An intelligent construction management system and method based on the Internet of Things

Abstract

The application discloses an intelligent construction management system and method based on Internet of Things, and relates to the technical field of construction management.The application collects historical material quantity data of construction sites of different scales, constructs a material consumption prediction model after data preprocessing, determines a replenishment trigger node in combination with a material replenishment time and a reserved buffer time, and avoids material supply interruption.The application calculates a corrected material consumption rate based on a "time-material quantity" data set, constructs a timing feature by fusing process constraint information, establishes a construction progress prediction model by fitting a loss function, quantifies the progress, triggers process connection, divides a site sub-region according to a process, associates materials, classifies construction personnel according to skills and associates processes, compares a predicted construction period with a standard construction period to determine progress deviation, calculates the number of supplementary or redundant personnel based on single-person operation efficiency, and realizes dynamic scheduling of personnel, so that the intelligent and accurate level of construction management is effectively improved, and resource allocation and construction efficiency are optimized.

Description

Technical Field

[0001] This invention relates to the field of construction management technology, specifically an intelligent construction management system and method based on the Internet of Things. Background Technology

[0002] In current construction management, material demand forecasting relies heavily on manual experience, lacking systematic collection and preprocessing of historical material data from construction sites of all sizes. This makes it difficult to accurately build predictive models, easily leading to material shortages or stockpiles. Construction progress quantification lacks scientific basis, failing to combine material consumption rates with process constraints to establish predictive models, making it impossible to timely predict progress deviations and achieve efficient process connections. Site resource associations are chaotic, failing to divide sub-areas by process and associate them with corresponding materials, and failing to classify construction personnel by skill qualifications and associate them with processes, resulting in low resource matching efficiency. Personnel scheduling relies on experience-based judgment, failing to combine progress deviations with individual work efficiency to calculate supplementary or redundant personnel, easily leading to manpower waste or shortages. Overall, the level of intelligence and precision in construction management is low, hindering the improvement of construction efficiency. To address these shortcomings in current construction management, an intelligent management solution based on the Internet of Things is urgently needed. Summary of the Invention

[0003] The purpose of this invention is to provide an intelligent construction management system and method based on the Internet of Things to solve the problems raised in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: an intelligent construction management method based on the Internet of Things, the method comprising the following steps: Step S1: Collect the required material quantity data for the complete construction phase of construction sites of various scales in history, preprocess the required material quantity data, draw a scatter plot based on the processed required material quantity data, and construct a material consumption prediction model for construction sites of various scales. Step S1-1: Classify the construction sites according to their different scales based on the construction area. Specifically, the range for small-scale sites is [x1, x2], the range for medium-scale sites is [x2-x3], and the range for large-scale sites is [x3-x4]. Here, x1, x2, x3, and x4 are the threshold values ​​for classifying the construction area of ​​different-scale construction sites. Step S1-2: Collect the required material quantities for n construction sites of various sizes throughout the entire process; Step S1-3: For the collected material quantities required from n construction sites of various sizes, perform data preprocessing, specifically as follows: For outliers, the 3σ principle is used to remove extreme data. Specifically, the mean and standard deviation of the required material quantity are calculated, and values ​​that are not in the interval [μ-3σ,μ+3σ] are removed. In the formula, μ is the mean and σ is the standard deviation. For missing values, linear interpolation is used to fill in the missing values; Normalize the required material quantity; Steps S1-4: For the required material quantities of construction sites of the same scale, calculate the average required material quantity. Based on the average required material quantity, draw a scatter plot with time as the horizontal axis and the required material quantity of each type of material as the vertical axis. Steps S1-5: Fit the scatter plot using a multinomial algorithm to construct a material consumption prediction model, specifically as follows: ; In the formula, y represents the required quantity of a certain type of material at a specific moment on the construction site, x represents the time variable of the construction progress, a0 is the basic constant of the polynomial fitting, and a1-a n The trend coefficients obtained from the fitting are denoted as .

[0005] By collecting and preprocessing historical material quantity data from construction sites of various sizes, a material consumption prediction model is constructed. This provides accurate material consumption data support for determining the timing of subsequent material replenishment and quantifying construction progress, avoiding prediction biases caused by reliance on human experience.

[0006] Step S2: Replenish materials based on the time required for material consumption to reach 0 as predicted by the material consumption prediction model, combined with the time required for material mobilization. Step S2-1: Calculate the time required for material consumption to reach 0 based on the material consumption prediction model, and denote it as t1; Step S2-2: Divide the time required for material replenishment into material outbound review time, material loading time, transportation time, unloading time, and acceptance time. Collect historical material replenishment time data for each type, use the average as the standard value, and calculate the material replenishment time t2, specifically: ; In the formula, t2 is the time required for material replenishment. For material outbound approval time, For material loading time, For transportation time, For unloading time, For the acceptance time; Step S2-3: Calculate the material replenishment trigger time t0, and perform the material replenishment operation based on t0, specifically as follows: ; In the formula, To allow for buffer time, the plan is dynamically formulated based on the actual business scenario; When the actual construction progress time is greater than or equal to the material replenishment trigger time, it is determined that there is a physical risk of supply interruption, and the material replenishment process is triggered.

[0007] By combining the depletion time calculated by the material consumption prediction model with the time of each stage of material mobilization, the replenishment trigger time can be determined. This allows for the early identification of material supply disruption risks and timely replenishment, preventing construction interruptions due to material shortages or waste caused by excessive material stockpiling.

