BIM-based engineering progress and cost dynamic management and control optimization method and system

Abstract

The invention provides a BIM-based engineering progress and cost dynamic management and control optimization method and system, and relates to the technical field of engineering management and control optimization, and the method comprises the steps: building a digital twin basic platform with a real-time sensing capability based on a BIM model and multi-source sensor data; a progress plan and cost reference data are imported, a progress-cost correlation model is established, a comprehensive deviation value is calculated, and multiple groups of optimization schemes including resource configuration, process organization and cost control parameters are automatically generated; parallel simulation is carried out on the digital twin platform, progress and cost prediction results are obtained, multi-target evaluation is carried out, and an optimal scheme is selected and issued to a site for execution; and continuously collecting actual execution data, comparing the actual execution data with a simulation result, and when a deviation exceeds a threshold value, updating a progress-cost correlation model in the digital twin platform by using the actual data, thereby realizing adaptive evolution and forming dynamic collaborative management and control of progress and cost. The accuracy and efficiency of progress and cost control can be effectively improved, and the project risk is reduced.

Description

Technical Field

[0001] The present invention relates to the optimization technology of project management and control, and particularly to a dynamic management and control optimization method and system for project progress and cost based on BIM. Background Art

[0002] Building Information Modeling (BIM) technology has been widely used in the field of engineering construction, providing digital support for the whole life cycle management of engineering projects. Through BIM technology, the three-dimensional visualization, information integration and collaborative management of engineering projects can be realized. In the construction stage of engineering projects, BIM technology can be used to simulate the construction process, optimize the construction plan, control the construction progress and cost. Traditional construction management methods mainly rely on manual experience and static data, and it is difficult to adapt to the complex and changeable construction site environment. With the rapid development of technologies such as the Internet of Things, big data and artificial intelligence, the integration of these new technologies with BIM technology can realize the dynamic management and control and optimization of construction progress and cost.

[0003] However, the existing BIM-based engineering progress and cost management and control methods still have some defects and deficiencies:

[0004] Lack of real-time perception ability: Traditional BIM models are usually static and it is difficult to reflect the real-time changes of the construction site. Due to the lack of real-time perception of information such as construction resources, personnel, equipment, etc., the prediction and control of progress and cost are not accurate enough.

[0005] Weak correlation between progress and cost: Most of the existing methods manage progress and cost separately, lacking in-depth analysis of the correlation between the two. This makes it difficult to effectively coordinate the relationship between progress and cost, resulting in the difficulty of maximizing the overall benefits of the project.

[0006] The generation and evaluation methods of optimization schemes are not intelligent enough: Traditional optimization schemes mainly rely on manual experience and lack intelligent auxiliary decision-making support. This leads to low efficiency in generating optimization schemes and it is difficult to ensure the effectiveness and feasibility of the schemes. Summary of the Invention

[0007] The embodiments of the present invention provide a dynamic management and control optimization method and system for project progress and cost based on BIM, which can solve the problems in the prior art.

[0008] In the first aspect of the embodiments of the present invention,

[0009] A dynamic management and control optimization method for project progress and cost based on BIM is provided, including:

[0010] The computer vision algorithm is used to analyze the BIM model to extract the engineering space information and component attribute information, and establish an initial construction scene model; visual sensors are deployed at the construction site to collect construction implementation status data, positioning sensors are deployed to collect construction personnel distribution data, and Internet of Things sensors are deployed to collect mechanical equipment operation data. The construction implementation status data, the construction personnel distribution data, and the mechanical equipment operation data are weighted and combined to generate multi-source data; the multi-source data is input into a pre-trained deep learning model for feature extraction and data fusion to generate real-time construction resource status data; the real-time construction resource status data is dynamically mapped with the initial construction scene model to build a digital twin basic platform with real-time perception capabilities;

[0011] Based on the digital twin basic platform, the construction schedule plan data and the cost control benchmark data are imported to establish a schedule-cost correlation model; the real-time construction resource status data is received in real time, and the current schedule completion situation and cost consumption situation are calculated through the schedule-cost correlation model, and the comprehensive deviation value is obtained by comparing with the construction schedule plan data and the cost control benchmark data; multiple groups of optimization schemes including resource allocation parameters, process organization parameters, and cost control parameters are automatically generated according to the comprehensive deviation value; the multiple groups of optimization schemes are input into the digital twin basic platform for parallel simulation to obtain the simulation prediction results of each scheme, and the simulation prediction results include schedule prediction results and cost prediction results;

[0012] The schedule prediction results and the cost prediction results are evaluated with multiple objectives, and the execution scheme with the optimal comprehensive benefit is selected; the optimal execution scheme is sent to the on-site management terminal through the digital twin basic platform, and the scheme execution monitoring module is started to continuously collect actual execution data; the actual execution data is compared and analyzed with the simulation prediction results in real time. When the comparison deviation exceeds the preset threshold, the actual execution data is used to update the schedule-cost correlation model in the digital twin basic platform to realize the adaptive evolution of the digital twin environment, ensure the accuracy of the next round of simulation verification, and form the digital twin dynamic collaborative control of the construction schedule and cost.

[0013] Based on the digital twin basic platform, the construction schedule plan data and the cost control benchmark data are imported to establish a schedule-cost correlation model; the real-time construction resource status data is received in real time, and the current schedule completion situation and cost consumption situation are calculated through the schedule-cost correlation model, and the comprehensive deviation value obtained by comparing with the construction schedule plan data and the cost control benchmark data includes:

[0014] Import the construction progress plan data and cost control benchmark data into the digital twin basic platform; extract the characteristics of the real-time status data of construction resources collected at the construction site, extract the operation efficiency characteristics from the personnel data, extract the energy consumption level characteristics from the equipment data, extract the loss rate characteristics from the material data, and construct the operation efficiency characteristics, the energy consumption level characteristics, and the loss rate characteristics into a resource allocation feature vector;

[0015] Construct a directed acyclic graph based on the logical dependency relationship between construction processes, extract the process completion degree characteristics and critical path characteristics from the directed acyclic graph, and construct the process completion degree characteristics and the critical path characteristics into a process implementation feature vector;

[0016] Construct a multi-layer neural network as a progress-cost correlation model, and set an attention mechanism module in the middle layer of the progress-cost correlation model; input the resource allocation feature vector and the process implementation feature vector into the progress-cost correlation model, calculate the dynamic correlation strength between the resource allocation feature vector and the process implementation feature vector through the attention mechanism module, and generate a resource-process interaction matrix;

[0017] Input the resource-process interaction matrix into the progress-cost correlation model, calculate the current construction progress completion situation and cost consumption situation, and obtain progress prediction data and cost prediction data; calculate the progress deviation value by comparing the progress prediction data with the construction progress plan data, calculate the cost deviation value by comparing the cost prediction data with the cost control benchmark data, and calculate the comprehensive deviation value based on the combination of the progress deviation data and the cost deviation data.

[0018] Calculating the progress deviation value by comparing the progress prediction data with the construction progress plan data, and calculating the cost deviation value by comparing the cost prediction data with the cost control benchmark data includes:

[0019] Collect basic data, where the basic data includes real-time construction site data and planned process completion data; extract the actual process completion data, resource usage data, and cost consumption data from the real-time construction site data, and store the actual process completion data, the resource usage data, and the cost consumption data in a sliding time window according to the time series;

[0020] Construct a progress prediction model, calculate the process completion rate based on the actual process completion data, and calculate the process completion rate by weighted calculation of the ratio of the actual completed project quantity of the process to the planned process completion data; analyze the position of the process in the critical path to determine the position importance coefficient, analyze the consumption of man, machine, and materials of the process to determine the resource consumption coefficient, and analyze the front and back dependency relationships of the process to determine the process correlation coefficient;

[0021] A weighted combination of the position importance coefficient, the resource consumption coefficient, and the process correlation coefficient is used to obtain the process weight coefficient; based on the product of the process completion rate and the process weight coefficient, progress prediction data is obtained; the progress prediction data is compared with the planned process completion data to calculate the progress deviation value;

[0022] A cost prediction model is constructed, and the labor cost, equipment cost, and material cost are calculated based on the resource usage data and the cost consumption data; the labor cost is obtained based on the product of the actual working hours and the actual labor unit price, the equipment cost is obtained based on the product of the actual equipment usage time and the actual equipment rental rate, and the material cost is obtained based on the product of the actual material usage and the actual material unit price;

[0023] The Kalman filter algorithm is used to perform noise smoothing processing on the labor cost, the equipment cost, and the material cost, and the smoothed data is combined to obtain cost prediction data; the cost prediction data is compared with the cost control benchmark data to calculate the cost deviation value.

