Engineering data planning system based on GIS, BIM and unmanned aerial vehicle

Abstract

The invention discloses an engineering data planning system based on a GIS, a BIM and an unmanned aerial vehicle, and the system comprises a data collection module which is used for collecting modeling data collected by the unmanned aerial vehicle and a material loss rate in historical engineering data; the model construction module is used for performing three-dimensional modeling by utilizing a GIS technology and BIM software to obtain an engineering project virtual model, and constructing a procurement cost prediction model by utilizing a machine learning algorithm; the resource planning module is used for acquiring the actual total material quantity, the equipment quantity and the personnel quantity required by different operation activities based on the engineering project virtual model and the loss rate; and the resource allocation module is used for determining the total amount of actually allocated resources based on the weather forecast data and allocating the resources to the operation area. The invention relates to the technical field of engineering resource planning, and solves the technical problems of resource waste and overhigh cost caused by neglecting the influence of material purchase cost planning and weather factors on engineering construction in an existing engineering data planning system.

Description

Technical Field

[0001] The present invention belongs to the field of engineering resource planning and relates to GIS and BIM technologies, and specifically to an engineering data planning system based on GIS, BIM and unmanned aerial vehicles. Background Art

[0002] With the continuous advancement of science and technology, the field of engineering construction has also ushered in unprecedented development opportunities. In particular, breakthroughs in information technology, remote sensing technology, and automation technology have provided more efficient, accurate, and intelligent solutions for engineering construction. The comprehensive application of geographic information system (GIS), building information modeling (BIM) technology, and drone technology has become an important trend in modern engineering construction management. GIS, with its powerful spatial analysis and data management capabilities, provides macro-geographical environment support for engineering planning; BIM realizes full life cycle management from design to construction to operation and maintenance by constructing refined three-dimensional building models. Drone technology, with its efficient and flexible data collection capabilities, provides unprecedented convenience for engineering site surveying and environmental monitoring.

[0003] A Chinese patent with application number CN201911012588.1 discloses "a construction planning and management system based on BIM+GIS". The system matches the bidding documents of new projects with the enterprise BIM family library, supplements and forms a project-level BIM library; uses existing GIS data to define the area scope for new projects, and forms GIS underlying three-dimensional information data; and automatically outputs a resource allocation table suitable for this project by matching enterprise construction capabilities, enterprise construction quotas, enterprise construction technical standards, work efficiency and other information, to achieve resource optimization and allocation.

[0004] As the complexity and scale of modern engineering construction continue to expand, engineering projects have higher and higher requirements for resource planning. In existing engineering data planning systems, the ability to allocate and optimize resources often depends on the accuracy and update status of input data, and only considers the relevant construction information of the enterprise, ignoring the procurement and deployment of resources and the impact of weather factors on engineering construction, which easily leads to waste of resources and cost overruns, affecting the smooth progress of construction. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an engineering data planning system based on GIS, BIM and drones, which is used to solve the technical problems of ignoring the cost planning of material procurement and the impact of weather factors on engineering construction in the existing engineering data planning system, resulting in resource waste and cost overruns.

[0006] To achieve the above objectives, the present invention provides an engineering data planning system based on GIS, BIM and UAV, including: a data acquisition module, a model building module, a resource planning module and a resource allocation module; wherein,

[0007] The data acquisition module is used to scan the project area through a drone to obtain modeling data; and to obtain the loss rate of each material in the historical project;

[0008] The model building module is used to import the modeling data into the GIS system to form a geospatial database; based on the geospatial database, use BIM software to perform three-dimensional modeling to obtain a virtual model of the engineering project; and use a machine learning algorithm to build a procurement cost prediction model;

[0009] The resource planning module is used to obtain the quantity of materials, equipment and personnel required for a number of operation activities based on the virtual model of the engineering project, and calculate the actual total amount of materials for a single operation activity based on the loss rate and the quantity of materials;

[0010] The resource allocation module is used to determine the total amount of resources required for several work activities according to the demand list of a single work activity after pre-processing the weather forecast data, and allocate the total amount of resources to the work area using the engineering project virtual model; wherein the weather forecast data is obtained through the weather forecast API, and the demand list includes the actual total amount of materials, the number of personnel and the number of equipment;

[0011] It should be noted that the quantity of materials required for the several work activities can be obtained by batch extracting the data of each component in the virtual model of the engineering project through an automated script, and the quantity of materials of different materials can be obtained by statistics.

