Building service personnel scheduling method

Abstract

The invention discloses a building service personnel scheduling method, and relates to the technical field of building service personnel scheduling, and the method comprises the following steps: collecting building data through collection equipment, designing a smart bracelet, collecting building service personnel data, obtaining the completion degree of corresponding building service according to each piece of building service data, and obtaining the completion degree of the building service through a neural network algorithm. Building a building service progress monitoring model, obtaining a building service personnel scheduling result according to the building service personnel data in combination with the building service progress monitoring model, and building a building service personnel scheduling model by using a random forest algorithm; according to the method, the smart bracelet coding technology, the smart bracelet acquisition equipment technology and the big data processing technology are closely combined with the modern information technology, real-time and comprehensive monitoring of the building service progress is achieved, and the intelligent degree in the scheduling process of the building service personnel is remarkably enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of building service personnel scheduling, and particularly relates to a building service personnel scheduling method. Background Art

[0002] Under the background of the booming development of the current construction industry, the scale and complexity of construction projects are constantly increasing. Large construction projects often involve numerous building service personnel, and the number of building service personnel can reach hundreds or even thousands. Traditional building service personnel scheduling methods mostly rely on the experience of managers and on-site observations. However, this method has drawbacks. Facing the complex and changeable construction site, it is difficult for managers to comprehensively and timely grasp the information of all building service personnel. At the same time, the lack of scientific scheduling is likely to cause personnel idleness or overwork. In addition, the construction site environment is complex, and there are problems of untimely and inaccurate information transmission, which further exacerbates the chaos of building service personnel scheduling. Therefore, a building service personnel scheduling method has emerged as the times require; Although the existing technology has made great progress in the direction of building service personnel scheduling, there are still some problems to be optimized. It is difficult for the existing technology to monitor the construction progress in real time, combine the construction progress with the real-time working hours, real-time working status and real-time location of building service personnel, and schedule the work of building service personnel unreasonably, resulting in low work efficiency of building service personnel. Summary of the Invention

[0003] To achieve the above objectives, the present invention is realized through the following technical solutions: A building service personnel scheduling method, including the following steps: Step 1: Use acquisition devices to collect building data, design smart bracelets to collect building service personnel data, and preprocess the building data and building service personnel data to provide data support for the subsequent steps; Step 2: According to various building service data, obtain the completion degree of the corresponding building service. Among them, the completion degree of the building service includes the completion degree of building foundation excavation, the completion degree of pile hole pouring, the completion degree of wall masonry, and the completion degree of building site cleaning; Step 3: Use the neural network algorithm to construct a building service progress monitoring model to realize the monitoring of the completion degree of building services such as foundation excavation, pile hole pouring, wall masonry, and building site cleaning; Step 4: According to the building service personnel data, combined with the building service progress monitoring model, obtain the building service personnel scheduling result; Step 5: Use the random forest algorithm to construct a building service personnel scheduling model; Step 6: Combine the building service personnel scheduling model to schedule building service personnel, solving the problems in the prior art that it is difficult to monitor the building work progress in real time and schedule the work of building service personnel.

[0004] A further improvement of the technical solution of the present invention lies in: in the said Step 1, by using the acquisition device, designing an intelligent bracelet, the process of acquiring building data and building service personnel data includes: The acquisition device includes a sounding rod, a concrete liquid level sensor, a tripod, an industrial camera, an optical remote sensing satellite, and a multispectral camera; the building data includes the foundation excavation depth, the height of the concrete liquid level in the pile hole, the image of the wall masonry surface, and the satellite image of the building site; the building service personnel data includes the code of the building service personnel, the real-time working duration, the real-time working status, and the real-time positioning. Vertically place the sounding rod into the foundation excavation pit, read the scale value flush with the ground to obtain the foundation excavation depth; use the concrete liquid level sensor to collect the height of the concrete liquid level in the pile hole; use the tripod to fix the industrial camera at a position perpendicular to the center of the wall masonry surface, and collect the image of the wall masonry surface through the industrial camera; mount the multispectral camera on the optical remote sensing satellite, debug the focus, calibration, and parameter settings of the multispectral camera, and when the optical remote sensing satellite reaches the sky above the building site, obtain the satellite image of the building site through the multispectral camera. The intelligent bracelet includes a hardware part, a software part, a data transmission and storage part, and a background management part. Among them, the hardware part is composed of a main control chip, an acquisition module, a communication module, a power supply module, and a display and interaction module; the software part is composed of an operating system, a processing module, and a user interface; for the hardware part, select the STM32 chip as the main control chip, equip the acquisition module with a GPS locator, and equip the display and interaction module with an OLED display screen and physical buttons. Use the GPS locator in the intelligent bracelet to collect the real-time positioning of the building service personnel; code the building service personnel according to the order of their employment, and input the code of the building service personnel into the intelligent bracelet through data entry to obtain the code of the building service personnel; record the start work and end work times according to the pressing conditions of the start work button and the end work button, and switch the real-time working status of the building service personnel in real time to obtain the real-time working duration and real-time working status of the building service personnel, and the real-time working status includes an idle state and a busy state.