[0008] Step S3: Calculate the material consumption rate based on the time output by the material consumption prediction model, quantify the construction progress, and construct a construction progress prediction model. Step S3-1: Extract the required material quantities of various materials corresponding to n time nodes in the historical construction cycle, and construct a "time-material quantity" dataset; Step S3-2: Classify the dataset according to the construction process. Based on the classified dataset, calculate the material consumption difference between two adjacent time nodes and the corresponding time interval. Then, use the material consumption difference divided by the corresponding time interval to calculate the consumption rate v of each material in each time zone. Step S3-3: Correct the calculated consumption rate v using the mean correction method; Step S3-4: Collect basic constraint information of construction procedures, including logical dependencies between procedures, buffer time between procedures, and total material usage required for a single procedure. Step S3-5: Sort the processes according to the logical dependencies between processes, and construct the time sequence features based on the construction time, material consumption rate, process connection buffer time, and total amount of materials required for the process. The specific time sequence features are the cumulative material consumption, material consumption completion rate, and connection time effectiveness coefficient. Step S3-6: Calculate the time series features, specifically as follows: Cumulative material consumption: ; In the formula, Let be the cumulative material consumption of the i-th process up to the current moment. For material consumption rate, Construction time; Material consumption completion rate: ; In the formula, Let be the material consumption completion rate of the i-th process. Let be the cumulative material consumption of the i-th process. This represents the total amount of materials required for the i-th process. Connection time effective coefficient: ; In the formula, This is the effective time coefficient for the connection between the i-th process and the (i+1)-th process. Let be the material consumption completion rate of the i-th process, when <1 hour, =0, connection time is not calculated. When =1, =1, the connection time is officially included in the start time of the next process; Steps S3-7: Divide the data into training and validation sets in a 7:3 ratio, using time-series features as input and process completion rate as output. Then, minimize the loss function to fit the construction progress prediction model, specifically: ; In the formula, For process completion, , These are the fitted regression coefficients. Let be the material consumption completion rate of the i-th process. This is the error term; Step S3-8: When the model predicts the completion rate of the current process... When =1, the connection time constraint is automatically triggered, combined with The condition for the condition to take effect is 1. The start time of the next process is calculated as follows: ; In the formula, The start time of the next process. Let i be the estimated completion time of the current process i. This represents the connection time between the i-th process and the (i+1)-th process.

[0009] By quantifying construction progress through material consumption rates and constructing a progress prediction model, and by integrating process constraint information, the completion degree of processes can be predicted and the connection can be triggered, providing a scientific basis for construction progress control and orderly progress of processes.

[0010] Step S4: Divide the construction site into sub-areas according to the construction site procedures, associate the construction site sub-areas with materials according to the business scenarios of each construction site sub-area procedures, classify construction personnel into technical trades, and associate technical trades with construction site procedures. Step S4-1: Based on the process division of the construction flow, divide the entire construction site into corresponding sub-areas, with each sub-area corresponding to one process, and construct a "process-sub-area" set; Step S4-2: For the process business scenario of each construction site sub-area, sort out all the material types required for the process, and bind the sub-area number with the corresponding material list by establishing association mapping rules; Step S4-3: Collect the skill qualifications of all construction personnel, classify them into different job categories based on their skill qualifications, and build a "personnel-job category" file.

[0011] By dividing the site into sub-regions according to work processes and associating them with materials, and by classifying personnel according to skills and associating them with work processes, the correspondence between site resources and work processes is clarified, laying a precise matching foundation for subsequent resource allocation and personnel scheduling.

[0012] Step S5: Predict the completion time of construction site procedures based on the construction progress prediction model, set the standard completion time of procedures based on historical construction data, compare the predicted completion time of construction site procedures with the standard completion time of procedures, and schedule personnel according to the judgment results and the types of technical workers.

[0013] Step S5-1: Based on the construction progress prediction model and the relationship between the sub-regions of the construction site and the corresponding work processes, extract the estimated completion time of each work process in each sub-region and construct a "sub-region-work process-estimated completion time" correspondence table; Step S5-2: Based on historical construction site data of various scales, calculate the historical average completion time of n similar processes of the same scale, and use it as the standard completion time of the process; Step S5-3: For each process in each sub-region, calculate the deviation value △T between the "estimated completion time" and the "standard completion time of the process". Determine the type of deviation based on the deviation value. When △T<0, it is determined that the schedule is ahead of schedule. When △T=0, the schedule meets the standard. When △T>0, the schedule is behind schedule. Step S5-4: When the process completion time does not meet the standard process completion time, supplement the personnel in the sub-area, specifically as follows: Step S5-4-1: Extract historical work data of the target trade under the same scale and process based on historical construction data, and calculate the work efficiency of a single person per unit time for the target trade. Specifically: ; In the formula, E represents the individual work efficiency of the target public per unit of time. This refers to the total amount of materials consumed when the target trade participated in the operation within the same historical process. The total operation time used to process the total amount of materials consumed by the target public in the same historical process. The target number of workers involved in the same historical process; Step S5-4-2: For scenarios with delayed progress, calculate the amount of material required from the current moment of the process to its completion. Specifically: ; In the formula, This refers to the amount of material required from the current moment of the process until the process is completed. This represents the total amount of material required for this process. This represents the cumulative material consumption of this process up to the current moment. Step S5-4-3: Based on the amount of material required from the current moment of the process to its completion, and combined with the unit time work efficiency of the target worker, calculate the additional personnel required for the target worker. Specifically: ; In the formula, E represents the number of additional personnel required for the target job, and E represents the individual work efficiency per unit time for the target job. The remaining available time for the process. The number of employees currently on duty for the target job category; Step S5-4-4: For scenarios where the schedule is ahead of schedule, calculate the redundant number of personnel for the target job, specifically as follows: ; In the formula, For redundant personnel in the target job category, Let E represent the number of employees in the target job category, and E represent the individual work efficiency per unit time for the target job category. The remaining time after the process is completed ahead of schedule; Step S5-5: Based on the calculated number of additional personnel required for the target job and the redundant personnel for the target job, and in conjunction with the "personnel-job" classification file, find suitable technical personnel for the job and schedule personnel accordingly.