[0024] According to the comprehensive deviation value, multiple groups of optimization plans including resource allocation parameters, process organization parameters, and cost control parameters are automatically generated; the multiple groups of optimization plans are input into the digital twin basic platform for parallel simulation, and the simulation prediction results of each plan are obtained, and the simulation prediction results include progress prediction results and cost prediction results, including:

[0025] The comprehensive deviation value includes a progress deviation value and a cost deviation value. A progress optimization objective function is constructed based on the progress deviation value, and a cost optimization objective function is constructed based on the cost deviation value; the progress optimization objective function and the cost optimization objective function are input into an improved particle swarm algorithm, and multiple groups of optimization plans are generated through iterative optimization; each group of optimization plans includes resource allocation parameters, process organization parameters, and cost control parameters, where the resource allocation parameters are used to optimize the number of construction teams, the number of equipment, and the material supply volume, the process organization parameters are used to optimize the process interspersed relationship, the process duration, and the process resource requirements, and the cost control parameters are used to optimize the labor unit price, the equipment rate, and the material unit price;

[0026] A construction site model, a resource flow model, and a process implementation model are constructed on the digital twin basic platform; the resource allocation parameters are mapped to the resource flow model, the process organization parameters are mapped to the process implementation model, and the cost control parameters are mapped to the construction site model; a distributed computing architecture is used to allocate the mapped models to multiple computing nodes;

[0027] Execute parallel simulation on the multiple computing nodes; perform resource scheduling simulation based on the resource flow model to obtain simulation resource utilization prediction data, perform process execution simulation based on the process implementation model to obtain simulation schedule prediction data, and perform cost consumption simulation based on the construction site model to obtain simulation cost prediction data; combine the simulation resource utilization prediction data, the simulation schedule prediction data, and the simulation cost prediction data to form a simulation prediction result.

[0028] Construct a schedule optimization objective function based on the schedule deviation value, and construct a cost optimization objective function based on the cost deviation value, including:

[0029] Use the K-means clustering algorithm to divide the schedule deviation values into a deviation process group with a value higher than the preset deviation threshold and a deviation process group with a value lower than the preset deviation threshold, and use the analytic hierarchy process to construct a judgment matrix for the deviation process group with a value higher than the preset deviation threshold and the deviation process group with a value lower than the preset deviation threshold from three dimensions: process importance, process criticality, and process duration;

[0030] Calculate the eigenvector of the judgment matrix using the geometric mean method to obtain the process weight coefficient; sum the product of the process weight coefficient and the schedule deviation value, and construct a schedule optimization objective function based on the minimum value of the summation result;

[0031] The calculation formula for the schedule optimization objective function is as follows:

[0032]

[0033] Among them, F s is the schedule optimization objective function, m is the total number of processes, w i is the weight coefficient of the i-th process, and d i is the schedule deviation value of the i-th process;

[0034] Use the K-means clustering algorithm to divide the cost deviation values into a deviation cost group with a value higher than the preset deviation threshold and a deviation cost group with a value lower than the preset deviation threshold, and use the Delphi method to conduct expert scoring on the deviation cost group with a value higher than the preset deviation threshold and the deviation cost group with a value lower than the preset deviation threshold from three dimensions: cost ratio, cost controllability, and cost sensitivity, and obtain the cost weight coefficient through multiple rounds of expert scoring;

[0035] Sum the product of the cost weight coefficient and the cost deviation value, and construct a cost optimization objective function with the minimum value of the summation result;

[0036] The calculation formula for the cost optimization objective is as follows:

[0037]

[0038] Among them, F c is the cost optimization objective function, n is the total number of cost items, and W j is the weight coefficient of the j-th cost item, and C j is the cost deviation value of the j-th cost item.

[0039] Input the progress optimization objective function and the cost optimization objective function into the improved particle swarm algorithm, and generate multiple groups of optimization solutions through iterative optimization, including:

[0040] Calculate the adaptive weight coefficient according to the progress deviation value and the cost deviation value. Weight the absolute value of the progress deviation value and the absolute value of the cost deviation value to obtain the absolute value of the deviation coefficient. The progress weight coefficient in the adaptive weight coefficient is obtained based on the ratio of the absolute value of the progress deviation value to the absolute value of the deviation coefficient, and the cost weight coefficient in the adaptive weight coefficient is obtained based on the ratio of the absolute value of the cost deviation value to the absolute value of the deviation coefficient;;

[0041] Use the Logistics chaotic mapping to generate the initial particle swarm, map the initial particle swarm to the decision space to construct the particle swarm position vector; calculate the distance between the particle swarm position vector and the population center of gravity to obtain the population aggregation degree; set the adaptive mutation probability based on the population aggregation degree, and the adaptive mutation probability increases according to the exponential function law as the population aggregation degree increases;

[0042] Input the progress optimization objective function and the cost optimization objective function into the improved particle swarm algorithm; update the inertia weight in a non-linear decreasing manner, and the inertia weight decreases according to the cosine function law as the number of iterations increases; update the learning factor in an adaptive manner, and the learning factor includes an individual learning factor and a group learning factor, where the individual learning factor increases according to the exponential function law as the number of iterations increases, and the group learning factor decreases according to the exponential function law as the number of iterations increases;

[0043] In each iteration, calculate the degree of constraint violation based on the particle swarm position vector, and use the penalty function method to weight the degree of constraint violation, the progress optimization objective function, and the cost objective function to obtain the fitness value; calculate the crowding distance of each particle in the population; select the solutions with a crowding distance greater than the preset distance threshold as elite individuals and retain them for the next generation;

[0044] Perform local search on the elite individuals using the pattern search method to obtain the local search results of the elite individuals. The step size of the pattern search method decreases according to the exponential function law as the number of iterations increases; update the global optimal solution based on the local search results, and determine whether the termination condition is satisfied; when the termination condition is satisfied, output the global optimal solution as the optimization solution.

[0045] Perform multi-objective evaluation on the progress prediction result and the cost prediction result, and select the execution plan with the optimal comprehensive benefit; send the optimal execution plan to the on-site management terminal through the digital twin basic platform, and start the plan execution monitoring module to continuously collect actual execution data, including:

[0046] Calculate the progress benefit evaluation indicators based on the progress prediction result. The progress benefit evaluation indicators include the critical path duration compression amount indicator, the construction process continuity indicator, and the milestone node compliance indicator; calculate the cost benefit evaluation indicators according to the cost prediction result. The cost benefit evaluation indicators include the total cost savings rate indicator, the cost composition rationality indicator, and the cash flow matching degree indicator. Combine the progress benefit evaluation indicators and the cost benefit evaluation indicators to form a multi-objective evaluation indicator set;

[0047] Construct a multi-objective evaluation function, and normalize the indicator values in the multi-objective evaluation indicator set; set the normalized progress weight coefficient and the normalized cost weight coefficient based on the normalized indicator values; multiply the normalized progress weight coefficient by the normalized progress indicator value to obtain the progress weighted score, and multiply the normalized cost weight coefficient by the normalized cost indicator value to obtain the cost weighted score;

[0048] Perform multi-objective comprehensive evaluation on the progress weighted score and the cost weighted score, and calculate the comprehensive benefit score; sort multiple optimization plans according to the comprehensive benefit score; select the optimization plan with the highest comprehensive benefit score as the optimal execution plan;

[0049] Convert the optimal execution plan into a standard data format, generate an execution data packet including construction operation instructions and resource allocation plans; send the execution data packet to the on-site management terminal through the digital twin basic platform; start the plan execution monitoring module to collect actual execution data through the data collection devices deployed on the on-site management terminal.

[0050] In the second aspect of the embodiment of the present invention,

[0051] Provide a BIM-based dynamic control and optimization system for project progress and cost, including:

[0052] The first unit is used to parse the BIM model by using computer vision algorithms to extract engineering space information and component attribute information, and establish an initial construction scene model; deploy visual sensors at the construction site to collect construction implementation status data, deploy positioning sensors to collect construction personnel distribution data, deploy Internet of Things sensors to collect mechanical equipment operation data, and perform weighted combination on the construction implementation status data, the construction personnel distribution data, and the mechanical equipment operation data to generate multi-source data; input the multi-source data into a pre-trained deep learning model for feature extraction and data fusion to generate real-time construction resource status data; perform dynamic mapping on the real-time construction resource status data and the initial construction scene model to build a digital twin basic platform with real-time perception capabilities;

[0053] The second unit is used to import construction schedule plan data and cost control benchmark data based on the digital twin basic platform to establish a schedule-cost association model; receive the real-time construction resource status data in real time, calculate the current schedule completion situation and cost consumption situation through the schedule-cost association model, and compare with the construction schedule plan data and the cost control benchmark data to obtain a comprehensive deviation value; automatically generate multiple groups of optimization plans including resource configuration parameters, process organization parameters, and cost control parameters according to the comprehensive deviation value; input the multiple groups of optimization plans into the digital twin basic platform for parallel simulation to obtain simulation prediction results of each plan, and the simulation prediction results include schedule prediction results and cost prediction results;

[0054] The third unit is used to perform multi-objective evaluation on the schedule prediction results and the cost prediction results, and select the execution plan with the optimal comprehensive benefit; send the optimal execution plan to the on-site management terminal through the digital twin basic platform, and start the plan execution monitoring module to continuously collect actual execution data; perform real-time comparison and analysis on the actual execution data and the simulation prediction results, and when the comparison deviation exceeds the preset threshold, use the actual execution data to update the schedule-cost association model in the digital twin basic platform to realize the adaptive evolution of the digital twin environment, ensure the accuracy of the next round of simulation verification, and form the digital twin dynamic collaborative control of construction schedule and cost.

[0055] In the third aspect of the embodiments of the present invention,

[0056] There is provided an electronic device, including:

[0057] A processor;

[0058] A memory for storing instructions executable by the processor;

[0059] Wherein, the processor is configured to call the instructions stored in the memory to execute the method described above.

[0060] In the fourth aspect of the embodiments of the present invention,

[0061] a computer-readable storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the foregoing method is implemented.