[0012] Based on the above technical solutions, the use of drones to scan the project area can obtain accurate modeling data efficiently and quickly; the use of GIS technology combined with BIM software for three-dimensional modeling can create a virtual model of the project to improve the accuracy and visualization of engineering design; by analyzing historical engineering data, the predicted loss of the project is calculated based on the loss rate of materials required for historical projects, and a machine learning algorithm is used to build a procurement cost prediction model based on historical material price data, which can scientifically and effectively predict future material costs and help control project costs; finally, combined with weather forecast data, resources are deployed to the corresponding work area to ensure smooth construction and reduce resource waste caused by external factors such as weather.

[0013] Furthermore, the use of a machine learning algorithm to construct a procurement cost prediction model includes the following steps:

[0014] A1, data processing: after collecting historical material price data, perform data cleaning preprocessing and convert the data into a time series format to obtain time series data; wherein the historical material price data includes: material type, material price, price volatility, volume discount, material quantity, transportation cost, storage cost and total purchase cost;

[0015] A2, model construction and training: construct an ARIMA model, and divide the time series data into a training set and a validation set, use the training set and the validation set to train and validate the ARIMA model, and adjust the trained ARIMA model according to the validation results, and finally obtain a procurement cost prediction model whose input is material type, material price, price volatility, batch discount, material quantity, transportation cost, storage cost, and output is total procurement cost.

[0016] The cost prediction model for material procurement is constructed using machine learning algorithms. Through systematic data processing and precise model construction and training, the total procurement cost can be accurately predicted to provide cost planning support for the engineering data planning system, helping the system to make more reasonable procurement decisions, thereby controlling costs and improving efficiency.

[0017] Furthermore, the number of personnel required for a number of operations is obtained by the formula Calculate the number of people required for the i-th operation activity; where n represents the number of operations, W i represents the workload of the i-th activity, S i (0≤S i ≤1) represents the required proportion of male personnel for the i-th operation activity, M i represents the gender adjustment factor for male employees in the ith activity, F i represents the gender adjustment factor of female employees in the i-th job activity, E i represents the average labor efficiency of the i-th operation activity, N i represents the number of equipment for the i-th operation activity, D i It represents the efficiency improvement rate of equipment required for the i-th operation activity;

[0018] It should be noted that μ ij , S i 、M i 、F i 、E i , D i It is obtained by experts in this field based on the experience of historical engineering projects, and n, μ ij , S i 、M i 、F i 、E i , D iBoth are greater than 0.

[0019] Furthermore, the workload W of the i-th operation activity i By formula Calculated; where S ij represents the quantity of the jth material type in the ith activity, μ ij represents the unit construction time of the jth material type, m represents the number of material types, i and j are both positive integers, and m, i, j ≥ 1;

[0020] It should be noted that μ ij Obtained by experts in this field based on historical engineering project experience.

[0021] By comprehensively considering the specific parameters and factors of the operation activities, the number of personnel required for each operation activity can be accurately obtained, avoiding the errors caused by relying on experience and subjective judgment, and improving the accuracy and work efficiency of human resource allocation. The formula takes into account the proportion and adjustment factors of employees of different genders in specific operations, which helps to ensure the rationality and diversity of personnel allocation; at the same time, through the careful calculation of workload, labor efficiency and equipment requirements, it promotes the rational allocation of resources, avoids resource waste, and helps engineering projects effectively reduce costs.

[0022] Furthermore, the actual total amount of materials for a single operation is calculated by the formula R ij =S ij (1+η ij ) to obtain; where R ij represents the actual total amount of material of the jth material type in the i-th operation, S ij represents the quantity of material of the jth material type in the i-th operation, η ij Represents the loss rate of material j in the i-th operation activity.

[0023] Further, the preprocessing of the weather forecast data comprises the following steps:

[0024] B1, divide the project into several construction phases according to the preset project construction plan, and record the number of operations that can be carried out simultaneously in each construction phase;

[0025] B2, calculating the weather sensitivity of the plurality of work activities that can be performed simultaneously to the weather of the day respectively according to the weather forecast data.