[0014] By comparing the predicted construction period with the standard construction period to determine the progress deviation, and combining the individual work efficiency to calculate the number of personnel to supplement or redundancy, dynamic and precise personnel scheduling can be achieved, avoiding the impact of manpower waste or insufficient manpower on construction efficiency.

[0015] The system includes a material consumption prediction module, a material replenishment triggering module, a construction progress prediction module, a site resource association module, and a construction personnel scheduling module. The material consumption prediction module is used to collect material quantity data of construction sites of various scales during the complete construction phase, preprocess the data, draw scatter plots based on the processed data, and use a multinomial algorithm to fit and construct a material consumption prediction model for construction sites of various scales. The material replenishment triggering module is used to calculate the time required for material consumption to reach 0 based on the material consumption prediction model, collect historical data to determine the time for each stage of material outbound review, loading, transportation, unloading and acceptance, and calculate the total material replenishment time. It also combines the reserved buffer time to obtain the material replenishment triggering time, compares it with the actual construction time to determine the risk of material supply interruption and trigger the replenishment process. The construction progress prediction module is used to construct a "time-material quantity" dataset, calculate and correct the material consumption rate using the mean correction method, collect constraint information such as process logic dependency and connection buffer time to construct time series features, divide the training set and validation set according to the proportion, fit the construction progress prediction model with the time series features as input and the process completion degree as output, and trigger the calculation of the connection time of the next process when the predicted process completion degree is 1. The construction site resource association module is used to divide the construction site into sub-regions according to the construction process, sort out the materials required for each sub-region process and establish the association mapping between the sub-region and the materials, collect the skills and qualifications of construction personnel to classify technical jobs, build "personnel-job" files and establish the association between technical jobs and construction site processes; The construction personnel scheduling module is used to extract the estimated completion time of each sub-area process based on the construction progress prediction model, determine the standard completion time of the process using historical data and calculate the deviation value to determine the progress type, calculate the unit time work efficiency of the target job based on historical work data, calculate the number of supplementary personnel when the progress is delayed and the number of redundant personnel when the progress is ahead, and perform personnel scheduling in combination with the "personnel-job type" file.

[0016] The material consumption prediction module includes a historical material processing unit and a material consumption model construction unit; The historical material data processing unit is used to collect and preprocess historical material quantity data from construction sites of various sizes. The material consumption model building unit is used to draw a scatter plot based on the processed material quantity data and to use a polynomial algorithm to fit and build a material consumption prediction model. The material replenishment triggering module includes a material time calculation unit and a replenishment triggering determination unit; The material time calculation unit is used to calculate the time required for material consumption to reach 0 based on the material consumption prediction model, and to obtain the time required for material replenishment based on historical data. The replenishment trigger determination unit is used to calculate the material replenishment trigger time, compare it with the actual construction time to determine whether there is a risk of supply interruption, and trigger the replenishment process.

[0017] The construction progress prediction module includes a consumption rate calculation unit and a progress model construction unit; The consumption rate calculation unit is used to construct a "time-material quantity" dataset, calculate the material consumption rate at adjacent time nodes, and correct it using the mean correction method. The progress model construction unit is used to collect process constraint information to construct time sequence features, divide training and validation sets to fit the construction progress prediction model and trigger process connection. The construction site resource association module includes a sub-region material binding unit and a personnel type classification unit; The sub-region material binding unit is used to divide the construction site into sub-regions according to the construction process and establish an association mapping between the sub-regions and the materials required for the corresponding process. The personnel classification unit is used to collect the skills and qualifications of construction personnel to classify them into different types of work, build "personnel-type of work" files, and associate them with the corresponding construction site procedures.

[0018] The construction personnel scheduling module includes a progress deviation judgment unit and a scheduling personnel calculation unit; The schedule deviation judgment unit is used to extract the estimated completion time of the process, calculate the deviation value from the historical standard time, and determine the type of schedule deviation. The scheduling personnel calculation unit is used to calculate and schedule the number of additional or redundant personnel required in the event of a progress deviation scenario based on the individual's work efficiency per unit time.

[0019] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention collects and preprocesses historical material quantities from construction sites of various sizes, constructs a material consumption prediction model, and determines trigger nodes by combining replenishment time and buffer time, thereby avoiding material supply disruptions or stockpiling waste.

[0020] 2. This invention constructs a "time-material quantity" dataset and corrects the consumption rate, integrates process constraints to build time sequence characteristics, fits a progress prediction model and triggers process connection, scientifically quantifies progress and predicts deviations.

