Building service resource optimization method

Abstract

The invention discloses a building service resource optimization method, and relates to the technical field of building service resource optimization, and the method comprises the following steps: collecting the skill questionnaire data of building service personnel, designing an Internet of Things inventory collection module, collecting the real-time inventory data of building materials, and obtaining the scheduling result of the building service personnel according to the type of the building service personnel. According to the stock threshold values of the various building materials, obtaining allocation results of the various building materials, and constructing a building service personnel scheduling model by adopting a convolutional neural network algorithm; according to the method, a questionnaire survey technology, an Internet of Things acquisition technology, a neural network algorithm modeling technology and a genetic algorithm optimization technology are closely combined with a modern information technology, a building service resource allocation model is constructed by using a neural network algorithm, and the building service resource allocation model is optimized by using a genetic algorithm. The skill of the building service personnel and the stock of the building materials are monitored in real time, and the intelligent degree in the building service resource management process is remarkably enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of building service resource optimization, and in particular to a building service resource optimization method. Background Art

[0002] Under the traditional construction service resource management model, information flow is poor, making it difficult for all parties involved to share resource dynamics in real time. At the same time, human resource allocation relies heavily on experience and judgment, and cannot be flexibly adjusted according to the real-time progress of the project. This leads to idle personnel in some trades and insufficient staff in key positions. Different construction projects have huge differences in resource requirements at different stages, and traditional methods are unable to quickly respond to and adapt to such dynamic changes. As the construction industry continues to increase its requirements for quality, construction period and cost control, there is an urgent need for a construction service resource optimization method that breaks down information barriers and achieves accurate allocation, efficient utilization and dynamic adjustment of resources to improve the overall efficiency and competitiveness of construction projects. Although existing technologies have made great progress in the direction of optimizing construction service resources, there are still some problems that need to be optimized. Existing technologies make it difficult to classify construction service personnel according to their skills and assign construction service personnel in each category to corresponding positions, which makes the work efficiency of construction service personnel low and causes waste of human resources in the construction service process; moreover, traditional construction service resource optimization methods make it difficult to monitor the inventory of construction materials in real time, and lack the allocation of construction material inventory, resulting in waste of material resources in the construction service process. Summary of the Invention

[0003] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for optimizing building service resources, comprising the following steps: Step 1: Collect data on the skills of construction service personnel through questionnaire surveys, design an IoT inventory collection module, and collect real-time inventory data of construction materials, providing data support for subsequent steps; Step 2: Pre-process the construction service personnel skills questionnaire data and the real-time inventory data of building materials, classify the construction service personnel into categories, and set the thresholds for the real-time inventory data of various types of building materials; Step 3: Obtain construction service personnel scheduling results based on construction service personnel categories; obtain construction material allocation results using various construction material inventory thresholds; Step 4: Use the convolutional neural network algorithm to build a construction service personnel scheduling model; use the neural network algorithm to build a construction service resource allocation model; Step 5: Optimize the construction service resource allocation model using genetic algorithms; Step 6. Combining the construction service personnel scheduling model with the optimized construction service resource allocation model, the construction service personnel are scheduled and various types of construction materials are allocated. This solves the problem that the existing technology is difficult to assign jobs according to the skills of construction service personnel and difficult to monitor the inventory status of construction materials in real time and allocate the inventory of construction materials.

[0004] A further improvement of the technical solution of the present invention is that in step 1, the process of collecting questionnaire data on construction service personnel skills through a questionnaire survey includes: Use Wenjuanxing to set up questionnaire questions. The questionnaire questions include two questions. The first question is the construction service personnel number; the second question is the type of work they are engaged in, with ten options, namely carpenter, bricklayer, reinforcement worker, electrician, welder, scaffolder, painter, waterproofer, crane operator and installer; the questionnaire questions are sent to the mobile phone of each construction service personnel through Wenjuanxing, and the construction service personnel fill in the answers to the questionnaire to obtain the construction service personnel skill questionnaire data.

[0005] A further improvement of the technical solution of the present invention is that in step 1, an IoT inventory collection module is designed, and the process of collecting real-time inventory data of building materials includes: The IoT acquisition module includes a hardware unit and a software unit. The hardware unit consists of a weight sensor, a laser distance sensor, a liquid level sensor, an RFID reader / writer, a QR code scanner, and a data acquisition terminal. The software unit consists of data acquisition software, a cloud server software, and a mobile application. According to the measurement method of building materials, building materials are divided into weight building materials, liquid building materials, volume building materials, length building materials and quantity building materials; The real-time inventory data of building materials includes the real-time weight of weight-based building materials, the real-time liquid level height of liquid-based building materials, the real-time length of length-based building materials, the real-time volume of volume-based building materials and the real-time number of quantity-based building materials; The weight sensor in the Internet of Things inventory collection module is used to collect the real-time weight of weight-type building materials; the liquid level sensor in the Internet of Things inventory collection module is used to collect the real-time liquid level height of liquid-type building materials; the laser ranging sensor in the Internet of Things inventory collection module is used to collect the real-time length of length-type building materials; the laser ranging sensor in the Internet of Things inventory collection module is used to measure the real-time length, real-time width and real-time height of volume-type building materials, and the real-time volume of volume-type building materials is calculated using the volume formula; an RFID tag and a QR code are attached to each quantity-type building material, and the real-time number of quantity-type building materials entering the warehouse and the real-time number of quantity-type building materials leaving the warehouse are recorded respectively through the RFID reader and the QR code scanning device, and the real-time number of quantity-type building materials entering the warehouse and the real-time number of quantity-type building materials leaving the warehouse are obtained by calculating the difference between the real-time number of quantity-type building materials entering the warehouse and the real-time number of quantity-type building materials leaving the warehouse.