[0005] A further improvement of the technical solution of the present invention lies in: in the said Step 1, the process of preprocessing the building data and the building service personnel data includes: Perform data cleaning on the foundation excavation depth and the height of the concrete liquid level in the pile hole, remove outliers and duplicate values, grayscale the image of the wall masonry surface using the industrial camera, and perform Gaussian noise processing on the grayscale image of the wall masonry surface and the satellite image of the building site. Adopt mean filtering, calculate the average value of the pixels within the sliding window and replace the central pixel value, and perform Gaussian noise processing on the grayscale wall masonry surface image and the satellite image of the construction site.

[0006] A further improvement of the technical solution of the present invention lies in: in the second step, the process of obtaining the completion degree of the excavation of the building foundation and the completion degree of the pouring of the pile holes includes: Set the target foundation excavation depth of the building, calculate the proportion of the foundation excavation depth in the target foundation excavation depth of the building, and obtain the completion degree of the excavation of the building foundation; Set the pile top elevation, calculate the proportion of the height of the concrete liquid level in the pile hole in the pile top elevation, and obtain the completion degree of the pouring of the pile hole.

[0007] A further improvement of the technical solution of the present invention lies in: in the second step, the process of obtaining the completion degree of the wall masonry includes: According to the actual size of the reference object and the pixel size in the image, obtain the actual physical length represented by each pixel, use the Canny edge detection algorithm to extract the image edges of the wall surface and the wall masonry surface, utilize the extracted image edges of the wall surface to find the boundary points of the wall surface image, obtain the overall contour of the wall surface image, count the number of pixels in the overall contour of the wall surface image, calculate the square value of the actual physical length represented by each pixel, and obtain the total wall area through the product of the number of pixels in the overall contour of the wall surface image and the square value of the actual physical length represented by each pixel; Utilize the extracted image edges of the wall masonry surface to find the boundary points of the wall masonry surface image, obtain the overall contour of the wall masonry surface image, count the number of pixels in the overall contour of the wall masonry surface image, calculate the square value of the actual physical length represented by each pixel, obtain the wall masonry area through the product of the number of pixels in the overall contour of the wall masonry surface image and the square value of the actual physical length represented by each pixel, and obtain the completion degree of the wall masonry through the proportion of the wall masonry area in the total wall area.

[0008] A further improvement of the technical solution of the present invention lies in: in the second step, the process of obtaining the completion degree of the cleaning of the construction site includes: Utilize the Canny edge detection algorithm to identify the boundary of the construction site in the satellite image of the construction site, count the number of pixels within the area enclosed by the boundary, and convert the number of pixels within the area enclosed by the boundary into the total area of the construction site in combination with the spatial resolution of the satellite image of the construction site; Set the color threshold range of construction waste in the GIS software. Using the threshold segmentation function in the GIS software, based on the set color threshold range, extract the color areas in the satellite image of the construction site that are within the set color threshold range to obtain a binary image of the construction waste area. Use the area calculation tool in the GIS software to count the number of pixels in the binary image of the construction waste area. According to the spatial resolution of the satellite image of the construction site, convert the number of pixels in the binary image of the construction waste area into the area of the construction waste area. Obtain the cleaning completion degree of the construction site through the proportion of the area of the construction waste area in the total area of the construction site.