[0062] The beneficial effects of this application are as follows:

[0063] 1. Improve the accuracy and efficiency of progress and cost control: By using the BIM model, multi-source sensor data, and deep learning model, this method constructs a digital twin platform with real-time perception capabilities, which can monitor the status of construction resources, progress completion, and cost consumption in real time, and compare and analyze with the planned data, so as to more accurately grasp the project progress, detect deviations early, and avoid potential risks. The automated data collection and analysis process also greatly improves the control efficiency.

[0064] 2. Optimize resource allocation and process organization: Based on the progress-cost correlation model and the digital twin platform, this method can automatically generate multiple sets of optimization plans, and evaluate the progress and cost prediction results of each plan through parallel simulation, so as to select the plan with the best comprehensive benefits. This helps to optimize resource allocation, improve the efficiency of process organization, reduce costs, and shorten the construction period.

[0065] 3. Realize the dynamic collaborative control of construction progress and cost: By comparing the actual execution data with the simulation prediction results in real time and using the actual data to update the progress-cost correlation model in the digital twin platform, this method realizes the adaptive evolution of the digital twin environment, ensures the accuracy of simulation verification, forms the dynamic collaborative control of construction progress and cost, and improves the overall level of project management. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 is a schematic flow chart of the method for optimizing the dynamic control of engineering progress and cost based on BIM in the embodiments of the present invention;

[0067] Figure 2 is a schematic structural diagram of the system for optimizing the dynamic control of engineering progress and cost based on BIM in the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0069] The technical solution of the present invention will be described in detail below with specific embodiments. The following several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0070] Figure 1 It is a schematic flowchart of the method for optimizing the dynamic control of project progress and cost based on BIM in the embodiments of the present invention. As Figure 1 shown, the method includes:

[0071] S11. Parse the BIM model using computer vision algorithms to extract engineering space information and component attribute information, and establish an initial construction scene model; deploy visual sensors at the construction site to collect construction implementation status data, deploy positioning sensors to collect construction personnel distribution data, deploy Internet of Things sensors to collect mechanical equipment operation data, and perform weighted combination on the construction implementation status data, the construction personnel distribution data, and the mechanical equipment operation data to generate multi-source data; input the multi-source data into a pre-trained deep learning model for feature extraction and data fusion to generate real-time construction resource status data; perform dynamic mapping on the real-time construction resource status data and the initial construction scene model to construct a digital twin basic platform with real-time perception capabilities;

[0072] S12. Based on the digital twin basic platform, import construction progress plan data and cost control benchmark data, and establish a progress-cost association model; receive the real-time construction resource status data in real time, calculate the current progress completion situation and cost consumption situation through the progress-cost association model, and compare with the construction progress plan data and the cost control benchmark data to obtain a comprehensive deviation value; automatically generate multiple groups of optimization solutions including resource allocation parameters, process organization parameters, and cost control parameters according to the comprehensive deviation value; input the multiple groups of optimization solutions into the digital twin basic platform for parallel simulation to obtain simulation prediction results of each solution, and the simulation prediction results include progress prediction results and cost prediction results;

[0073] S13. Perform multi-objective evaluation on the progress prediction results and the cost prediction results, and select the optimal implementation solution with the best comprehensive benefit; send the optimal implementation solution to the on-site management terminal through the digital twin basic platform, and start the scheme execution monitoring module to continuously collect actual execution data; perform real-time comparison and analysis on the actual execution data and the simulation prediction results, and when the comparison deviation exceeds the preset threshold, use the actual execution data to update the progress-cost association model in the digital twin basic platform to realize the adaptive evolution of the digital twin environment, ensure the accuracy of the next round of simulation verification, and form the digital twin dynamic collaborative control of construction progress and cost.

[0074] In an alternative embodiment, based on the digital twin basic platform, construction progress plan data and cost control benchmark data are imported to establish a progress-cost correlation model; the real-time status data of construction resources is received in real time, and the current progress completion situation and cost consumption situation are calculated through the progress-cost correlation model, and the comprehensive deviation value obtained by comparing with the construction progress plan data and the cost control benchmark data includes:

[0075] Import construction progress plan data and cost control benchmark data into the digital twin basic platform; perform feature extraction on the real-time status data of construction resources collected at the construction site, extract operation efficiency features from personnel data, extract energy consumption level features from equipment data, extract loss rate features from material data, and construct the extracted operation efficiency features, energy consumption level features and loss rate features into a resource allocation feature vector;

[0076] Construct a directed acyclic graph based on the logical dependency relationship between construction processes, extract process completion degree features and critical path features from the directed acyclic graph, and construct the process completion degree features and the critical path features into a process implementation feature vector;

[0077] Construct a multi-layer neural network as a progress-cost correlation model, and set an attention mechanism module in the middle layer of the progress-cost correlation model; input the resource allocation feature vector and the process implementation feature vector into the progress-cost correlation model, and calculate the dynamic correlation strength between the resource allocation feature vector and the process implementation feature vector through the attention mechanism module to generate a resource-process interaction matrix;

[0078] Input the resource-process interaction matrix into the progress-cost correlation model, calculate the current construction progress completion situation and cost consumption situation, and obtain progress prediction data and cost prediction data; compare and calculate the progress prediction data with the construction progress plan data to obtain a progress deviation value, compare and calculate the cost prediction data with the cost control benchmark data to obtain a cost deviation value, and calculate a comprehensive deviation value based on the combination of the progress deviation data and the cost deviation data.

[0079] Based on the digital twin platform, by establishing a progress-cost correlation model, the real-time monitoring and prediction of the progress and cost of construction projects are realized, and comprehensive deviation analysis is provided. The core of this method is to use a multi-layer neural network combined with an attention mechanism to dynamically associate resource allocation and process implementation, so as to more accurately predict project progress and cost.

[0080] First, import the construction schedule data and cost control baseline data into the digital twin basic platform. The schedule data includes the planned start time, end time, duration of each process, and the logical relationship between processes. The cost control baseline data includes the budget cost, actual cost, and cost composition of each process. For example, in the foundation engineering stage of a certain project, the planned duration is 30 days and the budget cost is 1 million yuan.

[0081] Next, collect the resource status data at the construction site in real time, including personnel, equipment, and material data. Extract features from the collected data. Extract the operation efficiency feature from the personnel data, such as the time required for a worker to complete a unit of work. Extract the energy consumption level feature from the equipment data, such as the fuel consumption per hour of an excavator. Extract the loss rate feature from the material data, such as the ratio of the actual usage to the planned usage of cement. Combine the extracted operation efficiency, energy consumption level, and loss rate features into a resource allocation feature vector. For example, the resource allocation feature vector for a certain day can be expressed as [average operation efficiency of workers: 0.8, average fuel consumption of excavators: 10 liters / hour, cement loss rate: 5%].

[0082] Then, construct a directed acyclic graph according to the logical dependencies between construction processes. For example, the processes of foundation engineering include: excavation, foundation pouring, and backfilling. Among them, excavation is the pre - process of foundation pouring, and foundation pouring is the pre - process of backfilling. Extract the process completion degree feature from the directed acyclic graph, such as the proportion of currently completed processes. Extract the critical path feature, such as the length of the critical path and the completion status of the processes on the current critical path. Combine the process completion degree feature and the critical path feature into a process implementation feature vector. For example, the process implementation feature vector for a certain day can be expressed as [process completion degree: 60%, critical path length: 20 days, critical path completion degree: 50%].

[0083] Next, construct a multi - layer neural network as the schedule - cost correlation model. Set an attention mechanism module in the middle layer of the model. Input the resource allocation feature vector and the process implementation feature vector into the schedule - cost correlation model. The attention mechanism module will calculate the dynamic correlation strength between the resource allocation feature vector and the process implementation feature vector, and generate a resource - process interaction matrix. This matrix reflects the degree of influence of different resource allocations on the completion status of different processes. For example, the resource - process interaction matrix can show that an increase in the fuel consumption of the excavator has a greater impact on the completion progress of the foundation pouring process.

[0084] Input the resource - process interaction matrix into the schedule - cost correlation model to calculate the current construction progress completion and cost consumption, and obtain the schedule prediction data and cost prediction data. For example, the model predicts that the current progress completion is 65% and the cost consumption is 600,000 yuan. Compare the schedule prediction data with the construction schedule plan data to calculate the schedule deviation value, and compare the cost prediction data with the cost control baseline data to calculate the cost deviation value. For example, the schedule deviation value is +5% and the cost deviation value is -40%. Calculate the comprehensive deviation value based on the combination of the schedule deviation data and the cost deviation data. For example, the comprehensive deviation value is -30%.

[0085] The solution of this application can:

[0086] Improve prediction accuracy: By dynamically correlating resource allocation and process implementation through the attention mechanism, it can more accurately predict project schedule and cost, avoiding the prediction errors caused by traditional methods due to ignoring the impact of resource allocation on processes. Real - time monitoring and early warning: This method can receive construction resource status data in real - time, perform real - time calculations, promptly detect deviations in project schedule and cost, and give early warnings to provide decision - making support for project managers. Optimize resource allocation: Through the resource - process interaction matrix, it can analyze the impact of different resource allocations on process completion, thereby optimizing resource allocation, improving resource utilization efficiency, and reducing project costs.