[0021] 3. This invention achieves precise resource matching and reasonable personnel scheduling by dividing the construction site into sub-areas according to the process and associating materials with the process, classifying personnel according to skills and associating them with the process, and calculating the number of personnel by combining progress deviation and individual efficiency. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating an intelligent construction management method based on the Internet of Things according to the present invention. Figure 2 This is a schematic diagram of the structure of an IoT-based intelligent construction management system according to the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] Example 1: As Figures 1-2 As shown, the present invention provides a technical solution, an intelligent construction management method based on the Internet of Things, which includes the following steps: Step S1: Collect the required material quantity data for the complete construction phase of construction sites of various scales in history, preprocess the required material quantity data, draw a scatter plot based on the processed required material quantity data, and construct a material consumption prediction model for construction sites of various scales. Step S1-1: Classify the construction sites according to their different scales based on the construction area. Specifically, the range for small-scale sites is [x1, x2], the range for medium-scale sites is [x2-x3], and the range for large-scale sites is [x3-x4]. Here, x1, x2, x3, and x4 are the threshold values ​​for classifying the construction area of ​​different-scale construction sites. Step S1-2: Collect the required material quantities for n construction sites of various sizes throughout the entire process; Step S1-3: For the collected material quantities required from n construction sites of various sizes, perform data preprocessing, specifically as follows: For outliers, the 3σ principle is used to remove extreme data. Specifically, the mean and standard deviation of the required material quantity are calculated, and values ​​that are not in the interval [μ-3σ,μ+3σ] are removed. In the formula, μ is the mean and σ is the standard deviation. For missing values, linear interpolation is used to fill in the missing values; Normalize the required material quantity; Steps S1-4: For the required material quantities of construction sites of the same scale, calculate the average required material quantity. Based on the average required material quantity, draw a scatter plot with time as the horizontal axis and the required material quantity of each type of material as the vertical axis. Steps S1-5: Fit the scatter plot using a multinomial algorithm to construct a material consumption prediction model, specifically as follows: ; In the formula, y represents the required quantity of a certain type of material at a specific moment on the construction site, x represents the time variable of the construction progress, a0 is the basic constant of the polynomial fitting, and a1-a n The trend coefficients obtained from the fitting are denoted as .

[0025] By collecting and preprocessing historical material quantity data from construction sites of various sizes, a material consumption prediction model is constructed. This provides accurate material consumption data support for determining the timing of subsequent material replenishment and quantifying construction progress, avoiding prediction biases caused by reliance on human experience.

[0026] Step S2: Replenish materials based on the time required for material consumption to reach 0 as predicted by the material consumption prediction model, combined with the time required for material mobilization. Step S2-1: Calculate the time required for material consumption to reach 0 based on the material consumption prediction model, and denote it as t1; Step S2-2: Divide the time required for material replenishment into material outbound review time, material loading time, transportation time, unloading time, and acceptance time. Collect historical material replenishment time data for each type, use the average as the standard value, and calculate the material replenishment time t2, specifically: ; In the formula, t2 is the time required for material replenishment. For material outbound approval time, For material loading time, For transportation time, For unloading time, For the acceptance time; Step S2-3: Calculate the material replenishment trigger time t0, and perform the material replenishment operation based on t0, specifically as follows: ; In the formula, To allow for buffer time, the plan is dynamically formulated based on the actual business scenario; When the actual construction progress time is greater than or equal to the material replenishment trigger time, it is determined that there is a physical risk of supply interruption, and the material replenishment process is triggered.

[0027] By combining the depletion time calculated by the material consumption prediction model with the time of each stage of material mobilization, the replenishment trigger time can be determined. This allows for the early identification of material supply disruption risks and timely replenishment, preventing construction interruptions due to material shortages or waste caused by excessive material stockpiling.

[0028] Step S3: Calculate the material consumption rate based on the time output by the material consumption prediction model, quantify the construction progress, and construct a construction progress prediction model. Step S3-1: Extract the required material quantities of various materials corresponding to n time nodes in the historical construction cycle, and construct a "time-material quantity" dataset; Step S3-2: Classify the dataset according to the construction process. Based on the classified dataset, calculate the material consumption difference between two adjacent time nodes and the corresponding time interval. Then, use the material consumption difference divided by the corresponding time interval to calculate the consumption rate v of each material in each time zone. Step S3-3: Correct the calculated consumption rate v using the mean correction method; Step S3-4: Collect basic constraint information of construction procedures, including logical dependencies between procedures, buffer time between procedures, and total material usage required for a single procedure. Step S3-5: Sort the processes according to the logical dependencies between processes, and construct the time sequence features based on the construction time, material consumption rate, process connection buffer time, and total amount of materials required for the process. The specific time sequence features are the cumulative material consumption, material consumption completion rate, and connection time effectiveness coefficient. Step S3-6: Calculate the time series features, specifically as follows: Cumulative material consumption: ; In the formula, Let be the cumulative material consumption of the i-th process up to the current moment. For material consumption rate, Construction time; Material consumption completion rate: ; In the formula, Let be the material consumption completion rate of the i-th process. Let be the cumulative material consumption of the i-th process. This represents the total amount of materials required for the i-th process. Connection time effective coefficient: ; In the formula, This is the effective time coefficient for the connection between the i-th process and the (i+1)-th process. Let be the material consumption completion rate of the i-th process, when <1 hour, =0, connection time is not calculated. When =1, =1, the connection time is officially included in the start time of the next process; Steps S3-7: Divide the data into training and validation sets in a 7:3 ratio, using time-series features as input and process completion rate as output. Then, minimize the loss function to fit the construction progress prediction model, specifically: ; In the formula, For process completion, , These are the fitted regression coefficients. Let be the material consumption completion rate of the i-th process. This is the error term; Step S3-8: When the model predicts the completion rate of the current process... When =1, the connection time constraint is automatically triggered, combined with The condition for the condition to take effect is 1. The start time of the next process is calculated as follows: ; In the formula, The start time of the next process. Let i be the estimated completion time of the current process i. This represents the connection time between the i-th process and the (i+1)-th process.

[0029] By quantifying construction progress through material consumption rates and constructing a progress prediction model, and by integrating process constraint information, the completion degree of processes can be predicted and the connection can be triggered, providing a scientific basis for construction progress control and orderly progress of processes.