[0009] A further improvement of the technical solution of the present invention is that in step three, the process of constructing a building service progress monitoring model using a neural network algorithm includes: Using a neural network algorithm, construct a neural network model. Take the foundation excavation depth, the height of the concrete liquid level in the pile hole, the wall masonry area, the area of the construction waste area, the completion degree of the building foundation excavation, the completion degree of the pile hole pouring, the completion degree of the wall masonry, and the cleaning completion degree of the construction site as a data set, and divide it into a training set and a test set according to a ratio of 7:3. Select MLP as the neural network structure. The input layer includes four neurons, which receive the foundation excavation depth, the height of the concrete liquid level in the pile hole, the wall masonry area, and the area of the construction waste area. The hidden layer is configured with the MSE function. The output layer includes four neurons, which output the completion degree of the building foundation excavation, the completion degree of the pile hole pouring, the completion degree of the wall masonry, and the cleaning completion degree of the construction site. Input the training set data into the neural network model, set the learning rate to 0.01, and the number of iterative training times to 1000. The training process includes forward propagation and backward propagation. Among them, forward propagation is used to calculate the predicted output data, and backward propagation is used to update the weights and biases of the model. Through repeated iterative training, learn the non-linear relationship between the foundation excavation depth and the completion degree of the building foundation excavation, the non-linear relationship between the height of the concrete liquid level in the pile hole and the completion degree of the pile hole pouring, the non-linear relationship between the wall masonry area and the wall masonry area, and the non-linear relationship between the area of the construction waste area and the cleaning completion degree of the construction site until the set number of iterative training times is reached to obtain the trained neural network model. Input the test set data into the trained neural network model, use the MSE function to evaluate the error between the output value and the actual value of the neural network model, adjust the parameters of the neural network model according to the evaluation results, optimize the performance of the neural network model, and obtain the building service progress monitoring model.

[0010] A further improvement of the technical solution of the present invention is that in step four, the process of obtaining the building service personnel scheduling result according to the building service personnel data and combining the building service progress monitoring model includes: When the real-time working hours of building service personnel are less than 8 hours, the building service personnel are scheduled according to their real-time working status and real-time positioning; when the real-time working hours of building service personnel are equal to or greater than 8 hours, the building service personnel are not scheduled to work; Input the foundation excavation depth, the height of the concrete liquid level in the pile hole, the wall masonry area, and the construction waste area into the building service progress monitoring model, and the building service progress monitoring model outputs the completion degree of the corresponding building service; When the completion degree of the building service is less than 100%, schedule the building service personnel who are in the idle state and closest to the building service location according to the corresponding positioning to participate in the building service; when the completion degree of the building service reaches 100%, do not schedule the building service personnel to participate in the building service, and obtain the scheduling result of the building service personnel.

[0011] A further improvement of the technical solution of the present invention lies in: in the fifth step, the process of constructing a building service personnel scheduling model by using the random forest algorithm includes: Using the random forest algorithm, set the random forest model parameters, construct a random forest model, take the completion degree of the building service and its corresponding building service personnel scheduling result as a data set, divide it into a training set and a test set according to a ratio of 7:3, use the training set to train the random forest model, randomly extract samples from the training set, construct decision trees by using the randomly extracted samples, learn the non-linear relationship between the completion degree of the building service and the corresponding building service personnel scheduling result, and obtain a trained random forest model; Use the test set to evaluate the trained random forest model, evaluate the error between the building service personnel scheduling result output by the random forest model and the actual building service personnel scheduling result, adjust the random forest model parameters according to the evaluation result, optimize the performance of the random forest model, and obtain a building service personnel scheduling model.

[0012] A further improvement of the technical solution of the present invention lies in: in the sixth step, the process of scheduling building service personnel in combination with the building service personnel scheduling model includes: Input the completion degree of the building service into the building service personnel scheduling model to obtain the building service personnel scheduling result; When the completion degree of the building foundation excavation is less than 100%, schedule the building service personnel whose real-time working hours are less than 8 hours, are in the idle state, and are closest to the building foundation excavation location according to the corresponding positioning to carry out the foundation excavation work; when the completion degree of the building foundation excavation reaches 100%, do not schedule the building service personnel to carry out the foundation excavation work; When the completion degree of the pile hole pouring is less than 100%, dispatch the construction service personnel with a real-time working duration of less than 8 hours, in an idle state, and the closest located to the pile hole pouring site to carry out the pile hole pouring work; when the completion degree of the pile hole pouring reaches 100%, do not dispatch the construction service personnel to carry out the pile hole pouring work; When the completion degree of the wall masonry is less than 100%, dispatch the construction service personnel with a real-time working duration of less than 8 hours, in an idle state, and the closest located to the wall masonry site to carry out the wall masonry work; when the completion degree of the wall masonry reaches 100%, do not dispatch the construction service personnel to carry out the wall masonry work; When the completion degree of the building site cleaning is less than 100%, dispatch the construction service personnel with a real-time working duration of less than 8 hours, in an idle state, and the closest located to the construction waste area to carry out the building site cleaning work; when the completion degree of the building site cleaning reaches 100%, do not dispatch the construction service personnel to carry out the building site cleaning work.