[0087] In an alternative implementation, comparing the schedule prediction data with the construction schedule plan data to calculate the schedule deviation value, and comparing the cost prediction data with the cost control baseline data to calculate the cost deviation value includes:

[0088] Collect basic data, where the basic data includes real - time construction site data and planned process completion data; extract the actual process completion data, resource usage data, and cost consumption data from the real - time construction site data, and store the actual process completion data, the resource usage data, and the cost consumption data in a sliding time window according to the time series.

[0089] Build a schedule prediction model. Calculate the process completion rate based on the actual process completion data, and perform weighted calculation on the ratio of the actual completed project quantity of the process to the planned process completion data to obtain the process completion rate; analyze the position of the process in the critical path to determine the position importance coefficient, analyze the consumption of man, machine, and materials of the process to determine the resource consumption coefficient, and analyze the forward and backward dependencies of the process to determine the process correlation coefficient.

[0090] The weighted combination of the position importance coefficient, the resource consumption coefficient, and the process correlation coefficient is used to obtain the process weight coefficient; based on the product of the process completion rate and the process weight coefficient, the progress prediction data is obtained; the progress prediction data is compared and calculated with the process planned completion data to obtain the progress deviation value;

[0091] A cost prediction model is constructed, and the labor cost, equipment cost, and material cost are calculated based on the resource usage data and the cost consumption data; the labor cost is obtained based on the product of the actual working hours and the actual labor unit price, the equipment cost is obtained based on the product of the actual equipment usage time and the actual equipment rental rate, and the material cost is obtained based on the product of the actual material usage and the actual material unit price;

[0092] The Kalman filter algorithm is used to perform noise smoothing processing on the labor cost, the equipment cost, and the material cost, and the smoothed data is combined to obtain the cost prediction data; the cost prediction data is compared and calculated with the cost control benchmark data to obtain the cost deviation value.

[0093] A method for predicting the progress and cost deviation of an engineering project based on real-time data, the specific implementation steps are as follows:

[0094] First, collect basic data. This step requires obtaining real-time data from various sources such as sensors at the construction site, material management systems, and personnel attendance systems, such as the actual completed engineering quantities of each process, resource usage (including labor hours, equipment usage time, material consumption), and corresponding cost expenditures. At the same time, it is also necessary to collect the process planned completion data of the project, such as the planned start and end times of each process, the planned completed engineering quantity, etc. Suppose the planned completed engineering quantity of process A in a certain project is 1000 cubic meters, the actual completed engineering quantity is 800 cubic meters, the labor hours are 100 hours, the equipment usage time is 50 hours, and the material consumption is 200 tons.

[0095] Next, the collected real-time data at the construction site and the process planned completion data are stored in a sliding time window and organized according to the time series. The size of the sliding time window can be adjusted according to the specific situation of the project, for example, it can be set to one week or one month. The advantage of doing this is that it can dynamically track the progress and cost changes of the project and make predictions and adjustments in a timely manner.

[0096] Then, construct a progress prediction model. First, calculate the completion rate of each process. For example, the completion rate of process A is the actual completed engineering quantity of 800 cubic meters divided by the planned completed engineering quantity of 1000 cubic meters, and the result is 80%.

[0097] To more accurately predict the progress, it is necessary to consider the importance of each process. This can be determined by analyzing the position of the process in the critical path, the resource consumption, and the dependency relationship with other processes. For example, processes located on the critical path, those with high resource consumption, and those closely related to other processes have higher importance coefficients. Suppose the position importance coefficient of Process A is 0.8, the resource consumption coefficient is 0.9, and the process correlation coefficient is 0.7.

[0098] The position importance coefficient, resource consumption coefficient, and process correlation coefficient are weighted and combined to obtain the weight coefficient of the process.

[0099] Next, multiply the process completion rate by the process weight coefficient to obtain the progress prediction data. For example, the progress prediction data for Process A is 80% * 0.79 = 63.2%. Compare the progress prediction data with the planned completion data of the process to calculate the progress deviation value.

[0100] Subsequently, construct a cost prediction model. Based on the collected resource usage data and cost consumption data, calculate the labor cost, equipment cost, and material cost respectively. The calculation method for labor cost is the actual working hours multiplied by the actual labor unit price. For example, suppose the actual labor unit price is 50 yuan per hour, then the labor cost of Process A is 100 hours * 50 yuan per hour = 5000 yuan. The calculation method for equipment cost is the actual equipment usage time multiplied by the actual equipment rental rate. For example, suppose the actual equipment rental rate is 100 yuan per hour, then the equipment cost of Process A is 50 hours * 100 yuan per hour = 5000 yuan. The calculation method for material cost is the actual material usage multiplied by the actual material unit price. For example, suppose the actual material unit price is 1000 yuan per ton, then the material cost of Process A is 200 tons * 1000 yuan per ton = 200000 yuan.

[0101] To reduce the impact of data fluctuations, the Kalman filter algorithm is used to perform noise smoothing on the calculated labor cost, equipment cost, and material cost. Sum up the smoothed labor cost, equipment cost, and material cost to obtain the cost prediction data. Compare the cost prediction data with the cost control benchmark data to calculate the cost deviation value.

[0102] The solution of this application can:

[0103] Improving prediction accuracy: By comprehensively considering the process completion rate, location importance, resource consumption, and dependencies between processes, the project schedule and cost can be predicted more accurately. Achieving dynamic monitoring: Using a sliding time window and real-time data, the changes in the project schedule and cost can be dynamically tracked, and potential risks and problems can be detected in a timely manner. Assisting decision-making: By predicting schedule and cost variances, decision-making support can be provided to project managers to help them take effective measures to control the project schedule and cost.

[0104] In an alternative implementation, multiple optimization schemes including resource allocation parameters, process organization parameters, and cost control parameters are automatically generated according to the comprehensive deviation value; the multiple optimization schemes are input into the digital twin basic platform for parallel simulation, and the simulation prediction results of each scheme are obtained. The simulation prediction results include schedule prediction results and cost prediction results, including:

[0105] The comprehensive deviation value includes a schedule deviation value and a cost deviation value. A schedule optimization objective function is constructed based on the schedule deviation value, and a cost optimization objective function is constructed based on the cost deviation value; the schedule optimization objective function and the cost optimization objective function are input into an improved particle swarm algorithm, and multiple optimization schemes are generated through iterative optimization; each optimization scheme includes resource allocation parameters, process organization parameters, and cost control parameters. The resource allocation parameters are used to optimize the number of construction teams, the quantity of equipment, and the supply of materials. The process organization parameters are used to optimize the process interspersed relationship, the process duration, and the process resource requirements. The cost control parameters are used to optimize the labor unit price, the equipment rate, and the material unit price;

[0106] A construction site model, a resource flow model, and a process implementation model are constructed in the digital twin basic platform; the resource allocation parameters are mapped to the resource flow model, the process organization parameters are mapped to the process implementation model, and the cost control parameters are mapped to the construction site model; the mapped models are allocated to multiple computing nodes using a distributed computing architecture;

[0107] Parallel simulation is performed on the multiple computing nodes; resource scheduling simulation is performed based on the resource flow model to obtain simulation resource utilization prediction data, process execution simulation is performed based on the process implementation model to obtain simulation schedule prediction data, and cost consumption simulation is performed based on the construction site model to obtain simulation cost prediction data; the simulation resource utilization prediction data, the simulation schedule prediction data, and the simulation cost prediction data are combined to form simulation prediction results.

[0108] An optimization method for construction plans based on digital twins and improved particle swarm optimization algorithms can effectively improve the efficiency and accuracy of construction progress and cost control. The core of this method is to automatically generate multiple sets of optimized plans by comprehensively considering the progress deviation and cost deviation, and conduct parallel simulations on the digital twin platform, and finally select the optimal plan.

[0109] First, it is necessary to collect the actual progress and cost data of the construction project, compare them with the planned data, and calculate the progress deviation value and cost deviation value. For example, assume that the planned construction period of a certain project is 100 days, and the current actual construction period is 110 days, then the progress deviation value is 10 days; the planned cost is 10 million yuan, and the current actual cost is 11 million yuan, then the cost deviation value is 1 million yuan.

[0110] Next, construct a progress optimization objective function and a cost optimization objective function based on the progress deviation value and cost deviation value respectively. The goal of the progress optimization objective function is to minimize the progress deviation, and the goal of the cost optimization objective function is to minimize the cost deviation.

[0111] Then, input these two objective functions into the improved particle swarm optimization algorithm. The particle swarm optimization algorithm is an optimization algorithm that simulates the foraging behavior of bird flocks. By the mutual cooperation and information sharing among particles, it searches for the optimal solution. This method uses an improved particle swarm optimization algorithm to improve the convergence speed and global search ability of the algorithm. Through iterative optimization, the algorithm will generate multiple sets of optimized plans, and each set of plans includes resource allocation parameters, process organization parameters, and cost control parameters.

[0112] Taking one set of plans as an example, the resource allocation parameters may include: the number of construction teams increases by 10%, the number of equipment increases by 5%, and the material supply is advanced by 10 days; the process organization parameters may include: changing the interweaving relationship between process A and process B from sequential execution to parallel execution, shortening the duration of process C by 2 days, and increasing the resource demand of process D by 10%; the cost control parameters may include: reducing the labor unit price by 5%, reducing the equipment rate by 2%, and reducing the material unit price by 3%.