[0030] Step S4: Divide the construction site into sub-areas according to the construction site procedures, associate the construction site sub-areas with materials according to the business scenarios of each construction site sub-area procedures, classify construction personnel into technical trades, and associate technical trades with construction site procedures. Step S4-1: Based on the process division of the construction flow, divide the entire construction site into corresponding sub-areas, with each sub-area corresponding to one process, and construct a "process-sub-area" set; Step S4-2: For the process business scenario of each construction site sub-area, sort out all the material types required for the process, and bind the sub-area number with the corresponding material list by establishing association mapping rules; Step S4-3: Collect the skill qualifications of all construction personnel, classify them into different job categories based on their skill qualifications, and build a "personnel-job category" file.

[0031] By dividing the site into sub-regions according to work processes and associating them with materials, and by classifying personnel according to skills and associating them with work processes, the correspondence between site resources and work processes is clarified, laying a precise matching foundation for subsequent resource allocation and personnel scheduling.

[0032] Step S5: Predict the completion time of construction site procedures based on the construction progress prediction model, set the standard completion time of procedures based on historical construction data, compare the predicted completion time of construction site procedures with the standard completion time of procedures, and schedule personnel according to the judgment results and the types of technical workers.

[0033] Step S5-1: Based on the construction progress prediction model and the relationship between the sub-regions of the construction site and the corresponding work processes, extract the estimated completion time of each work process in each sub-region and construct a "sub-region-work process-estimated completion time" correspondence table; Step S5-2: Based on historical construction site data of various scales, calculate the historical average completion time of n similar processes of the same scale, and use it as the standard completion time of the process; Step S5-3: For each process in each sub-region, calculate the deviation value △T between the "estimated completion time" and the "standard completion time of the process". Determine the type of deviation based on the deviation value. When △T<0, it is determined that the schedule is ahead of schedule. When △T=0, the schedule meets the standard. When △T>0, the schedule is behind schedule. Step S5-4: When the process completion time does not meet the standard process completion time, supplement the personnel in the sub-area, specifically as follows: Step S5-4-1: Extract historical work data of the target trade under the same scale and process based on historical construction data, and calculate the work efficiency of a single person per unit time for the target trade. Specifically: ; In the formula, E represents the individual work efficiency of the target public per unit of time. This refers to the total amount of materials consumed when the target trade participated in the operation within the same historical process. The total operation time used to process the total amount of materials consumed by the target public in the same historical process. The target number of workers involved in the same historical process; Step S5-4-2: For scenarios with delayed progress, calculate the amount of material required from the current moment of the process to its completion. Specifically: ; In the formula, This refers to the amount of material required from the current moment of the process until the process is completed. This represents the total amount of material required for this process. This represents the cumulative material consumption of this process up to the current moment. Step S5-4-3: Based on the amount of material required from the current moment of the process to its completion, and combined with the unit time work efficiency of the target worker, calculate the additional personnel required for the target worker. Specifically: ; In the formula, E represents the number of additional personnel required for the target job, and E represents the individual work efficiency per unit time for the target job. The remaining available time for the process. The number of employees currently on duty for the target job category; Step S5-4-4: For scenarios where the schedule is ahead of schedule, calculate the redundant number of personnel for the target job, specifically as follows: ; In the formula, For redundant personnel in the target job category, Let E represent the number of employees in the target job category, and E represent the individual work efficiency per unit time for the target job category. The remaining time after the process is completed ahead of schedule; Step S5-5: Based on the calculated number of additional personnel required for the target job and the redundant personnel for the target job, and in conjunction with the "personnel-job" classification file, find suitable technical personnel for the job and schedule personnel accordingly.

[0034] By comparing the predicted construction period with the standard construction period to determine the progress deviation, and combining the individual work efficiency to calculate the number of personnel to supplement or redundancy, dynamic and precise personnel scheduling can be achieved, avoiding the impact of manpower waste or insufficient manpower on construction efficiency.

[0035] The system includes a material consumption prediction module, a material replenishment triggering module, a construction progress prediction module, a site resource association module, and a construction personnel scheduling module. The material consumption prediction module is used to collect material quantity data of construction sites of various scales during the complete construction phase, preprocess the data, draw scatter plots based on the processed data, and use a multinomial algorithm to fit and construct a material consumption prediction model for construction sites of various scales. The material replenishment triggering module is used to calculate the time required for material consumption to reach 0 based on the material consumption prediction model, collect historical data to determine the time for each stage of material outbound review, loading, transportation, unloading and acceptance, and calculate the total material replenishment time. It also combines the reserved buffer time to obtain the material replenishment triggering time, compares it with the actual construction time to determine the risk of material supply interruption and trigger the replenishment process. The construction progress prediction module is used to construct a "time-material quantity" dataset, calculate and correct the material consumption rate using the mean correction method, collect constraint information such as process logic dependency and connection buffer time to construct time series features, divide the training set and validation set according to the proportion, fit the construction progress prediction model with the time series features as input and the process completion degree as output, and trigger the calculation of the connection time of the next process when the predicted process completion degree is 1. The construction site resource association module is used to divide the construction site into sub-regions according to the construction process, sort out the materials required for each sub-region process and establish the association mapping between the sub-region and the materials, collect the skills and qualifications of construction personnel to classify technical jobs, build "personnel-job" files and establish the association between technical jobs and construction site processes; The construction personnel scheduling module is used to extract the estimated completion time of each sub-area process based on the construction progress prediction model, determine the standard completion time of the process using historical data and calculate the deviation value to determine the progress type, calculate the unit time work efficiency of the target job based on historical work data, calculate the number of supplementary personnel when the progress is delayed and the number of redundant personnel when the progress is ahead, and perform personnel scheduling in combination with the "personnel-job type" file.