[0013] The beneficial effects of the present invention are as follows: A method for dispatching construction service personnel. Compared with the traditional method for dispatching construction service personnel, the intelligent bracelet coding technology, intelligent bracelet acquisition device technology, and big data processing technology in the method of the present invention are closely combined with modern information technology to accurately capture construction data and construction service personnel data, obtain the completion degree of building foundation excavation, the completion degree of pile hole pouring, the completion degree of wall masonry, and the completion degree of building site cleaning, achieving real-time and comprehensive monitoring of the construction service progress. Through the neural network algorithm and the random forest algorithm, a construction service progress monitoring model and a construction service personnel dispatching model are respectively constructed, solving the problems in the prior art that it is difficult to monitor the construction work progress in real time, combining the construction work progress with the real-time working duration, real-time working status, and real-time positioning of construction service personnel, dispatching the work of construction service personnel, and the unreasonable dispatching of construction service personnel resulting in low work efficiency of construction service personnel, ensuring that the method in the present invention can be refined within a more accurate range for the dynamic monitoring standard of a method for dispatching construction service personnel, making the monitored data more accurate indicators under the same conditions. The research and application of this method significantly enhance the degree of intelligence in the process of dispatching construction service personnel. Description of the Drawings

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0015] Figure 1 It is a flowchart of a method for dispatching construction service personnel according to the present invention; Figure 2 It is a data flow logic diagram. Specific implementation manners

[0016] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0017] As Figure 1 shown, the present invention provides a method for scheduling construction service personnel, which consists of the following steps: Step 1: Use a collection device to collect construction data, design an intelligent bracelet to collect construction service personnel data, and preprocess the construction data and construction service personnel data to provide data support for the subsequent steps; Step 2: According to various construction service data, obtain the completion degree of the corresponding construction service. Among them, the completion degree of the construction service includes the completion degree of building foundation excavation, the completion degree of pile hole pouring, the completion degree of wall masonry, and the completion degree of construction site cleaning; Step 3: Use a neural network algorithm to construct a construction service progress monitoring model to realize the monitoring of the completion degree of construction services such as foundation excavation, pile hole pouring, wall masonry, and construction site cleaning; Step 4: According to the construction service personnel data and in combination with the construction service progress monitoring model, obtain the construction service personnel scheduling result; Step 5: Use a random forest algorithm to construct a construction service personnel scheduling model; Step 6: In combination with the construction service personnel scheduling model, schedule the construction service personnel, and solve the problems that it is difficult to monitor the construction work progress in real time and schedule the work of construction service personnel in the prior art.

[0018] Preferably, in Step 1, the process of using a collection device to design an intelligent bracelet to collect construction data and construction service personnel data includes: Among them, the collection device includes a sounding rod, a concrete liquid level sensor, a tripod, an industrial camera, an optical remote sensing satellite, and a multispectral camera; the construction data includes the foundation excavation depth, the concrete liquid level height in the pile hole, the wall masonry surface image, and the construction site satellite image; the construction service personnel data includes the code, real-time working hours, real-time working status, and real-time positioning of the construction service personnel; Place the depth gauge vertically into the foundation excavation pit, read the scale value flush with the ground, and obtain the foundation excavation depth; use a concrete level sensor to collect the height of the concrete liquid level in the pile hole; use a tripod to fix the industrial camera at a position perpendicular to the center of the wall masonry surface, and use the industrial camera to collect images of the wall masonry surface; carry a multispectral camera on the optical remote sensing satellite, debug the focus, calibration and parameter settings of the multispectral camera, and when the optical remote sensing satellite arrives over the construction site, use the multispectral camera to obtain satellite images of the construction site; The smart bracelet includes hardware, software, data transmission and storage, and background management. The hardware consists of a main control chip, an acquisition module, a communication module, a power module, and a display interaction module. The software consists of an operating system, a processing module, and a user interface. For the hardware, the STM32 chip is used as the main control chip, the acquisition module is equipped with a GPS locator, and the display interaction module is equipped with an OLED display and physical buttons. The GPS locator in the smart bracelet is used to collect the real-time location of the construction service personnel; the construction service personnel are coded according to their entry order, and the codes of the construction service personnel are input into the smart bracelet through data entry to obtain the codes of the construction service personnel; according to the pressing of the start work button and the end work button, the start and end work time are recorded, the work status of the construction service personnel is switched in real time, and the real-time working time and real-time working status of the construction service personnel are obtained, and the real-time working status includes idle status and busy status.

[0019] Preferably, in step 1, the process of preprocessing the building data and building service personnel data includes: Data cleaning was performed on the foundation excavation depth and the concrete liquid level in the pile hole to remove abnormal values ​​and duplicate values. The wall masonry surface image was grayscaled using an industrial camera, and Gaussian noise processing was performed on the grayscaled wall masonry surface image and the satellite image of the construction site. Mean filtering is used to calculate the average value of pixels in the sliding window to replace the central pixel value, and Gaussian noise processing is performed on the grayscale wall masonry surface image and the satellite image of the construction site.