[0006] A further improvement of the technical solution of the present invention is that in step 2, the process of pre-processing the construction service personnel skill questionnaire data and the real-time inventory data of building materials, classifying construction service personnel, and setting thresholds for the real-time inventory data of various types of building materials includes: Data cleaning was performed on the construction service personnel skills questionnaire data and the real-time inventory data of construction materials to remove duplicate values and outliers; According to the skills questionnaire data of construction service personnel, construction service personnel are divided into carpenters, bricklayers, steel workers, electricians, welders, scaffolders, painters, waterproofers, crane operators and installers; According to the demand for building material resources in construction services, the lower and upper thresholds for the weight of weight-type building materials, the lower and upper thresholds for the liquid level height of liquid-type building materials, the lower and upper thresholds for the length of length-type building materials, the lower and upper thresholds for the volume of volume-type building materials, and the lower and upper thresholds for the number of quantity-type building materials are set respectively.

[0007] A further improvement of the technical solution of the present invention is that in step 3, the process of obtaining the construction service personnel scheduling result according to the construction service personnel category includes: Based on the skill questionnaire data and construction service personnel categories of construction service personnel, a construction service personnel information database is established to record the category and number of each construction service personnel. Through a greedy algorithm, priorities are set for construction service jobs according to the progress and importance of construction tasks. According to the categories of construction service personnel and in the order of the priorities of construction service jobs, personnel matching the categories of construction service personnel are dispatched to the corresponding jobs in turn to obtain the construction service personnel scheduling results.

[0008] A further improvement of the technical solution of the present invention is that in step 3, the process of obtaining the building material allocation results by using the inventory thresholds of various building materials includes: When the real-time weight of the weight-type building materials is lower than the lower limit threshold of the weight of the weight-type building materials, it indicates that the weight-type building materials are insufficient in stock; when the real-time weight of the weight-type building materials is higher than the upper limit threshold of the weight of the weight-type building materials, it indicates that the weight-type building materials are redundant in stock; When the real-time liquid level of the liquid building material is lower than the lower limit threshold of the liquid building material, it indicates that the inventory of the liquid building material is insufficient; when the real-time liquid level of the liquid building material is higher than the upper limit threshold of the liquid building material, it indicates that the inventory of the liquid building material is redundant; When the real-time length of the length-type building materials is lower than the lower limit threshold of the length of the length-type building materials, it indicates that the inventory of the length-type building materials is insufficient; when the real-time length of the length-type building materials is higher than the upper limit threshold of the length of the length-type building materials, it indicates that the inventory of the length-type building materials is redundant; When the real-time volume of the volumetric building materials is lower than the lower limit threshold of the volume of the volumetric building materials, it indicates that the volumetric building materials are insufficient in stock; when the real-time volume of the volumetric building materials is higher than the upper limit threshold of the volume of the volumetric building materials, it indicates that the volumetric building materials are redundant in stock; When the real-time number of quantity-based building materials is lower than the lower limit threshold of the number of quantity-based building materials, it indicates that the inventory of quantity-based building materials is insufficient; when the real-time number of quantity-based building materials is higher than the upper limit threshold of the number of quantity-based building materials, it indicates that the inventory of quantity-based building materials is redundant; Through the above process, the building material allocation results are obtained, and the building material allocation results include weight-based building material allocation results, liquid-based building material allocation results, length-based building material allocation results, volume-based building material allocation results, and quantity-based building material allocation results.

[0009] A further improvement of the technical solution of the present invention is that in step 4, the process of using a convolutional neural network algorithm to construct a construction service personnel scheduling model includes: The building service personnel categories and their corresponding dispatch results are used as a data set, which is divided into a training set and a test set in a ratio of 7:3. The convolutional neural network algorithm is used to design a convolutional neural network architecture. The convolutional neural network architecture consists of an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. Ten input channels are set in the input layer to input the building service personnel categories, and ten output channels are set in the output layer to output the corresponding building service personnel dispatch results. The convolutional neural network model is constructed. The training set data is input into the convolutional neural network model, the output value of the convolutional neural network is calculated through forward propagation, the gradient is calculated through backpropagation, the parameters of the convolutional neural network model are updated according to the gradient, the nonlinear relationship between the building service personnel category and its corresponding dispatch result is learned, and the trained convolutional neural network model is obtained; Input the test set data into the trained convolutional neural network model, compare the output results of the convolutional neural network model with the actual construction service personnel scheduling results, evaluate the performance of the trained convolutional neural network model, adjust the convolutional neural network model parameters, optimize the convolutional neural network model, and obtain the construction service personnel scheduling model.