[0036] The material consumption prediction module includes a historical material processing unit and a material consumption model construction unit; The historical material data processing unit is used to collect and preprocess historical material quantity data from construction sites of various sizes. The material consumption model building unit is used to draw a scatter plot based on the processed material quantity data and to use a polynomial algorithm to fit and build a material consumption prediction model. The material replenishment triggering module includes a material time calculation unit and a replenishment triggering determination unit; The material time calculation unit is used to calculate the time required for material consumption to reach 0 based on the material consumption prediction model, and to obtain the time required for material replenishment based on historical data. The replenishment trigger determination unit is used to calculate the material replenishment trigger time, compare it with the actual construction time to determine whether there is a risk of supply interruption, and trigger the replenishment process.

[0037] The construction progress prediction module includes a consumption rate calculation unit and a progress model construction unit; The consumption rate calculation unit is used to construct a "time-material quantity" dataset, calculate the material consumption rate at adjacent time nodes, and correct it using the mean correction method. The progress model construction unit is used to collect process constraint information to construct time sequence features, divide training and validation sets to fit the construction progress prediction model and trigger process connection. The construction site resource association module includes a sub-region material binding unit and a personnel type classification unit; The sub-region material binding unit is used to divide the construction site into sub-regions according to the construction process and establish an association mapping between the sub-regions and the materials required for the corresponding process. The personnel classification unit is used to collect the skills and qualifications of construction personnel to classify them into different types of work, build "personnel-type of work" files, and associate them with the corresponding construction site procedures.

[0038] The construction personnel scheduling module includes a progress deviation judgment unit and a scheduling personnel calculation unit; The schedule deviation judgment unit is used to extract the estimated completion time of the process, calculate the deviation value from the historical standard time, and determine the type of schedule deviation. The scheduling personnel calculation unit is used to calculate and schedule the number of additional or redundant personnel required in the event of a progress deviation scenario based on the individual's work efficiency per unit time.

[0039] Example 2: Calculating t1: Substitute the cement consumption down to 0 into the model and solve the equation 0 = 100 + 20x - 0.5x 2 Therefore, x = 45 days, which means t1 = 45 days; Calculate t2: Collect historical material replenishment data and take the average time of each step: outbound approval time t out =2. Loading t load =1 day, transportation t trans =3 days, unloading t unload =0.5 days, acceptance time check =0.5 days, and according to the formula, t2 = 7 days; Set a buffer time Δt = 2 days. According to t0 = t1 - t2 - Δt, we get t0 = 45 - 7 - 2 = 36 days. When construction reaches the 36th day, the cement replenishment process is triggered. Example 3: Cement consumption at 10 construction time points was extracted to construct a "time-material quantity" dataset. Taking the 10th day (450 tons) and the 20th day (300 tons) as examples, the material consumption difference was 150 tons after a 10-day time interval. After correction by the mean correction method, v = 14.5 tons / day. Constraint information: Operation 1 (foundation construction) depends on operation 0 (site leveling), with a connection time t. link =2 days, the amount of cement required for process 1 is Z1=500 tons; Timing characteristics: On the 20th day of construction, the cumulative material consumption Q1 = 14.5 × 20 = 290 tons, and the material consumption completion rate C1 = 290 / 500 = 58%. Since C1 < 1, the effective coefficient K for the connection time is... t =0; The dataset is divided into a 7:3 ratio. Using time-series features as input and process completion percentage as output, a fitted model is established: y pred =0.0018C1+0.982; (θ=0.982, θ1=0.0018, ϵ=0.002) When construction reached its 35th day, y pred =1, trigger connection time calculation, the start time of process 2 is: X start2 =X finish1 +t link =37 days; Example 4: Estimated completion time for process 1: X finish1 =35 days, and the historical average completion time of process 1 for n=20 projects of the same scale is 32 days, with a deviation value △T=35-32=3 days; Individual efficiency E: Historical process efficiency Q his_total =5000 tons, t his_total =320 days, calculated as E=Q his_total / (t his_total ×n his This yields E = 1.5625 tons / person / day; Additional personnel N sup Current Q curr =290 tons, Q remain =500-290=210 tons, t remain =12 days, P curr =10 people, calculate N sup ==1.2, rounded up to 2 people, dispatch 2 cement workers from the "Personnel-Job Type" file to supplement Area A, to ensure that Process 1 is completed on time according to the standard. It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. An intelligent construction management method based on the Internet of Things, characterized in that: The intelligent management method includes the following steps: Step S1: Collect the required material quantity data for the complete construction phase of construction sites of various scales in history, preprocess the required material quantity data, draw a scatter plot based on the processed required material quantity data, and construct a material consumption prediction model for construction sites of various scales. Step S2: Replenish materials based on the time required for material consumption to reach 0 as predicted by the material consumption prediction model, combined with the time required for material mobilization. Step S3: Calculate the material consumption rate based on the time output by the material consumption prediction model, quantify the construction progress, and construct a construction progress prediction model. Step S4: Divide the construction site into sub-areas according to the construction site procedures, associate the construction site sub-areas with materials according to the business scenarios of each construction site sub-area procedures, classify construction personnel into technical trades, and associate technical trades with construction site procedures. Step S5: Predict the completion time of construction site procedures based on the construction progress prediction model, set the standard completion time of procedures based on historical construction data, compare the predicted completion time of construction site procedures with the standard completion time of procedures, and schedule personnel according to the judgment results and the types of technical workers.