[0026] Furthermore, the method for obtaining the weather sensitivity includes:

[0027] C1, extract the weather forecast data of the day; wherein the weather forecast data includes: temperature T, humidity H, wind speed V and rainfall P;

[0028] C2. The weather sensitivity S is obtained through the calculation formula S = ω1T + ω2H + ω3V + ω4P, where ω i (i = 1, 2, 3, 4) represents the influence weight coefficients of different weather forecast data on different operation activities.

[0029] Furthermore, determining the total amount of resources required for several operation activities according to the requirement list of a single operation activity includes:

[0030] D1. Compare the weather sensitivity S of several operation activities to the current day's weather with the sensitivity threshold St; if S < St, mark several operation activities as priority activities; otherwise, mark several operation activities as activities that cannot be carried out.

[0031] D2. Extract the requirement lists corresponding to several single operation activities in the priority activities, and calculate the total amount of resources required for the priority activities by summation.

[0032] The calculation of weather sensitivity provides quantitative data support for project managers, making the decision-making process more scientific and reasonable. By considering weather sensitivity, activities that are more suitable to be carried out under specific weather conditions can be arranged first, thereby maximizing work efficiency and quality, and construction delays and losses caused by adverse weather can be reduced. Resources can be allocated more reasonably to ensure the effective utilization of resources.

[0033] Furthermore, allocating the total amount of resources to the operation area using the virtual model of the engineering project includes the following steps:

[0034] E1. Set the material procurement period, and use the procurement cost prediction model to determine the best material procurement date within the procurement period.

[0035] E2. Procure materials on the best material procurement date, and use GIS path planning technology to plan the shortest procurement path and the shortest resource allocation path, and allocate the total amount of resources to the operation area according to the shortest procurement path and the shortest resource allocation path.

[0036] It should be noted that the material procurement period is within the previous construction stage.

[0037] Furthermore, using the procurement cost prediction model to determine the best material procurement date within the procurement period includes the following steps:

[0038] F1. Collect and input the material price data of the current day, and use the procurement cost prediction model to predict the material procurement costs for several days within the procurement period.

[0039] F2. Draw a cost change trend curve according to the material procurement costs.

[0040] F3, based on the cost change trend curve, select the date with the lowest purchase cost as the best material purchase date.

[0041] By determining the timing of material procurement through predictive models, materials can be purchased when prices are lower, thereby reducing the overall cost of the project; the application of GIS path planning technology ensures that the path from the supplier to the construction site is the shortest, reducing transportation time and costs and improving the efficiency of resource allocation.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] By using drones to obtain accurate modeling data, using GIS technology to process the modeling data into a geospatial database, and using BIM software for three-dimensional modeling, a virtual model of the engineering project was created, which improved the accuracy and visualization of the engineering design; in addition, a machine learning algorithm was used to analyze historical material price data, and a procurement cost prediction model that can predict future material costs was constructed, providing a scientific and effective tool for project cost control; a list of resources required for the work activities was obtained through the virtual model of the engineering project, and the total amount of resources was determined in combination with weather forecast data and personnel-related information, and finally GIS path planning technology was used to optimize the path of material procurement and resource allocation, which improved the accuracy and work efficiency of resource allocation and reduced the waste of resources caused by external factors such as weather. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A schematic diagram of the process flow of the engineering data planning system based on GIS, BIM and drones provided by the present invention;

[0046] Figure 2 A schematic diagram of a process for determining the total amount of resources provided by the present invention;

[0047] Figure 3 A schematic diagram of a resource allocation process based on a procurement cost prediction model and GIS path planning technology provided by the present invention;

[0048] Figure 4 This is a schematic diagram of the framework of the engineering data planning system based on GIS, BIM and drones provided by the present invention. DETAILED DESCRIPTION

[0049] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] See also Figure 1-Figure 4 The embodiment of the present invention provides an engineering data planning system based on GIS, BIM and UAV, comprising: a data acquisition module, a model building module, a resource planning module and a resource allocation module which are progressively connected, and the output of the data acquisition module is communicatively connected with the input of the resource allocation module; wherein,

[0051] The data acquisition module is used to scan the project area through drones to obtain modeling data; and, based on historical project data, obtain the loss rate of materials required for the project;

[0052] The model building module is used to import modeling data into the GIS system to form a geospatial database; based on the geospatial database, use BIM software to perform three-dimensional modeling to obtain a virtual model of the engineering project; and based on historical material price data, use machine learning algorithms to build a procurement cost prediction model;

[0053] The resource planning module is used to obtain the quantity of materials, equipment and personnel required for several work activities based on the virtual model of the engineering project, and calculate the actual total amount of materials for a single work activity based on the loss rate and material quantity;

[0054] The resource allocation module is used to determine the total amount of resources required for several work activities based on the demand list of a single work activity after pre-processing the weather forecast data, and allocate the total amount of resources to the work area using the engineering project virtual model; the weather forecast data is obtained through the weather forecast API, and the demand list includes the actual total amount of materials, the number of personnel, and the number of equipment;

[0055] It should be noted that the quantity of materials required for several work activities can be obtained through automated scripts, by batch extracting the data of each component in the virtual model of the engineering project and statistically obtaining the quantity of different materials.