[0113] On the digital twin basic platform, it is necessary to construct a construction site model, a resource flow model, and a process implementation model. Map the above-generated resource allocation parameters to the resource flow model, process organization parameters to the process implementation model, and cost control parameters to the construction site model. For example, "the number of construction teams increases by 10%" in the resource allocation parameters will be reflected in the number of personnel in the resource flow model, "shortening the process duration by 2 days" will be reflected in the process duration of the process implementation model, and "reducing the labor unit price by 5%" will be reflected in the cost accounting of the construction site model.

[0114] The mapped model is distributed to multiple computing nodes using a distributed computing architecture, and parallel simulations are performed on each computing node. Resource scheduling simulations are carried out based on the resource flow model to obtain predicted simulation resource utilization data, such as equipment utilization rate, personnel idle rate, etc.; process execution simulations are carried out based on the process implementation model to obtain predicted simulation progress data, such as the completion time of each process, total project duration, etc.; cost consumption simulations are carried out based on the construction site model to obtain predicted simulation cost data, such as labor costs, material costs, equipment costs, etc.

[0115] Finally, the predicted simulation resource utilization data, predicted simulation progress data, and predicted simulation cost data are combined to form the simulation prediction result. For example, the simulation prediction result of a certain plan is: the project duration is shortened by 5 days, and the cost is reduced by 8 million yuan. By comparing the simulation prediction results of each plan, the optimal plan can be selected for actual construction, thereby improving the efficiency and accuracy of construction progress and cost control.

[0116] The solution of this application can:

[0117] By automatically generating multiple sets of optimization plans and using digital twin technology for parallel simulations, the manual intervention and the time for plan evaluation are greatly reduced, and the plan optimization efficiency is significantly improved. By comprehensively considering the schedule deviation and cost deviation and using an improved particle swarm optimization algorithm for optimization, more comprehensive and reasonable optimization plans can be generated, thereby improving the quality of plan optimization. Performing simulations on the digital twin platform can simulate the real construction environment and resource flow conditions, thereby verifying the feasibility of the plan and reducing the risk of plan implementation.

[0118] In an optional implementation manner, constructing a schedule optimization objective function based on the schedule deviation value and constructing a cost optimization objective function based on the cost deviation value includes:

[0119] Using the K-means clustering algorithm to divide the schedule deviation values into a deviation process group higher than the preset deviation threshold and a deviation process group lower than the preset deviation threshold, and using the analytic hierarchy process to construct a judgment matrix for the deviation process group higher than the preset deviation threshold and the deviation process group lower than the preset deviation threshold from three dimensions of process importance, process criticality, and process duration;

[0120] Using the geometric mean method to calculate the eigenvector of the judgment matrix to obtain the process weight coefficient; adding the product of the process weight coefficient and the schedule deviation value, and constructing a schedule optimization objective function based on the minimum value of the summation result;

[0121] The calculation formula of the schedule optimization objective function is as follows:

[0122]

[0123] Among them, Fs is the progress optimization objective function, m is the total number of processes, and w i is the weight coefficient of the i-th process, and d i is the progress deviation value of the i-th process;

[0124] Use the K-means clustering algorithm to divide the cost deviation values into a deviation cost group higher than the preset deviation threshold and a deviation cost group lower than the preset deviation threshold. Use the Delphi method to conduct expert scoring on the deviation cost group higher than the preset deviation threshold and the deviation cost group lower than the preset deviation threshold from three dimensions: cost proportion, cost controllability, and cost sensitivity. Obtain the cost weight coefficient through multiple rounds of expert scoring;

[0125] Sum the products of the cost weight coefficient and the cost deviation value, and construct a cost optimization objective function with the minimum value of the summation result;

[0126] The calculation formula of the cost optimization objective is as follows:

[0127]

[0128] where F c is the cost optimization objective function, n is the total number of cost items, and W j is the weight coefficient of the j-th cost item, and C j is the cost deviation value of the j-th cost item.

[0129] A project progress and cost optimization method based on deviation values. The core of this method is to construct optimization objective functions according to the deviation values of progress and cost respectively, and use them to guide project execution to achieve dual optimization of progress and cost.

[0130] First, collect project progress data, including the planned completion time and actual completion time of each process. Then, calculate the progress deviation value of each process, that is, the difference between the actual completion time and the planned completion time.

[0131] Next, use the K-means clustering algorithm to group these progress deviation values. Set a preset deviation threshold, group the processes with progress deviation values higher than the threshold into one group, and the processes with progress deviation values lower than the threshold into another group. The purpose of doing this is to distinguish the processes with large and small progress deviations for more targeted optimization.

[0132] For the two groups of processes after division, construct judgment matrices from three dimensions: process importance, process criticality, and process duration. For example, project experts can be invited to make pairwise comparisons of the importance of different processes in these three dimensions based on experience and assign corresponding weight values to finally form a judgment matrix.

[0133] Then, the geometric mean method is used to calculate the eigenvector of the judgment matrix, and the weight coefficient of each process is obtained. This coefficient reflects the importance of different processes in the overall project progress.

[0134] Multiply the weight coefficient of each process by its schedule deviation value, and sum up the results of all processes to obtain a value. Construct a schedule optimization objective function with the goal of minimizing this value. This means that for a process with a larger weight coefficient, the smaller its schedule deviation value, the less impact it has on the overall project schedule, which is more conducive to the project being completed on time.

[0135] The same idea is also applied to cost optimization. First, collect project cost data, including the budget value and actual value of each cost item. Calculate the cost deviation value of each cost item, which is the difference between the actual value and the budget value.

[0136] Use the K-means clustering algorithm to group the cost deviation values, grouping the cost items with cost deviation values higher than the preset threshold into one group and those lower than the threshold into another group.

[0137] For the two groups of cost items after division, conduct expert scoring from three dimensions: cost proportion, cost controllability, and cost sensitivity. For example, invite financial experts to score the importance of different cost items in these three dimensions, and finally determine the weight coefficient of each cost item through multiple rounds of scoring.

[0138] Multiply the weight coefficient of each cost item by its cost deviation value, and sum up the results of all cost items to obtain a value. Construct a cost optimization objective function with the goal of minimizing this value. This means that for a cost item with a larger weight coefficient, the smaller its cost deviation value, the less impact it has on the overall project cost, which is more conducive to the project's cost control.

[0139] For example, a project contains two cost items with weight coefficients of 0.7 and 0.3 respectively, and cost deviation values of 1 and -2 respectively. Then the value of the cost optimization objective function is 0.7 * 1 + 0.3 * (-2) = 0.1.

[0140] The solution of this application can:

[0141] Improve the accuracy of project schedule and cost management. By performing clustering analysis and weight assignment on the deviation values, key processes and cost items that have a greater impact on the project schedule and cost can be more accurately identified, and thus more targeted optimization measures can be taken. Enhance the effectiveness of project schedule and cost control. By constructing an optimized objective function, the objectives of project schedule and cost management can be quantified, and guided by this, the project execution strategy can be continuously adjusted to improve the effectiveness of project schedule and cost control. Improve the scientificity and standardization of project management. This method uses scientific methods such as clustering algorithms, analytic hierarchy process, and Delphi method, and combines expert experience to make project schedule and cost management more scientific and standardized, which helps to improve the level of project management.

[0142] In an alternative embodiment, the schedule optimization objective function and the cost optimization objective function are input into an improved particle swarm optimization algorithm, and multiple sets of optimization solutions are generated through iterative optimization, including:

[0143] Calculate the adaptive weight coefficient according to the schedule deviation value and the cost deviation value. The absolute value of the deviation coefficient is obtained by weighting the absolute value of the schedule deviation value and the absolute value of the cost deviation value. The schedule weight coefficient in the adaptive weight coefficient is obtained based on the ratio of the absolute value of the schedule deviation value to the absolute value of the deviation coefficient, and the cost weight coefficient in the adaptive weight coefficient is obtained based on the ratio of the absolute value of the cost deviation value to the absolute value of the deviation coefficient.

[0144] Use Logistics chaotic mapping to generate the initial particle swarm, map the initial particle swarm to the decision space to construct the particle swarm position vector; calculate the distance between the particle swarm position vector and the population centroid to obtain the population aggregation degree; set the adaptive mutation probability based on the population aggregation degree, and the adaptive mutation probability increases according to the exponential function law as the population aggregation degree increases.

[0145] Input the schedule optimization objective function and the cost optimization objective function into an improved particle swarm optimization algorithm; update the inertia weight in a non-linear decreasing manner, and the inertia weight decreases according to the cosine function law as the number of iterations increases; update the learning factor in an adaptive manner, where the learning factor includes an individual learning factor and a group learning factor. The individual learning factor increases according to the exponential function law as the number of iterations increases, and the group learning factor decreases according to the exponential function law as the number of iterations increases.

[0146] In each iteration, calculate the degree of constraint violation based on the particle swarm position vector, and use the penalty function method to weight the degree of constraint violation, the schedule optimization objective function, and the cost objective function to obtain the fitness value; calculate the crowding distance of each particle in the population; select the solutions with a crowding distance greater than the preset distance threshold as elite individuals and retain them for the next generation.

[0147] Perform local search on the elite individuals using the pattern search method to obtain the local search results of the elite individuals. The step size of the pattern search method decreases according to the exponential function law with the number of iterations. Update the global optimal solution based on the local search results and determine whether the termination condition is satisfied. When the termination condition is satisfied, output the global optimal solution as the optimization plan.