[0010] A further improvement of the technical solution of the present invention is that in step 4, the process of constructing a building service resource allocation model using a neural network algorithm includes: A neural network model is constructed by using a neural network algorithm. The real-time weight of weight-type building materials and their corresponding allocation results, the real-time liquid level height of liquid-type building materials and their corresponding allocation results, the real-time length of length-type building materials and their corresponding allocation results, the real-time volume of volume-type building materials and their corresponding allocation results, and the real-time number of quantity-type building materials and their corresponding allocation results are used as data sets, which are divided into training set and test set in a ratio of 7:3. MLP is selected as the neural network structure. The input layer includes five neurons, which receives the real-time weight of weight-type building materials, the real-time liquid level height of liquid-type building materials, the real-time length of length-type building materials, the real-time volume of volume-type building materials, and the real-time number of quantity-type building materials. The hidden layer is configured with an MSE function. The output layer includes five neurons, which outputs the allocation results of weight-type building materials, liquid-type building materials, length-type building materials, volume-type building materials, and quantity-type building materials. 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 back propagation, wherein the forward propagation is used to calculate the predicted output data, and the back propagation is used to update the weights and biases of the model. Through repeated iterative training, the nonlinear relationship between the real-time weight of weight-type building materials and the allocation results of weight-type building materials, the nonlinear relationship between the real-time liquid level height of liquid-type building materials and the allocation results of liquid-type building materials, the nonlinear relationship between the real-time length of length-type building materials and the allocation results of length-type building materials, the nonlinear relationship between the real-time volume of volume-type building materials and the allocation results of volume-type building materials, and the nonlinear relationship between the real-time number of quantity-type building materials and the allocation results of quantity-type building materials are learned until the set number of iterative training times is reached, and the trained neural network model is obtained; The test set data is input into the trained neural network model, and the MSE function is used to evaluate the error between the output value of the neural network model and the actual value. The parameters of the neural network model are adjusted according to the evaluation results to obtain the building service resource optimization model.

[0011] A further improvement of the technical solution of the present invention is that: in step 5, the process of optimizing the construction service resource allocation model by using genetic algorithm includes: Encode the input data and output data of the building service resource optimization model, assign input codes 1, 2, 3, 4, 5, and 6 to the building service personnel category, the real-time weight of weight-type building materials, the real-time liquid level height of liquid-type building materials, the real-time length of length-type building materials, the real-time volume of volume-type building materials, and the real-time number of quantity-type building materials respectively; and assign output codes A, B, C, D, E, and F to the building service personnel scheduling results, the allocation results of weight-type building materials, the allocation results of liquid-type building materials, the allocation results of length-type building materials, the allocation results of volume-type building materials, and the allocation results of quantity-type building materials respectively; According to the scale of the building service resource optimization model, an initial population is randomly generated, which consists of n individuals. The codes of the n individuals correspond to the input data and output data of the building service resource optimization model, and a fitness function is constructed to evaluate the fitness of each individual. Through the roulette wheel selection method, individuals are selected from the current population to form the next generation population according to individual fitness. Two individuals are randomly selected from the next generation population. According to the crossover probability, the coding position is selected to cross and generate two new individuals. The individual coding position is randomly selected, the coding value of the coding position is changed, and the individuals are compiled. The individuals after selection, crossover and mutation operations are composed of a new population to replace the previous generation. The number of iterations is set, and the selection, crossover and mutation operations are repeated on the population until the number of iterations is reached to optimize the building service resource optimization model.

[0012] A further improvement of the technical solution of the present invention is that in step 6, the process of scheduling construction service personnel and allocating various types of construction materials by combining the construction service personnel scheduling model with the optimized construction service resource allocation model includes: Input the building service personnel category into the building service personnel scheduling model, and the building service personnel scheduling model outputs the corresponding building service personnel scheduling results. According to the building service personnel scheduling results, the corresponding building service personnel are dispatched to the corresponding job positions; The real-time data of various types of building materials are input into the optimized construction service resource allocation model to obtain the allocation results of various types of building materials. Based on the building material allocation results, when the inventory of building materials is insufficient, the building materials are purchased to replenish the inventory of corresponding building materials; when the inventory of building materials is redundant, the construction service order is adjusted to give priority to the use of this type of building materials.