[0056] Taking the construction project as an example, in the data acquisition module and the model building module, firstly, the drone equipped with a high-resolution camera and a lidar system is used to fly along the planned route to collect high-precision images and point cloud data of buildings, terrain and surrounding areas; then the point cloud data is imported into the GIS system, and the data is cleaned, corrected and classified to generate accurate geospatial information; then the processed data is used to build a geospatial database containing terrain, landforms, objects and location information; based on the geospatial database, BIM software such as Revit or ArchiCAD is used to design the structure, exterior wall, interior layout, etc. of the building, and detailed information such as material type, structural size, pipeline layout, etc. is added to build an accurate virtual model of the project;

[0057] At the same time, in the data collection module, it is also necessary to collect data on historical construction projects, including material purchase volume, actual usage and loss records, and calculate the loss rate of key building materials such as concrete, steel bars, bricks, etc., to provide a basis for subsequent material budgeting and procurement;

[0058] The model building module also includes building a procurement cost prediction model. Specifically, first collect procurement information from historical construction projects and market price data to obtain historical material price data; the historical material price data includes: material type, material price, price volatility, bulk discount, material quantity, transportation cost, storage cost and total procurement cost; then clean the collected data, including removing outliers, processing missing values, correcting errors and eliminating duplicate data operations to ensure data quality and reliability; then convert the cleaned data into a time series format so that it can reflect the trend of material prices over time;

[0059] The converted time series data is divided into a training set and a validation set. The training set is used to train the model, and the validation set is used to test the prediction effect of the model. The ARIMA model is constructed using a machine learning algorithm, and the training set is used to train the ARIMA model to learn the long-term trends and time fluctuations in the data. The validation set is then used to test the prediction ability of the trained ARIMA model, and the accuracy of the model is evaluated by comparing the difference between the actual value and the predicted value. According to the verification results, the ARIMA model is adjusted, such as adjusting the parameter settings or model structure, to improve its prediction performance. After training and adjustment, the final procurement cost prediction model is obtained. The model can output the predicted total procurement cost for the next few days based on the material type, current price, price volatility, bulk discount, material quantity, transportation cost, and storage cost of the input day.

[0060] In order to better plan resources, it is necessary to plan and deploy materials, equipment and personnel in a unified manner. Specifically, in the resource planning module, we first use automated scripts to batch extract the data of each component in the virtual model of the engineering project, and statistically obtain the theoretical quantity of different materials; then, based on the loss rate of different materials, we use the formula R ij =S ij (1+η ij ) to obtain; where R ij represents the actual total amount of material of the jth material type in the i-th operation, S ij represents the quantity of material of the jth material type in the i-th operation, η ij represents the loss rate of material j in the i-th operation; through the virtual model, the model, specification and quantity of equipment required to complete a specific operation can also be determined;

[0061] For each work activity i, its workload W i The formula can be It is calculated that S ij represents the quantity of the jth material type in the ith activity, μ ij It represents the unit construction time of the jth material type, which is obtained from the experience of historical engineering projects. m represents the number of material types. i and j are both positive integers, and m, i, j ≥ 1.

[0062] According to the workload of each operation activity, and referring to the historical engineering project experience data, the gender adjustment factor M of different operation activities is obtained. i and F i , the required proportion of male personnel S i , average labor efficiency E i And the efficiency improvement rate of the required equipment D i , and then further through the formula Calculate the number of personnel required; where M i represents the gender adjustment factor of male employees, F i represents the gender adjustment factor of female employees, N i Indicates the number of devices;

[0063] The gender adjustment factor here reflects the difference in efficiency between genders in different work activities, and can more accurately calculate the work efficiency of personnel of different genders in specific work activities, thereby deriving more accurate personnel requirements; the number of equipment and the equipment's work efficiency improvement rate are used to evaluate the impact of increasing equipment investment on improving work efficiency, thereby reflecting the adjustment of equipment to personnel allocation.