[0020] Preferably, in step 2, the process of obtaining the degree of completion of the building foundation excavation and the degree of completion of the pile hole pouring includes: Set the target foundation excavation depth of the building, calculate the proportion of the foundation excavation depth in the target foundation excavation depth of the building, and obtain the completion degree of the building foundation excavation; Set the pile top elevation, calculate the ratio of the concrete liquid level in the pile hole to the pile top elevation, and obtain the completion degree of the pile hole pouring.

[0021] Preferably, in step 2, the process of obtaining the wall construction completion degree includes: According to the actual size of the reference object and the pixel size in the image, obtain the actual physical length represented by each pixel. Use the Canny edge detection algorithm to extract the image edges of the wall surface and the wall masonry surface. Utilize the extracted image edges of the wall surface to find the boundary points of the wall surface image, obtain the overall contour of the wall surface image, count the number of pixels in the overall contour of the wall surface image, calculate the square value of the actual physical length represented by each pixel, and obtain the total wall area through the product of the number of pixels in the overall contour of the wall surface image and the square value of the actual physical length represented by each pixel. Utilize the extracted image edges of the wall masonry surface to find the boundary points of the wall masonry surface image, obtain the overall contour of the wall masonry surface image, count the number of pixels in the overall contour of the wall masonry surface image, calculate the square value of the actual physical length represented by each pixel, obtain the wall masonry area through the product of the number of pixels in the overall contour of the wall masonry surface image and the square value of the actual physical length represented by each pixel, and obtain the wall masonry completion degree through the proportion of the wall masonry area in the total wall area.

[0022] Preferably, in step two, the process of obtaining the cleaning completion degree of the construction site includes: Use the Canny edge detection algorithm to identify the boundary of the construction site in the satellite image of the construction site, count the number of pixels within the area enclosed by the boundary, and convert the number of pixels within the area enclosed by the boundary into the total area of the construction site in combination with the spatial resolution of the satellite image of the construction site. Set the color threshold range of construction waste in the GIS software. Use the threshold segmentation function in the GIS software to extract the color area within the set color threshold range in the satellite image of the construction site based on the set color threshold range, obtain the binary image of the construction waste area. Use the area calculation tool in the GIS software to count the number of pixels in the binary image of the construction waste area, convert the number of pixels in the binary image of the construction waste area into the area of the construction waste area according to the spatial resolution of the satellite image of the construction site, and obtain the cleaning completion degree of the construction site through the proportion of the area of the construction waste area in the total area of the construction site.

[0023] Preferably, in step three, the process of constructing the construction service progress monitoring model using the neural network algorithm includes: Using the neural network algorithm, a neural network model is constructed. The foundation excavation depth, the height of the concrete liquid level in the pile hole, the masonry area of the wall, the area of the construction waste area, the completion degree of the foundation excavation of the building, the completion degree of the pile hole pouring, the completion degree of the wall masonry, and the completion degree of the building site cleaning are used as the data set, and are divided into a training set and a test set according to the ratio of 7:3. MLP is selected as the neural network structure. The input layer includes four neurons, which receive the foundation excavation depth, the height of the concrete liquid level in the pile hole, the masonry area of the wall, and the area of the construction waste area. The hidden layer is configured with the MSE function. The output layer includes four neurons, and outputs the completion degree of the foundation excavation of the building, the completion degree of the pile hole pouring, the completion degree of the wall masonry, and the completion degree of the building site cleaning; The training set data is input into the neural network model. The learning rate is set to 0.01, and the number of iterative training times is 1000. The training process includes forward propagation and backward propagation. Among them, forward propagation is used to calculate the predicted output data, and backward propagation is used to update the weights and biases of the model. By repeating the iterative training, learn the non-linear relationship between the foundation excavation depth and the completion degree of the building foundation excavation, the non-linear relationship between the height of the concrete liquid level in the pile hole and the completion degree of the pile hole pouring, the non-linear relationship between the masonry area of the wall and the masonry area of the wall, and the non-linear relationship between the area of the construction waste area and the completion degree of the building site cleaning, until the set number of iterative training times is reached, and obtain the trained neural network model; The test set data is input into the trained neural network model. Using the MSE function, evaluate the error between the output value and the actual value of the neural network model, adjust the parameters of the neural network model according to the evaluation results, optimize the performance of the neural network model, and obtain the building service progress monitoring model.