2. The intelligent construction management method based on the Internet of Things according to claim 1, characterized in that: The specific steps of step S1 are as follows: Step S1-1: Classify the construction sites according to their different scales based on the construction area. Specifically, the range for small-scale sites is [x1, x2], the range for medium-scale sites is [x2-x3], and the range for large-scale sites is [x3-x4]. Here, x1, x2, x3, and x4 are the threshold values ​​for classifying the construction area of ​​different-scale construction sites. Step S1-2: Collect the required material quantities for n construction sites of various sizes throughout the entire process; Step S1-3: For the collected material quantities required from n construction sites of various sizes, perform data preprocessing, specifically as follows: For outliers, the 3σ principle is used to remove extreme data. Specifically, the mean and standard deviation of the required material quantity are calculated, and values ​​that are not in the interval [μ-3σ,μ+3σ] are removed. In the formula, μ is the mean and σ is the standard deviation. For missing values, linear interpolation is used to fill in the missing values; Normalize the required material quantity; Steps S1-4: For the required material quantities of construction sites of the same scale, calculate the average required material quantity. Based on the average required material quantity, draw a scatter plot with time as the horizontal axis and the required material quantity of each type of material as the vertical axis. Steps S1-5: Fit the scatter plot using a multinomial algorithm to construct a material consumption prediction model, specifically as follows: ； In the formula, y represents the required quantity of a certain type of material at a specific moment on the construction site, x represents the time variable of the construction progress, a0 is the basic constant of the polynomial fitting, and a1-a n The trend coefficients obtained from the fitting are denoted as .

3. The intelligent construction management method based on the Internet of Things according to claim 2, characterized in that: The specific steps of step S2 are as follows: Step S2-1: Calculate the time required for material consumption to reach 0 based on the material consumption prediction model, and denote it as t1; Step S2-2: Divide the time required for material replenishment into material outbound review time, material loading time, transportation time, unloading time, and acceptance time. Collect historical material replenishment time data for each type, use the average as the standard value, and calculate the material replenishment time t2, specifically: ； In the formula, t2 is the time required for material replenishment. For material outbound approval time, For material loading time, For transportation time, For unloading time, For the acceptance time; Step S2-3: Calculate the material replenishment trigger time t0, and perform the material replenishment operation based on t0, specifically as follows: ； In the formula, To allow for buffer time, the plan is dynamically formulated based on the actual business scenario; When the actual construction progress time is greater than or equal to the material replenishment trigger time, it is determined that there is a physical risk of supply interruption, and the material replenishment process is triggered.

4. The intelligent construction management method based on the Internet of Things according to claim 3, characterized in that: The specific steps of step S3 are as follows: Step S3-1: Extract the required material quantities of various materials corresponding to n time nodes in the historical construction cycle, and construct a "time-material quantity" dataset; Step S3-2: Classify the dataset according to the construction process. Based on the classified dataset, calculate the material consumption difference between two adjacent time nodes and the corresponding time interval. Then, use the material consumption difference divided by the corresponding time interval to calculate the consumption rate v of each material in each time zone. Step S3-3: Correct the calculated consumption rate v using the mean correction method; Step S3-4: Collect basic constraint information of construction procedures, including logical dependencies between procedures, buffer time between procedures, and total material usage required for a single procedure. Step S3-5: Sort the processes according to the logical dependencies between processes, and construct the time sequence features based on the construction time, material consumption rate, process connection buffer time, and total amount of materials required for the process. The specific time sequence features are the cumulative material consumption, material consumption completion rate, and connection time effectiveness coefficient. Step S3-6: Calculate the time series features, specifically as follows: Cumulative material consumption: ； In the formula, Let be the cumulative material consumption of the i-th process up to the current moment. For material consumption rate, Construction time; Material consumption completion rate: ； In the formula, Let be the material consumption completion rate of the i-th process. Let be the cumulative material consumption of the i-th process. This represents the total amount of materials required for the i-th process. Connection time effective coefficient: ； In the formula, This is the effective time coefficient for the connection between the i-th process and the (i+1)-th process. Let be the material consumption completion rate of the i-th process, when <1 hour, =0, connection time is not calculated. When =1, =1, the connection time is officially included in the start time of the next process; Steps S3-7: Divide the data into training and validation sets in a 7:3 ratio, using time-series features as input and process completion rate as output. Then, minimize the loss function to fit the construction progress prediction model, specifically: ； In the formula, For process completion, , These are the fitted regression coefficients. Let be the material consumption completion rate of the i-th process. This is the error term; Step S3-8: When the model predicts the completion rate of the current process... When =1, the connection time constraint is automatically triggered, combined with The condition for the condition to take effect is 1. The start time of the next process is calculated as follows: ； In the formula, The start time of the next process. Let i be the estimated completion time of the current process i. This represents the connection time between the i-th process and the (i+1)-th process.

5. The intelligent construction management method based on the Internet of Things according to claim 4, characterized in that: The specific steps of step S4 are as follows: Step S4-1: Based on the process division of the construction flow, divide the entire construction site into corresponding sub-areas, with each sub-area corresponding to one process, and construct a "process-sub-area" set; Step S4-2: For the process business scenario of each construction site sub-area, sort out all the material types required for the process, and bind the sub-area number with the corresponding material list by establishing association mapping rules; Step S4-3: Collect the skill qualifications of all construction personnel, classify them into different job categories based on their skill qualifications, and build a "personnel-job category" file.