[0148] An engineering schedule and cost optimization method based on an improved particle swarm algorithm aims to balance the engineering schedule and cost objectives and seek the best resource allocation plan. This method introduces improved mechanisms such as adaptive weight coefficients, chaotic mapping initialization, adaptive mutation, non-linear decreasing inertia weight, adaptive learning factors, penalty function constraint handling, elite retention strategy, and pattern search local optimization, effectively improving the optimization performance and convergence speed of the algorithm.

[0149] First, determine the schedule optimization objective function and the cost optimization objective function. For example, the schedule optimization objective function can be defined as the minimization of the time required to complete the project, and the cost optimization objective function can be defined as the minimization of the total project cost.

[0150] Then, calculate the schedule deviation value and the cost deviation value. For example, the schedule deviation value can be defined as the difference between the planned completion time and the actual completion time, and the cost deviation value can be defined as the difference between the budgeted cost and the actual cost. The weighted sum of the absolute value of the schedule deviation value and the absolute value of the cost deviation value is calculated to obtain the absolute value of the deviation coefficient. The schedule weight coefficient is equal to the ratio of the absolute value of the schedule deviation value to the absolute value of the deviation coefficient, and the cost weight coefficient is equal to the ratio of the absolute value of the cost deviation value to the absolute value of the deviation coefficient. These two weight coefficients will be used to balance the importance of the schedule and cost objectives in the optimization process. Suppose the schedule deviation value is 5 days and the cost deviation value is 100,000 yuan, and the weighted coefficients of the schedule and cost are set to 0.6 and 0.4 respectively. Then the absolute value of the deviation coefficient is 5 * 0.6 + 10 * 0.4 = 7, the schedule weight coefficient is (5 * 0.6) / 7 ≈ 0.43, and the cost weight coefficient is (10 * 0.4) / 7 ≈ 0.57.

[0151] Next, use the Logistics chaotic mapping to generate the initial particle swarm. Map the generated initial particle swarm to the decision space to construct the particle swarm position vector. The decision space can include decision variables such as resource allocation and task scheduling. Calculate the distance between the particle swarm position vector and the population centroid to obtain the population aggregation degree. Set the adaptive mutation probability according to the population aggregation degree. The mutation probability increases according to the exponential function law with the increase of the population aggregation degree to enhance the ability of the algorithm to jump out of the local optimum. For example, the mutation probability can be set to e^(-1 / aggregation degree).

[0152] Input the progress optimization objective function and the cost optimization objective function into the improved particle swarm algorithm. Update the inertia weight in a non-linear decreasing manner. The inertia weight decreases according to the cosine function rule as the number of iterations increases. For example, the inertia weight can be set to 0.9*cos(iteration number * π / maximum iteration number). Update the learning factors in an adaptive manner. The individual learning factor increases according to the exponential function rule as the number of iterations increases, and the swarm learning factor decreases according to the exponential function rule as the number of iterations increases.

[0153] In each iteration, calculate the degree of constraint violation based on the particle swarm position vector. For example, the constraint conditions can include resource limitations, time limitations, etc. Use the penalty function method to weight the degree of constraint violation, the progress optimization objective function, and the cost objective function to obtain the fitness value. Calculate the crowding distance of each particle in the population. Select the solutions with a crowding distance greater than the preset distance threshold as elite individuals to be retained for the next generation to maintain population diversity.

[0154] Perform local search on the elite individuals using the pattern search method to obtain the local search results of the elite individuals. The step size of the pattern search method decreases according to the exponential function rule as the number of iterations increases. For example, the step size can be set to the initial step size * e^(-iteration number). Update the global optimal solution based on the local search results and determine whether the termination condition is satisfied. The termination condition can be reaching the maximum number of iterations or the improvement degree of the solution being less than the preset threshold. When the termination condition is satisfied, output the global optimal solution as the optimization plan.

[0155] The solution of this application can:

[0156] Improve the optimization efficiency: Through improvement mechanisms such as adaptive weight coefficients, chaotic mapping initialization, adaptive mutation, non-linear decreasing inertia weight, and adaptive learning factors, this method can find the global optimal solution more quickly and accurately, thus improving the optimization efficiency. Enhance the solution quality: Through mechanisms such as penalty function constraint handling, elite retention strategy, and pattern search local optimization, this method can effectively handle constraint conditions, maintain population diversity, and perform local fine search, thus enhancing the solution quality. Balance the progress and cost objectives: Through adaptive weight coefficients, this method can dynamically adjust the importance of the progress and cost objectives in the optimization process according to the actual situation, thus achieving the balanced optimization of progress and cost.

[0157] In an optional implementation manner, perform multi-objective evaluation on the progress prediction result and the cost prediction result, and select the execution plan with the optimal comprehensive benefit; send the optimal execution plan to the on-site management terminal through the digital twin basic platform, and start the plan execution monitoring module to continuously collect actual execution data including:

[0158] Calculate the schedule benefit evaluation indicators based on the schedule prediction results. The schedule benefit evaluation indicators include the critical path duration compression volume indicator, the construction process continuity indicator, and the milestone node compliance indicator; calculate the cost benefit evaluation indicators according to the cost prediction results. The cost benefit evaluation indicators include the total cost savings rate indicator, the cost composition rationality indicator, and the cash flow matching degree indicator. Combine the schedule benefit evaluation indicators and the cost benefit evaluation indicators through weighted combination to form a multi-objective evaluation indicator set;

[0159] Construct a multi-objective evaluation function, and normalize the indicator values in the multi-objective evaluation indicator set; set the normalized schedule weight coefficient and the normalized cost weight coefficient based on the normalized indicator values; multiply the normalized schedule weight coefficient by the normalized schedule indicator value to obtain the schedule weighted score, and multiply the normalized cost weight coefficient by the normalized cost indicator value to obtain the cost weighted score;

[0160] Conduct a multi-objective comprehensive evaluation on the schedule weighted score and the cost weighted score, and calculate the comprehensive benefit score; rank multiple optimization plans according to the comprehensive benefit score; select the optimization plan with the highest comprehensive benefit score as the optimal implementation plan;

[0161] Convert the optimal implementation plan into a standard data format, and generate an execution data packet containing construction operation guides and resource allocation plans; send the execution data packet to the on-site management terminal through the digital twin basic platform; start the plan execution monitoring module, and collect actual execution data through the data collection devices deployed on the on-site management terminal.

[0162] The multi-objective optimization execution method for engineering projects based on the digital twin platform includes the following steps:

[0163] First, establish a project digital twin model. This model contains data throughout the project life cycle, such as design drawings, construction plans, resource information, cost budgets, etc. Taking a construction project as an example, the digital twin model includes a building information model (BIM), a project schedule plan, a resource database (including manpower, materials, equipment, etc.), a cost database, etc.

[0164] Next, conduct plan prediction and evaluation. Based on the digital twin model, generate multiple optimized execution plans. Each plan contains different schedule arrangements, resource allocations, and cost budgets. For example, Plan 1: Adopt flow production, increase manpower input, and shorten the construction period; Plan 2: Optimize resource allocation, reduce material waste, and reduce costs; Plan 3: Balance the construction period and costs to seek an overall optimal plan.

[0165] Progress and cost forecasts are made for each plan. Using project historical data, expert experience, and forecasting models, forecast the critical path duration, construction process continuity, milestone node completion, total cost, cost composition, and cash flow for each plan. For example, Plan 1 forecasts a 10% reduction in duration and a 5% increase in total cost; Plan 2 forecasts no change in duration and a 3% reduction in total cost; Plan 3 forecasts a 5% reduction in duration and a 1% reduction in total cost.

[0166] Then, calculate the progress and cost-benefit evaluation indicators. Based on the forecast results, calculate the progress benefit indicators and cost-benefit indicators for each plan. The progress benefit indicators include the critical path duration compression, construction process continuity, and milestone node compliance. The cost-benefit indicators include the total cost savings rate, cost composition rationality, and cash flow matching degree. For example, the critical path duration compression for Plan 1 is 10 days, the construction process continuity score is 0.9, and the milestone node compliance is 100%; the total cost savings rate for Plan 2 is 3%, the cost composition rationality score is 0.8, and the cash flow matching degree is 90%; the critical path duration compression for Plan 3 is 5 days, the construction process continuity score is 0.95, the milestone node compliance is 95%, the total cost savings rate is 1%, the cost composition rationality score is 0.9, and the cash flow matching degree is 95%.

[0167] After that, conduct multi-objective evaluation and plan ranking. Combine the progress benefit indicators and cost-benefit indicators through weighting to form a multi-objective evaluation indicator set. Set the progress weight coefficient and cost weight coefficient. For example, the progress weight is 0.6 and the cost weight is 0.4. Multiply the weight coefficient by the indicator value to obtain the progress weighted score and cost weighted score for each plan. Add the progress weighted score and cost weighted score to obtain the comprehensive benefit score. For example, the comprehensive benefit score for Plan 1 is 0.85, the comprehensive benefit score for Plan 2 is 0.75, and the comprehensive benefit score for Plan 3 is 0.88. Rank the multiple plans according to the comprehensive benefit score, and select the plan with the highest comprehensive benefit score as the optimal implementation plan. In this case, Plan 3 has the highest comprehensive benefit score, so Plan 3 is selected as the optimal implementation plan.