[0024] Preferably, in step four, the process of obtaining the building service personnel scheduling result according to the building service personnel data and combining the building service progress monitoring model includes: When the real-time working hours of the building service personnel are less than 8h, schedule the building service personnel to work according to their real-time working status and real-time location; when the real-time working hours of the building service personnel are equal to or greater than 8h, do not schedule the building service personnel to work; Input the foundation excavation depth, the height of the concrete liquid level in the pile hole, the masonry area of the wall, and the area of the construction waste area into the building service progress monitoring model, and the building service progress monitoring model outputs the completion degree of the corresponding building service; When the completion degree of the building service is less than 100%, schedule the building service personnel who are in the idle state and are closest to the building service location to participate in the building service; when the completion degree of the building service reaches 100%, do not schedule the building service personnel to participate in the building service, and obtain the building service personnel scheduling result.

[0025] Preferably, in step five, the process of constructing a building service personnel scheduling model using the random forest algorithm includes: Using the random forest algorithm, set the random forest model parameters, construct a random forest model, take the completion degree of building services and their corresponding building service personnel scheduling results as a data set, and divide it into a training set and a test set according to a ratio of 7:3. Use the training set to train the random forest model, randomly extract samples from the training set, construct decision trees using the randomly extracted samples, learn the non-linear relationship between the completion degree of building services and the corresponding building service personnel scheduling results, and obtain a trained random forest model; Use the test set to evaluate the trained random forest model, evaluate the error between the building service personnel scheduling results output by the random forest model and the actual building service personnel scheduling results, adjust the random forest model parameters according to the evaluation results, optimize the performance of the random forest model, and obtain a building service personnel scheduling model.

[0026] Preferably, in step six, the process of scheduling building service personnel in combination with the building service personnel scheduling model includes: Input the completion degree of building services into the building service personnel scheduling model to obtain the building service personnel scheduling results; When the completion degree of building foundation excavation is less than 100%, schedule building service personnel with a real-time working duration of less than 8 hours, in an idle state, and located closest to the building foundation excavation site to carry out foundation excavation work; when the completion degree of building foundation excavation reaches 100%, do not schedule building service personnel to carry out foundation excavation work; When the completion degree of pile hole pouring is less than 100%, schedule building service personnel with a real-time working duration of less than 8 hours, in an idle state, and located closest to the pile hole pouring site to carry out pile hole pouring work; when the completion degree of pile hole pouring reaches 100%, do not schedule building service personnel to carry out pile hole pouring work; When the completion degree of wall masonry is less than 100%, schedule building service personnel with a real-time working duration of less than 8 hours, in an idle state, and located closest to the wall masonry site to carry out wall masonry work; when the completion degree of wall masonry reaches 100%, do not schedule building service personnel to carry out wall masonry work; When the completion degree of building site cleaning is less than 100%, schedule building service personnel with a real-time working duration of less than 8 hours, in an idle state, and located closest to the construction waste area to carry out building site cleaning work; when the completion degree of building site cleaning reaches 100%, do not schedule building service personnel to carry out building site cleaning work.

[0027] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claimed rights.

Claims

1. A method for scheduling building service personnel, characterized in that: It includes the following steps: Step 1: Use the acquisition device to collect building data, design an intelligent bracelet to collect data of building service personnel, and preprocess the building data and the data of building service personnel; Step 2: According to various building service data, obtain the completion degree of the corresponding building service. Among them, the completion degree of the building service includes the completion degree of building foundation excavation, the completion degree of pile hole pouring, the completion degree of wall masonry, and the completion degree of building site cleaning; Step 3: Use the neural network algorithm to construct a building service progress monitoring model; Step 4: According to the data of building service personnel and in combination with the building service progress monitoring model, obtain the scheduling result of building service personnel; Step 5: Use the random forest algorithm to construct a building service personnel scheduling model; Step 6: In combination with the building service personnel scheduling model, schedule building service personnel.

