to obtain a third risk assessment result; determine it as a high risk level according to the third risk assessment result, and send information to the alarm center and the medical care center according to the high risk level.

[0133] In an embodiment of the present application, when a high risk level occurs, it means that a medical situation has occurred at the construction site. After issuing an alarm and notifying the management personnel, a message will also be released to the alarm center and the medical center. Specifically, the positioning position of the construction site and the positioning position of the target medical center are obtained. The target medical center is the medical center closest to the construction site within a preset range. The optimal rescue route is planned according to the positioning position of the construction site and the positioning position of the target medical center; when the ambulance on-board terminal is identified, the optimal rescue route is sent to the ambulance on-board terminal, so that the ambulance on-board terminal drives according to the optimal rescue route, and the people who have accidents at the construction site are urgently transported to the medical center for treatment, thereby more effectively ensuring the safety of the construction site.

[0134] See also Figure 5 , the present application also provides a construction engineering safety supervision system based on a gradient boosting tree, comprising:

[0135] A first acquisition unit 501 is used to acquire historical data of the construction site, wherein the historical data includes historical construction environment parameters, historical construction personnel behavior data and physiological index data;

[0136] A preprocessing unit 502, configured to preprocess the historical data to obtain preprocessed data;

[0137] A second acquisition unit 503 uses the preprocessed data to train a gradient boosting tree model to obtain a target gradient boosting tree model, where the target gradient boosting tree model is used to identify and predict the behavior of workers at the construction site and a potential dangerous environment;

[0138] The collection unit 504 is used to collect the behavior data, construction environment parameters and physiological index data of the workers on the construction site in real time;

[0139] An input unit 505 is used to input the behavior data of the on-site workers, the construction environment parameters and the physiological index data of the workers into the target gradient boosting tree model to obtain a risk assessment result;

[0140] A determination unit 506, configured to determine a risk level according to the risk assessment result, and determine a target operation according to the risk level;

[0141] The execution unit 507 is used to implement safety supervision of the construction site through the target operation.

[0142] See also Figure 6 , the present application also provides a construction engineering safety supervision device based on a gradient boosting tree, comprising:

[0143] Processor 601, memory 602, input and output unit 603, bus 604;

[0144] The processor 601 is connected to the memory 602, the input and output unit 603 and the bus 604;

[0145] The memory 602 stores a program, and the processor 601 calls the program to execute the method described in the first aspect and any one of the first aspects above.

[0146] The present application also relates to a computer-readable storage medium on which a program is stored, wherein when the program is run on a computer, the computer executes the method as described in any one of the first aspect and the first aspect above.

[0147] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0148] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0149] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0150] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0151] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program code.

Claims

1. A construction engineering safety supervision method based on gradient boosting tree, characterized in that: The method comprises: Acquire historical data of the construction site, wherein the historical data includes historical construction environment parameters, historical construction personnel behavior data and physiological index data; Preprocessing the historical data to obtain preprocessed data; Using the preprocessed data to train a gradient boosting tree model to obtain a target gradient boosting tree model, wherein the target gradient boosting tree model is used to identify and predict the behavior of workers and potential dangerous environments at the construction site; Collecting the behavior data, construction environment parameters and physiological index data of the workers at the construction site in real time; Inputting the behavior data of the on-site workers, the construction environment parameters and the physiological index data of the workers into the target gradient boosting tree model to obtain risk assessment results; Determining a risk level based on the risk assessment results, and determining a target operation based on the risk level; The target operation is used to achieve safety supervision of the construction site.

2. The construction engineering safety supervision method based on gradient boosting tree according to claim 1 is characterized in that: Obtain historical data of the construction site, including historical construction environment parameters, historical construction personnel behavior data and physiological index data, including: Determine the history start time and data type; Retrieving various types of construction site data from a database according to the historical start time; Retrieving the historical data from multiple types of data at the construction site according to the data type, the historical data including historical construction environment parameters, historical construction personnel behavior data and physiological index data; The historical construction environment parameters include average temperature and average humidity; The average temperature is: Among them, Ti is the temperature value of the i-th record, N is the total number of records, and S is the average temperature; The average humidity is: Among them, Ti is the humidity value of the i-th record, N is the total number of records, and R is the average humidity; The historical physiological index data of the construction workers include average heart rate and average body temperature; The average heart rate is: Among them, HRi is the heart rate value of the i-th record, K is the total number of records, and P is the average heart rate; The average body temperature is: Among them, BTi is the heart rate value of the i-th record, K is the total number of records, and M is the average heart rate.