[0064] Finally, in the resource allocation module, the weather sensitivity S of the start date of the next construction phase must be calculated based on the weather forecast data. The calculation formula is S = ω1T + ω2H + ω3V + ω4P, where the weather forecast data includes: temperature T, humidity H, wind speed V and rainfall P, ω i (i=1,2,3,4) represents the weight coefficient of the impact of different weather forecast data on different work activities; then, activities with weather sensitivity less than the sensitivity threshold are selected as priority activities, and the demand list of priority activities is extracted, including the required quantity of materials, personnel and equipment, and the total amount of resources is calculated by summing them up;

[0065] For example, suppose that in a construction project, the completion rate of the foundation construction phase has reached 50%, and now it is necessary to allocate resources for the next main structure construction phase. First, the weather forecast data for the start date of the next construction phase is obtained through the weather forecast API as follows: temperature 30°C, humidity 64%, wind speed 8km / h, rainfall 60mm; then the main structure construction phase is divided into the following work activities: reinforcement engineering, formwork construction, concrete mixing and concrete pouring; set a threshold for the weather forecast data of each work activity, and obtain the weather sensitivity calculation table as follows:

[0066]

[0067]

[0068] Assuming the weather sensitivity is 30, all work activities in the next construction phase are priority activities. At this time, the total amount of all resources required for the priority activities is calculated for the next step of procurement and deployment.

[0069] Next, the material price data of the day is input into the procurement cost prediction model, the predicted cost for each day in the procurement cycle is output, and the cost change curve is drawn. Then, based on the curve chart, the date with the lowest procurement cost is selected to purchase materials. Finally, GIS path planning technology is used to plan the shortest procurement path and the shortest resource allocation path, and the total amount of resources is allocated to the work area.

[0070] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0071] Working principle of the present invention:

[0072] S1: Use drones for efficient scanning to collect necessary modeling data to ensure the comprehensiveness and accuracy of information; and combine historical engineering data to calculate the loss rate of different materials to provide a scientific basis for subsequent material procurement and use;

[0073] S2: By importing the collected data into the GIS system and using BIM software for advanced 3D modeling, an accurate and reliable virtual model of the engineering project is created to improve the visualization and accuracy of the design;

[0074] S3: Uses ARIMA machine learning algorithm to build a model based on historical material price data to predict future material costs and help project cost control and decision-making;

[0075] S4: Based on the virtual model of the engineering project and the personnel and material calculation formulas, the materials, equipment and personnel configuration required for each work activity are counted; through the detailed analysis and preprocessing of weather forecast data, the sensitivity of different work activities to the weather is evaluated, and activities under suitable conditions are prioritized to cope with adverse weather conditions; finally, the cost prediction model is used to determine the best time to purchase materials, and combined with GIS path planning technology, the entire path of resources from procurement to deployment is optimized to reduce costs and improve efficiency.

[0076] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. Engineering data planning system based on GIS, BIM and drones, It is characterized in that include: Data collection module, model building module, resource planning module and resource allocation module; among them, The data acquisition module is used to scan the project area through a drone to obtain modeling data; and to obtain the loss rate of each material in the historical project; The model building module is used to import the modeling data into the GIS system to form a geospatial database; based on the geospatial database, use BIM software to perform three-dimensional modeling to obtain a virtual model of the engineering project; and use a machine learning algorithm to build a procurement cost prediction model; The resource planning module is used to obtain the quantity of materials, equipment and personnel required for a number of operation activities based on the virtual model of the engineering project, and calculate the actual total amount of materials for a single operation activity based on the loss rate and the quantity of materials; The resource allocation module is used to pre-process the weather forecast data and determine the total amount of resources required for several work activities based on the demand list of a single work activity, and use the virtual model of the engineering project to allocate the total amount of resources to the work area; wherein the weather forecast data is obtained through the weather forecast API, and the demand list includes the actual total amount of materials, the number of personnel and the number of equipment.