2. The method for scheduling construction service personnel according to claim 1, wherein: In the said Step 1, the process of using the acquisition device to design an intelligent bracelet to collect building data and the data of building service personnel includes: The acquisition device includes a sounding rod, a concrete liquid level sensor, a tripod, an industrial camera, an optical remote sensing satellite, and a multispectral camera; the building data includes the foundation excavation depth, the height of the concrete liquid level in the pile hole, the wall masonry surface image, and the building site satellite image; the data of building service personnel includes the code, real-time working hours, real-time working status, and real-time positioning of building service personnel; Vertically place the sounding rod into the foundation excavation pit, read the scale value flush with the ground to obtain the foundation excavation depth; use the concrete liquid level sensor to collect the height of the concrete liquid level in the pile hole; use the tripod to fix the industrial camera at a position perpendicular to the center of the wall masonry surface, and collect the wall masonry surface image through the industrial camera; install the multispectral camera on the optical remote sensing satellite, debug the focus, calibration, and parameter settings of the multispectral camera, and when the optical remote sensing satellite reaches the sky above the building site, obtain the building site satellite image through the multispectral camera; Use the GPS locator in the intelligent bracelet to collect the real-time positioning of building service personnel; code the building service personnel according to the order of their employment, input the code of the building service personnel into the intelligent bracelet through data entry to obtain the code of the building service personnel; record the start and end working times according to the pressing conditions of the start work button and the end work button, and switch the real-time working status of building service personnel in real time to obtain the real-time working hours and real-time working status of building service personnel. The real-time working status includes the idle state and the busy state.

3. The method for scheduling building service personnel according to claim 2, characterized in that: In the said Step 1, the process of preprocessing the building data and the data of building service personnel includes: Perform data cleaning on the foundation excavation depth and the height of the concrete liquid level in the pile hole, remove outliers and duplicate values, grayscale the wall masonry surface image using the industrial camera, and perform Gaussian noise processing on the grayscaled wall masonry surface image and the building site satellite image; Adopt mean filtering, calculate the average value of the pixels within the sliding window to replace the central pixel value, and perform Gaussian noise processing on the grayscaled wall masonry surface image and the building site satellite image.

4. A building service personnel scheduling method according to claim 3, characterized in that: In the said Step 2, the process of obtaining the completion degree of building foundation excavation and the completion degree of pile hole pouring includes: Set the target foundation excavation depth of the building, calculate the proportion of the foundation excavation depth in the target foundation excavation depth of the building, and obtain the completion degree of the building foundation excavation; Set the pile top elevation, calculate the proportion of the concrete liquid level height in the pile hole in the pile top elevation, and obtain the completion degree of the pile hole pouring.

5. The method for scheduling construction service personnel according to claim 4, wherein: In the second step, the process of obtaining the completion degree of wall masonry includes: According to the actual size of the reference object and the pixel size in the image, obtain the actual physical length represented by each pixel. Use the Canny edge detection algorithm to extract the image edges of the wall surface and the wall masonry surface. Utilize the extracted image edge of the wall surface to find the boundary points of the wall surface image, obtain the overall contour of the wall surface image, count the number of pixels in the overall contour of the wall surface image, calculate the square value of the actual physical length represented by each pixel, and obtain the total wall area through the product of the number of pixels in the overall contour of the wall surface image and the square value of the actual physical length represented by each pixel; Utilize the extracted image edge of the wall masonry surface to find the boundary points of the wall masonry surface image, obtain the overall contour of the wall masonry surface image, count the number of pixels in the overall contour of the wall masonry surface image, calculate the square value of the actual physical length represented by each pixel, obtain the wall masonry area through the product of the number of pixels in the overall contour of the wall masonry surface image and the square value of the actual physical length represented by each pixel, and obtain the completion degree of wall masonry through the proportion of the wall masonry area in the total wall area.

6. The method for scheduling building service personnel according to claim 5, wherein: In the second step, the process of obtaining the completion degree of building site cleaning includes: Use the Canny edge detection algorithm to identify the boundary of the building site in the satellite image of the building site, count the number of pixels within the area enclosed by the boundary, and convert the number of pixels within the area enclosed by the boundary into the total area of the building site in combination with the spatial resolution of the satellite image of the building site; Set the color threshold range of construction waste in the GIS software. Use the threshold segmentation function in the GIS software to extract the color area within the set color threshold range in the satellite image of the building site based on the set color threshold range, obtain the binary image of the construction waste area. Use the area calculation tool in the GIS software to count the number of pixels in the binary image of the construction waste area, convert the number of pixels in the binary image of the construction waste area into the area of the construction waste area according to the spatial resolution of the satellite image of the building site, and obtain the completion degree of building site cleaning through the proportion of the area of the construction waste area in the total area of the building site.