[0013] The beneficial effects of the present invention are as follows: a construction service resource optimization method. Compared with traditional construction service resource optimization methods, the questionnaire survey technology, Internet of Things collection technology, convolutional neural network algorithm modeling technology, neural network algorithm modeling technology and genetic algorithm optimization technology in the method of the present invention are closely integrated with modern information technology, accurately capturing construction service personnel skill questionnaire data and real-time building material inventory data, achieving real-time and comprehensive monitoring of construction service personnel skills and building material inventory. A convolutional neural network algorithm is used to construct a construction service personnel scheduling model, a neural network algorithm is used to construct a construction service resource allocation model, and a genetic algorithm optimization technology is used to optimize the construction service resource allocation model, thereby improving the performance of the construction service resource allocation model. This solves the problems that traditional methods are difficult to classify personnel according to construction service personnel skills and reasonably allocate positions, and are difficult to monitor and allocate building material inventory in real time, resulting in waste of human resources and material resources. This ensures that the method of the present invention can refine the dynamic monitoring standards for construction service resource optimization within a more precise range, making the monitored data a more accurate indicator under the same conditions. The development and application of this method significantly enhances the level of intelligence in the construction service resource management process. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0015] Figure 1 A flow chart of a construction service resource optimization method according to the present invention; Figure 2 This is a logical diagram of data flow. DETAILED DESCRIPTION

[0016] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0017] like Figure 1 As shown, the present invention provides a construction service resource optimization method, which consists of the following steps: Step 1: Collect data on the skills of construction service personnel through questionnaire surveys, design an IoT inventory collection module, and collect real-time inventory data of construction materials, providing data support for subsequent steps; Step 2: Pre-process the construction service personnel skills questionnaire data and the real-time inventory data of building materials, classify the construction service personnel into categories, and set the thresholds for the real-time inventory data of various types of building materials; Step 3: Obtain construction service personnel scheduling results based on construction service personnel categories; obtain construction material allocation results using various construction material inventory thresholds; Step 4: Use the convolutional neural network algorithm to build a construction service personnel scheduling model; use the neural network algorithm to build a construction service resource allocation model; Step 5: Optimize the construction service resource allocation model using genetic algorithms; Step 6. Combining the construction service personnel scheduling model with the optimized construction service resource allocation model, the construction service personnel are scheduled and various types of construction materials are allocated. This solves the problem that the existing technology is difficult to assign jobs according to the skills of construction service personnel and difficult to monitor the inventory status of construction materials in real time and allocate the inventory of construction materials.

[0018] Preferably, in step 1, the process of designing an IoT inventory collection module to collect real-time inventory data of building materials includes: The IoT acquisition module includes a hardware unit and a software unit. The hardware unit consists of a weight sensor, a laser ranging sensor, a liquid level sensor, an RFID reader / writer, a QR code scanner, and a data acquisition terminal. The software unit consists of data acquisition software, a cloud server software, and a mobile application. According to the measurement method of building materials, building materials are divided into weight building materials, liquid building materials, volume building materials, length building materials and quantity building materials; The real-time inventory data of building materials includes the real-time weight of weight-based building materials, the real-time liquid level of liquid-based building materials, the real-time length of length-based building materials, the real-time volume of volume-based building materials, and the real-time number of quantity-based building materials. The weight sensor in the Internet of Things inventory collection module is used to collect the real-time weight of weight-type building materials; the liquid level sensor in the Internet of Things inventory collection module is used to collect the real-time liquid level height of liquid-type building materials; the laser ranging sensor in the Internet of Things inventory collection module is used to collect the real-time length of length-type building materials; the laser ranging sensor in the Internet of Things inventory collection module is used to measure the real-time length, real-time width and real-time height of volume-type building materials, and the real-time volume of volume-type building materials is calculated using the volume formula; an RFID tag and a QR code are attached to each quantity-type building material, and the real-time number of quantity-type building materials entering the warehouse and the real-time number of quantity-type building materials leaving the warehouse are recorded respectively through the RFID reader and the QR code scanning device, and the real-time number of quantity-type building materials entering the warehouse and the real-time number of quantity-type building materials leaving the warehouse are obtained by calculating the difference between the real-time number of quantity-type building materials entering the warehouse and the real-time number of quantity-type building materials leaving the warehouse.

[0019] Preferably, in step 2, the process of pre-processing the construction service personnel skill questionnaire data and the real-time inventory data of construction materials, classifying the construction service personnel into categories, and setting thresholds for the real-time inventory data of various types of construction materials includes: Data cleaning was performed on the construction service personnel skills questionnaire data and the real-time inventory data of construction materials to remove duplicate values and outliers; According to the skills questionnaire data of construction service personnel, construction service personnel are divided into carpenters, bricklayers, steel workers, electricians, welders, scaffolders, painters, waterproofers, crane operators and installers; According to the demand for building material resources in construction services, the lower and upper thresholds for the weight of weight-type building materials, the lower and upper thresholds for the liquid level height of liquid-type building materials, the lower and upper thresholds for the length of length-type building materials, the lower and upper thresholds for the volume of volume-type building materials, and the lower and upper thresholds for the number of quantity-type building materials are set respectively.