[0168] Finally, issue the implementation plan and conduct monitoring. Convert the optimal implementation plan into an execution data packet containing construction operation guides and resource allocation plans. Send the execution data packet to the on-site management terminal through the digital twin basic platform. Start the plan execution monitoring module, and collect actual execution data through the data collection devices deployed on the on-site management terminal, such as construction progress, resource consumption, cost expenditure, etc. Compare and analyze the collected actual execution data with the optimal implementation plan, promptly discover deviations and make adjustments to ensure the smooth progress of the project.

[0169] The solution of this application can:

[0170] Improve project management efficiency. Through digital twin technology, digital management of the entire project process can be achieved, improving information transmission efficiency, reducing communication costs, and thus enhancing project management efficiency. Optimize resource allocation. By conducting multi-objective evaluations of multiple solutions, the solution with the optimal comprehensive benefits can be selected to achieve optimized resource allocation, reduce resource waste, and lower project costs. Enhance the scientific nature of decision-making. Based on data analysis and prediction models, the implementation status of the project can be monitored and evaluated in real time, providing a scientific basis for project decision-making and improving the accuracy and effectiveness of decision-making.

[0171] Figure 2 This is a schematic structural diagram of the BIM-based dynamic control and optimization system for project progress and cost in an embodiment of the present invention. As Figure 2 shown, the system includes:

[0172] The first unit is used to parse the BIM model by using computer vision algorithms to extract engineering space information and component attribute information, and establish an initial construction scene model; deploy visual sensors at the construction site to collect construction implementation status data, deploy positioning sensors to collect construction personnel distribution data, deploy Internet of Things sensors to collect mechanical equipment operation data, and perform weighted combination on the construction implementation status data, the construction personnel distribution data, and the mechanical equipment operation data to generate multi-source data; input the multi-source data into a pre-trained deep learning model for feature extraction and data fusion to generate real-time construction resource status data; perform dynamic mapping on the real-time construction resource status data and the initial construction scene model to construct a digital twin basic platform with real-time perception capabilities;

[0173] The second unit is used to import construction schedule plan data and cost control benchmark data based on the digital twin basic platform to establish a schedule-cost association model; receive the real-time construction resource status data in real time, calculate the current schedule completion situation and cost consumption situation through the schedule-cost association model, and compare with the construction schedule plan data and the cost control benchmark data to obtain a comprehensive deviation value; automatically generate multiple groups of optimization solutions including resource allocation parameters, process organization parameters, and cost control parameters according to the comprehensive deviation value; input the multiple groups of optimization solutions into the digital twin basic platform for parallel simulation to obtain simulation prediction results of each solution, and the simulation prediction results include schedule prediction results and cost prediction results;

[0174] A third unit is used to conduct multi-objective evaluation on the progress prediction result and the cost prediction result, and select an implementation plan with the optimal comprehensive benefit; the optimal implementation plan is sent to the on-site management terminal through the digital twin basic platform, and the plan execution monitoring module is started to continuously collect actual execution data; the actual execution data is compared and analyzed with the simulation prediction result in real time. When the comparison deviation exceeds the preset threshold, the actual execution data is used to update the progress-cost correlation model in the digital twin basic platform, realizing the adaptive evolution of the digital twin environment, ensuring the accuracy of the next round of simulation verification, and forming the digital twin dynamic collaborative control of the construction progress and cost.

[0175] In the third aspect of the embodiments of the present invention,

[0176] A kind of electronic device is provided, including:

[0177] A processor;

[0178] A memory for storing instructions executable by the processor;

[0179] Wherein, the processor is configured to call the instructions stored in the memory to execute the method described above.

[0180] In the fourth aspect of the embodiments of the present invention,

[0181] A computer-readable storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described above is implemented.

[0182] The present invention can be a method, a device, a system and / or a computer program product. The computer program product can include a computer-readable storage medium, on which computer-readable program instructions for executing various aspects of the present invention are uploaded.

[0183] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. The BIM-based project progress and cost dynamic control optimization method is characterized by: include: Use computer vision algorithms to analyze BIM models to extract engineering space information and component attribute information, and establish an initial construction scene model; Deploy visual sensors at the construction site to collect construction implementation status data, deploy positioning sensors to collect construction personnel distribution data, and deploy Internet of Things sensors to collect mechanical equipment operation data. Perform weighted combination of the construction implementation status data, the construction personnel distribution data, and the mechanical equipment operation data to generate multi-source data; input the multi-source data into a pre-trained deep learning model for feature extraction and data fusion to generate real-time status data of construction resources; dynamically map the real-time status data of construction resources with the initial construction scene model to build a digital twin basic platform with real-time perception capabilities; Based on the digital twin basic platform, the construction schedule data and cost control benchmark data are imported to establish a progress-cost association model; the real-time status data of the construction resources is received in real time, and the current progress completion status and cost consumption status are calculated through the progress-cost association model, and compared with the construction schedule data and the cost control benchmark data to obtain a comprehensive deviation value; according to the comprehensive deviation value, multiple groups of optimization schemes including resource configuration parameters, process organization parameters and cost control parameters are automatically generated; Inputting the multiple groups of optimization schemes into the digital twin basic platform for parallel simulation to obtain simulation prediction results of each scheme, wherein the simulation prediction results include schedule prediction results and cost prediction results; Perform multi-objective evaluation on the progress forecast results and the cost forecast results, and select the best execution plan with comprehensive benefits; send the best execution plan to the on-site management terminal through the digital twin basic platform, and start the plan execution monitoring module to continuously collect actual execution data; The actual execution data is compared and analyzed with the simulation prediction results in real time. When the comparison deviation exceeds a preset threshold, the progress-cost association model in the digital twin basic platform is updated using the actual execution data to achieve adaptive evolution of the digital twin environment, ensure the accuracy of the next round of simulation verification, and form dynamic collaborative management and control of digital twins for construction progress and cost.

2. The method according to claim 1, characterized in that Based on the digital twin basic platform, the construction schedule data and cost control benchmark data are imported to establish a progress-cost association model; the real-time status data of the construction resources is received in real time, and the current progress completion status and cost consumption status are calculated through the progress-cost association model, and the comprehensive deviation values ​​obtained by comparing with the construction schedule data and the cost control benchmark data include: Importing construction schedule data and cost control benchmark data into the digital twin basic platform; extracting features from the real-time status data of construction resources collected at the construction site, extracting operating efficiency features from personnel data, extracting energy consumption level features from equipment data, extracting loss rate features from material data, and constructing the extracted operating efficiency features, energy consumption level features, and loss rate features into a resource configuration feature vector; Constructing a directed acyclic graph based on the logical dependency relationship between the construction processes, extracting process completion characteristics and critical path characteristics from the directed acyclic graph, and constructing the process completion characteristics and the critical path characteristics into a process implementation feature vector; A multi-layer neural network is constructed as a progress-cost association model, and an attention mechanism module is set in the middle layer of the progress-cost association model; the resource configuration feature vector and the process implementation feature vector are input into the progress-cost association model, and the dynamic association strength between the resource configuration feature vector and the process implementation feature vector is calculated by the attention mechanism module to generate a resource-process interaction matrix; The resource-process interaction matrix is ​​input into the progress-cost association model, and the current construction progress completion status and cost consumption status are calculated to obtain progress forecast data and cost forecast data; the progress forecast data is compared with the construction schedule data to obtain a progress deviation value, and the cost forecast data is compared with the cost control benchmark data to obtain a cost deviation value; a comprehensive deviation value is obtained based on a combination of the progress deviation data and the cost deviation data.

3. The method according to claim 2, characterized in that Comparing the progress forecast data with the construction progress plan data to obtain a progress deviation value, and comparing the cost forecast data with the cost control benchmark data to obtain a cost deviation value include: Collect basic data, the basic data including real-time data of the construction site and process plan completion data; extract actual process completion data, resource usage data and cost consumption data from the real-time data of the construction site, and store the actual process completion data, the resource usage data and the cost consumption data in a sliding time window according to a time series; Construct a progress prediction model, calculate the process completion rate based on the actual completion data of the process, and perform weighted calculation on the ratio of the actual completion amount of the process to the planned completion data of the process to obtain the process completion rate; analyze the position of the process in the critical path to determine the position importance coefficient, analyze the man-machine-material consumption of the process to determine the resource consumption coefficient, and analyze the front-end dependency relationship of the process to determine the process correlation coefficient; The weighted combination of the position importance coefficient, the resource consumption coefficient and the process association coefficient obtains the process weight coefficient; the progress forecast data is obtained based on the product of the process completion rate and the process weight coefficient; the progress forecast data is compared with the process plan completion data to obtain the progress deviation value; Constructing a cost prediction model to calculate labor cost, equipment cost and material cost based on the resource usage data and the cost consumption data; obtaining the labor cost based on the product of actual working hours and actual labor unit price, obtaining the equipment cost based on the product of actual equipment usage time and actual equipment rental rate, and obtaining the material cost based on the product of actual material usage and actual material unit price; A Kalman filter algorithm is used to perform noise smoothing on the labor cost, the equipment cost and the material cost, and the smoothed data are combined to obtain cost forecast data; the cost forecast data is compared with the cost control benchmark data to calculate a cost deviation value.