7. A method for scheduling construction service personnel according to claim 6, characterized in that: In the third step, the process of constructing a building service progress monitoring model using the neural network algorithm includes: Using the neural network algorithm, a neural network model is constructed. The foundation excavation depth, the height of the concrete liquid level in the pile hole, the masonry area of the wall, the area of the construction waste area, the completion degree of the foundation excavation of the building, the completion degree of the pile hole pouring, the completion degree of the wall masonry, and the completion degree of the construction site cleaning are used as the data set, and are divided into a training set and a test set according to a ratio of 7:

3. MLP is selected as the neural network structure. The input layer includes four neurons, which receive the foundation excavation depth, the height of the concrete liquid level in the pile hole, the masonry area of the wall, and the area of the construction waste area. The hidden layer is configured with the MSE function. The output layer includes four neurons, and outputs the completion degree of the foundation excavation of the building, the completion degree of the pile hole pouring, the completion degree of the wall masonry, and the completion degree of the construction site cleaning; The training set data is input into the neural network model. The learning rate is set to 0.01, and the number of iterative training times is 1000. The training process includes forward propagation and backward propagation. Among them, forward propagation is used to calculate the predicted output data, and backward propagation is used to update the weights and biases of the model. By repeating the iterative training, learn the non-linear relationship between the foundation excavation depth and the completion degree of the foundation excavation of the building, the non-linear relationship between the height of the concrete liquid level in the pile hole and the completion degree of the pile hole pouring, the non-linear relationship between the masonry area of the wall and the masonry area of the wall, and the non-linear relationship between the area of the construction waste area and the completion degree of the construction site cleaning, until the set number of iterative training times is reached, and obtain the trained neural network model; The test set data is input into the trained neural network model. Using the MSE function, evaluate the error between the output value and the actual value of the neural network model, adjust the parameters of the neural network model according to the evaluation results, optimize the performance of the neural network model, and obtain the building service progress monitoring model.

8. A method for scheduling construction service personnel according to claim 7, characterized in that: In the fourth step described above, the process of obtaining the building service personnel scheduling result according to the building service personnel data and combining the building service progress monitoring model includes: When the real-time working hours of the building service personnel are less than 8h, schedule the work of the building service personnel according to their real-time working status and real-time location; when the real-time working hours of the building service personnel are equal to or greater than 8h, do not schedule the work of the building service personnel; Input the foundation excavation depth, the height of the concrete liquid level in the pile hole, the masonry area of the wall, and the area of the construction waste area into the building service progress monitoring model, and the building service progress monitoring model outputs the completion degree of the corresponding building service; When the completion degree of the building service is less than 100%, schedule the building service personnel who are in the idle state and are closest to the building service location to participate in the building service; when the completion degree of the building service reaches 100%, do not schedule the building service personnel to participate in the building service, and obtain the building service personnel scheduling result.

9. A method for scheduling building service personnel according to claim 8, characterized in that: In the fifth step described above, the process of constructing the building service personnel scheduling model using the random forest algorithm includes: Using the random forest algorithm, set the parameters of the random forest model, construct the random forest model, take the completion degree of the building service and its corresponding building service personnel scheduling results as the data set, and divide it into a training set and a test set according to the ratio of 7:

3. Use the training set to train the random forest model, randomly extract samples from the training set, construct decision trees using the randomly extracted samples, learn the non-linear relationship between the completion degree of the building service and the corresponding building service personnel scheduling results, and obtain the trained random forest model; Use the test set to evaluate the trained random forest model, evaluate the error between the building service personnel scheduling results output by the random forest model and the actual building service personnel scheduling results, adjust the random forest model parameters according to the evaluation results, optimize the performance of the random forest model, and obtain the building service personnel scheduling model.

10. A method for scheduling building service personnel according to claim 9, characterized in that: In step six mentioned above, the process of scheduling building service personnel in combination with the building service personnel scheduling model includes: Input the completion degree of the building service into the building service personnel scheduling model to obtain the building service personnel scheduling results; When the completion degree of the building foundation excavation is less than 100%, schedule the building service personnel with a real-time working duration of less than 8 hours, in an idle state and located closest to the building foundation excavation site to carry out the foundation excavation work; when the completion degree of the building foundation excavation reaches 100%, do not schedule building service personnel to carry out the foundation excavation work; When the completion degree of the pile hole pouring is less than 100%, schedule the building service personnel with a real-time working duration of less than 8 hours, in an idle state and located closest to the pile hole pouring site to carry out the pile hole pouring work; when the completion degree of the pile hole pouring reaches 100%, do not schedule building service personnel to carry out the pile hole pouring work; When the completion degree of the wall masonry is less than 100%, schedule the building service personnel with a real-time working duration of less than 8 hours, in an idle state and located closest to the wall masonry site to carry out the wall masonry work; when the completion degree of the wall masonry reaches 100%, do not schedule building service personnel to carry out the wall masonry work; When the completion degree of the building site cleaning is less than 100%, schedule the building service personnel with a real-time working duration of less than 8 hours, in an idle state and located closest to the construction waste area to carry out the building site cleaning work; when the completion degree of the building site cleaning reaches 100%, do not schedule building service personnel to carry out the building site cleaning work.

Images