[0020] Preferably, in step 3, the process of obtaining the construction service personnel scheduling result according to the construction service personnel category includes: Based on the skill questionnaire data and construction service personnel categories of construction service personnel, a construction service personnel information database is established to record the category and number of each construction service personnel. Through a greedy algorithm, priorities are set for construction service jobs according to the progress and importance of construction tasks. According to the categories of construction service personnel and in the order of the priorities of construction service jobs, personnel matching the categories of construction service personnel are dispatched to the corresponding jobs in turn to obtain the construction service personnel scheduling results.

[0021] Preferably, in step 3, the process of obtaining the building material allocation results by using the inventory thresholds of various building materials includes: When the real-time weight of the weight-type building materials is lower than the lower limit threshold of the weight of the weight-type building materials, it indicates that the weight-type building materials are insufficient in stock; when the real-time weight of the weight-type building materials is higher than the upper limit threshold of the weight of the weight-type building materials, it indicates that the weight-type building materials are redundant in stock; When the real-time liquid level of the liquid building material is lower than the lower limit threshold of the liquid building material, it indicates that the inventory of the liquid building material is insufficient; when the real-time liquid level of the liquid building material is higher than the upper limit threshold of the liquid building material, it indicates that the inventory of the liquid building material is redundant; When the real-time length of the length-type building materials is lower than the lower limit threshold of the length of the length-type building materials, it indicates that the inventory of the length-type building materials is insufficient; when the real-time length of the length-type building materials is higher than the upper limit threshold of the length of the length-type building materials, it indicates that the inventory of the length-type building materials is redundant; When the real-time volume of the volumetric building materials is lower than the lower limit threshold of the volume of the volumetric building materials, it indicates that the volumetric building materials are insufficient in stock; when the real-time volume of the volumetric building materials is higher than the upper limit threshold of the volume of the volumetric building materials, it indicates that the volumetric building materials are redundant in stock; When the real-time number of quantity-based building materials is lower than the lower limit threshold of the number of quantity-based building materials, it indicates that the inventory of quantity-based building materials is insufficient; when the real-time number of quantity-based building materials is higher than the upper limit threshold of the number of quantity-based building materials, it indicates that the inventory of quantity-based building materials is redundant; Through the above process, the building material allocation results are obtained, and the building material allocation results include weight-based building material allocation results, liquid-based building material allocation results, length-based building material allocation results, volume-based building material allocation results, and quantity-based building material allocation results.

[0022] Preferably, in step 4, the process of using a convolutional neural network algorithm to construct a construction service personnel scheduling model includes: The building service personnel categories and their corresponding dispatch results are used as a data set, which is divided into a training set and a test set in a ratio of 7:3. The convolutional neural network algorithm is used to design a convolutional neural network architecture. The convolutional neural network architecture consists of an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. Ten input channels are set in the input layer to input the building service personnel categories, and ten output channels are set in the output layer to output the corresponding building service personnel dispatch results. The convolutional neural network model is constructed. The training set data is input into the convolutional neural network model, the output value of the convolutional neural network is calculated through forward propagation, the gradient is calculated through backpropagation, the parameters of the convolutional neural network model are updated according to the gradient, the nonlinear relationship between the building service personnel category and its corresponding dispatch result is learned, and the trained convolutional neural network model is obtained; Input the test set data into the trained convolutional neural network model, compare the output results of the convolutional neural network model with the actual construction service personnel scheduling results, evaluate the performance of the trained convolutional neural network model, adjust the convolutional neural network model parameters, optimize the convolutional neural network model, and obtain the construction service personnel scheduling model.

[0023] Preferably, in step 4, the process of constructing a construction service resource allocation model using a neural network algorithm includes: A neural network model is constructed by using a neural network algorithm. The real-time weight of weight-type building materials and their corresponding allocation results, the real-time liquid level height of liquid-type building materials and their corresponding allocation results, the real-time length of length-type building materials and their corresponding allocation results, the real-time volume of volume-type building materials and their corresponding allocation results, and the real-time number of quantity-type building materials and their corresponding allocation results are used as data sets, which are divided into training set and test set in a ratio of 7:3. MLP is selected as the neural network structure. The input layer includes five neurons, which receives the real-time weight of weight-type building materials, the real-time liquid level height of liquid-type building materials, the real-time length of length-type building materials, the real-time volume of volume-type building materials, and the real-time number of quantity-type building materials. The hidden layer is configured with an MSE function. The output layer includes five neurons, which outputs the allocation results of weight-type building materials, liquid-type building materials, length-type building materials, volume-type building materials, and quantity-type building materials. 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 back propagation, wherein the forward propagation is used to calculate the predicted output data, and the back propagation is used to update the weights and biases of the model. Through repeated iterative training, the nonlinear relationship between the real-time weight of weight-type building materials and the allocation results of weight-type building materials, the nonlinear relationship between the real-time liquid level height of liquid-type building materials and the allocation results of liquid-type building materials, the nonlinear relationship between the real-time length of length-type building materials and the allocation results of length-type building materials, the nonlinear relationship between the real-time volume of volume-type building materials and the allocation results of volume-type building materials, and the nonlinear relationship between the real-time number of quantity-type building materials and the allocation results of quantity-type building materials are learned until the set number of iterative training times is reached, and the trained neural network model is obtained; The test set data is input into the trained neural network model, and the MSE function is used to evaluate the error between the output value of the neural network model and the actual value. The parameters of the neural network model are adjusted according to the evaluation results to obtain the building service resource optimization model.