4. The method according to claim 1, characterized in that: Automatically generate multiple groups of optimization schemes including resource configuration parameters, process organization parameters and cost control parameters according to the comprehensive deviation value; input the multiple groups of optimization schemes into the digital twin basic platform for parallel simulation to obtain simulation prediction results of each scheme, wherein the simulation prediction results include schedule prediction results and cost prediction results including: The comprehensive deviation value includes a schedule deviation value and a cost deviation value, a schedule optimization objective function is constructed based on the schedule deviation value, and a cost optimization objective function is constructed based on the cost deviation value; the schedule optimization objective function and the cost optimization objective function are input into an improved particle swarm algorithm, and multiple groups of optimization schemes are generated through iterative optimization; each group of optimization schemes includes resource configuration parameters, process organization parameters and cost control parameters, wherein the resource configuration parameters are used to optimize the number of construction teams, the number of equipment and the supply of materials, the process organization parameters are used to optimize the process interlacing relationship, the process duration and the process resource demand, and the cost control parameters are used to optimize the labor unit price, the equipment rate and the material unit price; Constructing a construction site model, a resource flow model and a process implementation model on the digital twin basic platform; mapping the resource configuration parameters to the resource flow model, mapping the process organization parameters to the process implementation model, and mapping the cost control parameters to the construction site model; and using a distributed computing architecture to distribute the mapped models to multiple computing nodes; Parallel simulation is performed on the multiple computing nodes; based on the resource flow model, resource scheduling simulation is performed to obtain simulation resource utilization prediction data; based on the process implementation model, process execution simulation is performed to obtain simulation progress prediction data; based on the construction site model, cost consumption simulation is performed to obtain simulation cost prediction data; the simulation resource utilization prediction data, the simulation progress prediction data and the simulation cost prediction data are combined to form a simulation prediction result.

5. The method according to claim 4, characterized in that Constructing a schedule optimization objective function based on the schedule deviation value, and constructing a cost optimization objective function based on the cost deviation value comprises: The K-means clustering algorithm is used to divide the progress deviation value into a deviation process group higher than a preset deviation threshold and a deviation process group lower than the preset deviation threshold, and a hierarchy analysis method is used to construct a judgment matrix for the deviation process group higher than the preset deviation threshold and the deviation process group lower than the preset deviation threshold from three dimensions: process importance, process criticality and process duration; The geometric mean method is used to calculate the eigenvector of the judgment matrix to obtain the process weight coefficient; the product of the process weight coefficient and the progress deviation value is added, and the progress optimization objective function is constructed based on the minimum value of the sum result; The calculation formula of the schedule optimization objective function is as follows: Among them, F s is the schedule optimization objective function, m is the total number of processes, w i is the weight coefficient of the ith process, d i is the progress deviation value of the i-th process; The K-means clustering algorithm is used to divide the cost deviation value into a deviation cost group higher than a preset deviation threshold and a deviation cost group lower than the preset deviation threshold, and the Delphi method is used to perform expert scoring on the deviation cost group higher than the preset deviation threshold and the deviation cost group lower than the preset deviation threshold from three dimensions: cost proportion, cost controllability, and cost sensitivity, and a cost weight coefficient is obtained through multiple rounds of expert scoring; Adding the product of the cost weight coefficient and the cost deviation value, and constructing a cost optimization objective function with the minimum value of the sum; The cost optimization target calculation formula is as follows: Among them, F c is the cost optimization objective function, n is the total number of cost items, W j is the weight coefficient of the jth cost item, C j is the cost deviation value of the jth cost item.

6. The method according to claim 4, characterized in that Inputting the progress optimization objective function and the cost optimization objective function into the improved particle swarm algorithm, and generating multiple groups of optimization solutions through iterative optimization include: An adaptive weight coefficient is calculated according to the progress deviation value and the cost deviation value, and the absolute value of the deviation coefficient is obtained by weighting the absolute value of the progress deviation value and the absolute value of the cost deviation value, wherein the progress weight coefficient in the adaptive weight coefficient is obtained based on the ratio of the absolute value of the progress deviation value to the absolute value of the deviation coefficient, and the cost weight coefficient in the adaptive weight coefficient is obtained based on the ratio of the absolute value of the cost deviation value to the absolute value of the deviation coefficient; An initial particle swarm is generated by using Logistic chaos mapping, and the initial particle swarm is mapped to the decision space to construct a particle swarm position vector; the distance between the particle swarm position vector and the population center of gravity is calculated to obtain the population aggregation degree; an adaptive mutation probability is set based on the population aggregation degree, and the adaptive mutation probability increases according to the law of an exponential function as the population aggregation degree increases; Input the progress optimization objective function and the cost optimization objective function into the improved particle swarm algorithm; update the inertia weight in a nonlinear decreasing manner, wherein the inertia weight decreases according to the cosine function law as the number of iterations increases; update the learning factor in an adaptive manner, wherein the learning factor includes an individual learning factor and a group learning factor, wherein the individual learning factor increases according to the exponential function law as the number of iterations increases, and the group learning factor decreases according to the exponential function law as the number of iterations increases; In each iteration, the constraint violation degree is calculated based on the particle swarm position vector, and the constraint violation degree, the progress optimization objective function and the cost objective function are weighted by the penalty function method to obtain the fitness value; the crowding distance of each particle in the population is calculated; and the solution whose crowding distance is greater than a preset distance threshold is selected as the elite individual to be retained for the next generation; A pattern search method is used to perform local search on the elite individual to obtain a local search result of the elite individual, wherein the step size of the pattern search method decreases exponentially with the number of iterations; a global optimal solution is updated based on the local search results to determine whether a termination condition is met; when the termination condition is met, the global optimal solution is output as an optimization solution.

7. The method according to claim 1, characterized in that Conduct multi-objective evaluation on the progress forecast results and the cost forecast results, and select the implementation plan with the best comprehensive benefits; The optimal execution plan is sent to the on-site management terminal through the digital twin basic platform, and the plan execution monitoring module is started to continuously collect actual execution data, including: Based on the progress forecast result, a progress benefit evaluation index is calculated, and the progress benefit evaluation index includes a critical path construction period compression index, a construction process continuity index, and a milestone node compliance index; based on the cost forecast result, a cost benefit evaluation index is calculated, and the cost benefit evaluation index includes a total cost saving rate index, a cost composition rationality index, and a cash flow matching index, and the progress benefit evaluation index and the cost benefit evaluation index are weighted and combined to form a multi-objective evaluation index set; Constructing a multi-objective evaluation function, normalizing the index values ​​in the multi-objective evaluation index set; setting a normalized progress weight coefficient and a normalized cost weight coefficient based on the normalized index values; multiplying the normalized progress weight coefficient by the normalized progress index value to obtain a progress weighted score, and multiplying the normalized cost weight coefficient by the normalized cost index value to obtain a cost weighted score; Perform a multi-objective comprehensive evaluation on the progress weighted score and the cost weighted score to calculate a comprehensive benefit score; sort multiple optimization plans according to the comprehensive benefit score; and select the optimization plan with the highest comprehensive benefit score as the optimal execution plan; The optimal execution plan is converted into a standard data format to generate an execution data packet including a construction work instruction and a resource allocation plan; the execution data packet is sent to the on-site management terminal through the digital twin basic platform; the plan execution monitoring module is started to actually execute the data through the data acquisition equipment deployed by the on-site management terminal.

8. A BIM-based engineering progress and cost dynamic control optimization system, used to implement the method described in any one of claims 1 to 7, characterized in that: include: The first unit is used to use computer vision algorithms to analyze BIM models to extract engineering space information and component attribute information and establish an initial construction scene model; Deploy visual sensors at the construction site to collect construction implementation status data, deploy positioning sensors to collect construction personnel distribution data, and deploy Internet of Things sensors to collect mechanical equipment operation data. Perform weighted combination of the construction implementation status data, the construction personnel distribution data, and the mechanical equipment operation data to generate multi-source data; input the multi-source data into a pre-trained deep learning model for feature extraction and data fusion to generate real-time status data of construction resources; dynamically map the real-time status data of construction resources with the initial construction scene model to build a digital twin basic platform with real-time perception capabilities; The second unit is used to import the construction schedule data and the cost control benchmark data based on the digital twin basic platform, and establish a progress-cost association model; receive the real-time status data of the construction resources in real time, calculate the current progress completion status and cost consumption status through the progress-cost association model, and compare them with the construction schedule data and the cost control benchmark data to obtain a comprehensive deviation value; and automatically generate multiple groups of optimization solutions including resource configuration parameters, process organization parameters and cost control parameters according to the comprehensive deviation value; Inputting the multiple groups of optimization schemes into the digital twin basic platform for parallel simulation to obtain simulation prediction results of each scheme, wherein the simulation prediction results include schedule prediction results and cost prediction results; The third unit is used to perform multi-objective evaluation on the progress forecast result and the cost forecast result, and select the implementation plan with the best comprehensive benefits; The optimal execution plan is sent to the on-site management terminal through the digital twin basic platform, and the plan execution monitoring module is started to continuously collect actual execution data; The actual execution data is compared and analyzed with the simulation prediction results in real time. When the comparison deviation exceeds a preset threshold, the progress-cost association model in the digital twin basic platform is updated using the actual execution data to achieve adaptive evolution of the digital twin environment, ensure the accuracy of the next round of simulation verification, and form dynamic collaborative management and control of digital twins for construction progress and cost.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method described in any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images