3. The construction engineering safety supervision method based on gradient boosting tree according to claim 1 is characterized in that: Preprocessing the historical data to obtain preprocessed data includes: Determine whether the historical data contains non-construction environment parameters, non-historical construction personnel behavior data, and non-physiological index data; If yes, then data cleaning is performed on the historical data to obtain target historical data, wherein the data cleaning is used to process non-construction environment parameters, non-historical construction personnel behavior data, and non-physiological indicator data; The target historical data is standardized to obtain the preprocessed data.

4. The construction engineering safety supervision method based on gradient boosting tree according to claim 1 is characterized in that: Inputting the behavior data of the on-site workers, the construction environment parameters and the physiological index data of the workers into the target gradient boosting tree model to obtain risk assessment results, including: Preprocessing the behavior data of the on-site staff, the construction environment parameters and the physiological index data of the staff to obtain target preprocessed data; Inputting the target preprocessed data into the target gradient boosting tree model to obtain a first risk assessment result; Determining a risk level based on the risk assessment results, and determining a target operation based on the risk level, including: A low risk level is determined according to the first risk assessment result, and an operation of issuing an alarm is determined according to the low risk level.

5. The construction engineering safety supervision method based on gradient boosting tree according to claim 1 is characterized in that: Inputting the behavior data of the on-site workers, the construction environment parameters and the physiological index data of the workers into the target gradient boosting tree model to obtain risk assessment results, including: Preprocessing the behavior data of the on-site staff, the construction environment parameters and the physiological index data of the staff to obtain target preprocessed data; Inputting the target preprocessed data into the target gradient boosting tree model to obtain a second risk assessment result; Determining a risk level based on the risk assessment results, and determining a target operation based on the risk level, including: The medium risk level is determined according to the second risk assessment result, and the risk information is sent to the management terminal according to the medium risk level, so that the management terminal sends the risk information to the management personnel.

6. The construction engineering safety supervision method based on gradient boosting tree according to claim 1 is characterized in that: Inputting the behavior data of the on-site workers, the construction environment parameters and the physiological index data of the workers into the target gradient boosting tree model to obtain risk assessment results, including: Preprocessing the behavior data of the on-site staff, the construction environment parameters and the physiological index data of the staff to obtain target preprocessed data; Inputting the target preprocessed data into the target gradient boosting tree model to obtain a third risk assessment result; Determining a risk level based on the risk assessment results, and determining a target operation based on the risk level, including: A high risk level is determined according to the third risk assessment result, and information is sent to an alarm center and a medical care center according to the high risk level.

7. The construction engineering safety supervision method based on gradient boosting tree according to claim 6 is characterized in that: After determining that the risk level is high according to the third risk assessment result, and sending information to the alarm center and the medical care center according to the high risk level, the method further includes: Obtaining the positioning position of the construction site and the positioning position of a target medical care center, wherein the target medical care center is a medical care center within a preset range that is closest to the construction site; Planning an optimal rescue route according to the location of the construction site and the location of the target medical center; When the ambulance vehicle terminal is identified, the optimal rescue route is sent to the ambulance vehicle terminal.

8. A construction engineering safety supervision system based on gradient boosting tree, characterized in that: The system comprises: A first acquisition unit is used to acquire historical data of the construction site, wherein the historical data includes historical construction environment parameters, historical construction personnel behavior data and physiological index data; A preprocessing unit, used for preprocessing the historical data to obtain preprocessed data; A second acquisition unit uses the preprocessed data to train a gradient boosting tree model to obtain a target gradient boosting tree model, wherein the target gradient boosting tree model is used to identify and predict the behavior of workers at the construction site and a potential dangerous environment; A collection unit, used to collect the behavior data, construction environment parameters and physiological index data of the workers on the construction site in real time; An input unit, used to input the behavior data of the on-site workers, the construction environment parameters and the physiological index data of the workers into the target gradient boosting tree model to obtain a risk assessment result; a determination unit, configured to determine a risk level according to the risk assessment result, and determine a target operation according to the risk level; An execution unit is used to implement safety supervision of the construction site through the target operation.

9. A construction engineering safety supervision device based on gradient boosting tree, characterized in that: The device comprises: Processor, memory, input-output unit, and bus; The processor is connected to the memory, the input and output unit, and the bus; The memory stores a program, and the processor calls the program to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a program stored thereon, wherein the program, when executed on a computer, performs the method according to any one of claims 1 to 7.

Images