[0024] Preferably, in step 5, the process of optimizing the construction service resource allocation model using a genetic algorithm includes: Encode the input data and output data of the building service resource optimization model, assign input codes 1, 2, 3, 4, 5, and 6 to the building service personnel category, the real-time weight of weight-type building materials, the real-time liquid level height of liquid-type building materials, the real-time length of length-type building materials, the real-time volume of volume-type building materials, and the real-time number of quantity-type building materials respectively; and assign output codes A, B, C, D, E, and F to the building service personnel scheduling results, the allocation results of weight-type building materials, the allocation results of liquid-type building materials, the allocation results of length-type building materials, the allocation results of volume-type building materials, and the allocation results of quantity-type building materials respectively; According to the scale of the building service resource optimization model, an initial population is randomly generated, which consists of n individuals. The codes of the n individuals correspond to the input data and output data of the building service resource optimization model, and a fitness function is constructed to evaluate the fitness of each individual. Through the roulette wheel selection method, individuals are selected from the current population to form the next generation population according to individual fitness. Two individuals are randomly selected from the next generation population. According to the crossover probability, the coding position is selected to cross and generate two new individuals. The individual coding position is randomly selected, the coding value of the coding position is changed, and the individuals are compiled. The individuals after selection, crossover and mutation operations are composed of a new population to replace the previous generation. The number of iterations is set, and the selection, crossover and mutation operations are repeated on the population until the number of iterations is reached to optimize the building service resource optimization model.

[0025] Preferably, in step six, the process of scheduling construction service personnel and allocating various types of construction materials by combining the construction service personnel scheduling model with the optimized construction service resource allocation model includes: Input the building service personnel category into the building service personnel scheduling model, and the building service personnel scheduling model outputs the corresponding building service personnel scheduling results. According to the building service personnel scheduling results, the corresponding building service personnel are dispatched to the corresponding job positions; The real-time data of various types of building materials are input into the optimized construction service resource allocation model to obtain the allocation results of various types of building materials. Based on the building material allocation results, when the inventory of building materials is insufficient, the building materials are purchased to replenish the inventory of corresponding building materials; when the inventory of building materials is redundant, the construction service order is adjusted to give priority to the use of this type of building materials.

[0026] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for optimizing building service resources, characterized by: The following steps are involved: Step 1: Collect data on the skills of construction service personnel through questionnaire surveys, design an IoT inventory collection module, and collect real-time inventory data of construction materials; Step 2: Pre-process the construction service personnel skills questionnaire data and the real-time inventory data of building materials, classify the construction service personnel into categories, and set the thresholds for the real-time inventory data of various types of building materials; Step 3: Obtain the construction service personnel scheduling results according to the construction service personnel category; Use the inventory thresholds of various building materials to obtain the results of building material allocation; Step 4: Use the convolutional neural network algorithm to build a construction service personnel scheduling model; use the neural network algorithm to build a construction service resource allocation model; Step 5: Optimize the construction service resource allocation model using genetic algorithms; Step 6: Combine the construction service personnel scheduling model with the optimized construction service resource allocation model to schedule construction service personnel and allocate various types of construction materials.

2. A construction service resource optimization method according to claim 1, characterized in that: In step 1, the process of collecting questionnaire data on construction service personnel skills through questionnaire survey includes: Use Wenjuanxing to set up questionnaire questions. The questionnaire questions include two questions. The first question is the construction service personnel number; the second question is the type of work they are engaged in, with ten options, namely carpenter, bricklayer, reinforcement worker, electrician, welder, scaffolder, painter, waterproofer, crane operator and installer; the questionnaire questions are sent to the mobile phone of each construction service personnel through Wenjuanxing, and the construction service personnel fill in the answers to the questionnaire to obtain the construction service personnel skill questionnaire data.