6. The intelligent construction management method based on the Internet of Things according to claim 5, characterized in that: The specific steps of step S5 are as follows: Step S5-1: Based on the construction progress prediction model and the relationship between the sub-regions of the construction site and the corresponding work processes, extract the estimated completion time of each work process in each sub-region and construct a "sub-region-work process-estimated completion time" correspondence table; Step S5-2: Based on historical construction site data of various scales, calculate the historical average completion time of n similar processes of the same scale, and use it as the standard completion time of the process; Step S5-3: For each process in each sub-region, calculate the deviation value △T between the "estimated completion time" and the "standard completion time of the process". Determine the type of deviation based on the deviation value. When △T<0, it is determined that the schedule is ahead of schedule. When △T=0, the schedule meets the standard. When △T>0, the schedule is behind schedule. Step S5-4: When the process completion time does not meet the standard process completion time, supplement the personnel in the sub-area, specifically as follows: Step S5-4-1: Extract historical work data of the target trade under the same scale and process based on historical construction data, and calculate the work efficiency of a single person per unit time for the target trade. Specifically: ； In the formula, E represents the individual work efficiency of the target public per unit of time. This refers to the total amount of materials consumed when the target trade participated in the operation within the same historical process. The total operation time used to process the total amount of materials consumed by the target public in the same historical process. The target number of workers involved in the same historical process; Step S5-4-2: For scenarios with delayed progress, calculate the amount of material required from the current moment of the process to its completion. Specifically: ； In the formula, This refers to the amount of material required from the current moment of the process until the process is completed. This represents the total amount of material required for this process. This represents the cumulative material consumption of this process up to the current moment. Step S5-4-3: Based on the amount of material required from the current moment of the process to its completion, and combined with the unit time work efficiency of the target worker, calculate the additional personnel required for the target worker. Specifically: ； In the formula, E represents the number of additional personnel required for the target job, and E represents the individual work efficiency per unit time for the target job. The remaining available time for the process. The number of employees currently on duty for the target job category; Step S5-4-4: For scenarios where the schedule is ahead of schedule, calculate the redundant number of personnel for the target job, specifically as follows: ； In the formula, For redundant personnel in the target job category, Let E represent the number of employees in the target job category, and E represent the individual work efficiency per unit time for the target job category. The remaining time after the process is completed ahead of schedule; Step S5-5: Based on the calculated number of additional personnel required for the target job and the redundant personnel for the target job, and in conjunction with the "personnel-job" classification file, find suitable technical personnel for the job and schedule personnel accordingly.

7. An intelligent construction management system based on the Internet of Things, characterized in that: The system includes a material consumption prediction module, a material replenishment triggering module, a construction progress prediction module, a site resource association module, and a construction personnel scheduling module. The material consumption prediction module is used to collect material quantity data of construction sites of various scales during the complete construction phase, preprocess the data, draw scatter plots based on the processed data, and use a multinomial algorithm to fit and construct a material consumption prediction model for construction sites of various scales. The material replenishment triggering module is used to calculate the time required for material consumption to reach 0 based on the material consumption prediction model, collect historical data to determine the time for each stage of material outbound review, loading, transportation, unloading and acceptance, and calculate the total material replenishment time. It also combines the reserved buffer time to obtain the material replenishment triggering time, compares it with the actual construction time to determine the risk of material supply interruption and trigger the replenishment process. The construction progress prediction module is used to construct a "time-material quantity" dataset, calculate and correct the material consumption rate using the mean correction method, collect constraint information such as process logic dependency and connection buffer time to construct time series features, divide the training set and validation set according to the proportion, fit the construction progress prediction model with the time series features as input and the process completion degree as output, and trigger the calculation of the connection time of the next process when the predicted process completion degree is 1. The construction site resource association module is used to divide the construction site into sub-regions according to the construction process, sort out the materials required for each sub-region process and establish the association mapping between the sub-region and the materials, collect the skills and qualifications of construction personnel to classify technical jobs, build "personnel-job" files and establish the association between technical jobs and construction site processes; The construction personnel scheduling module is used to extract the estimated completion time of each sub-area process based on the construction progress prediction model, determine the standard completion time of the process using historical data and calculate the deviation value to determine the progress type, calculate the unit time work efficiency of the target job based on historical work data, calculate the number of supplementary personnel when the progress is delayed and the number of redundant personnel when the progress is ahead, and perform personnel scheduling in combination with the "personnel-job type" file.

8. The intelligent construction management system based on the Internet of Things according to claim 7, characterized in that: The material consumption prediction module includes a historical material processing unit and a material consumption model construction unit; The historical material data processing unit is used to collect and preprocess historical material quantity data from construction sites of various sizes. The material consumption model building unit is used to draw a scatter plot based on the processed material quantity data and to use a polynomial algorithm to fit and build a material consumption prediction model. The material replenishment triggering module includes a material time calculation unit and a replenishment triggering determination unit; The material time calculation unit is used to calculate the time required for material consumption to reach 0 based on the material consumption prediction model, and to obtain the time required for material replenishment based on historical data. The replenishment trigger determination unit is used to calculate the material replenishment trigger time, compare it with the actual construction time to determine whether there is a risk of supply interruption, and trigger the replenishment process.

9. The intelligent construction management system based on the Internet of Things according to claim 7, characterized in that: The construction progress prediction module includes a consumption rate calculation unit and a progress model construction unit; The consumption rate calculation unit is used to construct a "time-material quantity" dataset, calculate the material consumption rate at adjacent time nodes, and correct it using the mean correction method. The progress model construction unit is used to collect process constraint information to construct time sequence features, divide training and validation sets to fit the construction progress prediction model and trigger process connection. The construction site resource association module includes a sub-region material binding unit and a personnel type classification unit; The sub-region material binding unit is used to divide the construction site into sub-regions according to the construction process and establish an association mapping between the sub-regions and the materials required for the corresponding process. The personnel classification unit is used to collect the skills and qualifications of construction personnel to classify them into different types of work, build "personnel-type of work" files, and associate them with the corresponding construction site procedures.

10. The intelligent construction management system based on the Internet of Things according to claim 7, characterized in that: The construction personnel scheduling module includes a progress deviation judgment unit and a scheduling personnel calculation unit; The schedule deviation judgment unit is used to extract the estimated completion time of the process, calculate the deviation value from the historical standard time, and determine the type of schedule deviation. The scheduling personnel calculation unit is used to calculate and schedule the number of additional or redundant personnel required in the event of a progress deviation scenario based on the individual's work efficiency per unit time.

Images