2. According to the engineering data planning system based on GIS, BIM and drones according to claim 1, It is characterized in that The method of using a machine learning algorithm to construct a procurement cost prediction model includes the following steps: A1, data processing: after collecting historical material price data, perform data cleaning preprocessing and convert the data into a time series format to obtain time series data; wherein the historical material price data includes: material type, material price, price volatility, volume discount, material quantity, transportation cost, storage cost and total purchase cost; A2, model construction and training: construct an ARIMA model, and divide the time series data into a training set and a validation set, use the training set and the validation set to train and validate the ARIMA model, and adjust the trained ARIMA model according to the validation results, and finally obtain a procurement cost prediction model whose input is material type, material price, price volatility, batch discount, material quantity, transportation cost, storage cost, and output is total procurement cost.

3. According to the engineering data planning system based on GIS, BIM and drones as claimed in claim 1, It is characterized in that The method for obtaining the number of personnel required for the several operations is through the formula Calculate the number of people required for the i-th operation activity; where n represents the number of operations, W i represents the workload of the i-th activity, S i (0≤S i ≤1) represents the required proportion of male personnel for the i-th operation activity, M i represents the gender adjustment factor for male employees in the ith activity, F i represents the gender adjustment factor of female employees in the i-th job activity, E i represents the average labor efficiency of the i-th operation activity, N i represents the number of equipment for the i-th operation activity, D i It represents the efficiency improvement rate of equipment required for the i-th operation activity.

4. According to the engineering data planning system based on GIS, BIM and drones as claimed in claim 3, It is characterized in that The workload W of the i-th operation activity i By formula Calculated; where S ij represents the quantity of the jth material type in the ith activity, μ ij represents the unit construction time of the jth material type, m represents the number of material types, i and j are both positive integers, and m, i, j ≥ 1.

5. The engineering data planning system based on GIS, BIM and drone according to claim 1, It is characterized in that The actual total amount of materials for the single operation activity is calculated by the formula R ij =S ij (1+η ij ) to obtain; where R ij represents the actual total amount of material of the jth material type in the i-th operation, S ij represents the quantity of material of the jth material type in the i-th operation, η ij Represents the loss rate of material j in the i-th operation activity.

6. The engineering data planning system based on GIS, BIM and drone according to claim 1, It is characterized in that The preprocessing of weather forecast data comprises the following steps: B1, divide the project into several construction phases according to the preset project construction plan, and record the number of operations that can be carried out simultaneously in each construction phase; B2. Calculate the weather sensitivities of the several simultaneously executable job activities to the weather on the current day according to the weather forecast data.

7. The engineering data planning system based on GIS, BIM and unmanned aerial vehicle according to claim 6, wherein, the method for obtaining the weather sensitivity includes: C1. Extract the weather forecast data for the current day; wherein, the weather forecast data includes: temperature T, humidity H, wind speed V and rainfall P; C2, by calculating the formula S = ω 1 T+ω 2 H+ω 3 V+ω 4 P obtains weather sensitivity S, where ω i (i=1,2,3,4) represents the weight coefficient of the impact of different weather forecast data on different work activities.

8. The engineering data planning system based on GIS, BIM and unmanned aerial vehicle according to claim 1, wherein, the determination of the total amount of resources required for several job activities according to the requirement list of a single job activity includes: D1. Compare the weather sensitivity S of several job activities to the weather on the current day with the sensitivity threshold St; if S < St, mark several job activities as priority activities; otherwise, mark several job activities as non-executable activities; D2. Extract the requirement lists corresponding to several single job activities in the priority activities, and calculate the total amount of resources required for the priority activities by summation.

9. The engineering data planning system based on GIS, BIM and unmanned aerial vehicle according to claim 1, wherein, allocating the total amount of resources to the job area by using the virtual model of the engineering project includes the following steps: E1. Set the material procurement period, and use the procurement cost prediction model to determine the best material procurement date within the procurement period; E2. Procure materials on the best material procurement date, and use GIS path planning technology to plan the shortest procurement path and the shortest resource allocation path, and allocate the total amount of resources to the job area according to the shortest procurement path and the shortest resource allocation path.

10. The engineering data planning system based on GIS, BIM and unmanned aerial vehicle according to claim 9, wherein, using the procurement cost prediction model to determine the best material procurement date within the procurement period, includes the following steps: F1. Collect and input the material price data for the current day, and use the procurement cost prediction model to predict the material procurement costs for several days within the procurement period; F2. Draw a cost change trend curve according to the material procurement costs; F3. Select the date with the lowest procurement cost as the best material procurement date according to the cost change trend curve.

Images