3. A construction service resource optimization method according to claim 2, characterized in that: In step 1, the process of designing an IoT inventory collection module to collect real-time inventory data of building materials includes: The IoT acquisition module includes a hardware unit and a software unit. The hardware unit consists of a weight sensor, a laser distance sensor, a liquid level sensor, an RFID reader / writer, a QR code scanner, and a data acquisition terminal. The software unit consists of data acquisition software, a cloud server software, and a mobile application. According to the measurement method of building materials, building materials are divided into weight building materials, liquid building materials, volume building materials, length building materials and quantity building materials; The real-time inventory data of building materials includes the real-time weight of weight-based building materials, the real-time liquid level height of liquid-based building materials, the real-time length of length-based building materials, the real-time volume of volume-based building materials and the real-time number of quantity-based building materials; The weight sensor in the Internet of Things inventory collection module is used to collect the real-time weight of weight-type building materials; the liquid level sensor in the Internet of Things inventory collection module is used to collect the real-time liquid level height of liquid-type building materials; the laser ranging sensor in the Internet of Things inventory collection module is used to collect the real-time length of length-type building materials; the laser ranging sensor in the Internet of Things inventory collection module is used to measure the real-time length, real-time width and real-time height of volume-type building materials, and the real-time volume of volume-type building materials is calculated using the volume formula; an RFID tag and a QR code are attached to each quantity-type building material, and the real-time number of quantity-type building materials entering the warehouse and the real-time number of quantity-type building materials leaving the warehouse are recorded respectively through the RFID reader and the QR code scanning device, and the real-time number of quantity-type building materials entering the warehouse and the real-time number of quantity-type building materials leaving the warehouse are obtained by calculating the difference between the real-time number of quantity-type building materials entering the warehouse and the real-time number of quantity-type building materials leaving the warehouse.

4. A construction service resource optimization method according to claim 3, characterized in that: In step 2, the process of pre-processing the construction service personnel skills questionnaire data and the real-time inventory data of construction materials, classifying construction service personnel into categories, and setting thresholds for the real-time inventory data of various types of construction materials includes: Data cleaning was performed on the construction service personnel skills questionnaire data and the real-time inventory data of construction materials to remove duplicate values and outliers; According to the skills questionnaire data of construction service personnel, construction service personnel are divided into carpenters, bricklayers, steel workers, electricians, welders, scaffolders, painters, waterproofers, crane operators and installers; According to the demand for building material resources in construction services, the lower and upper thresholds for the weight of weight-type building materials, the lower and upper thresholds for the liquid level height of liquid-type building materials, the lower and upper thresholds for the length of length-type building materials, the lower and upper thresholds for the volume of volume-type building materials, and the lower and upper thresholds for the number of quantity-type building materials are set respectively.

5. A construction service resource optimization method according to claim 4, characterized in that: In step 3, the process of obtaining the construction service personnel scheduling result according to the construction service personnel category includes: Based on the skill questionnaire data and construction service personnel categories of construction service personnel, a construction service personnel information database is established to record the category and number of each construction service personnel. Through a greedy algorithm, priorities are set for construction service jobs according to the progress and importance of construction tasks. According to the categories of construction service personnel and in the order of the priorities of construction service jobs, personnel matching the categories of construction service personnel are dispatched to the corresponding jobs in turn to obtain the construction service personnel scheduling results.

6. A construction service resource optimization method according to claim 5, characterized in that: In step 3, the process of obtaining the building material allocation results using the inventory thresholds of various building materials includes: When the real-time weight of the weight-type building materials is lower than the lower limit threshold of the weight of the weight-type building materials, it indicates that the weight-type building materials are insufficient in stock; when the real-time weight of the weight-type building materials is higher than the upper limit threshold of the weight of the weight-type building materials, it indicates that the weight-type building materials are redundant in stock; When the real-time liquid level of the liquid building material is lower than the lower limit threshold of the liquid building material, it indicates that the inventory of the liquid building material is insufficient; when the real-time liquid level of the liquid building material is higher than the upper limit threshold of the liquid building material, it indicates that the inventory of the liquid building material is redundant; When the real-time length of the length-type building materials is lower than the lower limit threshold of the length of the length-type building materials, it indicates that the inventory of the length-type building materials is insufficient; when the real-time length of the length-type building materials is higher than the upper limit threshold of the length of the length-type building materials, it indicates that the inventory of the length-type building materials is redundant; When the real-time volume of the volumetric building materials is lower than the lower limit threshold of the volume of the volumetric building materials, it indicates that the volumetric building materials are insufficient in stock; when the real-time volume of the volumetric building materials is higher than the upper limit threshold of the volume of the volumetric building materials, it indicates that the volumetric building materials are redundant in stock; When the real-time number of quantity-based building materials is lower than the lower limit threshold of the number of quantity-based building materials, it indicates that the inventory of quantity-based building materials is insufficient; when the real-time number of quantity-based building materials is higher than the upper limit threshold of the number of quantity-based building materials, it indicates that the inventory of quantity-based building materials is redundant; Through the above process, the building material allocation results are obtained, and the building material allocation results include weight-based building material allocation results, liquid-based building material allocation results, length-based building material allocation results, volume-based building material allocation results, and quantity-based building material allocation results.

7. A construction service resource optimization method according to claim 6, characterized in that: In step 4, the process of using a convolutional neural network algorithm to construct a construction service personnel scheduling model includes: The building service personnel categories and their corresponding dispatch results are used as a data set, which is divided into a training set and a test set in a ratio of 7:

3. The convolutional neural network algorithm is used to design a convolutional neural network architecture. The convolutional neural network architecture consists of an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. Ten input channels are set in the input layer to input the building service personnel categories, and ten output channels are set in the output layer to output the corresponding building service personnel dispatch results. The convolutional neural network model is constructed. The training set data is input into the convolutional neural network model, the output value of the convolutional neural network is calculated through forward propagation, the gradient is calculated through backpropagation, the parameters of the convolutional neural network model are updated according to the gradient, the nonlinear relationship between the building service personnel category and its corresponding dispatch result is learned, and the trained convolutional neural network model is obtained; Input the test set data into the trained convolutional neural network model, compare the output results of the convolutional neural network model with the actual construction service personnel scheduling results, evaluate the performance of the trained convolutional neural network model, adjust the convolutional neural network model parameters, optimize the convolutional neural network model, and obtain the construction service personnel scheduling model.

8. The construction service resource optimization method according to claim 7, characterized in that: In step 4, the process of constructing a construction service resource allocation model using a neural network algorithm includes: A neural network model is constructed by using a neural network algorithm. The real-time weight of weight-type building materials and their corresponding allocation results, the real-time liquid level height of liquid-type building materials and their corresponding allocation results, the real-time length of length-type building materials and their corresponding allocation results, the real-time volume of volume-type building materials and their corresponding allocation results, and the real-time number of quantity-type building materials and their corresponding allocation results are used as data sets, which are divided into training set and test set in a ratio of 7:

3. MLP is selected as the neural network structure. The input layer includes five neurons, which receives the real-time weight of weight-type building materials, the real-time liquid level height of liquid-type building materials, the real-time length of length-type building materials, the real-time volume of volume-type building materials, and the real-time number of quantity-type building materials. The hidden layer is configured with an MSE function. The output layer includes five neurons, which outputs the allocation results of weight-type building materials, liquid-type building materials, length-type building materials, volume-type building materials, and quantity-type building materials. 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 back propagation, wherein the forward propagation is used to calculate the predicted output data, and the back propagation is used to update the weights and biases of the model. Through repeated iterative training, the nonlinear relationship between the real-time weight of weight-type building materials and the allocation results of weight-type building materials, the nonlinear relationship between the real-time liquid level height of liquid-type building materials and the allocation results of liquid-type building materials, the nonlinear relationship between the real-time length of length-type building materials and the allocation results of length-type building materials, the nonlinear relationship between the real-time volume of volume-type building materials and the allocation results of volume-type building materials, and the nonlinear relationship between the real-time number of quantity-type building materials and the allocation results of quantity-type building materials are learned until the set number of iterative training times is reached, and the trained neural network model is obtained; The test set data is input into the trained neural network model, and the MSE function is used to evaluate the error between the output value of the neural network model and the actual value. The parameters of the neural network model are adjusted according to the evaluation results to obtain the building service resource optimization model.

9. The construction service resource optimization method according to claim 8, characterized in that: In step 5, the process of optimizing the construction service resource allocation model using genetic algorithm includes: Encode the input data and output data of the building service resource optimization model, and assign input codes 1, 2, 3, 4, 5, and 6 to the building service personnel category, the real-time weight of weight-type building materials, the real-time liquid level height of liquid-type building materials, the real-time length of length-type building materials, the real-time volume of volume-type building materials, and the real-time number of quantity-type building materials, respectively; Assign output codes A, B, C, D, E, and F to the construction service personnel dispatch results, weight-based construction material allocation results, liquid-based construction material allocation results, length-based construction material allocation results, volume-based construction material allocation results, and quantity-based construction material allocation results, respectively; According to the scale of the building service resource optimization model, an initial population is randomly generated, which consists of n individuals. The codes of the n individuals correspond to the input data and output data of the building service resource optimization model, and a fitness function is constructed to evaluate the fitness of each individual. Through the roulette wheel selection method, individuals are selected from the current population to form the next generation population according to individual fitness. Two individuals are randomly selected from the next generation population. According to the crossover probability, the coding position is selected to cross and generate two new individuals. The individual coding position is randomly selected, the coding value of the coding position is changed, and the individuals are compiled. The individuals after selection, crossover and mutation operations are composed of a new population to replace the previous generation. The number of iterations is set, and the selection, crossover and mutation operations are repeated on the population until the number of iterations is reached to optimize the building service resource optimization model.

10. The construction service resource optimization method according to claim 9, characterized in that: In step 6, the process of scheduling construction service personnel and allocating various types of construction materials by combining the construction service personnel scheduling model with the optimized construction service resource allocation model includes: Input the building service personnel category into the building service personnel scheduling model, and the building service personnel scheduling model outputs the corresponding building service personnel scheduling results. According to the building service personnel scheduling results, the corresponding building service personnel are dispatched to the corresponding job positions; The real-time data of various types of building materials are input into the optimized construction service resource allocation model to obtain the allocation results of various types of building materials. Based on the building material allocation results, when the inventory of building materials is insufficient, the building materials are purchased to replenish the inventory of corresponding building materials; when the inventory of building materials is redundant, the construction service order is adjusted to give priority to the use of this type of building materials.

Images